Enhancing intrusion detection against denial of service and distributed denial of service attacks: Leveraging extended Berkeley packet filter and machine learning algorithms
Anand N., Saifulla M.A., Aakula P.K., Ponnuru R.B., Patan R., Reddy C.R.P.
Article, IET Communications, 2025, DOI Link
View abstract ⏷
As organizations increasingly rely on network services, the prevalence and severity of Denial of Service (DoS) and Distributed Denial of Service (DDoS) attacks have emerged as significant threats. The cornerstone of effectively addressing these challenges lies in the timely and precise detection capabilities offered by advanced intrusion detection systems (IDS). Hence, an innovative IDS framework is introduced that seamlessly integrates the extended Berkeley Packet Filter (eBPF) with powerful machine learning algorithms—specifically Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), and TwinSVM—enabling unparalleled real-time detection of DDoS attacks. This cutting-edge solution provides a robust and scalable IDS framework to combat DoS and DDoS threats with high efficiency, leveraging eBPF's capabilities within the Linux kernel to bypass typical user space constraints. The methodology encompasses several key steps: (a) Collection of data from the renowned CIC-IDS-2017 repository; (b) Processing the raw data through a meticulous series of steps, including transmission, cleaning, reduction, and discretization; (c) Utilizing an ANOVA F-test for the extraction of critical features from the preprocessed data; (d) Application of various ML algorithms (DT, RF, SVM, and TwinSVM) to analyze the extracted features for potential intrusion; (e) Implementing an eBPF program to capture network traffic and harness trained model parameters for efficient attack detection directly within the kernel. The experimental results reveal outstanding accuracy rates of 99.38%, 99.44%, 88.73%, and 93.82% for DT, RF, SVM, and TwinSVM, respectively, alongside remarkable precision values of 99.71%, 99.65%, 84.31%, and 98.49%. This high-speed, accurate detection model is ideally suited for high-traffic environments such as data centers. Furthermore, its foundational architecture paves the way for future advancements, including the potential integration of eBPF with XDP to achieve even lower-latency packet processing. The experimental code is available at the GitHub repository link: https://github.com/NemalikantiAnand/Project.
Securing Software Defined Networks: A Comprehensive Analysis of Approaches, Applications, and Future Strategies Against DoS Attacks
Anand N., Saifulla M.A., Babu Ponnuru R., Reddy Alavalapati G., Patan R., Gandomi A.H.
Article, IEEE Access, 2025, DOI Link
View abstract ⏷
Software Defined Networks (SDN) offer advantages over traditional networks, such as programmability, flexibility, and scalability, making them ideal for implementing and managing new networks while lowering associated expenses. In this article, we will examine and assess various approaches, looking at the benefits and limitations of each solution based on factors such as efficiency, user satisfaction, delay, and other relevant factors. In addition, we have conducted extensive analysis on SDN technology, including the most recent research and applications in areas such as 5G, Wi-Fi networks, IoT-based automated vehicle technology, satellite networks, smart grids, green and renewable energy, and AI. However, we should remember that even with all these applications, these networks are still susceptible to Denial of Service (DoS) and Distributed DoS (DDoS) attacks, which can cause serious disruption to network operations. This article also provides a thorough overview of the threat landscape for SDN and DoS attacks, highlighting the various attacks and their potential impact on network operations and sensitive data security. To mitigate the risks associated with these attacks, it is crucial to have effective solutions in place. We must constantly research and develop new strategies and approaches to counter DoS attacks in SDN as attackers continually discover new vulnerabilities in these networks. Furthermore, we highlight various detection and mitigation strategies for DoS attacks in SDN and emphasize the importance of constantly innovating and developing new approaches to secure SDN. Moreover, we delve into the future of SDN security and provide valuable insights for network administrators, security professionals, and researchers in devising effective strategies to protect SDNs from DoS attacks.
An Emoticon-Based Novel Sarcasm Pattern Detection Strategy to Identify Sarcasm in Microblogging Social Networks
Nirmala M., Gandomi A.H., Babu M.R., Babu L.D.D., Patan R.
Article, IEEE Transactions on Computational Social Systems, 2024, DOI Link
View abstract ⏷
Online social networks are one of the prime modes of communication used by people to voice their opinions and sentiments, especially after the advancement of digital gadgets and overall technology. Mining such sentiments and analyzing the polarity of user opinions is a trending research issue with high business value. Identifying, detecting, and understanding sarcasm is an important topic in the field of sentiment analysis. Despite being complex and challenging, automated detection of sarcasm is also a relatively less explored research area. In this article, we present a novel sarcasm pattern detection technique using emoticons to identify sarcasm in microblogging social networks like Twitter. Initially, we classify the tweets only with emoticons based on a decision tree classification approach. Afterward, we incorporate the SentiWordNet library and a separate emoticon library to find the polarities of the tokenized words and emoticons. Finally, we present a comparison of the polarity of the tweets and the polarity of the emoticons to detect sarcasm in tweets.
Development of IoT-Enabled Smart Water Metering System
Wen S.D., Desa H., Azizan M.A., Hussain A.-S.T., Tanveer M.H., Patan R.
Conference paper, Proceedings of International Conference on Artificial Life and Robotics, 2024,
View abstract ⏷
This paper introduces a smart water meter that utilizes the capabilities of the Internet of Things (IoT) to automate the collection of meter readings. The primary goal of this project is to create an IoT-based device for reading water meters, while simultaneously developing a compatible mobile application. Instead of relying on manual meter reading, which requires human effort, this project proposes the use of an IoT-enabled water meter to collect the data automatically. The device employs a camera and Convolutional Neural Network (CNN) for image processing, making it easy to detect the meter reading accurately. The IoT system architecture involves the use of an ESP32 CAM for data collection, a laptop as a gateway, and the Message Queuing Telemetry Transport (MQTT) protocol for data transfer. The collected data is stored in Firebase's real-time database, and the mobile application is designed to monitor and analyze the data. A functional prototype of the device is constructed and tested in a housing area. The collected data is then monitored through the developed mobile application. Lastly, the data is analyzed to assess the suitability of the proposed method, and recommendations for future improvements are provided.
Securing Data Exchange in the Convergence of Metaverse and IoT Applications
Conference paper, ACM International Conference Proceeding Series, 2023, DOI Link
View abstract ⏷
The convergence of Metaverse and Internet of Things (IoT) presents new opportunities for exchanging data, but it also introduces unprecedented security challenges. With the proliferation of IoT devices, the risk of unauthorized access and data breaches is on the rise, posing significant threats to data confidentiality and integrity. To address these challenges and protect user privacy, comprehensive security solutions are essential. We propose the SafeMetaNet approach, which combines proximity-based authentication, encryption, and blockchain technology to establish secure data exchange in the IoT-Metaverse convergence. SafeMetaNet ensures data confidentiality and integrity through encryption and establishes a tamper-proof record of data exchange using blockchain technology. We evaluated the approach's performance using various metrics, including latency, throughput, and two security metrics: data confidentiality and data integrity, and compared it with existing approaches. Our findings show that SafeMetaNet outperforms existing approaches, providing improved security. SafeMetaNet is a promising solution for secure data exchange in the IoT-Metaverse convergence.
Mutual Informative MapReduce and Minimum Quadrangle Classification for Brain Tumor Big Data
Ramachandran M., Patan R., Kumar A., Hosseini S., Gandomi A.H.
Article, IEEE Transactions on Engineering Management, 2023, DOI Link
View abstract ⏷
Machine learning algorithms such as support vector machine (SVM) have been widely used to detect brain tumors in big data environments. However, the SVM classifier is unsuitable for a large dataset as the complexity involved is found to be high. Therefore, in this article, a MapReduce model is introduced with SVM to handle large-scale data and deal with this issue. In this article, a framework called mutual informative MapReduce and minimum quadrangle classification (MIMR-MQC) is introduced for brain tumor detection to handle challenges associated with big data classification. Here, preprocessing is performed using MIMR, which removes unwanted and redundant attributes in the brain tumor dataset. This technique reduces the computation complexity and time using a big dataset for detecting the brain tumors. Then, the minimum quadrangle support vector machine model is created using Lagrange multipliers and radial basis kernel function for improving the efficiency of the classification process. The MIMR-MQC framework is validated on a standard dataset called Central Brain tumor Registry of the United States (CBTRUS). Results show that the proposed model observed 21% of higher detection accuracy by minimizing the computational complexity and detection time by 37% and 27%, respectively in comparison with existing models. A comparison with state-of-the-art machine learning techniques, the MIMR-MQC framework performs better in terms of brain tumor detection time and accuracy due to the better distribution of data.
Tripartite Transmitting Methodology for Intermittently Connected Mobile Network (ICMN)
Sekaran R., Al-Turjman F., Patan R., Ramasamy V.
Article, ACM Transactions on Internet Technology, 2023, DOI Link
View abstract ⏷
Mobile network is a collection of devices with dynamic behavior where devices keep moving, which may lead to the network track to be connected or disconnected. This type of network is called Intermittently Connected Mobile Network (ICMN). The ICMN network is designed by splitting the region into 'n' regions, ensuring it is a disconnected network. This network holds the same topological structure with mobile devices in it. This type of network routing is a challenging task. Though research keeps deriving techniques to achieve efficient routing in ICMN such as Epidemic, Flooding, Spray, copy case, Probabilistic, and Wait, these derived techniques for routing in ICMN are wise with higher packet delivery ratio, minimum latency, lesser overhead, and so on. A new routing schedule has been enacted comprising three optimization techniques such as Privacy-Preserving Ant Routing Protocol (PPARP), Privacy-Preserving Routing Protocol (PPRP), and Privacy-Preserving Bee Routing Protocol (PPBRP). In this paper, the enacted technique gives an optimal result following various network characteristics. Algorithms embedded with productive routing provide maximum security. Results are pointed out by analysis taken from spreading false devices into the network and its effectiveness at worst case. This paper also aids with the comparative results of enacted algorithms for secure routing in ICMN.
Computational Intelligent Sensor-Rank Consolidation Approach for Industrial Internet of Things (IIoT)
Mekala M.S., Rizwan P., Khan M.S.
Article, IEEE Internet of Things Journal, 2023, DOI Link
View abstract ⏷
Continues field monitoring and searching sensor data remains an imminent element emphasizes the influence of the Internet of Things (IoT). Most of the existing systems are concede spatial coordinates or semantic keywords to retrieve the entail data, which are not comprehensive constraints because of sensor cohesion, unique localization haphazardness. To address this issue, we propose deep-learning-inspired sensor-rank consolidation (DLi-SRC) system that enables 3-set of algorithms. First, sensor cohesion algorithm based on Lyapunov approach to accelerate sensor stability. Second, sensor unique localization algorithm based on rank-inferior measurement index to avoid redundancy data and data loss. Third, a heuristic directive algorithm to improve entail data search efficiency, which returns appropriate ranked sensor results as per searching specifications. We examined thorough simulations to describe the DLi-SRC effectiveness. The outcomes reveal that our approach has significant performance gain, such as search efficiency, service quality, sensor existence rate enhancement by 91%, and sensor energy gain by 49% than benchmark standard approaches.
Automatic Detection of API Access Control Vulnerabilities in Decentralized Web3 Applications
Conference paper, Proceedings - 2023 IEEE International Conference on Decentralized Applications and Infrastructures, DAPPS 2023, 2023, DOI Link
View abstract ⏷
Web3 is a blockchain-powered web evolution. In many situations, Web3 smart contracts require data from outside their applications (off-chain data) via APIs to function as designed. Existing APIs in Web3 facing the most common and critical risks originate through access control vulnerabilities (i.e., Broken Object Level Authorization, Broken Function Level Authorization, and Broken Authentication). Such vulnerabilities during runtime cannot be spotted during the development and testing phases of a Web3 application that integrates APIs. Continuous monitoring is the key to proactive hunting access control attacks, which are not attainable through manual monitoring. In this paper, we design a real-time automated security monitoring approach named the access behavior learning (ABL) model for early detection and prevention of access control attacks before they could cause any damage. In two steps, the ABL approach predicts an attacker's access behavior in response to environmental behavior. First, it verifies the API providers and oracle by defining authentication schemes using OpenAPI Specification (OAS) standard to identify the API endpoints to endorse authenticity. In addition, it validates the oracle-level authentication security schemes for approving authentication. Second, it scans metadata for the current access record and compares it with the previous access records, such as location, application id, and API key, to form a baseline that determines authentication. Using this baseline, ABL determines legitimate application access based on both factors for identifying its authentication. ABL approach retains API security by designing an efficient correlation to enable complex off-chain computation by predicting API access attacks. The ABL approach is evaluated against different Web3 applications with varying levels of access control vulnerabilities where applied for early attack detection and prevention. Compared to traditional manual detection processes, the ABL approach offers early automated detection and prevention of attacks during runtime, which results in enhanced security measures and reduces the risk of potential threats.
Blockchain Security Using Merkle Hash Zero Correlation Distinguisher for the IoT in Smart Cities
Patan R., Manikandan R., Parameshwaran R., Perumal S., Daneshmand M., Gandomi A.H.
Article, IEEE Internet of Things Journal, 2022, DOI Link
View abstract ⏷
Internet of Things (IoT) data is one of the most important assets in business models for offering various ubiquitous and brilliant services. The IoT is provided with the advantage of susceptibility that cybercriminals and other malicious users. Even though smart cities are intended to extend productivity and efficiency, residents and authorities face risks when they avoid cybersecurity. The conventional blockchain methods were introduced to ensure the secure management and examination of the smart city big data. But, the blockchains are found to have computationally high costs, and failed to improve the security, not adequate resource-constrained IoT devices have been designated for smart cities. In order to address these issues, the proposed novel blockchain model called blockchain secured Merkle hash zero correlation distinguisher (BSMH-ZCD) is suitable for IoT devices within the cloud infrastructure. The objective of the BSMH-ZCD method is to enhance security and reduce the run time and computational overhead. Initially, the Merkle hash tree is used to create the hash value with every transaction. Next, the zero correlation distinguisher is applied to perform the data encryption and decryption operation for the ARX block for obtaining proficient secure data access in the IoT devices. Experimental assessment of the proposed BSMH-ZCD method and existing methods are carried out by using the taxi driver data set and Novel Corona Virus 2019 data set with different factors, such as running time, computational complexity, and security with respect to a number of blocks and executions. By using the taxi driver data set, the experimental results reveal that the BSMH-ZCD method performs better with a 19% improvement in security, 20% reduction of computational complexity, and 29% faster running time for IoT compared to existing works.
Knowledge engineering–based DApp using blockchain technology for protract medical certificates privacy
Rupa C., MidhunChakkarvarthy D., Patan R., Prakash A.B., Pradeep G.G.S.
Article, IET Communications, 2022, DOI Link
View abstract ⏷
In the Industry 4.0 era, an inherited featured technology, blockchain, plays a vital role in knowledge engineering applications. Blockchain provides privacy to sensitive data as an intelligent agent, so its adoption rate increases in all the advanced domains. Especially in the health care department, blockchain technology usage helps avoid attacks like the Wannacry ransomware attack during 2017. Therefore, this paper described a decentralised application (DApp) expert system using public blockchain to create and maintain official health documents, especially medical certificates. Current existing systems, either paper-based or database or clouds to save the medical certificates, have more scope to do attacks. Hence, proposed a blockchain-based DApp that acts as an interface between intelligent agents, blockchains, and system related to the medical certificates. The main strength of this paper is implementation results, which are not among the maximum literary works currently available. The associate cost for conducting distributed application operations on the blockchain in terms of Gas comprehensively presented here. Furthermore, it consists of comparing the system's non-functional functions by considering blockchain and non-blockchain environments. Also, presented the simulation results with the performance results compared with the existed systems.
Lung cancer disease detection using service-oriented architectures and multivariate boosting classifier
Chandrasekar T., Raju S.K., Ramachandran M., Patan R., Gandomi A.H.
Article, Applied Soft Computing, 2022, DOI Link
View abstract ⏷
Big data analytics in healthcare is emerging as a promising field to extract valuable information from large databases and enhance results with fewer costs. Although numerous methods have been proposed for big data analytics in the medical field, an authorized entity is required to access data, inhibiting diagnosis accuracy and efficiency. Particularly, the detection of lung cancer is critical as it is the third most common type of cancer occurring in both males and females in the US and a leading cause of cancer-related deaths worldwide, the detection of lung cancer. Therefore, this study introduces the Multivariate Ruzicka Regressed eXtreme Gradient Boosting Data Classification (MRRXGBDC) technique and service-oriented architecture (SOA) to improve the prediction accuracy and reduce the prediction time of lung cancer in big data analytics. Service-oriented architectures (SOAs) provide a set of healthcare services, where patient data are stored in the database of a physician or other certified entity. After receiving the patient data as input, several multivariate Ruzicka logistic regression trees are constructed by the physician to calculate the relationship between the dependent and independent variables. With this regression analysis, the presence or absence of disease is discovered. The experimental results reveal that the MRRXGBDC technique performs better with 10% improvement in prediction accuracy, 50% reduction of false positives, and 11% faster prediction time for lung cancer detection compared to existing works.
Deep learning-influenced joint vehicle-to-infrastructure and vehicle-to-vehicle communication approach for internet of vehicles
Mekala M.S., Dhiman G., Patan R., Kallam S., Ramana K., Yadav K., Alharbi A.O.
Article, Expert Systems, 2022, DOI Link
View abstract ⏷
The internet of vehicle (IoV) orchestration is an emerging technology in heterogeneous vehicles to contrivance diverse intelligent transportation applications. The roadside unit (RSU) plays a vital role during service provisioning. Vehicle-to-vehicle and vehicle-to-infrastructure communications have consistently accomplished the services in a vehicular network. However, persisting the increased vehicles' quality of experience and network vendors' utilities and which RSUs have to select for effective, reliable service are critical open research challenges to consolidate RSU services to enhance network service utility rate. In this article, we design a deep learning-inspired RSU Service Consolidation Approach based on two-models to enhance the service reliability by formulating the RSU coverage issue with the RSU Migration model and content delivery issue with Linear Programming-based Multicast model. Adaptive Packet-Error measurement system to optimize service reliability rate at the edge of cooperative vehicular network based on content correlation. The performance and efficiency are examined based on MATLAB. The simulation outcome shows RSC approach has low execution cost by 39%, service reliability rate by 71% than the state-of-art approaches.
Deming least square regressed feature selection and Gaussian neuro-fuzzy multi-layered data classifier for early COVID prediction
Mydukuri R.V., Kallam S., Patan R., Al-Turjman F., Ramachandran M.
Article, Expert Systems, 2022, DOI Link
View abstract ⏷
Coronavirus disease (COVID-19) is a harmful disease caused by the new SARS-CoV-2 virus. COVID-19 disease comprises symptoms such as cold, cough, fever, and difficulty in breathing. COVID-19 has affected many countries and their spread in the world has put humanity at risk. Due to the increasing number of cases and their stress on administration as well as health professionals, different prediction techniques were introduced to predict the coronavirus disease existence in patients. However, the accuracy was not improved, and time consumption was not minimized during the disease prediction. To address these problems, least square regressive Gaussian neuro-fuzzy multi-layered data classification (LSRGNFM-LDC) technique is introduced in this article. LSRGNFM-LDC technique performs efficient COVID prediction with better accuracy and lesser time consumption through feature selection and classification. The preprocessing is used to eliminate the unwanted data in input features. Preprocessing is applied to reduce the time complexity. Next, Deming Least Square Regressive Feature Selection process is carried out for selecting the most relevant features through identifying the line of best fit. After the feature selection process, Gaussian neuro-fuzzy classifier in LSRGNFM-LDC technique performs the data classification process with help of fuzzy if-then rules for performing prediction process. Finally, the fuzzy if-then rule classifies the patient data as lower risk level, medium risk level and higher risk level with higher accuracy and lesser time consumption. Experimental evaluation is performed by Novel Corona Virus 2019 Dataset using different metrics like prediction accuracy, prediction time, and error rate. The result shows that LSRGNFM-LDC technique improves the accuracy and minimizes the time consumption as well as error rate than existing works during COVID prediction.
Efficient tumor volume measurement and segmentation approach for CT image based on twin support vector machines
Sathish K., Narayana Y.V., Mekala M.S., Rizwan P., Kallam S.
Article, Neural Computing and Applications, 2022, DOI Link
View abstract ⏷
Suspicious volumetric tumor (SVT) segmentation of a CT-image (CTi) and analysing changes in the volume of tumor is a significantly challenging task for the identification of lung cancer. In this regard, we design a two-step suspicious volumetric tumor segmentation (SVTS) approach based on an adaptive multiple resolution contour (AMRC) models for effective SVT segmentation. First, the high-intensity-pixels edge centroid of SVT (HECS) method is designed to identify the SVT location in CTi, and these outcomes are subsequently conceding threshold values to fix the level set method (LSM). Second, HECS outcomes are recognised using particle swarm optimisation (PSO) which is harmonised twin support vector machines (TSVM) to achieve segmentation accuracy. An open-source tumor cancer imaging archive (TCIA) dataset, 529 abnormal tissues (ATs) of the lung from the lung image database consortium (LIDC), are conceded to assess the performance of the SVT segmentation approach. The average segmentation accuracy of NLTC, TCIA, and LIDC datasets are 73.19%, 76.21% and 75.89%, respectively, compared with standard benchmark approaches. Subsequently, our framework efficiently classified the normal and abnormal CTi based on the SVT segmentation accuracy rate.
N-Gram-Based Machine Learning Approach for Bot or Human Detection from Text Messages
Kavadi D.P., Sanaboina C.S., Patan R., Gandomi A.
Conference paper, ACM International Conference Proceeding Series, 2022, DOI Link
View abstract ⏷
Social bots are computer programs created for automating general human activities like the generation of messages. The rise of bots in social network platforms has led to malicious activities such as content pollution like spammers or malware dissemination of misinformation. Most of the researchers focused on detecting bot accounts in social media platforms to avoid the damages done to the opinions of users. In this work, n-gram based approach is proposed for a bot or human detection. The content-based features of character n-grams and word n-grams are used. The character and word n-grams are successfully proved in various authorship analysis tasks to improve accuracy. A huge number of n-grams is identified after applying different pre-processing techniques. The high dimensionality of features is reduced by using a feature selection technique of the Relevant Discrimination Criterion. The text is represented as vectors by using a reduced set of features. Different term weight measures are used in the experiment to compute the weight of n-grams features in the document vector representation. Two classification algorithms, Support Vector Machine, and Random Forest are used to train the model using document vectors. The proposed approach was applied to the dataset provided in PAN 2019 competition bot detection task. The Random Forest classifier obtained the best accuracy of 0.9456 for bot/human detection.
Fuzzy Deep Neural Learning Based on Goodman and Kruskal’s Gamma for Search Engine Optimization
Jayaraman S., Ramachandran M., Patan R., Daneshmand M., Gandomi A.H.
Article, IEEE Transactions on Big Data, 2022, DOI Link
View abstract ⏷
Search engine optimization (SEO) is a significant problem for enhancing a website's visibility with search engine results. SEO issues, such as Site Popularity, Content Quality, Keyword Density, and Publicity, were not considered during the search engine optimization process. Therefore, the retrieval rate of the existing techniques is inadequate. In this study, Triangular Fuzzy Deep Structured Learning-Based Predictive Page Ranking (TFDSL-PPR) technique is proposed to solve these limitations. First, the TFDSL-PPR technique takes a number of user queries as input in the input layer, and then it employs four hidden layers in order to deeply analyze the web pages based on an input query. The first hidden layer determines the keywords from the user query. The second hidden layer measures the site popularity, content quality, keyword density and publicity of all web pages in the search engine. It then accomplishes Goodman and Kruskal's Gamma Predictive Ranking process in the third hidden layer, where it ranks the web pages by considering their similarities. The proposed TFDSL-PPR technique is applied to the ClueWeb09 Dataset with respect to a variety of user queries. The results are benchmarked by existing methods based on several metrics such as retrieval rate, time, and false-positive rate.
Performance Improvement of Blockchain-based IoT Applications using Deep Learning Techniques
Conference paper, 2022 4th International Conference on Blockchain Computing and Applications, BCCA 2022, 2022, DOI Link
View abstract ⏷
Internet of Things (IoT) deployments have increased drastically based on third-party (fog-assisted architecture) mechanisms to store, process, and share sensor data. IoT environments are mostly vulnerable to security threats due to the lack of intrinsic security measures. Blockchain technology with an untrusty framework to establish trust communication among IoT devices becomes a major concern in lightweight IoT frameworks. To solve this trust issue, we propose a DeepIoT-Block model that combines the consensual deep learning (CDL) technique using the elliptic Diffihelman protocol to strengthen the blockchain-based data storage scheme (BDSS) and Directed Acyclic Graph (DAG) to construct the blockchain network. DeepIoT-Block has implemented using a blockchain system for IoT applications to address storage security issues. DeepIoT-Block guarantees simultaneous computational complexity and transaction efficiency. The performance of the proposed model was verified and validated for IoT-based smart road traffic data. The simulation outcomes show that our proposed model, DeepIoT-Block, is computationally efficient and secure for larger scale IoT applications.
Securing Healthcare Data Using Decentralized Approach
Shree D.N., Krishna D.V.L., Patan R.
Conference paper, International Conference on Sustainable Computing and Data Communication Systems, ICSCDS 2022 - Proceedings, 2022, DOI Link
View abstract ⏷
According to WHO, brain stroke seems to be the second most common cause overall, accounting for about eleven percent of all mortality. Data security and privacy are in great demand in the healthcare industry. Data is now kept in a centralized manner in present systems, with all data being stored in a single area. In such systems, there is a high possibility for an intruder or third party to access and change the data. In Healthcare, data is the most crucial factor, so if there are any small changes made by the intruder in the data, it may lead to provide false outcome. In this proposed system, we secure the data in a decentralized approach using IPFS protocol and Block chain. We can reduce the risk of data failures and outages while improving security, performance, and privacy using this strategy. The required data will be collected and be trained with the ANN algorithm to get the final model.
Recognition of Dubious Tissue by Using Supervised Machine Learning Strategy
Pradeep Ghantasala G.S., Nageswara Rao D., Patan R.
Conference paper, Lecture Notes in Mechanical Engineering, 2022, DOI Link
View abstract ⏷
Bosom malignancy is the primary stage of disease detection. Classifiers are thus constantly wanted with higher accuracy. A highly accurate classifier gives fewer opportunities to misinterpret a malignant growth patient. This paper explores how the concept of strategic recession is portrayed in a modified, enhanced manner. For minimizing cost efficiency, both inclination plunge and propelled streamlining are used. The theory, which is a sigmoid capacity, involves a weighing dimension of β. The weighting variable depends on the number of highlights, dataset size, and the type of simplification method used. Through correctly estimating β, which is part of the quantity and type of enhancement systems used, the accuracy of the bosom disease position is fundamentally improving. By increasing precision, affectability, and specialty, the achieved results are promising.
Securing Healthcare Data using Decentralized Approach
Shree D.N., Venkata Lohitha Krishna D., Patan R.
Conference paper, Proceedings of the International Conference on Electronics and Renewable Systems, ICEARS 2022, 2022, DOI Link
View abstract ⏷
According to WHO, brain stroke seems to be the second most common cause overall, accounting for about eleven percent of all mortality. Data security and privacy are in great demand in the healthcare industry. Data is now kept in a centralized manner in present systems, with all data being stored in a single area. In such systems, there is a high possibility for an intruder or third party to access and change the data. In Healthcare, as the data is the most crucial factor, so if there are any small changes made by the intruder in the data, it may lead to provide false outcome. In this proposed system, the data are secured in a decentralized approach using IPFS (InterPlanetary File System) protocol and Block chain. The risk of data failures and outages can be reduced while improving security, performance, and privacy using this strategy. The required data will be collected from the IPFS network by using the hash value and it will be trained with the ANN (Artificial Neural Network) algorithm to get the final model.
Diagnosis of COVID-19 from Chest X-rays Using CNN and Determination of Its Severity by Text Analysis
Pujitha G., Siva Parvathi P., Phaneendra L.V.S., Snehita N., Patan R.
Conference paper, Lecture Notes in Networks and Systems, 2022, DOI Link
View abstract ⏷
In India, the effect of COVID-19 has been worst because of various reasons like huge population, lack of necessary medical infrastructure, lack of awareness among people, inability to identify people with actual severe conditions and many more. Some people are waiting for more than a day to get the test results besides having rapid diagnosing kits. Due to a lack of awareness among people, patients with mild conditions are joining hospitals, leaving no place for severely infected patients. There is a need to automate the diagnosis of COVID-19 and identify the people with actual severe conditions so that those patients can be equipped with the required medical infrastructure and can potentially stop the process of spreading the disease and can even reduce the mortality rate. This need motivated us to propose a model which can diagnose COVID-19 and detect patients with severe conditions. Chest X-rays of individuals are efficient and can be used for rapid diagnosis of COVID-19 as X-ray centers are available even at rural areas. The proposed system automates the detection of COVID-19 and distinguishes the COVID-19 cases from other pneumonia and normal cases using a 11-layer Convolution Neural Network (CNN) model. We can use text analysis techniques on the patient's health condition which can be obtained by collecting details of the patient like age, body temperature, need for supplementary oxygen requirement, etc., we can identify the severity of the disease. The proposed CNN model achieved a 0.84 accuracy and on test data.
A Secured Certificateless Sign-encrypted Blockchain Communication for Intelligent Transport System
Patan R., Parizi R.M., Pouriyeh S., Khan M.S., Gandomi A.H.
Conference paper, 2022 IEEE Conference on Communications and Network Security, CNS 2022, 2022, DOI Link
View abstract ⏷
Data communication in the intelligent transport system suffers from many security vulnerabilities. It is essential to protect the vehicles from the distribution of fake messages and concurrently preserve the privacy of those vehicles against tracking attacks. Conventional security methods are not sufficient to provide well-needed security support. In this paper, an efficient technique called Gentle Boost Clustered Diffie-Hellman Certificateless Signcryption-based Blockchain Security Frame-work (GeBlock) is proposed to improve communication security. Initially, the vehicle's information is collected from the dataset. Then, the collected vehicle data are grouped and given to the data block in the underlying Blockchain. The Gaussian expected maximization clustering is a weak learner for grouping each vehicle's data. This process minimizes the processing time for secure data-sharing in the intelligent transport system. After that, the Diffie-Hellman Certificateless Signcryption is performed to protect the data from unauthorized entities. Diffie-Hellman Certificateless Signcryption performs the encryption and digital signature verification process where only an authorized entity can access the vehicle data. In the encryption process, the clustered vehicle data is converted into ciphertext. The digital signature verification is performed on the receiver side to decrypt the ciphertext into the plain text. The confidentiality rate is improved in data communication based on signature verification. Experimental evaluation is performed using Warrigal Dataset, and the different parameters such as clustering accuracy, data confidentiality rate, and processing time are measured.
Gaussian relevance vector MapReduce-based annealed Glowworm optimization for big medical data scheduling
Patan R., Kallam S., Gandomi A.H., Hanne T., Ramachandran M.
Article, Journal of the Operational Research Society, 2022, DOI Link
View abstract ⏷
Various big-data analytics tools and techniques have been developed for handling massive amounts of data in the healthcare sector. However, scheduling is a significant problem to be solved in smart healthcare applications to provide better quality healthcare services and improve the efficiency of related processes when considering large medical files. For this purpose, a new hybrid model called Gaussian Relevance Vector MapReduce-based Annealed Glowworm Optimization Scheduling (GRVM-AGS) was designed to improve the balancing of large medical data files between different physicians with higher scheduling efficiency and minimal time. First, a GRVM model was developed for the predictive analysis of input medical data. This model reduces the storage complexity of large medical data analysis by means of eliminating unwanted patient information and predicts the disease class with help of a Gaussian kernel function. Afterwards, GRVM performs AGS to schedule the efficient workloads among multiple datacenters based on the luciferin value in the smart healthcare environment with reduced scheduling time. Through computational experiments, we demonstrate that GRVM-AGS increases the scheduling efficiency and reduces the scheduling time of large medical data analysis compared to state-of-the-art approaches.
Kinematic adaptive frequency sampling combined spatio temporal features for snow monitoring in aerospace applications
Ramalingam P., Gopalakrishnan L., Ramachandran M., Patan R.
Article, Expert Systems with Applications, 2021, DOI Link
View abstract ⏷
A new era of aerospace systems has instigated highly coupled frameworks, leading to a significant rise in design complexity. The lack of present-day design systems to govern this complexity has resulted in considerable time and schedule overruns compromising the accuracy during the development of military and commercial platforms. This work presents the framework for a new design process to reduce the complexity and improve accuracy using Spatio Temporal-based Kinematic Adaptive Sampling (ST-KAS). First, dynamic modeling of the Time Factor Matrix (TFM) and Spatial Association Matrix (SAM) based on the location and time is performed to extract relevant features. Second, the Kinematic Adaptive Frequency Sampling Algorithm is designed through a dynamic model and a Probability Uncertainty Measure. However, an adaptive control measure is required to flexibly cope with the uncertainty because the operating environment of the TFM and SAM is varied, and uncertainty exists depending on the number of locations to be analyzed for monitoring snow in aerospace applications. The performance of the Kinematic Adaptive Frequency Sampling is also verified through a numerical simulation according to computational overhead, computational time, and probability of fatality. Simulation experiments show that the suggested solution can minimize the complexity rate for sensing while maintaining the error rate at acceptable levels.
Duo-Stage Decision: A Framework for Filling Missing Values, Consistency Check, and Repair of Decision Matrices in Multicriteria Group Decision Making
Raghunathan K., Soundarapandian R.K., Gandomi A.H., Ramachandran M., Patan R., Madda R.B.
Article, IEEE Transactions on Engineering Management, 2021, DOI Link
View abstract ⏷
With high uncertainty and vagueness in the decision-making process, maintaining consistency in the decision matrix is an open challenge. Previous studies on the intuitionistic fuzzy (IF) theory focused on the consistency of preference relation but ignored consistency of the decision matrix. In this article, efforts are made to propose a new duo-stage decision framework in the context of IF set to better circumvent the challenge. Often, decision makers (DMs) hesitate to provide certain values in the decision matrix that are filled randomly, resulting in inaccuracies in the decision-making process. To alleviate this issue, a new systematic procedure is developed that sensibly fills the missing data in the first stage. Following the first stage, consistency of the decision matrix is determined by extending Cronbach's alpha coefficient to IF context. Furthermore, efforts are made to repair inconsistent decision matrix iteratively. In the second stage, a new aggregation operator is presented for aggregation of DMs' preferences. Also, a new mathematical model is proposed for criteria weight estimation, and a procedure is developed for ranking objects. The practical use of the proposed framework is demonstrated using a numerical example, and the strengths and weaknesses of the framework are investigated.
A Study on Multi-class Classification of Breast Cancer Images using Ensemble Network and Transfer Learning
Article, Recent Patents on Engineering, 2021, DOI Link
View abstract ⏷
Background: Breast cancer causes millions of deaths all over the world every year. It has become the most common type of cancer in women. Early detection will help in better prognosis and increase the chance of survival. Automating the classification using Computer-Aided Diagnosis (CAD) systems can make the diagnosis less prone to errors. Multi-class classification and Binary classification of breast cancer is a challenging problem. Convolutional neural network architectures extract specific feature descriptors from images, which cannot represent different types of breast cancer. This leads to false positives in classification, which is undesirable in disease diagnosis. Methods: The current paper presents an ensemble Convolutional neural network for multi-class classification and Binary classification of breast cancer. The feature descriptors from each network are combined to produce the final classification. In this paper, histopathological images are taken from the publicly available BreakHis dataset and classified into 8 classes. Results: The proposed ensemble model can perform better when compared to the methods proposed in the literature. The results showed that the proposed model could be a viable approach for breast cancer classification. Conclusion: In this paper, an approach for multi-class classification on the breast images for cancer detection is proposed. The proposed architecture can be a viable option for the classification of his-topathology images.
A Novel Approach for Efficient Packet Transmission in Volunteered Computing MANET
Sekaran R., Patan R., Al-Turjman F.
Article, ACM Transactions on Internet Technology, 2021, DOI Link
View abstract ⏷
A mobile ad hoc network (MANET) is summarized as a combination device that can move, synchronize and converse without any preceding management. Enhancing the lifetime energy is based on the status of the concerned channel. The node is accomplished of control the control messages. Due to unplanned methods of energy conservation, the node lifespan and quality of packet flow is defaced in the existing solution. It results in a network-To-node-energy trade-off, ensuing in a failure of the post-network. This failure results in reduced time-To-live and higher overhead. This paper discusses an effective buffer management mechanism, in addition to proposing a novel performance modeling in Volunteered Computing MANET and tactile internet Next, the best execution the nodes can accomplish under fractional data is completely portrayed for utilities for a general purpose. To associate the space between network efficiency and energy conservation based on the minimal overhead, this article proposes a switch state promoting mutual Optimized MAC protocol for conservation of a node's energy and the optimal use of available nodes before their energy drain. Simulation results are provided as proof of the proposed solution. The simulation results are compared with the existing system with performance measures of delay, throughput, energy consumption, and availability of the node.
A reinforcement learning optimization for future smart cities using software defined networking
Rajkumar K., Ramachandran M., Al-Turjman F., Patan R.
Article, International Journal of Machine Learning and Cybernetics, 2021, DOI Link
View abstract ⏷
Nowadays smart cities towards software defined network (SDN) approach will become better flexibility and manageability. A stronger, more dynamic network is an SDN network, which is precisely what a smart city network must be if it wants to be viable on a real-world scale. SDN architecture is developed to implement a learning framework for network optimization. The proposed method is called mixed-integer and reinforcement learned network optimization (MI-RLNO) for SDN monitoring. In the first phase, mixed-integer programming formulation is used as an optimization formulation for latency and convergence time. In the second phase, a reinforced Q Learning model is designed that uses communication and computation time as input state vector. Optimization formulation is used as the actions and strategies to be followed during the design and operation of communication networks, therefore contributing fairness and throughput. Simulation results improved the efficiency of the MI-RLNO method.
A novel handover mechanism of PmIpv6 for the support of multi-homing based on virtual interface
Krishnan I.L., Al-Turjman F., Sekaran R., Patan R., Hsu C.-H.
Article, Sustainability (Switzerland), 2021, DOI Link
View abstract ⏷
The Proxy Mobile IPv6 (PMIPv6) is a network-based accessibility managing protocol. Because of PMIPv6’s network-based approach, it accumulates the following additional benefits, such as discovery, efficiency. Nonetheless, PMIPv6 has inadequate sustenance for multi-homing mechanisms, since every mobility session must be handled through a different binding cache entry (BCE) at a local mobility anchor (LMA) according to the PMIPv6 specification, and thus PMIPv6 merely permits concurrent admittance for the mobile node (MN) which is present in the multi-homing concept. Consequently, when a multi-homed MN interface is detached from its admittance network, the LMA removes its moving part from the BCE, and the current flows connected with the apart interface are not transmitted to the multi-homed MN, even if a more multi-homed MN interface is still linked to another access network. A superior multi-homing support proposal is proposed to afford flawless mobility among the interfaces for a multi-homed MN to address this problem. The projected method can shift an application from a disconnected interface of a multi-home MN to an attached interface using the PMIPv6 fields of Auxiliary Advertisement of Neighbor Detection (AAND).
Game the Oretic Approach for Cloud Service Negotiation
Ramesh C., Santhiya K., Kumar R.S., Patan R.
Article, International Journal of Grid and High Performance Computing, 2021, DOI Link
View abstract ⏷
Cloud computing is a booming technology in the area of digital markets. Tackling the nonfunctional characteristics is a big challenge between service consumers (SC) and service providers (SP). Without proper negotiation between the participants specifying their quality of service (QoS) requirements, service level agreement (SLA) cannot be achieved. Two strategies that are commonly prevalent in the negotiation process are concession model and trade off model. The concession model assures the service consumer (SC) receiving the services on time without any deferment. But service consumer has only limited utility. To balance the utility and achievement rates, the authors propose a mixed negotiation approach for cloud service negotiation, which is based on “Game of Chicken.” Extensive results show that a mixed negotiation approach brings equal amount of satisfaction to both service consumer and service provider in terms of achieving higher utility and outperforms the concession approach, while taking fewer time delays than that of a tradeoff approach.
A dual deep neural network with phrase structure and attention mechanism for sentiment analysis: An ablation experiment on Chinese short financial texts
Rao D., Huang S., Jiang Z., Deverajan G.G., Patan R.
Article, Neural Computing and Applications, 2021, DOI Link
View abstract ⏷
Sentiment analysis of short texts is difficult for their simplicity and compactness. This goes a step further when it comes to the Chinese texts. Although deep learning achieved better accuracy in sentiment analysis, there is a lack of explain-ability. Thus, this paper evaluates the effectiveness of techniques for sentiment analysis of Chinese short financial texts with deep learning. For this, we built a Chinese short financial texts corpus (CSFC) and designed an ablation experiment. Beside the CFSC, we used a Chinese review collection and an English short-text repository in the experiment for comparison. There are five techniques involved. They are the Pinyin, the segmentation, the lexical analysis, the phrase structure and the attention mechanism. As results, we found that the phrase structure and the attention mechanism are two of the best. Therefore, the best model in the experiment is called a Phrase Structure and Attention-based Deep network model (PhraSAD). Moreover, to improve the classification accuracy on neutral data, we use a dual classifier strategy for 3-class problems. Experimental results showed that PhraSAD outperformed all other compared models on all experimental datasets.
Ensemble Classification and IoT-Based Pattern Recognition for Crop Disease Monitoring System
Nagasubramanian G., Sakthivel R.K., Patan R., Sankayya M., Daneshmand M., Gandomi A.H.
Article, IEEE Internet of Things Journal, 2021, DOI Link
View abstract ⏷
Internet of Things (IoT) in the agriculture field provides crops-oriented data sharing and automatic farming solutions under single network coverage. The components of IoT collect the observable data from different plants at different points. The data gathered through IoT components, such as sensors and cameras, can be used to be manipulated for a better farming-oriented decision-making process. This work proposes a system that observes the crops' growth and leaf diseases continuously for advising farmers in need. To provide analytical statistics on plant growth and disease patterns, the proposed framework uses machine learning (ML) techniques, such as support vector machine (SVM) and convolutional neural network (CNN). This framework produces efficient crop condition notifications to terminal IoT components which are assisting in irrigation, nutrition planning, and environmental compliance related to the farming lands. In this regard, this work proposes ensemble classification and pattern recognition for crop monitoring system (ECPRC) to identify plant diseases at the early stages. The proposed ECPRC uses ensemble nonlinear SVM (ENSVM) for detecting leaf and crop diseases. In addition, this work performs comparative analysis between various ML techniques, such as SVM, CNN, naïve Bayes, and K -nearest neighbors. In this experimental section, the results show that the proposed ECPRC system works optimally compared to the other systems.
BDN-GWMNN: Internet of Things (IoT) Enabled Secure Smart City Applications
Peneti S., Sunil Kumar M., Kallam S., Patan R., Bhaskar V., Ramachandran M.
Article, Wireless Personal Communications, 2021, DOI Link
View abstract ⏷
Nowadays, next-generation networks such as the Internet of Things (IoT) and 6G are played a vital role in providing an intelligent environment. The development of technologies helps to create smart city applications like the healthcare system, smart industry, and smart water plan, etc. Any user accesses the developed applications; at the time, security, privacy, and confidentiality arechallenging to manage. So, this paper introduces the blockchain-defined networks with a grey wolf optimized modular neural network approach for managing the smart environment security. During this process, construction, translation, and application layers are created, in which user authenticated based blocks are designed to handle the security and privacy property. Then the optimized neural network is applied to maintain the latency and computational resource utilization in IoT enabled smart applications. Then the efficiency of the system is evaluated using simulation results, in which system ensures low latency, high security (99.12%) compared to the multi-layer perceptron, and deep learning networks.
Performance analysis of machine learning algorithms for big data classification: Ml and ai-based algorithms for big data analysis
Punia S.K., Kumar M., Stephan T., Deverajan G.G., Patan R.
Article, International Journal of E-Health and Medical Communications, 2021, DOI Link
View abstract ⏷
In broad, three machine learning classification algorithms are used to discover correlations, hidden patterns, and other useful information from different data sets known as big data. Today, Twitter, Facebook, Instagram, and many other social media networks are used to collect the unstructured data. The conversion of unstructured data into structured data or meaningful information is a very tedious task. The different machine learning classification algorithms are used to convert unstructured data into structured data. In this paper, the authors first collect the unstructured research data from a frequently used social media network (i.e., Twitter) by using a Twitter application program interface (API) stream. Secondly, they implement different machine classification algorithms (supervised, unsupervised, and reinforcement) like decision trees (DT), neural networks (NN), support vector machines (SVM), naive Bayes (NB), linear regression (LR), and k-nearest neighbor (K-NN) from the collected research data set. The comparison of different machine learning classification algorithms is concluded.
Multivariate regressive deep stochastic artificial learning for energy and cost efficient 6G communication
Sekaran R., Ramachandran M., Patan R., Al-Turjman F.
Article, Sustainable Computing: Informatics and Systems, 2021, DOI Link
View abstract ⏷
In recent years, with the development of 6 G networks in mobile computing, the energy consumption of data centers has increased significantly. Therefore, energy saving in data centers has become an important research direction for sustainable computing. High-energy consumption is not only detrimental to the environment but also raises the operating costs. In order to improve the energy and cost aware communication, a new technique called Multivariate Regressive Deep Stochastic Artificial Structure Learning (MRDSASL) is introduced in the 6 G network. The input layer of deep stochastic artificial Structure Learning receives the several nodes and it transferred into the next layer called hidden layer where the node energy levels are estimated. Followed by, the received signal strength of the nodes is evaluated in the next consecutive hidden layer. Then the spectrum utilization is also measured in the third hidden layer. At last hidden layer, the multivariate regression function is employed to analyze the estimated node status with the threshold. Finally, the soft step activation function finds the efficient nodes through the regression analysis. Based on the deep analysis, the 6 G architecture is designed with the efficient nodes. By selecting the node with higher energy, signal strength and spectrum utilization, data communication performance can be improved with minimum cost in 6 G network. The simulation assessment of proposal technique and other related works are carried out in terms of metrics namely energy consumption, cost and packet delivery ratio. The simulation result illustrates that the MRDSASL technique improves the packet delivery ratio 12 %, minimizes the energy consumption by 12 %, and reduces the delay 12 % as compared to state-of-the-art works. The assessment and conferred results reveal the improvement of proposed technique in the 6 G network.
An Improved IDAF-FIT Clustering Based ASLPP-RR Routing with Secure Data Aggregation in Wireless Sensor Network
Babu M.V., Alzubi J.A., Sekaran R., Patan R., Ramachandran M., Gupta D.
Article, Mobile Networks and Applications, 2021, DOI Link
View abstract ⏷
In recent years, Wireless Sensor Network (WSN) became a key technology for monitoring and tracking applications in a wide application range. Still, an energy-efficient data gathering protocol has become the most challenging issue. This is because each sensor node in the network is equipped with limited energy resources. To achieve better energy efficiency, better network communication, and minimized delay, clustering is introduced. Therefore, the clustering-based techniques for data gathering play a vital role in terms of energy-saving and increasing the lifetime of the network due to cluster head election and data aggregation. In this proposed methodology, the Integration of Distributed Autonomous Fashion with Fuzzy If-then Rules (IDAF-FIT) algorithm is proposed for clustering, and also the Cluster Head (CH) is elected in the meanwhile. After that, to transmit the packet from source to the destination node by choosing an optimal path, the routing concept is initiated. For this purpose, an Adaptive Source Location Privacy Preservation Technique using Randomized Routes (ASLPP-RR) is presented for routing. Also, Secure Data Aggregation based on Principle Component Analysis (SDA-PCA) algorithm is performed with end-to-end confidentiality and integrity. Finally, the security of confidential data is analyzed properly to obtain a better result than the existing approaches. The overall performance of the proposed methodology when compared with existing is expressed in terms of 20% higher packet delivery ratio, 15% lower packet dropping ratio, 18% higher residual energy, 22% higher network lifetime, and 16% lower energy consumption.
Internet of things-based fog and cloud computing technology for smart traffic monitoring
Dhingra S., Madda R.B., Patan R., Jiao P., Barri K., Alavi A.H.
Article, Internet of Things (Netherlands), 2021, DOI Link
View abstract ⏷
Internet of Things (IoT) is changing the world by connecting billions of physical and virtual objects with distinctive identities to the Internet. This fusion results in generating huge volumes of data that might not be manageable using today's storage and data analytics technologies. Although cloud computing offers services to tackle this issue at infrastructural level, its efficiency for time sensitive applications (e.g. oil, gas, and traffic monitoring) is still questionable. Arguably, transferring massive amount of data to the cloud for storage and processing may lead to cloud overloading and saturation of network bandwidth. In this study, an integrated fog and cloud computing framework is introduced to overcome the limitations of real-time analytics, latency and network congestion of basic cloud services for traffic monitoring. The proposed approach is implemented to prototype a smart traffic monitoring system (STMS). The proposed monitoring system is designed for congestion monitoring and traffic light management. It can also be tuned to detect traffic incidents that requires immediate assistance during congestion. In this framework, a tiny computer-on-module serves as a fog node to collect real-time data from geographically distributed sensors and to transfer it to the cloud for storage and processing. The results show the efficiency of the fog network in improving the performance of the cloud platform in terms of reducing the response time and increasing the bandwidth. Furthermore, the proposed integrated fog and cloud framework is interfaced with Tweeter to send alerts about traffic congestion to be subscribed users in the form of Tweet messages.
Machine learning-based left ventricular hypertrophy detection using multi-lead ECG signal
Jothiramalingam R., Jude A., Patan R., Ramachandran M., Duraisamy J.H., Gandomi A.H.
Article, Neural Computing and Applications, 2021, DOI Link
View abstract ⏷
This work proposes a novel method for the detection of Left Ventricular Hypertrophy (LVH) from a multi-lead ECG signal. Left Ventricle walls become thick due to prolonged hypertension which may fail to pump heart effectively. The imaging techniques can be used as an alternative diagnose LVH; however, they are more expensive and time-consuming than proposed LVH. To overcome this issue, an algorithm to the diagnosis of LVH using ECG signal based on machine learning techniques were designed. In LVH detection, the pathological attributes such as R wave, S wave, inversion of QRS complex, changes in ST segment noticed in the ECG signal. This clinical information extracted as a feature by applying continuous wavelet transform. The signals were reconstructed with the frequency between 10 and 50 Hz from the wavelet. This followed by the detection of R wave and S wave peaks to obtain the relevant LVH diagnostic features. The Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Ensemble of Bagged Tree, AdaBoost classifiers were employed and the results are compared with four neural network classifiers including Multilayer Perceptron (MLP), Scaled Conjugate Gradient Backpropagation Neural Network (SCG NN), Levenberg–Marquardt Neural Network (LMNN) and Resilient Backpropagation Neural network (RPROP). The data source includes Left Ventricular Hypertrophy and healthy ECG signal from PTB diagnostic ECG database and St Petersburg INCART 12-Lead Arrhythmia Database. The results revealed that the proposed work can diagnose LVH successfully using neural network classifiers. The accuracy in detecting LVH is 86.6%, 84.4%, 93.3%,75.6%, 95.6%, 97.8%, 97.8%, 88.9% using SVM, KNN, Ensemble of Bagged Tree, AdaBoost, MLP, SCG NN, LMNN and RPROP classifiers, respectively.
Cryptography-based deep artificial structure for secure communication using IoT-enabled cyber-physical system
Kannan C., Dakshinamoorthy M., Ramachandran M., Patan R., Kalyanaraman H., Kumar A.
Article, IET Communications, 2021, DOI Link
View abstract ⏷
Internet of things (IoTs) enabled cyber-physical systems is a system that provides communication between physical devices and cyber environment. They run independently without any user interaction. Because the IoT devices are vulnerable to a variety of attacks, security is a noteworthy factor in the development process during communication. To improve secure communication with minimum time consumption, a novel technique called jackknife regressive Schmidt Samoa cryptography-based deep artificial structure learning (JRSSC-DASL) is introduced. Initially, the data is monitored by IoT devices and is collected from the dataset. The proposed deep artificial structure learning technique trains the gathered data with multiple layers. Then, the collected data is analysed in the first hidden layer with the help of the jackknife regression function by learning the feature and it classifies the data with higher accuracy. The classified data is sent to the next hidden layer where encryption is performed using Schmidt Samoa (SS) encryption algorithm. Then, the encrypted data is sent to the cloud server where the decryption is performed using the SS decryption algorithm. The cloud server obtains the original data and it is stored in their database for further processing. This process enhances the security of data communication and achieves high data confidentiality with less processing time. Experimental estimation is performed on the factors such as classification accuracy, confidentiality rate, processing time and memory usage to the number of data sensed from IoT device. Conferred results reveal that the proposed JRSSC-DASL technique has high confidentiality rate and minimum processing time as well as memory usage when compared to state-of-the-art methods.
Improved salient object detection using hybrid Convolution Recurrent Neural Network
Kousik N., Natarajan Y., Arshath Raja R., Kallam S., Patan R., Gandomi A.H.
Article, Expert Systems with Applications, 2021, DOI Link
View abstract ⏷
Salient object detection is a critical and active field that aims at the detection of objects in a video, however, it draws increased attention among researchers. With increasing dynamic video data, the performance of saliency object detection method has been degrading with conventional object detection methods. The challenges lie with blurry moving targets, rapid movement of objects and background occlusion or dynamic background change on foreground regions in video frames. Such challenges result in poor saliency detection. In this paper, we design a deep learning model to address the issues, which uses a novel framework by combining the idea of Convolutional Neural Network (CNN) with Recurrent Neural Network (RNN) for video saliency detection. The proposed method aims at developing a spatiotemporal model that exploits temporal, spatial and local constraint cues to achieve global optimization. The task of finding the salient objects in benchmark dynamic video datasets is then carried out by capturing the temporal, spatial and local constraint features with the Convolution Recurrent Neural Network (CRNN). The CRNN is evaluated on benchmark datasets against conventional video salient object detection methods in terms of precision, F-measure, mean absolute error (MAE) and computational load. The experiments reveal that the CRNN model achieves improved performance than other state-of-the-art saliency models in terms of increased speed and reduced computational load.
Article linear weighted regression and energy-aware greedy scheduling for heterogeneous big data
Kallam S., Patan R., Ramana T.V., Gandomi A.H.
Article, Electronics (Switzerland), 2021, DOI Link
View abstract ⏷
Data are presently being produced at an increased speed in different formats, which complicates the design, processing, and evaluation of the data. The MapReduce algorithm is a distributed file system that is used for big data parallel processing. Current implementations of MapReduce assist in data locality along with robustness. In this study, a linear weighted regression and energy-aware greedy scheduling (LWR-EGS) method were combined to handle big data. The LWR-EGS method initially selects tasks for an assignment and then selects the best available machine to identify an optimal solution. With this objective, first, the problem was modeled as an in-teger linear weighted regression program to choose tasks for the assignment. Then, the best available machines were selected to find the optimal solution. In this manner, the optimization of resources is said to have taken place. Then, an energy efficiency-aware greedy scheduling algorithm was presented to select a position for each task to minimize the total energy consumption of the MapReduce job for big data applications in heterogeneous environments without a significant performance loss. To evaluate the performance, the LWR-EGS method was compared with two related approaches via MapReduce. The experimental results showed that the LWR-EGS method effectively reduced the total energy consumption without producing large scheduling overheads. Moreover, the method also reduced the execution time when compared to state-of-the-art methods. The LWR-EGS method reduced the energy consumption, average processing time, and scheduling overhead by 16%, 20%, and 22%, respectively, compared to existing methods.
5G Integrated Spectrum Selection and Spectrum Access using AI-based Frame work for IoT based Sensor Networks
Sekaran R., Goddumarri S.N., Kallam S., Ramachandran M., Patan R., Gupta D.
Article, Computer Networks, 2021, DOI Link
View abstract ⏷
The convulsive advancement of multiple-input multiple-output devices and ultra-dense networks has been extensively considered as the key facilitators that ease the evolution and formation of 5G systems. The explosive growth of wireless devices necessitates the deployment of the Internet of Things (IoT), which is the potential of interconnecting diversified things using wireless communications. To enable wireless accesses of IoT devices, Artificial Intelligence (AI) plays a significant role in 5G network. While existing end-to-end learning and adaptive model require continuous monitoring and dynamic changes cannot achieve global optimization due to wireless signal classifiers and a higher amount of interference. In this work, an integrated spectrum selection and spectrum access using a greedy and AI-based framework to allow the forthcoming and subsequent demands on 5G and beyond is presented. Fractional Knapsack Greedy-based strategy is introduced, and Langrange Hyperplane-based approach is utilized to realize the AI-based strategies for spectrum selection and spectrum allocation for IoT-enabled sensor networks. This framework is called as Fractional Knapsack and Langrange Hyperplane Spectrum Access (FK-LHSA). First Fractional Knapsack Multi-band spectrum selection (FKMSS) model is designed along with an energy consumption model to optimize channel or spectrum throughput. Next, a Lagrange Hyperplane (LH) spectrum access model is designed to minimize spectrum access delay and improve spectrum access accuracy. The simulation results show that the proposed FKM model and LH model can effectively reduce the spectrum access delay along with the improvement of throughput and spectrum access accuracy.
Ant Colony Optimization Based Quality of Service Aware Energy Balancing Secure Routing Algorithm for Wireless Sensor Networks
Rathee M., Kumar S., Gandomi A.H., Dilip K., Balusamy B., Patan R.
Article, IEEE Transactions on Engineering Management, 2021, DOI Link
View abstract ⏷
Existing routing protocols for wireless sensor networks (WSNs) focus primarily either on energy efficiency, quality of service (QoS), or security issues. However, a more holistic view of WSNs is needed, as many applications require both QoS and security guarantees along with the requirement of prolonging the lifetime of the network. The limited energy capacity of sensor nodes forces a tradeoff to be made between network lifetime, QoS, and security. To address these issues, an ant colony optimization based QoS aware energy balancing secure routing (QEBSR) algorithm for WSNs is proposed in this article. Improved heuristics for calculating the end-to-end delay of transmission and the trust factor of the nodes on the routing path are proposed. The proposed algorithm is compared with two existing algorithms: distributed energy balanced routing and energy efficient routing with node compromised resistance. Simulation results show that the proposed QEBSR algorithm performed comparatively better than the other two algorithms.
Cancer prediction and diagnosis hinged on HCML in IOMT environment
Ghantasala G.S.P., Kumari N.V., Patan R.
Book chapter, Machine Learning and the Internet of Medical Things in Healthcare, 2021, DOI Link
View abstract ⏷
Machine learning (ML) is a postulation of artificial intelligence (AI) to facilitate the supply system of rules with the capability to routinely learn and improve from occurrences without being unambiguously programmed. ML centers on the improvement of computer programs that are able to enter information. The basic assertion of ML is that algorithms can collect input data and use statistical investigation to predict an output at the same time as updating outputs as fresh data becomes accessible. Health care restores health by the treatment and prevention of disease particularly by trained and licensed professionals. The value of HCML is its facility to progress on huge datasets ahead of the scope of human capability, and then reliably convert analysis of that data into clinical insights that assist the medical practitioner in the preparation and furnishing of care, finally leading to improved outcomes. Applications of ML in healthcare are identifying diseases and diagnosis, drug discovery and manufacturing, medical imaging diagnosis, ML-based behavioral modification (MLBBM), smart health records, better radiotherapy, and outbreak prediction. Breast cancer (BC) is one of the most perilous types of diseases in the world and detecting this cancer in its initial stage helps in saving lives. Numerous women die every year of BC. ML algorithms can be accessible used for anticipation as well as designation of BC. Various ML algorithms are Naïve Bayes, Support Vector Machine, and K-Nearest Neighbor.
A trust-based fuzzy neural network for smart data fusion in internet of things
Malchi S.K., Kallam S., Al-Turjman F., Patan R.
Article, Computers and Electrical Engineering, 2021, DOI Link
View abstract ⏷
Internet of Things (IoT) devices generates a vast amount of data from extensive applications. Maintaining the sensed data with low energy consumption, delay time, and adaptive coverage fraction rate proportionally influences the storage capacity. To maintain a trade-off between above-listed factors, we proposed an Elfes Sugeno Fuzzy and Trust-based Neural Networks (ESF-TNN) approach enables 3-algorithms. First, Elfes Probability Sensing (EPS) Model addresses the coverage fraction of each IoT sensor. Second, Sugeno Fuzzy Processing model regulates the energy consumption by proportionately distributing data to nodes without the defuzzification process. Third, Trust-based Neural Data Storage algorithm enriches an adequate data storage capacity by considering the average classification ratio while processing regenerated data packets to pertain each interaction information via Trust Mechanism. Simulation results show that our proposed method effectively covers the monitored area with 15 Joules of energy consumption and 1-ms delay time along with sufficient storage capacity.
A machine learning approach for celebrity profiling
Kavadi D.P., Al-Turjman F., Reddy K.A.N., Patan R.
Article, International Journal of Ad Hoc and Ubiquitous Computing, 2021,
View abstract ⏷
The celebrity profiling is used to predict the sub-profiles like gender, fame, birth-year and occupation of a celebrity for a given textual content. The task of celebrity profiling is introduced in PAN Competition 2019. Most of the researchers in the competition have shown interest on stylistic features to differentiate the writing styles of the celebrities. In this work, a sub-profile based weighted approach is proposed to improve the accuracy of celebrity profiling. In this approach, most frequent terms are used to compute the document weight. The document weights were used to represent the document vectors instead of weights of features. The document vectors forwarded to machine learning algorithms to build the training model. The proposed method achieved competitive accuracies of 77.13% for gender prediction, 87.76% for fame prediction and 91.54% for occupation prediction. The accuracies of the proposed approach for sub-profiles prediction outperform several existing approaches for celebrity profiling.
Effective use of deep learning and image processing for cancer diagnosis
Prassanna J., Rahim R., Bagyalakshmi K., Manikandan R., Patan R.
Book chapter, Studies in Computational Intelligence, 2021, DOI Link
View abstract ⏷
The area of medical image processing obtains its significance with the requirement of precise and effective disease diagnosis over a short period. With manual processing becoming more complicated, stagnant and unfeasible with higher data size, there necessitates automatic processing that can transform contemporary medicine. Deep learning mechanisms can arrive at a higher rate of accuracy in processing and classifying images in comparison with human-level performance. Deep learning not only assist in selecting and extracting features but also possesses the potentiality of measuring predictive target audience and bestows prediction in a more action format to help doctors significantly. Unsupervised Deep Learning for cancer diagnosis is advantageous whenever the involvement of unlabeled data is huge. By bestowing unsupervised deep learning techniques to such unlabeled data, features of pixels that are superior compared to manually obtained features of pixels are said to be learned. Supervised Discriminating Deep Learning directly provides discriminating potentiality for cancer diagnosis purposes. Finally, hybrid deep learning for labeled and unlabeled data is specifically used for cancer diagnosis with a resource or poor pixel representations and hence early detection and diagnosis performed via bank features. Deep Neural Network, as the name implies includes several layers, emphasizing the complex non-linear relationships between the features present in the images, therefore contributing to higher accuracy. Deep Belief Network used in both supervised and unsupervised deep learning adopting greedy mechanism, maximizing the likelihood nature of detection and diagnosis at an early stage. Sequential event analysis is said to be performed by Recurrent Neural Network with the weights being shared across all neurons, contributing diagnosis accuracy. Certain fine-tuned learning parameters of consideration for better and precise learning are Interaction and Non-linear Rectified Activation function, Circumventing over-fitting via Dropout and Optimal Epoch Batch Normalization. In the last section, challenges about the application of deep learning for cancer diagnosis are discussed.
Smart Assistance of Elderly Individuals in Emergency Situations at Home
Reddy A.R., Ghantasala G.S.P., Patan R., Manikandan R., Kallam S.
Book chapter, Internet of Things, 2021, DOI Link
View abstract ⏷
Health monitoring products can improve essential services for elderly patients, with personalized customer service and prescription prompts being two practical areas of assistance. The use of IoT in assistive devices can help to reduce the severity of diseases such as influenza. This therapeutic assistance can also provide precautionary information for infectious diseases such as tuberculosis, malaria, influenza, and HIV. Automatic speech recognition (ASR) can provide computer-generated assistance through IoT devices. For example, the possibility of survival from a sudden infarction is considerably better if an individual obtains assistance in a short period of time. For older individuals, IoT devices can monitor for signs of mental and physical deterioration, with gesture evaluation, interaction, recognition, and alerting methods. This chapter examines emergency assistance in cases of stroke, for which the appropriate therapeutic support can improve the outcome of patients.
A DRL based 4-r Computation Model for Object Detection on RSU using LiDAR in IloT
Mekala M.S., Patan R., Gandomi A.H., Park J.H., Jung H.-Y.
Conference paper, 2021 IEEE Symposium Series on Computational Intelligence, SSCI 2021 - Proceedings, 2021, DOI Link
View abstract ⏷
Internet of vehicle (IoV) network comprises Road Side Unit (RSU), which has become a computation and communication device for effective LiDAR data communication (ex: object detect information) between vehicle-to-infrastructure (V2I) and vehicle-to-vehicle. However, the LiDARs generate a massive volume of 3D data with a notable redundancy rate leads to inadequate object detection accuracy, and the high operational cost of RSU due to inadequate resource and time consumption. Estimating the computation capacity for RSU selection is an NP-hard problem. To address this issue, we propose a Deep Reinforcement Learning (DRL) influenced 4-r computation model to measure RSU cost based on resource feasibility factor and object region detection rate based on novel region-of-interest (RoI) strategy. The resource feasibility factor appraises the residual capacity and cost of RSU based on a criterion of optimality. The RoI strategy eliminates irrelevant points, noise and ground points based on distance and shape measures of an object on RSU with feasible consumption of computation resources. The simulation results show that our mechanism achieves 83% average object detection accuracy rate, 81% average service rate and 17% service offloading rate than state-of-art approaches.
Improved deep learning techniques for better cancer diagnosis
Sekar K.R., Parameshwaran R., Patan R., Manikandan R., Kumar A.
Book chapter, Studies in Computational Intelligence, 2021, DOI Link
View abstract ⏷
Over the past several decades, Computer-Aided Diagnosis (CAD) for diagnosis of medical images has prospered due to the advancements in the digital world, advancements in software, hardware and precise and fine-tune images acquired from sensors. With the advancement in the field of medical and applications of Artificial Intelligence scaling to the height of improvement, modern state-of-the-art applications of Deep Learning for better cancer diagnosis have been incepted in recent years. CAD and computerized algorithms and solutions in diagnosing cancer obtained from different modalities, i.e., MRI, CT scans, OCT and so on plays an immense impact on disease diagnosis. Learning model based on transfer mechanisms that stored knowledge for one aspect and using it for another aspect with Deep Convolutional Neural Network paved the way for automatic diagnosis. Recently, improved deep learning algorithm has resulted in great success resulting in robust image characteristics, involving higher dimensions. Analysis of bi-cubic interpolation preprocessing technique paves way for robust obtaining of a region of interest. For an inflexible object with a higher amount of dissimilarity, a comprehensive form for detecting the region of interest and determination of actual positioning may not be robust. Robust perception and localization schemes are analyzed. By integrating Deep Learning with Neighborhood Position Search unseen cases are said to be identified and segmented accordingly via Maximum Likelihood decision rule, forming robust segmentation. The favorable result of an a better cancer diagnosis is indeed contingent on the cancer diagnosis however, an anticipating prediction should consider certain factors more than a straight forward diagnostic decision. Besides the application of different medical data analyses and image processing techniques used in the study of cancer diagnosis deeper insights of the relevant solutions in the light of higher collections of deep learning techniques are found to be vital. Hence, certain factors to be analyzed are the forecasting of risk involved, forecasting of cancer frequency and the forecasting of cancer survival. These factors are analyzed according to the diagnosis criterion, sensitivity, specificity, and accuracy.
DAWM: Cost-Aware Asset Claim Analysis Approach on Big Data Analytic Computation Model for Cloud Data Centre
Mekala M.S., Patan R., Islam S.K.H., Samanta D., Mallah G.A., Chaudhry S.A.
Article, Security and Communication Networks, 2021, DOI Link
View abstract ⏷
The heterogeneous resource-required application tasks increase the cloud service provider (CSP) energy cost and revenue by providing demand resources. Enhancing CSP profit and preserving energy cost is a challenging task. Most of the existing approaches consider task deadline violation rate rather than performance cost and server size ratio during profit estimation, which impacts CSP revenue and causes high service cost. To address this issue, we develop two algorithms for profit maximization and adequate service reliability. First, a belief propagation-influenced cost-aware asset scheduling approach is derived based on the data analytic weight measurement (DAWM) model for effective performance and server size optimization. Second, the multiobjective heuristic user service demand (MHUSD) approach is formulated based on the CPS profit estimation model and the user service demand (USD) model with dynamic acyclic graph (DAG) phenomena for adequate service reliability. The DAWM model classifies prominent servers to preserve the server resource usage and cost during an effective resource slicing process by considering each machine execution factor (remaining energy, energy and service cost, workload execution rate, service deadline violation rate, cloud server configuration (CSC), service requirement rate, and service level agreement violation (SLAV) penalty rate). The MHUSD algorithm measures the user demand service rate and cost based on the USD and CSP profit estimation models by considering service demand weight, tenant cost, and energy cost. The simulation results show that the proposed system has accomplished the average revenue gain of 35%, cost of 51%, and profit of 39% than the state-of-the-art approaches.
Image analysis and data processing for COVID-19
Kumar A., Manikandan R., Magesh S., Patan R., Ramesh S., Gupta D.
Book chapter, Data Science for COVID-19 Volume 1: Computational Perspectives, 2021, DOI Link
View abstract ⏷
COVID-19 is a deadly disease caused by the severe acute respiratory syndrome coronavirus (SARS-CoV-2). It was first discovered by variations in the respirational and immune systems of a patient who died of a severe acute respiratory syndrome. The first country heavily affected by coronavirus was China. The first case was detected in Wuhan city, China. This virus spreads rapidly from person to person. Based on laboratory tests for coronavirus disease in humans, it is suspected that bats are the natural source of spread of large varieties of virus. The two major viruses, SARS-CoV and Middle East respiratory syndrome coronavirus, originated from the bat; it caused an unexpected disease outbreak in the 21st century throughout the world. Researchers and doctors have investigated COVID in cadavers. The virus was detected in lung, trachea/bronchus, stomach, small intestine, distal convoluted renal tubule, sweat gland, pancreas, adrenal gland, parathyroid, pituitary, cerebrum, and liver. However, it was not noted in bone marrow, heart, aorta, cerebellum, thyroid, testis, esophagus, spleen, lymph node, ovary, muscle, or uterus. This chapter briefly discusses image analysis and data processing used to accelerate COVID-19 detection and support the efforts of researchers and physician to help infected people and break the chain of disease from person to person.
Deep Learning Approach Using 3D-ImpCNN Classification for Coronavirus Disease
Subramaniyan M., Sampathkumar A., Jain D.K., Ramachandran M., Patan R., Kumar A.
Book chapter, Studies in Computational Intelligence, 2021, DOI Link
View abstract ⏷
Coronavirus (COVID-19) is a disease which is spreading rapidly, and nearly 1,436,000 people have been infected in about 200 countries all over the world as of April 2020. It is essential to detect COVID-19 at the earliest stage to care for the infected patients and, moreover, to prevent spreading and protect uninfected people. Deep learning approach, namely, convolutional neural networks (CNNs), requires extensive training data. Due to the recent epidemic, collecting enormous radiographic images in a very short duration is a challenging task. The major issues toward the success of CNN approach is the smaller dataset. Training dataset is scaled, and the results of detecting COVID-19 are boosted by using the proposed 3D-ImpCNN approach. This paper introduces 3D_ImpCNN classification model to categorize the patient affected by COVID. The COVID-19 classification outcomes of the method introduced is analyzed which produced better results when compared against existing methods. Accuracy of 3D-ImpCNN classification method was 96.5%, and moreover this method assists in detecting COVID-19 in a rapid manner.
Adaptive Diagnosis of Lung Cancer by Deep Learning Classification Using Wilcoxon Gain and Generator
Obulesu O., Kallam S., Dhiman G., Patan R., Kadiyala R., Raparthi Y., Kautish S.
Retracted, Journal of Healthcare Engineering, 2021, DOI Link
View abstract ⏷
Cancer is a complicated worldwide health issue with an increasing death rate in recent years. With the swift blooming of the high throughput technology and several machine learning methods that have unfolded in recent years, progress in cancer disease diagnosis has been made based on subset features, providing awareness of the efficient and precise disease diagnosis. Hence, progressive machine learning techniques that can, fortunately, differentiate lung cancer patients from healthy persons are of great concern. This paper proposes a novel Wilcoxon Signed-Rank Gain Preprocessing combined with Generative Deep Learning called Wilcoxon Signed Generative Deep Learning (WS-GDL) method for lung cancer disease diagnosis. Firstly, test significance analysis and information gain eliminate redundant and irrelevant attributes and extract many informative and significant attributes. Then, using a generator function, the Generative Deep Learning method is used to learn the deep features. Finally, a minimax game (i.e., minimizing error with maximum accuracy) is proposed to diagnose the disease. Numerical experiments on the Thoracic Surgery Data Set are used to test the WS-GDL method's disease diagnosis performance. The WS-GDL approach may create relevant and significant attributes and adaptively diagnose the disease by selecting optimal learning model parameters. Quantitative experimental results show that the WS-GDL method achieves better diagnosis performance and higher computing efficiency in computational time, computational complexity, and false-positive rate compared to state-of-the-art approaches.
Machine Learning Inspired Phishing Detection (PD) for Efficient Classification and Secure Storage Distribution (SSD) for Cloud-IoT Application
Thirumallai C., Mekala M.S., Perumal V., Rizwan P., Gandomi A.H.
Conference paper, 2020 IEEE Symposium Series on Computational Intelligence, SSCI 2020, 2020, DOI Link
View abstract ⏷
Cloud-IoT data security and privacy have become a major problem due to its sensitivity, which curbs multiple cloud applications. In addition, if the encrypted data lives in one place, in many fields, such as the financial industry and government agencies, the man-in-the-middle-attack (MMA) and phishing attack (PA) may have chances of realising the extraction. The phishing goal is evaluated and predicted by most previous machine learning models through a discrete or continuous result. The current models lag in accurately determining both attacks because of this approach. We developed a three-step phishing detection (PD) framework inspired by machine learning and a secure storage distribution (SSD) for cloud to improve model accuracy and storage security. The partition-based selection of features is designed for phishing detection (PD) with a hybrid classifier approach and hyper-parameter classifier tuning. Initially, the entire data set is partitioned by entropy and is hybridised for each performing model partition. In order to reduce the complexity, the next entropy is applied to decrease the dimension of each partition. Finally, to improve precision, the performing model is optimised with hyper-parameter tuning. The partition-based feature choice with the hybrid classifier approach outperforms with 97.86% accuracy for both attack detection from the experimental and comparative results of SVM, LM, NN and RF. Atlast, SSD performance is evaluated against other storage models where SSD outperforms other models.
Partial derivative Nonlinear Global Pandemic Machine Learning prediction of COVID 19
Kavadi D.P., Patan R., Ramachandran M., Gandomi A.H.
Article, Chaos, Solitons and Fractals, 2020, DOI Link
View abstract ⏷
The recent worldwide outbreak of the novel coronavirus disease 2019 (COVID-19) opened new challenges for the research community. Machine learning (ML)-guided methods can be useful for feature prediction, involved risk, and the causes of an analogous epidemic. Such predictions can be useful for managing and intercepting the outbreak of such diseases. The foremost advantages of applying ML methods are handling a wide variety of data and easy identification of trends and patterns of an undetermined nature.In this study, we propose a partial derivative regression and nonlinear machine learning (PDR-NML) method for global pandemic prediction of COVID-19. We used a Progressive Partial Derivative Linear Regression model to search for the best parameters in the dataset in a computationally efficient manner. Next, a Nonlinear Global Pandemic Machine Learning model was applied to the normalized features for making accurate predictions. The results show that the proposed ML method outperformed state-of-the-art methods in the Indian population and can also be a convenient tool for making predictions for other countries.
Optimization of routing-based clustering approaches in wireless sensor network: Review and open research issues
Manuel A.J., Deverajan G.G., Patan R., Gandomi A.H.
Review, Electronics (Switzerland), 2020, DOI Link
View abstract ⏷
In today’s sensor network research, numerous technologies are used for the enhancement of earlier studies that focused on cost-effectiveness in addition to time-saving and novel approaches. This survey presents complete details about those earlier models and their research gaps. In general, clustering is focused on managing the energy factors in wireless sensor networks (WSNs). In this study, we primarily concentrated on multihop routing in a clustering environment. Our study was classified according to cluster-related parameters and properties and is subdivided into three approach categories: (1) parameter-based, (2) optimization-based, and (3) methodology-based. In the entire category, several techniques were identified, and the concept, parameters, advantages, and disadvantages are elaborated. Based on this attempt, we provide useful information to the audience to be used while they investigate their research ideas and to develop a novel model in order to overcome the drawbacks that are present in the WSN-based clustering models.
Segmentation of Nuclei in Histopathology images using Fully Convolutional Deep Neural Architecture
Natarajan V.A., Sunil Kumar M., Patan R., Kallam S., Noor Mohamed M.Y.
Conference paper, 2020 International Conference on Computing and Information Technology, ICCIT 2020, 2020, DOI Link
View abstract ⏷
Nuclei segmentation is an initial step in the automated analysis of digitized microscopic images. This paper focuses on utilizing the LinkNET-34 architecture for semantic segmentation of nuclei from the HE stained breast cancer histopathology images. The segmentation process is implemented in two stages where in the first stage the HE stained images are pre-processed to reduce the variance caused because of staining the microscopic images and scanning the slides. During the second stage the preprocessed images are given as input to the LinkNET network which consists of both down-sampling and up-sampling layers. The network is trained using a set of WSI patches released during the Data Science bowl 2018 competition. The performance of the deep learning model is evaluated based on the segmentation accuracy measured using the Dice Coefficient.
Smart healthcare and quality of service in IoT using grey filter convolutional based cyber physical system
Patan R., Pradeep Ghantasala G.S., Sekaran R., Gupta D., Ramachandran M.
Article, Sustainable Cities and Society, 2020, DOI Link
View abstract ⏷
The relationship between technology and healthcare society rises due to the intelligent Internet of Things (IoT) with endless networking capabilities for medical data analysis. Deep Neural Networks and the swift public embracement of medical wearable have been productively metamorphosed in the recent few years. Deep Neural Network-powered IoT allowed innovative developments for medical society and distinctive probabilities to the medical data analysis in the healthcare industry (Yin, Yang, Zhang, & Oki, 2016). Despite this progress, several issues still required to be handled while concerning the quality of service. The key to flourishing in the shift from client-oriented to patient-oriented medical data analysis for healthcare society is applying deep networks to provide a high level of quality in key attributes such as end-to-end response time, overhead and accuracy. In this paper, we propose a holistic Deep Neural Network-driven IoT smart health care method called, Grey Filter Bayesian Convolution Neural Network (GFB-CNN) based on real-time analytics. In this paper, we propose a holistic AI-driven IoT eHealth architecture based on the Grey Filter Bayesian Convolution Neural Network in which the key quality of service parameters like, time and overhead is reduced with a higher rate of accuracy. The feasibility of the method is investigated using a comprehensive Mobile HEALTH (MHEALTH) dataset. This illustrative example discusses and addresses all important aspects of the proposed method from design suggestions such as corresponding overheads, time, accuracy compared to state-of-the-art methods. By simulation, the performance of GFB-CNN method is compared to the state-of-the-art methods with various synthetically generated scenarios. Results show that with minimal time and overhead incurred for sensing and data collection, our method accurately evaluates medical data analysis for heart signals by efficient differentiation between healthy and unhealthy heart signals.
Secure and concealed watchdog selection scheme using masked distributed selection approach in wireless sensor networks
Soundararajan R., Palanisamy N., Patan R., Nagasubramanian G., Khan M.S.
Article, IET Communications, 2020, DOI Link
View abstract ⏷
Selecting secure and dynamic watchdogs for detecting attacks using a type of intrusion detection system (IDS). Theselection procedure of watchdogs in the random ad-hoc wireless sensor network is a load creation job in the absence of acentralised controller. In this type of network, the data processing transmission for the routing process and secure watchdogselection process create overhead in each node. It drains the energy of an individual node easily. Founded on these issues, thiswork concentrates on the secure selection of concealed watchdogs and maintenance of optimal watchdog availability ratio. Inthe random ad-hoc wireless sensor network, the secure and authorised watchdogs are selected from the neighbour list of eachnode on-demand basis to provide security for the network. In addition to this work concentrates on dynamic uncertain conditionsto build a secure and authenticated multi-watchdog system in the distributed scenario. The proposed system uses thecombination of both customised layer masking techniques and secure routing and monitoring techniques for the protection ofrandom ad-hoc wireless sensor networks.
Texture Recognization and Image Smoothing for Microcalcification and Mass Detection in Abnormal Region
Pradeep Ghantasala G.S., Venkateswarlu Naik B., Kallam S., Kumari N.V., Patan R.
Conference paper, 2020 International Conference on Computer Science, Engineering and Applications, ICCSEA 2020, 2020, DOI Link
View abstract ⏷
The second most important cause of death is breast cancer in the country. In the early stages of the disease, primary treatment is difficult as its mechanisms are virtually unknown. Nonetheless, some common signatures of this disease can be used to improve early diagnostics approaches that are important for female Life quality. Mammograms of X-ray are the primary diagnostic and early diagnosis method and are the key to improving the prognosis of breast cancer examination and recovery. Good contrast and sometimes very fluidity of mass and healthy glandular tissue have been described to assist in their treatment, radiologists and internists. Many computerized diagnostics programs have been developed. The method presented in this paper is an important study of visual texture-based mammography for early-stage tumor detection. A few pictures from the digital data base were taken to screen and diagnose cancer mammograms. The suggested algorithm could be used to differentiate mass and micro calcifications by morphological operators from the context fabric and then to separate them using machine learning.
Hash polynomial two factor decision tree using IoT for smart health care scheduling
Manikandan R., Patan R., Gandomi A.H., Sivanesan P., Kalyanaraman H.
Article, Expert Systems with Applications, 2020, DOI Link
View abstract ⏷
The steady growth of an aging population and increased frequency of chronic disease led to the development of Smart Health Care (SHC) systems. While patient prioritization is the core of any SHC system, handling the response time by medical practitioners is a prevailing challenge. With advancements in information technology, the concept of the Internet of Things (IoT) has made it possible to integrate SHC systems with the Cloud environment to not only ensure patient prioritization according to disease prevalence, but also to minimize response time. In this work, an IoT-based scheduling method, called the Hash Polynomial Two-factor Decision Tree (HP-TDT) is proposed to increase scheduling efficiency and reduce response time by classifying patients as being normal or in a critical state in minimal time. The HP-TDT scheduling method involves three stages including the registration stage, the data collection stage, and the scheduling stage. The registration phase is carried out through Open Address Hashing (OAH) model for reducing the key generation response time. Next, the data collection stage is performed using the Polynomial Data Collection (PDC) algorithm. By incorporating PDC, computation overhead is reduced because a number of operations are considered during data collection. Finally, scheduling is performed by applying two-factor, entropy and information gain according to a decision tree. With this, scheduling efficiency is improved due to the classification of patients as being normal or in a critical state. The proposed method minimizes response time, computational overhead, and improves essential scheduling efficiency.
VANETomo: A congestion identification and control scheme in connected vehicles using network tomography
Paranjothi A., Khan M.S., Patan R., Parizi R.M., Atiquzzaman M.
Article, Computer Communications, 2020, DOI Link
View abstract ⏷
The Internet of Things (IoT) is a vision for an internetwork of intelligent, communicating objects, which is on the cusp of transforming human lives. Smart transportation is one of the critical application domains of IoT and has benefitted from using state-of-the-art technology to combat urban issues such as traffic congestion while promoting communication between the vehicles, increasing driver safety, traffic efficiency and ultimately paving the way for autonomous vehicles. Connected Vehicle (CV) technology, enabled by Dedicated Short Range Communication (DSRC), has attracted significant attention from industry, academia, and government, due to its potential for improving driver comfort and safety. These vehicular communications have stringent transmission requirements. To assure the effectiveness and reliability of DRSC, efficient algorithms are needed to ensure adequate quality of service in the event of network congestion. Previously proposed congestion control methods that require high levels of cooperation among Vehicular Ad-Hoc Network (VANET) nodes. This paper proposes a new approach, VANETomo, which uses statistical Network Tomography (NT) to infer transmission delays on links between vehicles with no cooperation from connected nodes. Our proposed method combines open and closed loops congestion control in a VANET environment. Simulation results show VANETomo outperforming other congestion control strategies.
Classification of stroke disease using machine learning algorithms
Govindarajan P., Soundarapandian R.K., Gandomi A.H., Patan R., Jayaraman P., Manikandan R.
Retracted, Neural Computing and Applications, 2020, DOI Link
View abstract ⏷
This paper presents a prototype to classify stroke that combines text mining tools and machine learning algorithms. Machine learning can be portrayed as a significant tracker in areas like surveillance, medicine, data management with the aid of suitably trained machine learning algorithms. Data mining techniques applied in this work give an overall review about the tracking of information with respect to semantic as well as syntactic perspectives. The proposed idea is to mine patients’ symptoms from the case sheets and train the system with the acquired data. In the data collection phase, the case sheets of 507 patients were collected from Sugam Multispecialty Hospital, Kumbakonam, Tamil Nadu, India. Next, the case sheets were mined using tagging and maximum entropy methodologies, and the proposed stemmer extracts the common and unique set of attributes to classify the strokes. Then, the processed data were fed into various machine learning algorithms such as artificial neural networks, support vector machine, boosting and bagging and random forests. Among these algorithms, artificial neural networks trained with a stochastic gradient descent algorithm outperformed the other algorithms with a higher classification accuracy of 95% and a smaller standard deviation of 14.69.
Securing e-health records using keyless signature infrastructure blockchain technology in the cloud
Nagasubramanian G., Sakthivel R.K., Patan R., Gandomi A.H., Sankayya M., Balusamy B.
Retracted, Neural Computing and Applications, 2020, DOI Link
View abstract ⏷
Health record maintenance and sharing are one of the essential tasks in the healthcare system. In this system, loss of confidentiality leads to a passive impact on the security of health record whereas loss of integrity leads can have a serious impact such as loss of a patient’s life. Therefore, it is of prime importance to secure electronic health records. Health records are represented by Fast Healthcare Interoperability Resources standards and managed by Health Level Seven International Healthcare Standards Organization. Centralized storage of health data is attractive to cyber-attacks and constant viewing of patient records is challenging. Therefore, it is necessary to design a system using the cloud that helps to ensure authentication and that also provides integrity to health records. The keyless signature infrastructure used in the proposed system for ensuring the secrecy of digital signatures also ensures aspects of authentication. Furthermore, data integrity is managed by the proposed blockchain technology. The performance of the proposed framework is evaluated by comparing the parameters like average time, size, and cost of data storage and retrieval of the blockchain technology with conventional data storage techniques. The results show that the response time of the proposed system with the blockchain technology is almost 50% shorter than the conventional techniques. Also they express the cost of storage is about 20% less for the system with blockchain in comparison with the existing techniques.
Big data and IoT: Trends, issues and applications
Patan R., Nagasubharmanian G., Balusamy B.
Editorial, Recent Advances in Computer Science and Communications, 2020, DOI Link
Vedic arithmetic based high speed & less area mac unit for computing devices
Jayakumar S., Rajalingam P., Patan R., Ramachandran M.
Article, Recent Advances in Computer Science and Communications, 2020, DOI Link
View abstract ⏷
Background: The rapid improvement in technology enables design of high-speed devices, with development of modified computational elements for FPGA implementation. With complexity increasing day-to-day, there is demand for modified VLSI computational elements. Basically, for the past decade an improvement in basic VLSI Operators like Adder, multiplier is significant. The basic multiplication operator is been completely refined in the aspects of FPGA implementation. Materials and Methods: This paper presents a design of 32-bit high-speed MAC unit based on Vedic computations. Among the many sutras of Vedic mathematics, by using the urdhvatriyagbhyam sutra the products are generated in parallel. This proposed technique results in multiplication step reduction. Results: The result shows that the proposed MAC unit, the number of steps required for multiplication and addition has been reduced, it leads to the decrease in area size. In comparison with the performance of existing method to proposed MAC, the LUT's are reduced by 50 percent. Conclusion: This paper comprehensively describes the basic Multiplication operation using urdhvatriyaghyam sutra for parallel multiplication process. Based on the Vedic sutras, the performance was analyzed on a hardware platform Spartan-3E Xilinx FPGA Device for a 32-bit MAC unit. The Implementation results shoes reduction in critical delay and area when compared to con-ventional booth multiplier-based MAC Design. Hence this works concludes that the proposed Vedic multiplier is suitable for constructing high speed MAC units.
Enhancing the access privacy of IDAAS system using SAML protocol in fog computing
Rupa C.H., Patan R., Al-Turjman F., Mostarda L.
Article, IEEE Access, 2020, DOI Link
View abstract ⏷
Fog environment adoption rate is increasing day by day in the industry. Unauthorized accessing of data occurs due to the preservation of Identity and information of the users either at the endpoints or at the middleware. This paper proposes a methodology to protect and preserve the Identity during data transmission of the users. It uses fog computing for storage against security issues in the cloud and database environment. Cloud and database architectures failed to protect the data and Identity of users but the Fog computing based Identity management as a service (IDaaS) system can handle it with Security Assertion Mark-up Language (SAML) protocol and Pentatope based Elliptic Curve Crypto cipher. A detailed comparative study of the proposed and existing techniques is investigated by considering multi-authentication dialogue, security services, service providers, Identity, and access management.
Improving power and resource management in heterogeneous downlink OFDMA networks
Kousik N.G.V., Yuvaraj N., Suresh K., Patan R., Gandomi A.H.
Article, Information (Switzerland), 2020, DOI Link
View abstract ⏷
In the past decade, low power consumption schemes have undergone degraded communication performance, where they fail to maintain the trade-off between the resource and power consumption. In this paper, management of resource and power consumption on small cell orthogonal frequency-division multiple access (OFDMA) networks is enacted using the sleep mode selection method. The sleep mode selection method uses both power and resource management, where the former is responsible for a heterogeneous network, and the latter is managed using a deactivation algorithm. Further, to improve the communication performance during sleep mode selection, a semi-Markov sleep mode selection decision-making process is developed. Spectrum reuse maximization is achieved using a small cell deactivation strategy that potentially identifies and eliminates the sleep mode cells. The performance of this hybrid technique is evaluated and compared against benchmark techniques. The results demonstrate that the proposed hybrid performance model shows effective power and resource management with reduced computational cost compared with benchmark techniques.
Enhanced adaptive distributed energy-efficient clustering (EADEEC) for wireless sensor networks
Poluru R.K., Praveen Kumar Reddy M., Basha S.M., Patan R., Kallam S.
Article, Recent Advances in Computer Science and Communications, 2020, DOI Link
View abstract ⏷
Background: Recently Wireless Sensor Network (WSN) is a composed of a full number of arbitrarily dispensed energy-constrained sensor nodes. The sensor nodes help in sensing the data and then it will transmit it to sink. The Base station will produce a significant amount of energy while accessing the sensing data and transmitting data. High energy is required to move towards base station when sensing and transmitting data. WSN possesses significant challenges like saving energy and extending network lifetime. In WSN the most research goals in routing protocols such as robustness, energy efficiency, high reliability, network lifetime, fault tolerance, deployment of nodes and latency. Most of the routing protocols are based upon clustering has been proposed using heter-ogeneity. For optimizing energy consumption in WSN, a vital technique referred to as clustering. Methods: To improve the lifetime of network and stability we have proposed an Enhanced Adaptive Distributed Energy-Efficient Clustering (EADEEC). Results: In simulation results describes the protocol performs better regarding network lifetime and packet delivery capacity compared to EEDEC and DEEC algorithm. Stability period and network lifetime are improved in EADEEC compare to DEEC and EDEEC. Conclusion: The EADEEC is overall Lifetime of a cluster is improved to perform the network oper-ation: Data transfer, Node Lifetime and stability period of the cluster. EADEEC protocol evidently tells that it improved the throughput, extended the lifetime of network, longevity, and stability compared with DEEC and EDEEC.
Effective attack detection in internet of medical things smart environment using a deep belief neural network
Manimurugan S., Al-Mutairi S., Aborokbah M.M., Chilamkurti N., Ganesan S., Patan R.
Article, IEEE Access, 2020, DOI Link
View abstract ⏷
The Internet of Things (IoT) has lately developed into an innovation for developing smart environments. Security and privacy are viewed as main problems in any technology's dependence on the IoT model. Privacy and security issues arise due to the different possible attacks caused by intruders. Thus, there is an essential need to develop an intrusion detection system for attack and anomaly identification in the IoT system. In this work, we have proposed a deep learning-based method Deep Belief Network (DBN) algorithm model for the intrusion detection system. Regarding the attacks and anomaly detection, the CICIDS 2017 dataset is utilized for the performance analysis of the present IDS model. The proposed method produced better results in all the parameters in relation to accuracy, recall, precision, F1-score, and detection rate. The proposed method has achieved 99.37% accuracy for normal class, 97.93% for Botnet class, 97.71% for Brute Force class, 96.67% for Dos/DDoS class, 96.37% for Infiltration class, 97.71% for Ports can class and 98.37% for Web attack, and these results were compared with various classifiers as shown in the results.
Securing Data in Internet of Things (IoT) Using Cryptography and Steganography Techniques
Khari M., Garg A.K., Gandomi A.H., Gupta R., Patan R., Balusamy B.
Article, IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2020, DOI Link
View abstract ⏷
Internet of Things (IoT) is a domain wherein which the transfer of data is taking place every single second. The security of these data is a challenging task; however, security challenges can be mitigated with cryptography and steganography techniques. These techniques are crucial when dealing with user authentication and data privacy. In the proposed work, the elliptic Galois cryptography protocol is introduced and discussed. In this protocol, a cryptography technique is used to encrypt confidential data that came from different medical sources. Next, a Matrix XOR encoding steganography technique is used to embed the encrypted data into a low complexity image. The proposed work also uses an optimization algorithm called Adaptive Firefly to optimize the selection of cover blocks within the image. Based on the results, various parameters are evaluated and compared with the existing techniques. Finally, the data that is hidden in the image is recovered and is then decrypted.
Survival Study on Blockchain Based 6G-Enabled Mobile Edge Computation for IoT Automation
Sekaran R., Patan R., Raveendran A., Al-Turjman F., Ramachandran M., Mostarda L.
Article, IEEE Access, 2020, DOI Link
View abstract ⏷
Internet of Things (IoT) and Mobile Edge Computing (MEC) technology acts as a significant part of daily lives to facilitate control and monitoring of objects to revolutionize the ways that human interacts with physical world. IoT system includes large volume of data with network connectivity, power, and storage resources to transform data into meaningful information. Blockchain has decentralized nature to provide useful mechanism for addressing IoT challenges. Blockchain is distributed ledger with fundamental attributes, namely recorded, transparent, and decentralized. Blockchain formed participants in distributed ledger to record the transactions and communicate with other through trustless method. Security is considered as the most valuable features of Blockchain. IoT and Blockchain are emerging ideas for creating the applications to share the intrinsic features. Several existing works has been developed for the integration of blockchain with IoT. But, Blockchain protocols in the state-of-the-art works with IoT failed to consider the computational loads, delays, and bandwidth overhead which lead to new set of problems. The review estimates main challenges in integration of Blockchain and IoT technologies to attain high-level solutions by addressing the shortcomings and limitations of IoT and Blockchain technologies.
Detection and isolation of black hole attack in mobile ad hoc networks: A review
Nagasubramanian G., Sakthivel R.K., Patan R., Ehtemami A., Meyer-Baese A., Tahmassebi A., Gandomi A.H.
Conference paper, Proceedings of SPIE - The International Society for Optical Engineering, 2020, DOI Link
View abstract ⏷
Mobile Ad hoc Network or MANET is a wireless network that allows communication between the nodes that are in range of each other and are self-configuring. The distributed administration and dynamic nature of MANET makes it vulnerable to many kind of security attacks. One such attack is Black hole attack which is a well known security threat. A node drops all packets which it should forward, by claiming that it has the shortest path to the destination. Intrusion Detection system identifies the unauthorized users in the system. An IDS collects and analyses audit data to detect unauthorized users of computer systems. This paper aims in identifying Black-Hole attack against AODV with Intrusion Detection System, to analyze the attack and find its countermeasure.
ECMCRR-MPDNL for Cellular Network Traffic Prediction with Big Data
Dommaraju V.S., Nathani K., Tariq U., Al-Turjman F., Kallam S., Reddy M P.K., Patan R.
Article, IEEE Access, 2020, DOI Link
View abstract ⏷
Big data comprises a large volume of data (i.e., structured and unstructured) stored on a daily basis. Processing such volume of data is a complex task as well as the challenging one. This big data is applied in the cellular network for traffic prediction. Now, benefiting from the big data in cellular networks, it becomes possible to make the analyses one step further into the application level. In order to improve the traffic prediction accuracy with minimum time, Expected Conditional Maximization Clustering and Ruzicka Regression-based Multilayer Perceptron Deep Neural Learning (ECMCRR-MPDNL) technique is introduced. The ECMCRR-MPDNL technique initially collects a large volume of data over the spatial and temporal aspects of cellular networks. Then the collected data are trained with multiple layers such as one input layer, two hidden layers, and one output layer. The activation function is used at the output layer to predict the network traffic based on the similarity value with higher accuracy. These predictors are evaluated using real network traces. Finally, the error rate is calculated for minimizing the prediction error. Experimental evaluation is carried out using a big dataset with different metrics such as prediction accuracy, false-positive and prediction time. The observed result confirms that the proposed ECMCRR-MPDNL technique improves on an average the 98% of performance of network traffic prediction with higher accuracy and 20 % minimum time as well as the false-positive rate as compared to the state-of-the-art methods.
Automated 3-D lung tumor detection and classification by an active contour model and CNN classifier
Kasinathan G., Jayakumar S., Gandomi A.H., Ramachandran M., Fong S.J., Patan R.
Article, Expert Systems with Applications, 2019, DOI Link
View abstract ⏷
The World Health Organization (WHO) recently reported that the lung tumor was the leading cause of death worldwide. In this study, a practical computer-aided diagnosis (CAD) system is developed to increase a patient's chance of survival. Segmentation is acritical analysis tool for dividing a lung image into several sub-regions. This work characterized an automated 3-D lung segmentation tool modeled by an active contour model for computed tomography (CT) images. The proposed segmentation model is used to integrate the local image bias field formulation with the active contour model (ACM). Here, a local energy term is specified by using the mean squared error to reconcile severely in homogeneous CT images and used to detect and segment tumor regions efficiently with intensity inhomogeneity. In addition, a Multiscale Gaussian distribution was applied to the CT images for smoothening the evolution process, and features were determined. For proposed model evaluation, were used the Lung Image Database Consortium (LIDC-IDRI) data set that consisted of 850 lung nodule-lesion images that were segmented and refined to generate accurate 3D lesions of lung tumor CT images. Tumor portions were extracted with 97% accuracy. Using continuous feature extraction of 3-D images leads to attributing the deformation and quantifies the centroid displacement. In this work, predict the centroid displacement and contour points by a curve evolution method which results in more accurate predictions of contour changes and than the extracted images were classified using an Enhanced Convolutional Neural Network (CNN) Classifier. The experimental result shows that the modified Computer Aided Diagnosis (CAD) system has a high ability to acquire good accuracy and assures automated diagnosis of a lung tumor.
Optimal virtual machine selection for anomaly detection using a swarm intelligence approach
Selvaraj A., Patan R., Gandomi A.H., Deverajan G.G., Pushparaj M.
Article, Applied Soft Computing Journal, 2019, DOI Link
View abstract ⏷
Cloud computing plays a significant role in Healthcare Service (HCS) applications and rapidly improves it. A significant challenge is the selection of Virtual Machine (VM) in order to process a medical request. The optimal selection of VM increases the performance of HCS by minimizing the running time of the medical request and also substantially utilizes cloud resources. This paper presents a new idea for optimizing VM selection using a swarm intelligence approach called Analogous Particle swarm optimization (APSO) which works a cloud computing environment. To compute the running time of a medical request, three parameters are considered: Turnaround Time (TAT), Waiting time (WT), and CPU utilization. In addition, a selected optimal VM is used for predicting kidney disease. Early detection of kidney disease facilitates successful treatment. Here, the neural network is used as an automated technique to diagnose kidney disease. A set of experiments and comparisons were performed to analyze the proposed system (APSO and neural network). The results showed that the APSO model performed well, with an execution time of running all particle is 1 s (50 to 80%). Also, the proposed model improved the system efficiency by 5.6%. The precision of recognizing kidney disease using the neural network was 95.7% which outperfomed five other well-known classifiers.
Assistive pointer device for limb impaired people: A novel Frontier Point Method for hand movement recognition
Krishnamurthi R., Patan R., Gandomi A.H.
Article, Future Generation Computer Systems, 2019, DOI Link
View abstract ⏷
In this modern era, the use of computer technology and computing devices play significant role in every day human activities. From the disabled people perspective, there is huge demand to improve Human–Computer Interaction (HCI), to overcome their difficulty in using the standard interactive devices. Basically, HCI provides a way for humans to interact with a computer using a keyboard, a mouse, and other input devices in real-time. This paper proposes a novel assistive pointer device called Frontier Point method (FPM), which is based on a hand movement recognition technique. The proposed hand movement recognition technique primarily focuses on the direction of hand movement for dynamic recognition in real-time using least square fitting and virtual frame techniques. Next based on boundary values, such that if the hand crosses a boundary value of a given quadrant, then a SENDKEY stroke is generated that corresponds to that range. This method is implemented with the help of a depth sensor camera called Kinect. Kinect takes the RGB data and depth data of the human skeleton and generates coordinate information corresponding to specific body joints. Experiments were conducted in which different users were evaluated for their ability to navigate a PowerPoint presentation multiple times. Collectively, an average recognition time of 2.386 s was calculated with an average recognition rate of 97.37%.
A deep neural network based classifier for brain tumor diagnosis
Kumar A., Ramachandran M., Gandomi A.H., Patan R., Lukasik S., Soundarapandian R.K.
Article, Applied Soft Computing Journal, 2019, DOI Link
View abstract ⏷
Classification process plays a key role in diagnosing brain tumors. Earlier research works are intended for identifying brain tumors using different classification techniques. However, the False Alarm Rates (FARs) of existing classification techniques are high. To improve the early-stage brain tumor diagnosis via classification the Weighted Correlation Feature Selection Based Iterative Bayesian Multivariate Deep Neural Learning (WCFS-IBMDNL) technique is proposed in this work. The WCFS-IBMDNL algorithm considers medical dataset for classifying the brain tumor diagnosis at an early stage. At first, the WCFS-IBMDNL technique performs Weighted Correlation-Based Feature Selection (WC-FS) by selecting subsets of medical features that are relevant for classification of brain tumors. After completing the feature selection process, the WCFS-IBMDNL technique uses Iterative Bayesian Multivariate Deep Neural Network (IBMDNN) classifier for reducing the misclassification error rate of brain tumor identification. The WCFS-IBMDNL technique was evaluated in JAVA language using Disease Diagnosis Rate (DDR), Disease Diagnosis Time (DDT), and FAR parameter through the epileptic seizure recognition dataset.
Internet of things mobile-air pollution monitoring system (IoT-Mobair)
Dhingra S., Madda R.B., Gandomi A.H., Patan R., Daneshmand M.
Article, IEEE Internet of Things Journal, 2019, DOI Link
View abstract ⏷
Internet of Things (IoT) is a worldwide system of 'smart devices' that can sense and connect with their surroundings and interact with users and other systems. Global air pollution is one of the major concerns of our era. Existing monitoring systems have inferior precision, low sensitivity, and require laboratory analysis. Therefore, improved monitoring systems are needed. To overcome the problems of existing systems, we propose a three-phase air pollution monitoring system. An IoT kit was prepared using gas sensors, Arduino integrated development environment (IDE), and a Wi-Fi module. This kit can be physically placed in various cities to monitoring air pollution. The gas sensors gather data from air and forward the data to the Arduino IDE. The Arduino IDE transmits the data to the cloud via the Wi-Fi module. We also developed an Android application termed IoT-Mobair, so that users can access relevant air quality data from the cloud. If a user is traveling to a destination, the pollution level of the entire route is predicted, and a warning is displayed if the pollution level is too high. The proposed system is analogous to Google traffic or the navigation application of Google Maps. Furthermore, air quality data can be used to predict future air quality index (AQI) levels.
Hybrid model for security-aware cluster head selection in wireless sensor networks
Shankar A., Jaisankar N., Khan M.S., Patan R., Balamurugan B.
Article, IET Wireless Sensor Systems, 2019, DOI Link
View abstract ⏷
Wireless sensor network (WSN) is considered as the resource constraint network, in which the entire nodes have limited resources. In WSN, prolonging the lifetime of the network remains as the unsolved point. Accordingly, this study intends to propose a hybrid GGWSO (Grouped Grey Wolf Search Optimisation) algorithm to improve the performance of a cluster head selection in WSN, so that the network's lifetime can be extended. The proposed method concerns the main constraints associated with distance, delay, energy, and security. This study compares the performance of the proposed GGWSO with several traditional algorithms like artificial bee colony (ABC), fractional ABC, group search optimisation and Grey Wolf optimisation-based cluster head selection. During the performance analysis, the various ranges of risk, such as 20, 60, and 100% are added to validate the performance variations, by evaluating the number of alive nodes, and normalised network energy remained in the network. The simulation results have shown that there is a need for a hybrid model for attaining the superior results.
Enhancement of security in the internet of things (IoT) by using X.509 authentication mechanism
Karthikeyan S., Patan R., Balamurugan B.
Conference paper, Lecture Notes in Electrical Engineering, 2019, DOI Link
View abstract ⏷
Internet of Things (IoT) is the interconnection of physical entities to be combined with embedded devices like sensors, activators connected to the Internet which can be used to communicate from human to things for the betterment of the life. Information exchanged among the entities or objects, intruders can attack and change the sensitive data. The authentication is the essential requirement for security giving them access to the system or the devices in IoT for the transmission of the messages. IoT security can be achieved by giving access to authorized and blocking the unauthorized people from the internet. When using traditional methods, it is not guaranteed to say the interaction is secure while communicating. Digital certificates are used for the identification and integrity of devices. Public key infrastructure uses certificates for making the communication between the IoT devices to secure the data. Though there are mechanisms for the authentication of the devices or the humans, it is more reliable by making the authentication mechanism from X.509 digital certificates that have a significant impact on IoT security. By using X.509 digital certificates, this authentication mechanism can enhance the security of the IoT. The digital certificates have the ability to perform hashing, encryption and then signed digital certificate can be obtained that assures the security of the IoT devices. When IoT devices are integrated with X.509 authentication mechanism, intruders or attackers will not be able to access the system, that ensures the security of the devices.
Reliable and energy-efficient emergency transmission in wireless sensor networks
Singanamalla V., Patan R., Khan M.S., Kallam S.
Letter, Internet Technology Letters, 2019, DOI Link
View abstract ⏷
In the remote system, wireless sensors networks are used to forward messages of specific needs by minimizing energy consumption. This process needs to maintain the hubs with various activities of the network. The network components are suitable for conventional packet transmission, but not for emergency information transmission as it consistently requires high-quality links. In emergency information transmission, more cooperation is required by nodes, but at the same time, we must minimize the energy required in emergency transmission to formtopology construction, partitioning, relaying nodes clustering, and then cluster the total number of nodes. In this paper, proposed an energy-aware emergency transmission scheme which decreases the hub’s energy utilization maintained between 8% and 11% in reliable data transmission, increase transmission accuracy by 25%, and packet transmission delay decreases by 600 to 700 milliseconds while increasing the number of clusters in topology.
An intelligent approach for UAV and drone privacy security using blockchain methodology
Rana T., Shankar A., Sultan M.K., Patan R., Balusamy B.
Conference paper, Proceedings of the 9th International Conference On Cloud Computing, Data Science and Engineering, Confluence 2019, 2019, DOI Link
View abstract ⏷
In today's era drones and UAV are being used more and more for spying and warfare. Their excessive use makes them vulnerable to be hacked and used for malicious purposes. There are also security loopholes in this technology like the radio waves which can be exploited by the rivals and can cause a large amount of destruction or loss of data. This paper is written to improve the security of UAV and drones by using blockchain technology. Blockchain is a highly secured technology as it uses private key cryptography and peer to peer network. By incorporating this technology in transmitting signals from controller to drone or UAV, we can achieve an extra amount of security in transmitting of signals also it increases the connectivity.
To Identify Visible or Non-visible-Based Vehicular Ad Hoc Networks Using Proposed BBICR Technique
Suresh K., Rizwan P., Balamurugan B., Rajasekharababu M., Sreeji S.
Conference paper, Advances in Intelligent Systems and Computing, 2019, DOI Link
View abstract ⏷
In vehicular ad-hoc network design, the border node can be select based on one-hop neighbor data using a minimum neighbor based distance concept. Where the different existing approach and various protocols are examined for nodes are located nearest neighbor position lists are follows a distributed network based strategy. Thus, determine which vehicle/nodes share the least number of common neighbors. In this proposed paper, nodes which satisfy present state are typically outermost from next forwarding node of border side of intercommunication system model with border-based routing making hybridization, minimizing end-to-end delay and improving average throughput with our hybrid protocol that is BBICR, using MATLAB 2014Ra version.
Robust Defense Scheme Against Selective Drop Attack in Wireless Ad Hoc Networks
Poongodi T., Khan M.S., Patan R., Gandomi A.H., Balusamy B.
Article, IEEE Access, 2019, DOI Link
View abstract ⏷
Performance and security are two critical functions of wireless ad-hoc networks (WANETs). Network security ensures the integrity, availability, and performance of WANETs. It helps to prevent critical service interruptions and increases economic productivity by keeping networks functioning properly. Since there is no centralized network management in WANETs, these networks are susceptible to packet drop attacks. In selective drop attack, the neighboring nodes are not loyal in forwarding the messages to the next node. It is critical to identify the illegitimate node, which overloads the host node and isolating them from the network is also a complicated task. In this paper, we present a resistive to selective drop attack (RSDA) scheme to provide effective security against selective drop attack. A lightweight RSDA protocol is proposed for detecting malicious nodes in the network under a particular drop attack. The RSDA protocol can be integrated with the many existing routing protocols for WANETs such as AODV and DSR. It accomplishes reliability in routing by disabling the link with the highest weight and authenticate the nodes using the elliptic curve digital signature algorithm. In the proposed methodology, the packet drop rate, jitter, and routing overhead at a different pause time are reduced to 9%, 0.11%, and 45%, respectively. The packet drop rate at varying mobility speed in the presence of one gray hole and two gray hole nodes are obtained as 13% and 14% in RSDA scheme.
A survey of specific iot applications
Alzubi J.A., Manikandan R., Alzubi O.A., Gayathri N., Patan R.
Article, International Journal on Emerging Technologies, 2019,
View abstract ⏷
Internet of Things (IoT) is the prototype in which physical objects are connected through various mediums for purposeful interactive communication. The implementation of IoT in various applications, such as communication and connectivity, environment and infrastructure, healthcare, home and living areas, automation and augmented reality, is mentioned in the research paper, which also discusses the various challenges encountered in the application of IoT that are related to security, enterprises, consumer privacy, data, storage management, server technologies and data center network. The main vision of IoT is to enable living objects with computing and communicating abilities to facilitate interactions amongst themselves. The main objective of this paper is to impart knowledge about Internet of Things (IoT) in a wider perspective.
Improving the Response Time of M-Learning and Cloud Computing Environments Using a Dominant Firefly Approach
Sekaran K., Khan M.S., Patan R., Gandomi A.H., Krishna P.V., Kallam S.
Article, IEEE Access, 2019, DOI Link
View abstract ⏷
Mobile learning (m-learning) is a relatively new technology that helps students learn and gain knowledge using the Internet and Cloud computing technologies. Cloud computing is one of the recent advancements in the computing field that makes Internet access easy to end users. Many Cloud services rely on Cloud users for mapping Cloud software using virtualization techniques. Usually, the Cloud users' requests from various terminals will cause heavy traffic or unbalanced loads at the Cloud data centers and associated Cloud servers. Thus, a Cloud load balancer that uses an efficient load balancing technique is needed in all the cloud servers. We propose a new meta-heuristic algorithm, named the dominant firefly algorithm, which optimizes load balancing of tasks among the multiple virtual machines in the Cloud server, thereby improving the response efficiency of Cloud servers that concomitantly enhances the accuracy of m-learning systems. Our methods and findings used to solve load imbalance issues in Cloud servers, which will enhance the experiences of m-learning users. Specifically, our findings such as Cloud-Structured Query Language (SQL), querying mechanism in mobile devices will ensure users receive their m-learning content without delay; additionally, our method will demonstrate that by applying an effective load balancing technique would improve the throughput and the response time in mobile and cloud environments.
Intelligent data delivery approach for smart cities using road side units
Kulandaivel R., Balasubramaniam M., Al-Turjman F., Mostarda L., Ramachandran M., Patan R.
Article, IEEE Access, 2019, DOI Link
View abstract ⏷
Smart city progress from classical homogenous technologies with limited facility to heterogeneous interconnected network with immense capabilities. Furthermore, there is a good concern in expanding the scope of application in the smart city. The primary objective of the smart city is to achieve optimization and reinforce the Quality of Service (QoS) of applications by cleverer usage of urban resources. The QoS in the network is measured using several factors like end-end delay, energy consumption, packet loss and throughput. Several pitfalls are experienced in the existing routing innovation. In this proposal, a new technology-based routing structure is proposed. Road Side Units (RSU) will allow the planners to deploy the application without unfamiliar tools for data process and gathering. Data forwarding, acquisition and diffusion are simplified by RSU. K-Nearest Neighbor is used for finding the nearest neighbor nodes and it is optimized using Whale optimization Algorithm (WOA). The evaluation outcomes prove that the intended routing plot provides much spectacle than existing protocols for real time applications.
Recent trends in sustainable big data predictive analytics: Past contributions and future roadmap
Basha S.M., Rajput D.S., Bhushan S.B., Poluru R.K., Patan R., Manikandan R., Kumar A.
Article, International Journal on Emerging Technologies, 2019,
View abstract ⏷
As the vast amount of digital data is available and generated by most of the industries. To make use of such vast amount of data in critical decision making, Predictive analytics needs to perform on it. In the recent years Big Data Predictive Analytics (BDPA) is being a popularly used Technology to extract knowledge from huge data, addressing the many dimensions in all the industries. At this point of view, an attempt is made to understand the things happening around BDPA and its impact shown on businesses. This paper contributes in investigating the research carried out by observing current and past trends on BDPA from the last ten years and applying Machine Learning Algorithms in BDPA. Additionally, a standard reference model is developed. To provides a way to research in BDPA, finally list out the few challenges and issues of BDPA. The research carried out throughout the paper helps in providing the road map to the researchers in the area of BDPA.
Evaluating the Performance of Deep Learning Techniques on Classification Using Tensor Flow Application
Kallam S., Basha S.M., Singh Rajput D., Patan R., Balamurugan B., Khalandar Basha S.A.
Conference paper, Proceedings on 2018 International Conference on Advances in Computing and Communication Engineering, ICACCE 2018, 2018, DOI Link
View abstract ⏷
In Deep Learning, Artificial intelligence is the overall bigger domain, in which machines given the capability to learn new instances of data and then adapt to the basic domain of Machine Learning. Deep Learning is a subset of it, which goes into further accuracy that uses neural networking technology to go in and enable more complex situational data to come in and make more precise decisions. The objective of this research is to find out the details like Ratio of training data, Noise, Batch Size, Properties of features, learning rate, Type of Activation function, Level of Regularization, Rate of Regularization in constructing Neural Network on four different Classification Datasets after directly manipulating design providing in Tensor flow playground application. The Evaluation parameters consider in our experiments are Test loss and Training lose. The findings in our research is to specify that, how many hidden layers and number of neurons in each hidden layer are needed, for each type of classification problem. These findings help the researchers to fix the Maximum number of neurons and hidden layers needed in solving the four different types of classification problems by achieving test loss less than 0.005.
To detect and Recognize Object from Videos for Computer Vision by Parallel Approach using Deep Learning
Nalinipriya G., Baluswamy B., Patan R., Kallam S., Tamizharasi G.S., Babu M.R.
Conference paper, Proceedings on 2018 International Conference on Advances in Computing and Communication Engineering, ICACCE 2018, 2018, DOI Link
View abstract ⏷
Computer vision is the multidisciplinary domain extracts and analyses digital images in an automated manner. The application of computer vision is widespread and it ranges from agriculture to robotics. At present, computer vision adopts the concept of machine learning to build a model and solves classification problems. However, this technique becomes inefficient when it is directly applied to digital images as it ignores the structure and compositional nature of the images. Deep Convolutional Neural Network (CNN) acts as the best solution to traditional computer vision approaches as it learns to extract features from the raw images along with the classification process. In this paper, we present a deep learning based solution to computer vision problem. First, we define a CNN based approach to learn and extract features from the real time videos. Next, an extended linear support vector machine (SVM) classifier is used for object classification processes. Thus the proposed method make use of the combinational approach of the deep learning and machine learning to solve computer vision problems. Since deep CNN are massively parallel algorithms the application of CNN techniques with GPU forms the effective solution for computer vision problems. The experimental results are evaluated in terms performance, accuracy and simplicity measures.
Low energy aware communication process in IoT using the green computing approach
Kallam S., Madda R.B., Chen C.-Y., Patan R., Cheelu D.
Article, IET Networks, 2018, DOI Link
View abstract ⏷
The Internet of Things (IoT) is a ubiquitous network that interconnects and integrates the devices and cyberspace to enable the smart objects. It lays a platform to collect, process, and to analyse the data for monitoring and controlling the cyber- physical world by using IoT sensor devices. These sensor devices can be wired or wireless that connects to IoT. The wireless devices are battery-operated devices, unlike wired devices. The energy reduction is critical for battery-operated devices. The smart devices need an intelligent transmission that increases the life of the devices. There are difficulties in sensor management with regard to energy reduction by applying the energy-efficient communication energy saved over IoT devices communication. Finally, the low energy aware communication process can enhance device life time in IoT. Least energy aware communication technique is a promising paradigm for IoT is reduced 30% communication overhead.
Real-time big data computing for Internet of Things and cyber physical system aided medical devices for better healthcare
Rizwan P., Rajasekhara Babu M., Balamurugan B., Suresh K.
Conference paper, Proceedings of Majan International Conference: Promoting Entrepreneurship and Technological Skills: National Needs, Global Trends, MIC 2018, 2018, DOI Link
View abstract ⏷
The new generation of systems are may using integration called cyber-physical system (CPS). It includes computational, control and communication capabilities. How humans are interconnected to the each other, CPS also interact physical objects as well. Currently, the study of CPS is still in its initial stages and there exist many research issues. The CPS integrating with medical devices is easy but handling their quires very quickly it is very difficult. In This paper proposed Real-Time big data computing for CPS enabled medical device association. It includes the many cyber physical enhanced secured Internet of things (IoT) integrated Big data steam computing platforms, and their architecture and its application to the Medical device monitoring and decision support systems is specified. Finally, a medical device associated with big data stream computing platforms. Produce high performance in overall medical device computing, communication, control, resource management and scheduling cores.
A novel performance aware real-time data handling for big data platforms on Lambda architecture
Patan R., Rajasekhara Babu M.
Conference paper, International Journal of Computer Aided Engineering and Technology, 2018, DOI Link
View abstract ⏷
Big data is becoming a popular technology for analytics. But, its techniques and tools are very limited to solve the energy aware real time data handling problems. The real time data handling can be in one of the two computing areas: 1) batch computing; 2) stream computing. Stream computing environment uses round robin algorithm as default scheduling strategy whereas batch process uses distributed scheduling for allocation of its resources. But these computing are not considered proper energy aware distributed scheduling policies for allocation of its resources. This paper presents development of management policies that reduces the energy for the allocation of resources. The big data fusion has been used to improve the efficiency for handing different data types: Batch data, online data, and real-time data. A hybrid computational model has been applied to improve the performance further through Lambda architecture. Finally, experimental results have shown 20% performance improvement.
Real-time smart traffic management system for smart cities by using Internet of Things and big data
Rizwan P., Suresh K., Rajasekhara Babu M.
Conference paper, Proceedings of IEEE International Conference on Emerging Technological Trends in Computing, Communications and Electrical Engineering, ICETT 2016, 2017, DOI Link
View abstract ⏷
Smart Traffic management system (STMS) is a one of the important feature for smart city. Currently traffic management and alert systems are not fulling needs of STMS. It is more expensive and highly configurable to provide better service for traffic management. This paper proposes a low cost Real-Time smart traffic Management System to provide better service by deploying traffic indicators to update the traffic details instantly. Low cost vehicle detecting sensors are embed in the middle of road for every 500 meters or 1000 meters. Internet of Things (IoT) are being used to acquire traffic data quickly and send it for processing. The Real time streaming data is sent for Big Data analytics. There are several analytical scriptures to analyze the traffic density and provide solution through predictive analytics. A mobile application is developed as user interface to explore the density of traffic at various places and provides an alternative way for managing the traffic.
EEIoT: Energy efficient mechanism to leverage the Internet of Things (IoT)
Suresh K., Rajasekharababu M., Patan R.
Conference paper, Proceedings of IEEE International Conference on Emerging Technological Trends in Computing, Communications and Electrical Engineering, ICETT 2016, 2017, DOI Link
View abstract ⏷
IoT has become popular in smart vision of world development. It is more and more complex due to billions of heterogeneous wireless devices communicating each other. Each wireless sensor node or device consumes more energy for its communication. There are various techniques for reduction of this energy Minimum Energy Consumption Algorithm(MECA). But these techniques are inefficient due to direct deployment of Sensor nodes in the network without considering the more energy consume when transmitting. EEIoT proposes an Energy Efficient Internet of Things technique that deals and regulates energy factors in IoT efficiently. It is a self-adaptive technique that aims to minimize the energy harvesting in significant manner on Internet of Things. Finally, it presents a comparative result against existing methods on energy consumption factors.
Design and development of low investment smart hospital using internet of things through innovative approaches
Rizwan P., Babu M.R., Suresh K.
Article, Biomedical Research (India), 2017,
View abstract ⏷
Currently smart hospitals are very few as well as very expansive. The cost of these smart hospital set up can be reduced by deploying Internet of Things (IoT). IoT is booming technology in many fields for smart environments. This paper presents an innovative technical support for development of smart hospitals with low investment. Automation in dealing with medical things reduces the human intervention. Patient remote monitoring system monitors the chronic disease patient’s health condition continuously and generates alerts during abnormal situations of patient’s health. A Patient remote monitoring system includes wearable devices which are developed by using Internet of Things. The wearable devices track the patients’ health condition continuously. In addition, the hospital beds equipped with sensors that measure patient’s vital signs that can be converted to deploy as Internet of Medical Things (IoMT) technology. Finally, the proposed model built with very limited capital that provides better service for all kind of peoples.
Re-storm: Real-time energy efficient data analysis adapting storm platform
Patan R., Rajasekhara Babu M.
Article, Jurnal Teknologi, 2016, DOI Link
View abstract ⏷
It is necessary to model an energy efficient and stream optimization towards achieve high energy efficiency for Streaming data without degrading response time in big data stream computing. This paper proposes an Energy Efficient Traffic aware resource scheduling and Re-Streaming Stream Structure to replace a default scheduling strategy of storm is entitled as re-storm. The model described in three parts; First, a mathematical relation among energy consumption, low response time and high traffic streams. Second, various approaches provided for reducing an energy without affecting response time and which provides high performance in overall stream computing in big data. Third, re-storm deployed energy efficient traffic aware scheduling on the storm platform. It allocates worker nodes online by using hot-swapping technique with task utilizing by energy consolidation through graph partitioning. Moreover, re-storm is achieved high energy efficiency, low response time in all types of data arriving speeds.it is suitable for allocation of worker nodes in a storm topology. Experiment results have been demonstrated the comparing existing strategies which are dealing with energy issues without affecting or reducing response time for a different data stream speed levels. Finally, it shows that the re-storm platform achieved high energy efficiency and low response time when compared to all existing approaches.
A novel biomedical data solutions by using big data platforms for better health care service
Article, International Journal of Pharmacy and Technology, 2016,
View abstract ⏷
Big Data is broad term critical passion to apply health care service. Data play’s vital role in more fields as well as health care field. Patient current health condition known only progress for further better health care. In This paper present a medical data analysis, transfer, compute, store etc. actions by using big data platforms. Digital devices capture and generate different forms of data to produce different passion to processing area. For faster and deeper data tactics are need to perform on top of medical data sets. To reducing the time wastage and improving performance overall medical data processing strategy by using various tools storm, spark, and Hadoop etc. all-inclusive hybrid computation model. Theoretical evaluation model are to be designed shown in it. And Experimental prototype setup created a feasible environment for effective medical data processing. Finally, results compared by traditional data processing models analyze up to 30-40% efficiency shown proposed framework.
Performance improvement of Data analysis of IoT applications using restorm in big data stream computing platform
Rizwan P., RajasekharaBabu M.
Article, International Journal of Engineering Research in Africa, 2016, DOI Link
View abstract ⏷
Big Data and Internet of Things (IoT) are two popular technical terms in current IT industry. The analysis of IoT data consumes more energy since it is huge in size. This paper proposes a methodology re-storm that addresses energy issues and response time of IoT applications data. It uses big data stream computing for re-storm against existing method storm. The storm failed to address dynamic scheduling but re-storm deals with energy-efficient traffic aware resource scheduling. This paper presents a model that different traffic arriving rate of streams re-storm at multiple traffic levels for high energy efficiency, low response time. It deals at three levels, firstly, a mathematical model for high energy efficiency, low response time. Secondly, allocation of resources bearing in mind DVFS (Dynamic Voltage and Frequency Scaling) methods and existing effective optimal consolidation methods. Thirdly, online task allocation using hot swapping technique, streaming graph optimizing. Finally, the experimental results show that restorm has been improved the performance 30-40% against storm for real time data of IoT applications.
A study analysis of energy issues in big data
Patan R., Rajasekhara Babu M.
Article, International Journal of Applied Engineering Research, 2015,
View abstract ⏷
The rapid growth of data management Through Big Data techniques and increasing the burden of the data centers growing through the energy standards, time, cooling strategy. So developers are being concern about the huge Energy consumption in the data centers. This paper presents the energy efficiency and cooling issues in data centers and comparative analysis of data warehouse, data mining, cloud computing a) Techniques for managing energy in hardware level and software level b) Power and cooling Issues for consuming energy in data centers c) Comparison of various algorithms for load aggression and task scheduling. Finally to maximize the Energy efficiency of data centers there are some other component like Storage, memory and bandwidth that also consumes energy and must be taken under consideration while making energy efficient policies.
