With the rapid digitization of services, network traffic has surged, leading to increased cybersecurity risks such as Distributed Denial of Service (DDoS) and zero-day attacks. Zero-day attacks are particularly dangerous as they exploit unknown vulnerabilities and often bypass traditional Intrusion Detection Systems (IDS). While Deep Learning (DL)-based IDSs can automatically learn features without manual signature extraction, they often struggle to detect zero-day attacks, especially those with complex data patterns. Recently, hybrid DL approaches have shown promise by learning from historical network behavior to better identify such advanced threats. Thus, this research developed a Wide Residual Quantum Dilated Convolutional Neural Network for zero-day attack detection. In the training phase, the input target and source domains are passed to the Manifold alignment, and the outcome acquired is the transformed source and target domains. Then, Deep Fuzzy Clustering is utilized to cluster the transformed source domain. Furthermore, the clustered source domain and transformed target domain are applied over the Manhattan distance to generate labelled source and soft-labelled target data and are utilized for training the Wide Residual Quantum Dilated Convolutional Neural Network model to detect zero-day attacks. In the testing phase, zero-day attack detection is conducted to determine whether the attack is normal or a zero-day attack by utilizing a Wide Residual Quantum Dilated Convolutional Neural Network. The devised Wide Residual Quantum Dilated Convolutional Neural Network has gained superior performance with a True Negative Rate of 91.27 %, True Positive Rate of 91.79 %, accuracy of 91.57 %, F-measure of 90.18 %, and Precision of 90.81 %.

Intrusion detection systems are playing a critical role in protecting networks against advanced cyber threats. However, the discovery of unknown attacks is challenging, where these are the attacks which are completely novel and have no patches. In this paper, the authors present an unsupervised intrusion detection system that successfully detects zero-day attacks by applying unsupervised deep learning and machine learning methods. The proposed system was tested through extensive experimentation on famous benchmark datasets UNSW NB-15 and NSL-KDD. The experimentation outcome reflects the efficacy of the proposed approach in spotting zero-day attacks. Comparison with other related works showed that the proposed IDS system outperforms the existing systems.

Breast cancer is emphasized as one of the significant contributing factors to mortality among women worldwide, and early diagnosis is a major factor in increasing the survival rate. The conventional processing of images is a complex task that requires a high level of expertise, and this may result in inconsistencies in the results. In an effort to overcome these issues, this paper proposes a hybrid deep-learning Approach for the screening process in breast cancer from images in BUSI dataset. The proposed model integrates medical-aware preprocessing methods such as CLAHE, tissue segmentation for background removal, dataset-aware normalization, and data augmentation methods for improving the robustness and quality related to the images. Deep feature extraction is performed using a MobileNetV2 backbone network After the model has been trained on the image dataset, the features were reduced using averaging and fed into the dense layers. to extract a compact 256-dimensional feature vector. The extracted features are analyzed using an ensemble method that combines the Kernel Extreme Learning Machine (KELM) and the Deep Belief Network (DBN). The final results are obtained through the probabilistic combination of the two classifiers. The ensemble method takes advantage of the fast learning capability of KELM and the superior ability of DBN in modeling deep hierarchical structures, thereby improving the robustness and stability of the classification task. Experimental evaluation confirms that the developed hybrid framework achieves a classification accuracy of 96.15% in differentiating benign and malignant breast tumors. The proposed framework is computationally efficient and demonstrates strong potential for improving early breast cancer detection and supporting modern computer-aided diagnostic systems.

Sentiment analysis, an important part of natural language processing, looks for opinions and emotional polarity in written data like product reviews, social media posts, and customer feedback. Organizations can better understand user perspectives and make well-informed decisions with the aid of accurate sentiment classification. In order to enhance classification performance, we present an ensemble-based sentiment analysis framework in this work that combines transformer architectures with deep learning methods. The suggested method captures both contextual and hierarchical relationships in textual data using a Capsule Neural Network (CapsNet) and pre-trained transformer models like RoBERTa and ELECTRA. The models undergo preprocessing, tokenization, and evaluation on the SST-2 sentiment dataset.as well as feature extraction. A weighted ensemble voting strategy is used to combine the outputs of individual models based on optimized weight configurations in order to improve prediction accuracy and stability. According to experimental results, the accuracy of the RoBERTa model was 93.55%, whereas the accuracy of ELECTRA and CapsNet was 94.70%. The weighted ensemble model demonstrated consistent and dependable sentiment classification performance with an overall accuracy and F1- score of 94.70%. The suggested framework demonstrates how transformer-based architectures can be successfully combined with capsule networks and ensemble learning methods to create reliable sentiment analysis systems.

The objective of this paper is predicting the production of electrical power from human movements by the utilization of piezoelectric materials. The piezoelectric sensor creates electricity by applying mechanical pressure or vibration to the sensor along with movements like walking and running. The machine converts the mechanical energy present in the motion to electrical energy, which can be tapped and utilized to power small electronic devices such as LEDs, sensors, and wireless modules. Besides the power production function, machine learning is applied at a rudimentary level to investigate human movements and pressure. Based on the information, the power production can be estimated and the efficiencies enhanced. The integration of rudimentary machine learning and piezoelectric power harvesting is therefore a clean, green, and feasible means for tapping power from day-to-day human activities.

This research paper investigates a novel control design for the frequency control of Islanded Microgrid driven, equipped with diesel based generator engine, Wind and the Solar power without some energy storage devices. Fluctuations in frequency is being occurred due to the power consumption of (heat pump, freezer) non critical loads as well as plug in electric vehicle with its charging and discharging process. To investigate the performance metrix of Islanded Microgrid several step load disturbances conditions are included in wind, solar and load. Controller parameters are optimized by novel applications of Electric Eel's Foraging Optimization (EEFO) technique along with the most popular Particle swarm optimization (PSO) algorithm. Simulation results disclose that the EEFO optimized controller outperforms the other controllers in all aspects of performed disturbances.

Agriculture plays a crucial role in sustaining human life, and the global food supply is vulnerable to the devastating impact of plant diseases. The increasing threat to global food security due to plant diseases necessitates the development of efficient and accurate methods for early disease detection. Timely and accurate detection of diseases in crops is critical for ensuring food security and minimizing economic losses. Conventional approaches are time-consuming and may not scale effectively. This paper proposes three deep learning methos namely MLP, Convnets and Densenets for plant disease detection. A plant disease dataset from Kaggle was collected. The dataset consists of 25 classes of images five categories of plants namely apple, corn, tomato, potato and grape. The original dataset is divided into five datasets and three deep learning techniques namely Multi-Layer Perceptron, Convents and Densenets area applied. The experiments revealed that that Convnets performed better for apple, corn, grape and potato datasets disease classification and Densenet performed well for tomato dataset.

In this current work, one of the maiden approaches was made frequency regulation in a Standalone AC Microgrid (μG) by considering Spotted Hyena optimizer based Cascaded PI-PD controller. These μGrid can be formed by merging some the isolated such as renewable energy resources, wind power and also solar electricity irradiations. Discrepancy any these-sources will influence system frequency and hence-frequency control-theme in MG was challenging issue for all-the researchers. Inspite of these struggling this current paper consider a-Cascaded PI-PD-controllers as secondary frequency controller for the-Standalone μGrid, and a novel Spotted Hyena Optimizer (SHO) is used to tuning and obtaining the controller parameters. The proposed cascaded controllers inspected on a μGrid test system, and robustness is assessed considering -dissimilar variations in load. In order to manifest the effectiveness of the Cascaded PI-PD controller, it-is being compared to some more conventional controller as Proportional Integral (PI), and Proportional Integral and-Derivative (PID) controllers and also to verify the-potency of the-Spotted Hyena optimizer, the-results obtained-by the SHO are been-compared with other intelligence swarm-techniques.

Zero-day attack detection in Intrusion Detection Systems is challenging due to the lack of labeled instances. This paper applies manifold alignment approach of TL that transforms the source and target domains into a common latent space to evade the problem of different feature spaces and different marginal probability distributions among the domains. On the transformed space, a method is proposed for generating target soft labels to compensate for the lack of labeled target instances by applying the cluster correspondence procedures. On top of this, DNN is applied to build a framework for the detection of zero-day attacks. Authors have conducted several experiments using NSL-KDD and CIDD datasets to evaluate the performance of the proposed framework. From the experimental results it is evident that the proposed framework could successfully detect zero-day attacks on unseen data.

Machine learning based Intrusion Detection Systems (IDSs) have been explored by many researchers in the recent times and resulted in considerable success in dealing with known attacks by signature formation. However, new attacks due to their behavioral variation from the known attacks are unknown to the defender and are hard to discover using the known signatures and hence, remain as a challenging issue. In this paper, the challenge of detecting new attacks is handled through IDS collaboration using transfer learning. A Transfer learning framework is proposed by the authors for detecting new attacks with minimal labelled instances in cloud and non-cloud Intrusion Detection Network (IDN) environments. Transfer learning approach is applied to handle the detection of new attacks by modeling it as target task, involving a related source domain that has sufficient number of labeled instances. The learned knowledge from the source domain can be transformed to the target domain to compensate for the scarcity of labeled instances needed for new attack detection. To allow the smooth knowledge transfer among the domains which are having disparity in feature spaces and distributions, this paper presents a methodology for extraction of domain invariant features using manifold alignment process that transforms both source and target datasets into a common latent space. Extensive experimentation on multiple bench mark datasets was conducted in this paper. From the results, it is evident that the proposed method succussfully detects new attacks in cloud and non-cloud environments with high accuracy and low false positive rates.

Intrusion detection is an evolving area of research in the field of cyber-security. Machine learning offers many best methodologies to help intrusion detection systems (IDSs) for accurately identifying intrusions. Such IDSs analyze the features of traffic packets to identify different types of attacks. While most of the features used in IDS are numeric, some of the features like Protocol-type, Flag and Service are categorical and hence calls for an effective encoding scheme for transforming the categorical features into numeric form before applying PCA like techniques for extracting latent features from numeric data. In this paper, the authors investigate the suitability of encoding categorical features based on the posterior probability of an attack conditioned on the feature in the context of IDS. KNN classifier is used for construction of IDS on top of latent features in numeric form. The proposed method is trained and tested on NSL-KDD data set to predict one among the possible 40 distinct class labels for a test instance. Classification accuracy and false positive rate (FPR) are considered as performance metrics. The results have shown that the proposed approach is good at detecting intrusions with an accuracy of 98.05% and a false alarm rate of 0.35%.

Upon application of supervised machine learning techniques Intrusion Detection Systems (IDSs) are successful in detecting known attacks as they use predefined attack signatures. However, detecting zero-day attacks is challenged because of the scarcity of the labeled instances for zero-day attacks. Advanced research on IDS applies the concept of Transfer Learning (TL) to compensate the scarcity of labeled instances of zero-day attacks by making use of abundant labeled instances present in related domain(s). This paper explores the potential of Inductive and Transductive transfer learning for detecting zero-day attacks experimentally, where inductive TL deals with the presence of minimal labeled instances in the target domain and transductive TL deals with the complete absence of labeled instances in the target domain. The concept of domain adaptation with manifold alignment (DAMA) is applied in inductive TL where the variant of DAMA is proposed to handle transductive TL due to non-availability of labeled instances. NSL_KDD dataset is used for experimentation.

Intrusion detection System (IDS) is an evolving research area in cyber security, which aims to detect cyber-intrusions. Machine Learning, especially deep learning classifiers, offers promising solutions for signature-based intrusion detection provided there are abundant labeled examples. However, effectiveness of deep learning is hindered for zero-day attack detection due to lack of labelled examples; anomaly-based detection approaches often result in high FPR. Transfer Learning (TL) offers methodologies for building classifiers in a target domain containing minimal or no labelled data, leveraging the knowledge extracted from related source domain(s). When applied to zero-day attack detection, Transfer Learning models known attack data as source domain and descriptions of zero-day attacks as target domain with possible differences either in the feature space or in the proportions of attack to normal instances or both. The authors built a TL-based prototype using NSL-KDD dataset for experimentation on unification of feature space for detecting unlabeled R2L samples representing zero-day attacks from normal instances using labelled DoS samples. The proposed TL based classifier achieved 89.79% accuracy and 0.15% FPR which is higher than the state-of-the-art methods.

In this study, a remote caretaking system has been developed using the plantar pressure measurement feature. This system can be used by medical professionals for patients who require real-time telemonitoring of their gait patterns, activities, and postures. The system consists of a waist belt and accompanying instrumented shoes. The pair of shoes are embedded with tactile sensors, signal conditioning circuitry and Bluetooth communication. The waist belt consists of a Bluetooth module, an accelerometer, GPS module, micro-controller development board and a GPRS module. The complete system has the capability to obtain measurements of the plantar pressures, to detect a predefined posture or activity, calculate gait parameters, find locational information, and to detect falling accidents of the wearer. The system of waist belt and instrumented shoes poses Body Area Network (BAN) features, and establishes a small-scaled network that operates in the peripheral proximity of the human body, using Bluetooth communication. The data acquired by the waist belt is continuously transmitted via a GPRS link to a remote open-source Internet of Things (IOT) platform as data packets which consist of plantar pressure data, identified posture data, and GPS coordinates. The telemonitoring process of the patient is enhanced by the IOT dashboard and the Android application in this system, whereby the real-time data of the posture or activity and locational information can be monitored. To improve convenience, an Android-based mobile application and a web based telemonitoring platform have been implemented, wherein the location, gait information, predefined posture or activity, and falling accidents of the patient can be monitored. Moreover, real-time data is stored in the IOT, where the data stored in the IOT is available for post-processing of medical research studies.

The system was developed for remote care-taking applications which could be incorporated for patients. This system has utilised as a sensor integrated shoe and a waist belt. The foot pressures of the foot sole vital points are being measured along with the additional contribution from inertial measurement units. The measured data is being transmitted to a remote Internet of Thing (IOT) for further analysis and stored data in the (IOT) cloud would be available for future medical researchers. The system furthermore comprises activity and location tracking and fall detection system. Concerning the caretaker's convenience, an Android application has also developed.

Tactile sensors provide vital information of robotics, manufacturing, and day to day household electronic appliances. Off the shelf force sensors are generally not cohesive to specific application requirements, resulting subsequently in sensor modules with unsuitable dimensionality, output characteristics, and mechanical properties. Encompassing these issues, rapid prototyping/ 3D printing could be utilised to develop highly customisable tactile sensors. In this paper, a novel sensor structure for a conductive polymer based tactile sensor has discussed. The inherent problems in conductive polymer piezoresistive characteristics such as operation range deviation w.r.t. chemical composition has mitigated.