IoT and sensor technology have brought a paradigm shift to building energy management. This has created a high demand for energy due to population growth and biodiversity, so the thought of establishing smart energy management systems in buildings is just another trend. This service wields IoT and sensor tech to track, manage, and enhance energy use. Data on energy consumption, occupancy levels, and environmental conditions are collated by IoT devices (e.g., smart meters, sensors & actuators) embedded all over the building. This information is sent back to a central control system that uses sophisticated algorithms to monitor and control energy utilization. With real-time data, the system can automatically adjust lighting, heating, and cooling, and like other building systems, to keep occupants comfortable and use less energy. IoT and sensor technology can be coupled to monitor energy consumption patterns, allowing building managers to uncover inefficiencies in these systems as they arise, leading them toward data-driven decisions that eliminate waste. This not only results in cost savings to the building owner but also decreases the carbon footprint of that property. Furthermore, IoT and sensor technology integrations allow buildings to take part in demand response programs where they can adapt real-time energy consumption levels to balance the grid. This is essential in supporting a cleaner and greener energy system.

A software bug tracking system receives several bug reports in a rapid manner during the maintenance of software. In order to fix the important and urgent bugs, the triager has to assign severity and priority to individual bugs on time. However, there are a lot of uncertainties in the bug reports due to bias, noise, and abnormal data. At the same time, the presence of common terms in multiple severity and priority classes creates confusion in the mind of the triager. Furthermore, machine learning and deep learning approaches generally belong to discriminative learning with a clear-cut outcome. Instances of software bug reports are textual in nature. As a result, these are fuzzy and cannot be classified with a clear-cut outcome. To overcome the above problems, in this paper, an Intuitionistic Fuzzy Similarity Measure (IFSM) based severity prediction technique (IFSMSP) and priority prediction technique (IFSMPP) are proposed for predicting the severity and priority of a new bug by using already labeled bugs. Initially, the Synthetic Minority Oversampling Technique (SMOTE) is used to balance the severity and priority label of software bugs. Then the severity-term dictionary or priority-term dictionary is created by extracting the most frequent terms from the bug summary using text mining and Natural Language Processing (NLP). Then the data is represented using an intuitionistic fuzzy set (IFS) by calculating the membership, non-membership, and hesitancy degrees. Then 15 different IFSM techniques are investigated for predicting the severity and priority of software bugs. Experiments are carried out on large software bug repositories (Eclipse, Mozilla, Apache, and NetBeans) with a 10-fold cross-validation technique. IFSMSP outperformed other state-of-the-art priority models by obtaining an accuracy of 92.3%, 90.6%, 91.9%, and 91.2%, and IFSMPP outperformed other state-of-the-art models by obtaining an accuracy of 93.2%, 91.9%, 92.7%, and 92.3% on the Eclipse, Mozilla, Apache, and NetBeans software bug repositories, respectively.

In software development, a bug can occur due to multiple failures in software, and it may require multiple developers to fix it. In machine learning approaches, the bugs are assigned to a developer with a clear-cut outcome based on the agreed level of opinion from the assigner. However, instances of software bugs are textual and fuzzy. In this paper, two fuzzy systems: the fuzzy bug assignment technique for software developers and unique term relationships (FDUR) and the fuzzy bug assignment technique for software developers and category relationships (FDCR) are developed to measure the degree of relationships between developers, bugs, and its categories. The computed degree of relationship is used for handling the bugs with multiple categories and a set of developers involved in the development of software. To measure and compare the performance of both techniques with other existing techniques, the experiments are carried out on the benchmark software repositories.

In modern times, the software industry is more focused on the timely release of high-quality software. Software bugs have a significant impact on software quality and reliability. To complete the bug triaging process on time, the triager has to understand each bug and assign the correct priority to it. However, the bugs are reported rapidly, with lots of uncertainty and irregularities in the bug tracking system. Furthermore, there are multiple priority labels that are semantically close to each other. As a result, the triager is confused while understanding and prioritizing the bugs. To address these problems, the research presents an intuitionistic fuzzy representation of topic features-based software bug priority prediction (IFTBPP) technique. Initially, the imbalanced priority classes of software bugs are balanced using the synthetic minority oversampling technique. Then, topic modeling is used to create topics and terms for software bugs. The intuitionistic fuzzy set is used on the topics to compute various grades of a bug belonging to multiple priority classes. Finally, the similarity of a newly reported bug is calculated using intuitionistic fuzzy similarity measures with multiple priority classes. All the experiments of IFTBPP are conducted on Eclipse, Mozilla, Apache, and NetBeans repositories and compared with other existing models. The accuracy values obtained by IFTBPP on these repositories are 92.5%, 91.9%, 89.2%, and 93.9%, whereas the corresponding F-measure values are 91.7%, 91.3%, 88.9%, and 93.1%.

Nowadays, industries are more concerned with the timely delivery of quality software. The release of software totally depends upon the time required to fix the software bugs. The project team has to estimate the average time required to fix the bugs in accordance with the project schedule and available resources. The severity and priority of the software bug play a significant role in estimating the average time required to fix the bugs. However, the presence of multiple classes of severity and priority poses a greater challenge for the project team in terms of bug fixing time estimation. To address the aforementioned problem in this paper, an intuitionistic fuzzy similarity (IFS) measure-based bug time estimation technique is developed using the priority and severity of the software bug. The informative terms of severity and priority are used to determine the IFS measure of a new bug to multiple classes of severity and priority. The average bug fixing time for each severity and priority groups is utilized to predict the bug fixing time of a newly reported bug. The proposed bug estimation techniques provide a better MAE, RMSE, and R2 score over various software bug repositories compared to other bug fixing time estimation techniques.

In order to improve software reliability and quality, the triager must assess the severity of the software bug and allocate suitable resources on time. However, the triager faces many difficulties in understanding various software bugs that involve lots of uncertainty and irregularities. Additionally, it can be challenging for the triager to determine the severity of bugs that are semantically close to multiple severity labels. To address these problems, a topic modeling and intuitionistic fuzzy similarity measure-based software bug severity prediction technique (IFSBSP) is proposed in this paper. Initially, the Synthetic Minority Oversampling Technique (SMOTE) is applied to balance the severity classes in software bug repositories. Then topic modeling is used to generate topics based on the probability of underlying uncertainty in software bugs. Using these topics, the intuitionistic fuzzy membership, non-membership, and hesitancy membership degrees of a software bug are calculated for multiple severity labels. Then, 15 IFS techniques are investigated for a new bug in order to compute its similarity to multiple severity labels. The Eclipse, Mozilla, Apache, and NetBeans software bug repositories are used to evaluate the performance of IFSBSP and the state-of-the-art models. On these software bug repositories, the IFSBSP model outperforms state-of-the-art models by achieving accuracy of 91.6%, 90.9%, 88.1%, and 92.9% and an F-measure of 90.7%, 91.1%, 89.3%, and 91.7%, respectively.

Software bug repositories stores a wealth of information related to the problems that occurred during the software development. Today's software development is a modular approach, with multiple developers working in different locations all around the world. A software bug may belong to multiple categories and can be resolved by more than one developer. For understanding the multiple causes of software bugs and proper bug information management at large bug repositories, better classification of software bugs is needed. In the proposed work, a multi-label fuzzy system-based classification (ML-FBC) is proposed. A fuzzy system is used to compute the membership of software bugs into multiple categories. Then a fuzzy c-means clustering algorithm is used to create various clusters. Once the clusters are created, the cluster-category mapping is done for various software bugs. For a new bug, the fuzzy similarity values are computed, and the created cluster-category mappings are utilised to categorise it. Using a user-defined threshold value, a new bug is classified into multi-label categories. Experiments are carried out on available benchmark datasets to compare the performance measures F1 score, BEP score, Hloss, accuracy, training time, and testing time of various multi-label classifiers. The proposed ML-FBC outperforms existing multi-label classifiers.

Modern-day software is developed by multiple developers working remotely in various locations. Software bugs emerge in large numbers during the maintenance of software. Understanding these bugs and identifying suitable developers to fix these bugs are the most important tasks for the triager. However, a bug can occur for multiple reasons, and multiple developers may be involved in its creation. To address the aforementioned problems and improve the bug triaging process, intuitionistic fuzzy set-based ensemble bug triaging models are developed in this paper using the intuitionistic fuzzy similarity measures (IFSM) of the developer on the terms, categories, and topics associated with software bugs. The proposed ensemble techniques outperform other bug triaging techniques across multiple available software bug repositories and are able to identify suitable developers to fix the bugs with the highest accuracy of 0.947 and the highest F-measure of 0.944.

Software development is a collaborative process in which programmers build software by integrating all the stages of the software development life cycle (SDLC). A software repository is a central file storage location where various software packages are stored, and these packages are retrieved and shared between all the software development team members at various locations. The software repositories are divided into various categories based on cooperation, coordination, and communication among the stakeholders as well as evolutionary changes to various software arti-facts such as source code repositories, software bug repositories, historical repositories, run-time repositories and requirement documents, and other documentation. The software bug repository is an essential repository among the entire repositories since the completion of the software is entirely dependent on the bug fixing mechanism associated with this repository in software development. Today’s software systems are larger and more complex as they go through various stages from the requirement 98analysis phase to the maintenance phase. A variety of tasks and activities are carried out in each stage of software development, and these are expensive and vulnerable to errors. During software development, a large number of software bugs are continuously generated, and that has become the main reason for the delay in software completion. Hence, there is a vast demand for computational intelligent techniques to accomplish various tasks of software development. In recent years, fuzzy logic techniques emerged and played an important role in various fields of data mining and text mining. Since most of the content related to software bug repositories is text in nature, it is possible to effectively use fuzzy logic techniques to analyze these software bugs.

Software development is a modular approach which involves multiple developers and multi-tasking teams who are working together from various locations across the world. It is possible that a software bug may originate due to multiple reasons in multiple modules and can be fixed by multiple developers. Furthermore, there are a large number of software bugs that are unlabeled, vague, and noisy. As a result, it becomes a challenging task for the triager to find expert developers for fixing a newly reported bug from the available developers. To address the above problems, a combined approach of topic modeling and fuzzy logic-based bug triaging (TM-FBT) is proposed in this paper for efficient bug triaging. Topic modeling is used to create various topics of software bugs. Fuzzy logic is used to map developers with various topics to understand the multiple relationships between developers and software bugs. For a newly reported bug, the fuzzy similarity values are calculated and expert developers are identified by applying the fuzzy -cut on the similarity values. The outcomes of the TM-FBT approach are compared with various machine learning algorithms and the fuzzy logic-based Bugzie model on benchmark data sets. On the Eclipse, Mozilla, and NetBeans data sets, the TM-FBT approach yields an accuracy of 0.903, 0.887, and 0.851 respectively. Similarly, the TM-FBT model outperforms all other state-of-the-art models in all other performance measures.

Multi-attribute decision making (MADM) is a state-of-the-art, popular technique for dealing with real-world problems. An effective decision can be made for various real-world problems involving multiple attributes to decide a proper solution. Software testing and bug fixing are essential steps in the field of software engineering. Bug triaging is a real challenge in large-scale software development. Bug triaging is the process of allocating newly reported bugs to the best developer who meets the requirements for addressing them. In this paper, a software developer ranking model based on the Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) is proposed for an effective bug triaging process. Developers are ranked based on various criteria using the TOPSIS model for effective bug triaging. Assigning newly reported bugs to the appropriate and available software developer is a complex decision-making process. It involves consideration of multiple criteria for discovering the optimal solution. In software engineering, bug triaging refers to the process of allocating appropriate developers to a newly reported bug. This paper presents criteria for finding suitable developers using multi-criteria decision-making (MCDM) techniques. The Analytic Hierarchy Process (AHP) method is used to determine the weights of the criteria, and the TOPSIS MCDM technique is used to rank the most appropriate developer.

In the field of software development life cycle, the maintenance phase is one of the focused steps. Normally, thousands of bugs are reported daily by testers. So, it is very important to fix that bug as soon as possible. In the current era, various project are there that work on the same project and if bug not fixed timely the other product can easily overtake the company business, so to fix the newly arrived bug the project manager finds the best developer to fix it and assign to the developer, and this process is called bug triaging. For bug triaging task automation, various methods had been carried out by various researchers machine learning, information retrieval, deep learning, etc., but the cons with that method were that they were not able to fix the problem simultaneously like bug tossing, load balancing, and developer availability. Hence to overcome that we have proposed a method called technique for order of preference by similarity to ideal solution (TOPSIS) which is based on multi-criteria decision-making (MCDM), which will consider the developer metadata with various criteria to automate the task of bug triaging. Based on the criteria, the parameter (closeness ratio) will be calculated, and based on the parameter value, the developer will be ranked for bug triaging.

Finding similarities between objects is an important task in various fields of research. Advanced fuzzy logic-based similarity techniques are widely used in the literature for computing the similarity between objects. Despite the development of several similarity techniques in recent years, no fuzzy similarity measure package is available that can integrate all similarity techniques and assist a wide range of researchers, practitioners in performing their tasks efficiently. The package IPSFS is developed to compute the similarity among different objects. It includes several useful functions to compute the similarity between objects or items based on their intuitionistic, pythagorean, and spherical fuzzy relationships.

Software development is a modular approach involving multiple developers and multi-tasking teams working at different locations. A particular term in a software bug can belong to multiple modules and multiple developers’ profiles. Also, many people who report software bugs are unfamiliar with the exact technical terminology of software development, which causes the software bug to be unlabeled, vague, and noisy. Hence, analyzing, understanding, and assigning the newly reported bugs to the most appropriate developer is a challenging task for the triager. Intuitionistic Fuzzy Sets (IFS) consider the non-membership and hesitant values along with the membership values of the software bug terms mapped to the developers and thus provide a powerful tool for better analysis in cases where the same term can belong to multiple categories. Two IFS similarity measure-based techniques, namely, the Intuitionistic Fuzzy Similarity Model for Developer Term Relation (IFSDTR) and the Intuitionistic Fuzzy Similarity Model for Developer Category Relation (IFSDCR), are proposed in this work. In IFSDTR, a developer-term vocabulary is constructed based on the previous bug-fixing experience of software developers by considering the most frequent terms in the IFS representation of bugs they fixed earlier. In IFSDCR, software bugs are categorized into multiple categories and a developer-category relation is constructed. When a new bug is reported, the IFS similarity measure is calculated with the developer-term and developer-category relationship, and a fuzzy -cut is applied to find a group of expert developers to fix it. The proposed techniques are evaluated on the available data set and compared with existing approaches to bug triaging. On the Eclipse, Mozilla, and NetBeans data sets, the IFSDTR techniques yield an accuracy of 0.90, 0.89, and 0.87, respectively, whereas the IFSDCR yields a greater accuracy of 0.93, 0.90, and 0.88 for the Eclipse, Mozilla, and NetBeans data sets, respectively. Similarly, in all other performance measures, the proposed approaches outperform the state-of-the-art approaches.

Modern software development involves multiple developers working remotely in a distributed manner around the world. Software bugs are continuously generated for multiple reasons across various modules. It is possible that one software bug can affect multiple modules, and there can be multiple developers associated with it. Furthermore, many software bug reports are unlabeled, vague, and noisy. The triager faces significant challenges in identifying multiple causes of software bugs and finding expert developers for bug fixing. In this paper, the fuzzy set is extended to Intuitionistic Fuzzy Sets (IFS), and a novel bug triaging approach based on Intuitionistic Fuzzy Similarity (IFSim) measures is presented to overcome the aforementioned problems. The topic model is used to discover multiple relationships between developers and software bugs. IFS is used to separate developers based on their degree of membership and non-membership in a particular software category, with a degree of hesitation for some developers. For a new bug, 15 different IFSim measure techniques are investigated to compute the similarity with the existing software bugs. Finally, a fuzzy -cut is applied to find expert developers to repair it. The best results are obtained by considering the number of topics of 15 and 12 taxonomic terms for each topic. Among all the IFSim measure techniques, the similarity techniques proposed by Ye outperform other techniques. Experiments are carried out on available benchmark data sets, and the results are compared to traditional machine learning algorithms and the fuzzy logic-based Bugzie model.

The efficiency of the software depends on timely detection of bugs. For better quality and low-cost development bug fixing time should be minimised. Categorisation of software bugs helps to understand the root cause of software bugs and to improve triaging. As the software development approach is modular and multi-skilled, it is possible that one software bug can affect multiple modules, and multiple developers can fix newly reported bugs. Hence, a multi-label categorisation of software bugs is needed. Fuzzy similarity techniques can be helpful in understanding the belongingness of software bugs in multiple categories. In this paper a multi-label fuzzy similarity based categorisation technique is presented for effective categorisation of software bugs. Fuzzy similarity between a pair of bugs is computed and, based on a user defined threshold value, the bugs are categorised. Experiments are performed on software bug data sets, and the performance of the proposed classifier is evaluated.

The number and scale of medical databases is increasingly growing, and sophisticated data mining models may be able to assist physicians and professionals in making more effective and applicable decisions. Cervical cancer is a major type of gynaecological cancer and is amongst the live major malignant cancers in women around the world. Cervical cancer signs are usually undetectable in the early stages. The risk factors are developed due to a number of causes, including the human papillomavirus, sexually transmitted diseases (STDs), and smoking. Dimensionality reduction aids in the removal of redundant or irrelevant features from high-dimensional datasets.This work brings forward a novel hybrid Dimensionality Reduction DR) technique to transform data from higher dimensions to lower-feature subspace. This method combines four major techniques of dimensionality reduction i. e. truncated Singular Value Decomposition (tSVD), Principal Component Analysis(PCA), Independent Component Analysis (ICA), and Non-negative Matrix Factorisation (NMF) and combines the components obtained from each technique into a newer reduced data. The title SPIN hence stands for the significant initials of the base techniques used as mentioned respectively. The proposed method is implemented on the Cervical Cancer Risk dataset. To evaluate performance, the classification for suspected Biopsy examination is done using Decision Tree and random Forest Classifiers, which report an accuracy of 95.283% and 99.057% respectively, which is significantly high as compared to the 98% to 98.67% range present in the recent literatue; even with reduced number of components in lower feature sub-space.

Air Pollution is one of the major issues concerning the entire world. There are many pollutants in the atmosphere which cause the degradation of air leading to a harmful environment. This work presents the analysis of such pollutants and to predict them using the Auto Regressive Integrated Moving Average (ARIMA) model. ARIMA model is one of the time series analysis model which gives the prediction of certain values based on the historical data. The data set used in this model contains of various pollutants values observed on a specific date in a particular location. ARIMA model when applied on the data set resulted in the prediction of the pollutants. It is an efficient way by which we can find out whether the values of the pollutants are exceeding the limits prescribed by the World Health Organization (WHO). Thus it creates awareness among people and government so that certain actions can be taken to decrease the levels of such harmful pollutants. The effectiveness of this technique is investigated on the available data set and its performance is measured.

Prediction of stock prices has been the primary objective of an investor. Any future decision taken by the investor directly depends on the stock prices associated with a company. This work presents a hybrid approach for the prediction of intra-day stock prices by considering both time-series and sentiment analysis. Furthermore, it focuses on long short-term memory (LSTM) architecture for the time-series analysis of stock prices and Valence Aware Dictionary and sEntiment Reasoner (VADER) for sentiment analysis. LSTM is a modified recurrent neural network (RNN) architecture. It is efficient at extracting patterns over sequential time-series data, where the data spans over long sequences and also overcomes the gradient vanishing problem of RNN. VADER is a lexicon and rule-based sentiment analysis tool attuned to sentiments expressed in social media and news articles. The results of both techniques are combined to forecast the intra-day stock movement and hence the model named as LSTM-VDR. The model is first of its kind, a combination of LSTM and VADER to predict stock prices. The dataset contains closing prices of the stock and recent news articles combined from various online sources. This approach, when applied on the stock prices of Bombay Stock Exchange (BSE) listed companies, has shown improvements in comparison to prior studies.

Predictions based on Sequential Data such as time-series data of agricultural product prices play a crucial role in agriculture-based business. Determination of inflation in prices help farmers and associated businesses to take corrective measures for higher returns. However, unavailability of enough collective and accurate data for Indian Markets challenges accuracy. This paper captures the advantage of NN (Neural Networks) and FZ (Fuzzy Systems) for predictions based on time series analysis with limited data. NN learns by adjusting the weights between connecting neurons. This helps in pattern recognition of similar data points. Recent developments in DL (Deep Learning) such as the RNN (Recurrent Neural Network) variant, LSTM (Long Short Term Memory) dominates the trade market predictions. LSTM solves the gradient descent problem of traditional NN and remembers temporal patterns. Fuzzy systems, on the other hand, helps in making inference about human cognition through membership functions. Learning capabilities of NN and Fuzzy rules form the novel Neuro-Fuzzy system termed as FLSTM (Fuzzy-LSTM). Further, the data set contains monthly wholesale prices published by the Ministry of Commerce and Industry, Govt. of India for essential agricultural commodities. The evaluation based on the proposed work shows decent improvement than some standard DL model for various entities when subject to limited records.

Categorization of software bugs is an important task in software repository mining. Most of the information about the software bugs are in textual form, and it is difficult to categorize these bugs into a particular category as the some of the terms present in the software bugs can be common to multiple categories. Fuzzy similarity technique can be utilized to identify the belongingness of these bugs into different categories. In this paper, a binary software bug categorization technique using fuzzy similarity measure is proposed to classify the bugs as bugs or non-bugs. The fuzzy similarity of a software bug is computed and based on a user-defined threshold value the bug can either be assigned to bug or non-bug category. Experiments are performed on available software bug data sets and performance of proposed fuzzy similarity based classifier is evaluated using the parameters accuracy, F-measure, precision, and recall. The proposed algorithm is also compared with the existing standard machine learning algorithms.

A Wireless Ad Hoc Network (WANET) is a self configuring network where nodes, connected by wireless links and can move freely by changing its topology constantly. Wireless ad hoc network routing protocols are mainly based on reactive routing that uses minimum hop count. A WANET uses hop count as a parameter to measure the performance of the wireless link between nodes. The wireless links over a long distance may be slow or lossy that leads to poor throughput. Due to mobility, the links between distant node is broken quickly might be accused congestion. Therefore, among the multiple paths from source node to destination node we need to select a path which is more stable and avoids the congestion even if links broken. In this paper we proposed an algorithm OMRAODV that finds an optimal stable path among the paths available in between source to destination node. Simulation results show that OMRAODV has better performance than MAODV in terms of the metrics: End-to-End Delay, Packets Delivery Ratio, Throughput, Power Consumption, Network Load, Packet Received and Packet Lost.

The performance of wireless sensor networks (WSNs) degrades due to the presence of faulty sensor node. Therefore, fault node detection is an important problem in WSNs. The conventional fault detection methods where the faulty node is detected by measuring the outlyingness of the sensor data with respect to measured mean is not providing better performance in high noise environment. To overcome that problem, in this paper we have proposed centralized robust fault detection algorithm to identify soft faulty sensor node present in the network. The simulation results show that the detection accuracy and false alarm rate performance is much better compared to the conventional algorithm.

In this paper we have described the impact on efficiency of algebraic computation due to multi core systems using java as the programming language. Hence we had taken two machines with different specification having variants of Windows in them and made a comparative analysis taking five different input samples. During this process we came across several aspects on which the computation performance depends upon. In succeeding discussion we have given a vivid description of how these factors show variations when they are blended in different quantities thereby justifying the need of a robust algorithm and a high performance system for efficient computation of mathematical expressions with varying complexities.

In this paper we consider Mamdani fuzzy inference system to study for optimizing the buffer overflow probability in a single M/M/1 queue and two M/M/1 queue in tandem Jackson networks. Mamdani fuzzy inference system is proposed to estimate the service rate for the Jackson queueing network. The arrival rate and the highest overflow level of a particular queue are provided to the Mamdani fuzzy inference system which generates the service rate according to the fuzzy rule base. The arrival rate, the highest overflow level and the new service rate will be used to estimate the buffer overflow in a single M/M/1queueing network then in two queues in tandem queueing network. Simulation results shows that Mamdani fuzzy inference system reduce the buffer overflow probability as compared with the normal estimation of buffer overflow probability.

In this paper we consider a single M/M/1 queue and two M/M/1 queue in tandem Jackson networks for analyzing and estimating the overflow probability in a telecommunication networks. The arrival and service rates in a Jackson networks are modulated by finite state Markov process. First we estimated the buffer overflow in a single M/M/1 queueing network then we estimated the buffer overflow in two queues in tandem queueing network. Numerical and experimental results of buffer overflow on a single M/M/1 queue and a two queue in tandem are discussed.