Download This Paper Open PDF in Browser Add Paper to My Library Share: Permalink Using these links will ensure access to this page indefinitely Copy URL Copy DOI

Stack overflow is the largest online platform for learning and exchanging question answers for the computer programmers. On Stack Overflow, participants share topics that help programming learner, professionals, and experts. Using specific words or tags to describe a question makes it easier to explore the site. Tags are helpful in finding answers faster and connect with others who know about that topic. In this study we have chosen the stack overflow data set where in the first step exploratory data analysis is performed. Community detection algorithm is applied on 115 number of nodes and 490 number of links of the stack overflow dataset. In this paper, we use different community detection techniques and centrality metrics to analyses community detection in computer programming classes offered on Stack Overflow, a popular platform. To be more precise, we examine the community structure in the Stack Overflow courses using the Girvan-Newman, Louvain, Walk-trap, and Greedy modular community algorithms.Additionally, we assess the modularity of the identified communities by utilizing the Girvan-Newman algorithm, which measures the degree of network segmentation into modules. Furthermore, we provide valuable insights into the organization and clustering of users in online learning platforms, facilitating the development of targeted interventions and community management strategies to enhance the learning experience.

Digital health-based medical technology (m-health) uses mobile phones and other patient monitoring equipment to keep tabs on a patient's health. It is largely acknowledged as an important modern-era technological accomplishment. Traditionally, big data analytics and intelligent machines have been used in m-health to provide far more productive medical coverage. Current therapeutic research utilises a variety of data types, including electronic health records (EHRs), diagnostic images, and professional language that appear to be disparate, unclear, and disorganised. In addition, it makes a substantial contribution to the emergence of a large number of unstructured and jumbled data sources as a result of mobile platforms and healthcare infrastructure. The use of machine intelligence and big data analytics to enhance the mhealth infrastructure is thoroughly examined in this chapter. Additionally, various machine learning big data approaches and platforms are studied to the data source, methodology used, and application area. The overall findings of this study will undoubtedly affect the creation of techniques for processing m-health data more easily utilising a resource that incorporates big data and AI.

As the time is passing, our dependency on intelligent machines is continually growing, which demands for more interpretable and transparent models. So, in any specific department, the real standard of artificial intelligence is judged by only if artificial intelligence is capable of interpret the model’s working which will generate users’ trust. Basically, explainable artificial intelligence or XAI targets to give a proper explanation of any particular machine-learning system, known as ML also, which empowers users (which are basically humans) to think, completely trust, and generate explainable models as much as possible. Choosing a suitable method for creating an XAI-enabled application needs a proper and deep perceiving of the basic logics within XAI and the associated methods. Among all the methods, black box-based artificial intelligence or AI method, for example, DNN or deep neural networks, has been broadly used for constituting prototype which are predictive and can interpretate typical relationship inside a dataset and can be used for making predictions for new unidentified data items. By using post hoc methods, one can explain inner working of these complex decision logic which is hidden from user. Basically, methods which are based on post hoc, approximate the working of black box nature by fetching rapports between predictions and values having different features. In this article, we discuss different XAI methods, specially post hoc method on different data item set. Using this taxonomy, also explain the various scenario on which post hoc can be applied and also elaborates how Post hoc provides better understandability and interpretability to users. This taxonomy can be used as a reference and comprehensive review of XAI technique qualities and elements for novices, researchers, and practitioners. As a result, it offers the framework for future research that is focused, use-case-oriented, and sensitive to context.

The protocol known as blockchain, which is composed of blocks, utilizes a decentralized distributed system of nodes (miners). There are three parts to every block: information, which is represented by a hash, and the hash of a previous transaction. In order to regulate data after it has been stored, it is quite difficult to make changes. Mining is compensated for each encrypted function computation they carry out to verify the transaction. This research paper will provide a comprehensive understanding of blockchain-based technologies and how they are applied in a variety of industries, including those that deal with digital currencies, financial services, medical manufacturing, privacy, and a number of other fields. Digital money, notably the cryptocurrency Bitcoin, had previously been one of the most well-known network applications. As there have lately been several studies about the unique utilization of this sort of technology, we will discuss some of these academic works as well as the challenges encountered during the development of these kinds of applications. Blockchain technology is a quickly growing area of database technology that has recently found use in a wide range of industries, including the use of digital money, hospital administration, and other academic subjects. Because of how blockchain technology works and operates, these types of applications are now possible.

This research investigates the enhancement of maternal psychological health during pregnancy through the integration of E-health informatics and quantum photonics for security. The study reviews interventions and outcomes related to E-health technologies in maternal mental health, exploring intersections with quantum photonics for enhanced security measures. The primary objective is to assess the efficacy of E-health interventions in promoting maternal well-being, with an innovative link to quantum photonics for security. The study encompasses algorithmic approaches and predictive modeling, exploring potential synergy with quantum photonics for securing healthcare data. Using a systematic approach, publicly available datasets, including Kaggle, are employed. Data preprocessing addresses missing values, encodes categorical variables, and scales features. Eight machine learning algorithms are deployed for predictive modeling. Evaluation reveals distinctive performances among algorithms, with Random Forest leading in accuracy, precision, and recall. Quantum photonics integration is explored, laying the groundwork for securing health data. In conclusion, the study highlights Random Forest's potential in predicting psychological health risks, and integrating quantum photonics introduces innovative security measures. Future directions include refining predictive pathways, exploring additional features, and validating with diverse datasets. Advanced mathematical calculations, algorithmic enhancements, and deeper integration of quantum photonics are suggested to contribute to evolving digital health interventions and innovative studies in health prediction and data security.

It has grown more challenging to ensure security and trust as wireless communications become more common across a number of industries. Often, traditional security methods fall short in addressing the vulnerabilities that are common in wireless networks. This in-depth research explores the potential for combining blockchain and smart contract technology to increase the security of wireless communications. In addition to analyzing the fundamental concepts behind smart contracts, wireless communications, and blockchain, the research investigates how blockchain-based solutions may lower security concerns and increase trustworthiness. The benefits, drawbacks, and potential future developments of this emerging method are examined in various use cases and applications.

In recent years, developments in natural language processing (NLP) have made it possible for novel applications to be developed in the field of mental healthcare. Roberta and BERT are two examples of these advances. They are examples of state-of-the-art language models that have exhibited extraordinary skills in comprehending and processing human language. To enhance the efficiency and reduce the error rate, it proposes the integration of PSO in Bert and Roberta models at the time of pre-processing in order to filter useless data. Integration of PSO is done in both Bert and Roberta for filtering. The current study compares the proposed integrated approach with existing approaches on various validation measures like accuracy, Precision, Reccall and error rates. It demonstrates that LSTM achieves an accuracy of 99.2

Big data is a technique for storing and analyzing massive amounts of data. The use of this technical edge allows businesses and scientists to focus on revolutionary change. The extraordinary efficacy of this technology outperforms database management systems based on relational databases (RDBMS) and provides a number of computational approaches to help with storage bottlenecks, noise detection, and heterogeneous datasets, among other things. It also covers a range of analytic and computational approaches for extracting meaningful insights from massive amounts of data generated from a variety of sources. The ERP or SAP in data processing is a framework for coordinating essential operations and with the customer relationship and supply chain management. The business arrangements are transferred to optimize the whole inventory network. Despite the fact that an organization may have a variety of business processes, this article focuses on two continuous business use cases. The first is a data-processing model produced by a machine, the general design of this method, as well as the results of a variety of analytics scenarios. A commercial agreement based on diverse human-generated data is the second model. This model's data analytics describe the type of information needed for decision making in that industry. It also offers a variety of new viewpoints on big data analytics and computer techniques. The final section discusses the difficulties of dealing with enormous amounts of data.

Throughout this research, the development of a patients monitoring system for core body temperature and breathing rate—two crucial pulse oximetry covered. The surveillance system was constructed on an IoT platform using the Mega 2560 Arduino board and ESP8266 Wi-Fi Components. Two sensing systems that each utilize temperatures measurements to identify each obtain data value. The program’s goals are to develop a health - monitoring system that can identify, gather data readings, assess heart rhythm levels based on patient age, provide alarms for dangerous circumstances, and dis-play data remotely via Mobile applications. By making this effort, nursing staff would have less work to do while also having a far more practical way to monitor everyone’s physiological parameters all throughout hospitalization. The conventional method, typically requires a clinician to examine everyone and keep track of their physiological traits, is time-consuming. Caretakers utilizing this strategy might monitor patient’s condition by installing Mobile application on any Android smartphone. Nurses or physicians may quickly assess the previous cardiac rhythm state by collecting the information gathered from the system in the form of spreadsheets. The results were very similar when the two key indicators of this approach were contrasted to advanced standards by visual examination or regular measuring tools.

Medical services in Indian Subcontinent might be completely transformed by the application of artificial intelligence (AI) in healthcare. However, it also brings up significant ethical, legal, and societal consequences that must be addressed. The ethical ramifications of AI in Indian healthcare are examined in this research with particular attention paid to data security and privacy, computational bias, informed decision-making, and accountability. Data protection rules and regulations are covered, as well as the legal foundation for AI in healthcare. The influence of AI on healthcare workers and patient-doctor interactions is also examined, along with its societal ramifications, including concerns of equity and accessibility. In order to secure the ethical & egalitarian use of AI for medical care in the Indian subcontinent, the study emphasizes the need for strong ethical principles, current law, and involvement by stakeholders.

The ductal carcinoma has been represented as a diverse illness with several subgroups. Early recognition of a ductal carcinoma kind is critical in determining the patient's course of medical therapy. In the bioinformatics and biomedical, several research projects are being focused on the identification of the ductal carcinomatous cells as malignant benign tumors. In recent years for ductal carcinoma diagnosis, various machines learning (ML) approaches have been employed by the various researchers for the prediction of recurrence and survival of the ductal carcinomatous patients. Furthermore, by identifying essential highlights, ML tools may be used for the determination of the ductal carcinomatous causing malignant cells and tumors based on their relevance complicated data set classification in the mastography. Classification of masses in mammograms remains a significant problem, yet it is critical in assisting radiologists in making correct diagnoses. In this study, we present a deep learning methodology called Convolution Neural Networks (CNN) based categorization. CNN architectural models like as Mobile Net and Inception are used to classify mammography pictures as normal or abnormal.

Recent technological advancements have enabled the development of a variety of apps and programmes which can be used to produce decision-making resources for resolving day-to-day problems. It is a fusion of the physical and virtual worlds that enables people to engage with technology and the surroundings in novel ways. To allow this new reality, computer vision, screen technology, interface technologies, and graphics processing capabilities have all progressed. Augmented Reality (AR), Mixed Reality (MR), and Virtual Reality (VR) are just a few of the computing ideas that have emerged to achieve these objectives. This study investigates a review of previous research studies that have been authored. This evaluation was conducted to investigate the architecture which has already been suggested. MR implementations require appropriate ways to handle dynamic phenomena such as fast changes in the external environment and object mobility. More research into setting up a new computer aided design approach capable of handling independent landscape creation and massive data representation, with a concentration on virtually actual simulation inside an important scenario, is necessary to improve the MR mobile applications.

Life is the most precious asset, and thousands of times due to terrible car accidents lives are lost. However, real-time sleep detectors used in cars can significantly prevent these accidents and save precious lives around the world. The main reason is the driver's inattention, which is mainly called driver drowsiness. The driver’s drowsiness monitoring system is used in conjunction with a high-frequency detection system. The system uses the input video stream from the driver to target the driver’s natural visual changes, such as constantly closing the eyes and using artificial intelligence and scientific drowsiness to slow down the rate of changes in facial expressions and detection measures. The proposed work focuses on the different monitoring systems used in drowsiness detection and the process of the detection system. It is recommended to use a driver drowsiness detector connected to a key predictive analytics system. This research work focuses on the analysis of various sleepiness systems in order to perform a better predictive analysis. Machine learning is a very important example of predictive analytics, so this article focuses on various machine learning techniques and their effectiveness in detecting drowsiness in various systems.

During the urbanization of cities into smart cities, as cited by the Government of India, their mission is to make the cities more citizen-friendly and sustainable. This increases the already high demand of wireless connection available around the clock. Many governments are providing free hotspots with open channels that allows everyone to access without cost. As we know, wireless technology is the easiest form of connection, due to ease of installation and infrastructure. When we talk about smart cities using the Internet, we are concerned as to how to prevent unauthorized access and privacy of the people. Securing privacy and confidentiality of every citizen is the main goal. However, the open channel increases the risk of attacks that can happen to any one of us at any time. In this chapter we discuss some attacks that are threats to privacy and confidentiality of a citizen in an open channel (WI-FI) and, furthermore, we discuss a technique to prevent each and every citizen from these attacks.

The Internet of Things (IoT) has inexorably awakened advanced humans’ existence. Aside from the advantages that this innovative technology provides to the IoT device users, there are also cyber security concerns. Traditional cyber security approaches would not work on low-power IoT devices. As a result, numerous threat detection approaches and methods that are considerate the constraints of the Internet of Things have recently been created. To detect abnormalities in network traffic time series, this research offers a threat detection strategy that combines statistical and machine learning approaches. Furthermore, this novel architecture provides a light solution for cyber security because the logic of computing is a component of the edge layer. The technique performed nicely in spans of recall, precision, accuracy, and F-measure, according to the findings of the test bed testing.

The rapid development of communication technologies and expert systems have resulted in a large volume of medical data. Big data such as clinical data, omics data, and electronic health data are difficult to manage in real-time due to noise, large size, different formats, missing values and large features. Hence, it is more difficult for the health monitoring system to extract the correct information. Low quality and noisy data can lead to unnecessary treatment. To overcome these issues, we proposed Enriched Salp Swarm Optimization based Bidirectional Long Short Term Memory (ESSOBiLSTM) to monitor health. This method consists of four layers, such as the data collection layer, data storage layer, data analytics, and presentation layer. The initial layer handles a variety of information from main sources: wearable sensor devices (WSD), social network data, and medical records (MR). The second layer stores all the collected data from WSD, MR, and social network data to the cloud server through the wireless network. The proposed framework for performing big data analytics steps like preprocessing, filtering, dimensionality reduction, and classification is performed in the third layer. In the final layer, the doctor analyzes the patient's condition based on the classification results of the enriched SSO-BiLSTM. Based on the evaluation report, the proposed ESSOBiLSTM gives an accuracy of 85%, precision of 80%, RMSE of 0.6, MAE of 0.58, recall of 85% and F-measure of 79%. As a result, ESSOBiLSTM has proven to be more effective in monitoring health in large datasets.

The tremendous development and rapid evolution in computing advancements has urged a lot of organizations to expand their data as well as computational needs. Such type of services offers security concepts like confidentiality, integrity, and availability. Thus, a highly secured domain is the fundamental need of cloud environments. In addition, security breaches are also growing equally in the cloud because of the sophisticated services of the cloud, which cannot be mitigated efficiently through firewall rules and packet filtering methods. In order to mitigate the malicious attacks and to detect the malicious behavior with high detection accuracy, an effective strategy named Multiverse Fractional Calculus (MFC) based hybrid deep learning approach is proposed. Here, two network classifiers namely Hierarchical Attention Network (HAN) and Random Multimodel Deep Learning (RMDL) are employed to detect the presence of malicious behavior. The network classifier is trained by exploiting proposed MFC, which is an integration of multi-verse optimizer and fractional calculus. The proposed MFC-based hybrid deep learning approach has attained superior results with utmost testing sensitivity, accuracy, and specificity of 0.949, 0.939, and 0.947.

The field of Information Technology is buzzing with the new paradigm "Internet of Things" (IoT). Being an element of the Future Internet, IoT performs integration of technologies and communication solutions, the envisioned connectivity of heterogeneous devices procreates routing challenges in IoT, and it becomes important to specify how the current standard communication protocols can provide support for realization of this vision. This opens up a new research horizon for Mobile Ad Hoc Networks ( MANET ) protocols. New applications associated with the IoT often involve self-organization and collaboration among many autonomous wireless devices for which traditional infrastructure-based wireless networks are not suitable. MANETs, with their infrastructureless, spontaneous. and arbitrary multi-hop features are considered a popular approach for such scenarios, although they also face certain inherent challenges. Energy-efficient routing is one such area of interest, which require non-conventional paradigms for design and development of protocols. Swarm Intelligence ( SI )-based metaheuristic, owing to their self-organizing nature, prove to be an efficient solution for routing problems, to deliver events in an energy constraint MANET environment. In this chapter, we present an SI-based, energy-efficient hybrid routing protocol for MANETs. The proposed protocol consists of three phases: (i) Cluster Design phase; (ii) ACO-aided cluster head selection phase; and (iii) Data Transmission using route aggregation phase. Integration of the three phases for node clustering, data routing, and transmission, is the key aspect of our proposed protocol, which ultimately contributes to its robustness. Evaluation of simulation results shows that SI performs better in terms of packet delivery, energy consumption, and throughput with increased network life compared to the conventional hybrid routing protocols. One of the direct influences of routing protocol is the performance of route aggregation in MANET. This chapter presents a novel routing protocol that performs a cost-effective, reliable, and robust routing mechanism in MANET, with its highly compatibility with in-network route aggregation mechanism.

The phrase “IoT” mentions to any technology that makes it possible for a device to connect to the Internet. Data collecting is essential for such systems. The information is subsequently utilized for Internet-based control, monitoring, and transfer of data to other devices. Smart home technology is the future of domestic technology, aiming to offer and distribute a variety of services both inside and outside the home via networked devices in which all of the many applications and intelligence behind them are merged and interconnected. Given the constant availability of a broadband Internet connection, these smart gadgets have the potential to communicate information with one other. As a result, technology for the smart home is now a part of the Internet of Things (IoT). In this research paper, we have offered a framework for remote administration and monitoring IoT-enabled appliances and systems in this paper. Home automation provides homeowners with allowing them to have peace of mind to keep an eye on and defend their homes from afar.