Browse Items (11858 total)
Sort by:
-
EASM: An efficient AttnSleep model for sleep Apnea detection from EEG signals
This paper addresses the crucial task of automatic sleep stage classification to assist sleep experts in diagnosing sleep disorders such as sleep apnea and insomnia. The proposed solution presents a novel attention-based deep learning model called, Efficient Attention-sleep Model (EASM), designed specifically for sleep apnea detection using EEG signals. EASM incorporates a streamlined architecture that includes a modified Muti-Resolution Convolutional Neural Network (MRCNN), Adaptive Feature Recalibration (AFR), and a simplified Temporal Context Encoder (TCE) module to reduce complexity. To mitigate overfitting, ridge regression is utilized, which incorporates a penalty term to enhance model generalization. Furthermore, the proposed EASM utilizes a class-balanced focal loss function to address data imbalance issues. The effectiveness of EASM is evaluated on two publicly available datasets, SLEEP EDF-20 and SLEEP EDF-78. Comparative analysis of EASM against state-of-the-art models demonstrates its superior performance in terms of accuracy, training time, and model complexity. Notably, the proposed model achieves a 50% reduction in training time and a 55.7% decrease in complexity compared to the Attnsleep model. The EASM achieves a classification accuracy of 85.8% with minimum loss when compared to the Attnsleep model. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024. -
Farm field security system using CNN and GSM module
Loss of crops and the destruction of livestock have been a major problem for many people in rural areas due to grass-fed animals whose food is derived from plants. According to research 32% are herbivores [1]. Reduced emissions from deforestation as well as deforestation are the main reason for wildlife moving towards urban areas. It results in wildlife infestation and human and animal conflicts. Therefore, compensating for the rapid loss of crops and the slaughter of livestock requires animal shelter and isolation in order to restrict the entry of animals into farm fields. The paper describes an effective and reliable way to identify and repel wildlife from farmland and to send real-time data to the farmer indicating animal attack on fields. An image of an animal will be obtained by convolution neural networks using intensive reading algorithms that provide a message to the farmer using the GSM module. It uses a user alert system and the animal scaring method. The test results show that the proposed algorithm has high visual accuracy. The detection level of the test set is achievable and the detection result is reliable. 2024 Author(s). -
Test case reduction and SWOA optimization for distributed agile software development using regression testing
Regression testing is a well-established practice in software development, but its position and importance have shifted in recent years as agile approaches have grown in popularity, emphasizing the fundamental role of regression testing in preserving software quality. In previous techniques, the challenge to address is determining the number and size of clusters and optimization to stabilize the cost and efficacy of the strategy. To overcome all the existing drawbacks; this research study proposes test case reduction and Support-based Whale Optimization Algorithm (SWOA) for distributed agile software development using regression testing. The purpose of this research study is to look into regression testing strategies in agile development teams and to find out what they are optimum clustered test cases. The proposed strategy is divided into two stages: prioritization as well as selection. Prioritization and selection are carried out once the test instances have been retrieved and grouped. The test case clusters are sorted and prioritized in this stage to ensure that the most critical instances are chosen first. During this stage, the test case clusters undergo sorting and prioritization to guarantee that the most essential cases are selected initially. Second, the SWOA is used to choose test cases with a greater frequency of failure or coverage criterion. The results of the assessment metrics show that the proposed approach outperforms other current regression testing strategies substantially. Based on experimental findings, our proposed approach betters existing methods in terms of information performance. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024. -
Enhanced Geographical Information System Architecture for Geospatial Data
[No abstract available] -
Smartphone addiction among post-graduate management students: The Indian experience
This study aimed to recognize the patterns of smartphone addiction among post-graduate management students in the North-East Region of India. The validated Smartphone Addiction Proneness Scale (SAPS) was administered to the respondents, and two different methods, namely SAPS method and median-based scoring method, were used to measure smartphone addiction. The measurement results of smartphone addiction show evidence that the student respondents are not vulnerable to smartphone addiction. Principal component analysis with promax rotation (KaiserMeyerOlkin measure = 0.84; Bartletts test of sphericity = 0.000) demonstrated four crucial components that signify smartphone addiction which are habitual issues (issues relating to regularly or repeatedly doing or practicing something), withdrawal anxiety, tolerance, and usage outcomes. Gender was not seen to play a significant role in these components. The duration of use of a smartphone was seen to have a significant relationship with the component of habitual issues but not with the other components. 2023 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group. -
IoT-Based automated dust bins and improved waste optimization techniques for Smart City
Effective waste management systems are essential for maintaining sustainability, environmental health, and cleanliness in the age of smart cities. This chapter provides a thorough analysis of the combination of cutting-edge waste minimization techniques with the deployment of an internet of things-based automatic dust bin. The suggested system optimizes garbage collection, lowers operating costs, and has a less environmental effect by combining the creative use of proximity sensors, real-time data analytics, and smart bin technologies. Remote monitoring and administration are made possible by the linked ecosystem that is created by the integration with the internet of things (IoT). In order to further promote environmentally friendly urban life, the study also examines waste-to-energy technology, circular economy ideas, and sustainable waste management techniques. The results provide insightful information for scholars, decision-makers, and urban planners looking for ground-breaking waste management solutions for today's cities. 2024, IGI Global. -
IoT networks: Integrated learning for privacy-preserving machine learning
Financial fraud is a persistent problem for consumers and financial institutions worldwide. It loses billions of dollars annually. Consequently, a strong fraud detection system (FDS) is essential to minimizing damage to financial institutions as well as clients. One common technique for spotting fraud is to use machine learning algorithms, which analyze large volumes of data to help with pattern detection and future prediction. It is difficult for a centralized FDS to detect fraud trends when these problems are coupled. To train a fraud detection model, this work presents a framework for federated learning, a machine-learning environment in which several entities collaborate to solve a machine-learning problem under the guidance of a central server or service provider. Also, the chapter examines how combined learning can be used to protect privacy in machine learning in Internet of Things systems. It focuses on four main calculations: federated averaging (FedAvg), secure aggregation, holomorphic encryption-based federated learning, and differential privacy in combined learning. Extensive experiments were carried out to evaluate these computations in terms of proving accuracy, conserving protection, and computing efficiency. The findings are shown in the results, with FedAvg achieving the highest accuracy of 92.5% and secure conglomeration demonstrating competitive precision levels of 91.8%. Calculations for differential privacy and holomorphic encryption demonstrated strong security conservation with very little data leakage and security parameters of 2.5 and 1.0, respectively. With little communication overhead and the ability to alter accuracy and conserve protection, secure aggregation emerged as a potential configuration. The computational productivity assessments revealed that secure accumulation produced little communication overhead despite its strong security conservation, which makes it suitable for IoT scenarios with limited resources. By using this tactic, financial institutions may avoid sharing datasets and benefit from a shared model that has seen more fraud than any one bank has on its own. Thus, the sensitive data of the user is protected. The results of the chapter indicate that the federated model (federated averaging) may be as good as or better than the central model (multi-layer perceptron) in detecting financial fraud. This chapter adds to the growing conversation around mixed learning in the Internet of Things by providing insights into the trade-offs between accuracy, security, and efficacy and by laying the groundwork for future developments in privacy-preserving machine learning standards. 2025 selection and editorial matter, Ahmed A. Elngar, Diego Oliva and Valentina E. Balas. All rights reserved. -
Enhancing Natural Gas Price Prediction: A Machine Learning and Explainable AI Approach
This research includes an innovative approach to refine natural gas price predictions by employing advanced machine learning techniques, including Random Forest, Linear Regression, and Support Vector Machine algorithms. Against the backdrop of natural gas's increasing influence in the energy sector, both environmentally and economically, the study adopts a robust methodology using a comprehensive dataset from Kaggle. Through rigorous data preprocessing, feature engineering, and model training, the chosen algorithms are optimized to capture complex patterns within the data, demonstrating the potential to significantly enhance forecast precision. The application of these techniques aims to extract meaningful insights, providing stakeholders in the natural gas market with more accurate and reliable predictions, there by contributing to a deeper understanding of market dynamics and informed decision- making. 2024 IEEE. -
Iot based real time potholes detection system using image processing techniques
Accidents owing to potholes has become an alarming problem in todays life. The first step to solve this problem requires, designing a device embedded on the vehicle which can continuously scan the road surface for identifying potholes, alerting the driver in time and enable the driver to avoid the pothole. The second step is to introduce a technique to enable the device to locate the position of the pothole via GPS (Global Positioning System). The GPS data can be uploaded via a GPRS (General Packet Radio Service) module or Bluetooth module onto a data base which is stored locally. This database can then be transferred to the cloud using WiFi or 4G technology by connecting the system. The third aspect is to link the database to a network system incorporating mapping software such as Google Maps or Open-Street Map. The data in the system can be made available to the general public as well as municipalities and road maintenance agencies. Awareness of the location of potholes will help drivers to avoid those roads and being more careful while driving on the same roads. This paper focuses on the pothole detection task based on image processing algorithms and the data captured from ultrasonic sensor placed on the vehicle. The later steps were implemented through Bluetooth interface available in smartphones. IJSTR 2020. -
An Investigation on Machine Learning Models in Classification and Identifications Cervical Cancer Using MRI Scan
This study analyzes the effectiveness of machine learning models in the classification of cervical cancer using a dataset of 900 cancer and 200 non-cancer images gathered from online resources and hospitals. The dataset, covering both CT and MRI images, undergoes rigorous preprocessing, including standardization, normalization, and noise reduction, to enhance its quality for model training. Four machine learning models, namely VGG16, CNN, KNN, and RNN, are recruited to predict cancer and non-cancer cases. During the testing phase, VGG16 emerges as the most accurate, achieving an impressive accuracy of 95.44%, followed by CNN at 92.3%, KNN at 89.99%, and RNN at 86.233%. Performance parameters, such as precision, recall, F1 score, and accuracy, are fully analyzed, providing insights into each model's strengths and capabilities. These discoveries not only contribute to the advancement of cervical cancer diagnostic techniques but also underscore the potential of machine learning in medical imaging. The study emphasizes the relevance of model selection and provides a framework for future research endeavors seeking to enhance the accuracy and performance of cervical cancer diagnosis through the merger of advanced computational techniques with standard diagnostic practices. 2024 IEEE. -
Deep Learning Advancements in E-commerce Supply Chain Management in Forecasting and Optimization Strategies
In this study, the influence of deep learning technologies on the optimization of supply chain management in the context of the e-commerce industry is examined. Using a dataset of historical data of sales, inventories, market fluctuations, and customer and supplier details, I investigate the efficiency of different deep learning models to predict demand and facilitate the optimal balance of inventories. Long Short-Term Memory (LSTM), Recurrent Neural Networks (RNN), Convolutional Neural Networks (CNN), and a model proposed by the authors are defined and applied, considering their accuracy, precision, recall, and F-1 score. The results show that the proposed model outperforms traditional products, achieving 97.5% of accuracy. In the context of the comparative analysis, the specific features of CNN, LSTM, and RNN are revealed, helping to understand the benefits and drawbacks of each recommendation. As a result, the proposed model proves that deep learning technologies have the power to change the approach to predictive analytics and supply chain management, allowing practitioners to focus on strengths and overcome the weaknesses of their structures. The impact of data preprocessing and hyperparameters is also considered along with the necessity to choose the most appropriate model evaluation technique. In the future, it is possible to implement other complex deep learning models, integrate additional data, and address the problem of data scaling and heterogeneity. In the era of modern technologies, e-commerce organizations should take these findings into consideration to discover the potential of deep learning, improve supply chain performance, reduce costs, and attract clients. This research contributes to the topic of using deep learning technologies in supply chain management, promoting innovation, and changes that may affect the industry drastically. 2024 IEEE. -
Enhancing Patient Well-Being in Healthcare Through the Integration of IoT and Neural Network
This study analyses the revolutionary integration of Internet of Things (IoT) structures in healthcare through a complete examination of outstanding case research. The first case study focuses on real-time patient fitness monitoring in a clinic setting. The suggested device utilizes an Internet of Things-ready device that has many sensors, including oxygen, pressure, and temperature sensors. The issues of forecasting patient health in advance are handled with the deployment of machine learning models, notably Artificial Neural Networks (ANN), Decision Trees (DT), and Support Vector Machines (SVM). The second case study analyses IoT's effect on patient-precise medication identification and remote fitness monitoring, uncovering issues associated with accessibility, pricing, and human interfaces. Proposed alternatives, which incorporates greater education, increased accessibility, and user-pleasant interfaces with robust technical assistance, have been evaluated with 30 patients over a three-month duration. The results reveal a great growth in impacted person health, along with heightened attention of periodic health monitoring. The results highlight how IoT technologies may transform healthcare procedures by offering pro-active solutions for patients' well-being. This study offers insightful information that may be used to solve practical issues, promote patient-centered solutions, and broaden the scope of the healthcare period. A significant step towards a patient-centered and technologically advanced healthcare environment, the successful outcomes validate the capacity for sustained innovation, cooperation, and improvement in the integration of IoT systems for optimal patient care. 2024 IEEE. -
Enhanced Learning in IoT-Based Intelligent Plant Irrigation System for Optimal Growth and Water Management
This research looked at the transformative potential of cutting-edge machine learning algorithms in various areas of precision agriculture, with an emphasis on enhancing smart irrigation systems for onion farming. Using a vast sensor network and real-time monitoring, we investigated the performance of CNN, ANN, and SVM, three well-known machine learning algorithms. After extensive testing and investigation, our results reveal that CNN beats ANN and SVM in terms of outstanding accuracy in predicting plant water requirements. Because of CNN's superior predictive powers, our intelligent irrigation system maintains perfect soil conditions, resulting in increased agricultural yields and resource savings. The study's findings have important implications for modern agriculture, paving the way for data-driven, sustainable agricultural methods that address global concerns such as food security and environmental sustainability. As we approach the era of smart agriculture, our research demonstrates how technology has the potential to alter crop farming and aid in the development of a more resilient and successful agricultural industry. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
Comprehensive Comparative Analysis of Breast Cancer Forecasting Using Machine Learning Algorithms and Feature Selection Methods
This research leveraged machine learning models, including Deep Neural Network (DNN), Artificial Neural Network (ANN), and Support Vector Machine (SVM), to predict breast cancer from CT and MRI scans. A dataset comprising 2345 instances of malignant and benign cases was meticulously curated, with 80% allocated for training and 20% for testing. The experimental results revealed the DNN as the top-performing model, exhibiting remarkable accuracy (95.2%), precision (94.8%), recall (95.6%), and F1 score (95.2%). The ANN also demonstrated strong performance, achieving an accuracy of 93.6% with balanced precision and recall scores. In contrast, the SVM, while respectable, fell slightly behind the machine learning models in terms of overall accuracy and performance. Detailed confusion matrices further elucidated the models capabilities and limitations, providing valuable insights into their diagnostic prowess. These findings hold great promise for breast cancer diagnosis, offering a non-invasive and highly accurate means of early detection. Such a tool has the potential to enhance patient care, reduce the strain on healthcare systems, and alleviate patient anxiety. The success of this research highlights the transformative impact of advanced machine learning in medical imaging and diagnosis, signaling a path toward more efficient and effective healthcare solutions. Further research and clinical validation are essential to translate these promising results into practical applications that can positively impact patients and healthcare providers. The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. -
A Hybrid Edge-Cloud Computing Approach for Energy-Efficient Surveillance Using Deep Reinforcement Learning
This paper explores the novel application of Deep Reinforcement Learning (DRL) in designing a more efficient, scalable, and distributed surveillance architecture, which addresses concerns such as data storage limitations, latency, event detection accuracy, and significant energy consumption in cloud data centers. The proposed architecture employs edge and cloud computing to optimize video data processing and energy usage. The study further investigates the energy consumption patterns of such a system in detail. The implementation leverages machine learning models to identify optimal policies based on system interactions. The proposed solution is tested over an extensive period, resulting in a system capable of reducing latency, enhancing event detection accuracy, and minimizing energy consumption. 2023 IEEE. -
Evaluating the Categorical Exclusion of Khasi Women from Inheritance and Property Rights : A Case of East Khasi Hills
Customary laws govern inheritance among many tribal communities that fall within the ambit of the fifth and sixth schedules of the Indian Constitution. Under this papers scope, we shall look at the Khasi community hailing from the state of Meghalaya which is a matrilineal community. Where the Khasis draw their lineage from their mothers, there is a misnomer that women inherit and own the entire property. In light of the abovementioned background, the paper makes an analytical study of the customary inheritance rights of Khasi women, the nature of resource ownership and attempts to understand the grounds behind the claims of gender preference in the existing matrilineal system practised by the Khasis of Meghalaya. We also look at the intersection of gender and matrilineal system of inheritance in the Khasi community, the dispute between customs and legislations and examine whether there exists a need for codification. The paper also discusses the findings of the survey and focus group discussions including 90 Khasi women from East Khasi Hills and their growing consensus on equal inheritance rights but resistance towards statutory laws to govern their lives. JYOTI SINGH AND KAJORI BHATNAGAR, 2024. -
Perspectives on the Intersection of Gender, Customary Laws and Land Rights in India
For centuries, tribal communities in India have maintained distinct social and cultural identities, often with communal land ownership practices that were inclusive of women. The struggle of tribal women in India for land rights is a poignant manifestation of their fight against intersecting forms of oppression rooted in patriarchy, traditional power structures, and historical marginalisation. Given the existing background, this article discusses the intersection of property rights and gender relations in India, making a case for independent property rights for tribal women. It analyses the role of customary laws of inheritance in a legal pluralistic India and its conflict with positive law. The article also focuses on the role of the Indian judiciary in remedying the systemic discrimination against tribal women in India. It analyses the approach of the Indian courts in maintaining a balance between the autonomy granted to the tribes by the Indian Constitution and ensuring justice to women who are victims of such self-governance. 2024 Jyoti Singh and Kajori Bhatnagar. -
Uniform Civil Code, Legal Pluralism and Inheritance Rights of Tribal Indian Women
The 42nd Amendment to the Indian Constitution heralded India as a Sovereign, Socialist, Secular Democratic Republic. It initiated a constitutional narrative that has sparked ongoing debates and scrutiny regarding the true essence of Indias secularism. With the National Democratic Alliance (NDA) led by Bhartiya Janta Party(BJP) forming government with after the 2024 general elections, the discussion on potential implementation of the Uniform Civil Code at the forefront of political discourse. In this commentary, the authors discuss legal pluralism in India and the impact of the introduction of a uniform civil code on on customary laws of tribes, placing special emphasis on the inheritance rights of tribal women. The paper also discusses the approach of the higher courts in securing property rights for tribal women in the absence of such a code. 2024, Spoldzielczy Instytut Naukowy. All rights reserved. -
Bookstagrammers vs. BookTubers: A comparative study on readers' preferred social media book influencer
As the Internet has become a part of many people's daily lives, it has led to the growth of a reading culture influenced by book bloggers on different social media platforms. This chapter identifies two social media platforms that the readers utilize to share about the books they have read. While readers have found their reading space on social media platforms, some have become book influencers. This chapter identifies two categories of prominent literary influencers i.e., Bookstagrammers and BookTubers. Since the readers follow book influencers to learn about the latest books and to read their reviews before making their purchase decision. This chapter aims to compare and analyse the prominent categories of book influencers focusing on knowing more about the preferred book influencers from the readers' point of view. 2024, IGI Global. All rights reserved. -
Faculty acceptance of virtual teaching platforms for online teaching: Moderating role of resistance to change
Under this new normal world scenario, online teaching has been essential rather than a choice in continuing learning activities. During the COVID-19 period, virtual teaching platforms played an important role in the success of online teaching in various higher educational institutions. Thus, the current study attempted to predict faculty adoption of online platforms by introducing a set of essential drivers for engaging in online teaching. Following the theory of reasoned action, the study broadened the technology acceptance model variables and security and trust as extrinsic determinants and included resistance to change as moderators to invigorate the research model. Data were collected through an online survey with a sample size of 418 Indian respondents. Our results posit that perceived ease of use, usefulness, security and trust positively influence the faculty's intentions to adopt online platforms. In addition, the study also reported that positive intention leads to the actual use of virtual platforms. Furthermore, the research found the moderating role of the resistance to change dimension in the association of intention and actual use of virtual teaching platforms. The findings provide both theoretical and practical applications of educational technology. Implications for practice or policy The first step for accepting virtual teaching platforms is to help faculty to reduce their resistance for effective online teaching. Higher education institutions should have a policy promising faculty that online teaching using virtual teaching platforms will offer a safer and more trustworthy environment. Higher education institutions should undertake intense organisational renewal and implement bottom-up processes for synchronous learning. Regulators could frame a policy including virtual teaching platforms to provide interactive professional development opportunities. Articles published in the Australasian Journal of Educational Technology (AJET) are available under Creative Commons Attribution Non-Commercial No Derivatives Licence (CC BY-NC-ND 4.0). Authors retain copyright in their work and grant AJET right of first publication under CC BY-NC-ND 4.0.