Browse Items (16488 total)
Sort by:
-
Enhancing Metabolomics Pathway Prediction with Sequential Graph Convolutional Network
Metabolomics is a powerful tool for the understanding of biological systems by analysis of metabolites and their related pathways. Prediction of metabolic pathways is still one of the most challenging tasks because of the complexity of molecular structures and graph-structured metabolomics data. This article presents a robust framework using Graph Convolutional Networks (GCNs) to address the challenges. The methodology proposed includes first preprocessing through metabolite identification by mass spectrometry, and then it utilizes feature extraction through the RDKit library. The objective of the research is aim to metabolic pathway prediction using machine learning algorithm. Complex patterns and relationships are captured from the SMILES representation through the molecular graphs constructed and passed on for the GCN model to learn structured data. ReLU activation functions have been employed within a three-layer sequential GCN architecture that enables it to deliver highly accurate results while ensuring that they are understandable as well. The proposed sequential GCN Model was evaluated on the KEGG dataset with an accuracy of 98.00%, precision of 92.10%, and recall of 93.02%. The performance of these metrics is well beyond traditional approaches such as KNN, ensemble logistic regression, and other GCN based approaches. Thus, this work brings GCN based approaches closer to revolutionizing metabolic pathway prediction and the advancement of the metabolomics field. 2025 IEEE. -
Enhancing Mental Health and Treatment Adherence in HIV/AIDS Patients Through Strengthened Social Networks
The study explores how social networks and support enhance the health and treatment adherence of HIV patients. HIV/AIDS affects not only physical health but also leads to social stigma, discrimination, and emotional challenges. A strong social network improves the quality of life, reduces psychological issues like anxiety and depression, and promotes overall well-being. Strengthening network sustainability for vulnerable HIV/AIDS patients can enhance emotional support, self-care, and treatment adherence. Conducted in Pudukottai District, Tamil Nadu, the study involved 120 samples, with data collected through the Positive Network and NGO support. The findings offer policy implications, assist healthcare providers in managing affected individuals effectively, and highlight the role of NGO services in improving mental health outcomes and creating a supportive environment for PLHIV. Copyright 2026, IGI Global Scientific Publishing. -
Enhancing Medical Decision Support Systems withtheTwo-Parameter Logistic Regression Model
The logistic regression model is an invaluable tool for predicting binary response variables, yet it faces a significant challenge in scenarios where explanatory variables exhibit multicollinearity. Multicollinearity hinders the models ability to provide accurate and reliable predictions. To address this critical issue, this study introduces innovative combinations of Ridge and Liu estimators tailored for the two-parameter logistic regression model. To evaluate the effectiveness of the combination of ridge and Liu estimators under the two-parameter logistic regression, a real-world dataset from the medical domain is utilized, and Mean Squared Errors are employed as a performance metric. The findings of our investigation revealed that the ridge estimator, denoted as k4, outperforms other Liu estimators when multicollinearity is present in the data. The significance of this research lies in its potential to enhance the reliability of predictions for binary outcome variables in the medical domain. These novel estimators offer a promising solution to the multicollinearity challenge, contributing to more accurate and trustworthy results, ultimately benefiting medical practitioners and researchers alike. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024. -
Enhancing Malware Detection Through Hybrid Deep Learning Techniques
The detection of malware needs superior methods than basic signature detection because it remains vital to cybersecurity. This research examines malware classification through the deep learning approach by analyzing Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU) and develops a new BiGRU + CNN hybrid model. The main purpose is to achieve better detection performance through reduced numbers of false alarms. The research employs executable file feature data while implementing preprocessing methods together with fivefold cross-validation validation to establish strong model reliability. Experimental findings show CNN along with LSTM and GRU attains excellent recall values yet produces elevated erroneous positive predictions. The proposed BiGRU + CNN model delivers superiority over single-model architecture as it reaches 96.06% accuracy alongside 96.13% precision and 99.92% recall and 97.99% F1-score. The obtained results show that this integration has better malware detection capabilities thereby demonstrating its potential for cybersecurity applications. 2025 IEEE. -
Enhancing Lung Cancer Detection Accuracy: Implementing Smote for Balanced Learning
This research goal is to forecast lung cancer using machine learning, and addressing the dataset's class imbalance is a top priority. The data that was initially gathered was extremely unbalanced, with 87.38% of instances being of the minority class of lung cancer and only 12.62% being non-cancer cases. To address this imbalance, minority over-sampling through self-generated SMOTE (Synthetic Minority Over-sampling Technique) was implemented wherein there were 64.85% cases of lung cancer and 35.15% of non-lung cancer cases after deduplication. Logistic regression (LR), Gaussian naive Bayes, Support Vector Machine (SVM), Bernoulli naive Bayes, K nearest neighbors (KNN), Random Forest (RF), multi-layer perceptron, and extreme gradient boosting are among the machine learning methods that were tested. The best test performance was shown by the Random Forest and Extreme Gradient Boosting methods that achieved an accuracy of 97.3% followed by K Nearest Neighbors at 95.95%, and Multi-Layer Perceptron at 93.24%. This highlights the necessity of data balance and the ways in which these methods can improve the efficacy of predictive models for lung cancer. As such, this addition contributes to the dearly needed critical knowledge which may be a stepping stone for innovation within the domains of diagnosis and treatment medicine through machine learning. 2025 IEEE. -
Enhancing Low-Power VLSI Design through AI-Based Simulation and Optimization
AI and ML techniques have dramatically influenced rapid developments in low-power VLSI design with fast advancements in device simulations and power optimization strategies. AI-based simulation tools are now used for accurate modeling of power consumption, improving thermal analysis, and quickening design iterations through the detection of inefficiencies and optimization of energy consumption. In fact, this work focuses on some AI-enabled methods of power reduction techniques such as voltage scaling, clock gating, and leakage current minimization with respect to a sustainable VLSI design. Moreover, a synthetic dataset is created to mimic the actual power consumption trend in VLSI circuits so that predictive modeling and regression techniques can be used for power estimation. Different regression models are used to check the predictive accuracy, and it was found that the highest R2 score was 0.85 by Linear Regression, while the worst was achieved by Decision Tree Regression at 0.50. Results of the correlation analysis and models by machine learning clearly indicate that the frequency and operating voltage are the major contributors to consumption power, while gate counts have a relatively insignificant contribution. Introduction of AI in VLSI simulation enables the enhancement of power efficiency while maintaining sustainability outcomes by optimizing energy usage and cost reduction in terms of computation. 2025 IEEE. -
Enhancing Log File Analysis in Digital Forensics and Incident Response through Machine Learning
Log file analysis is crucial for identifying and exploring digital security incidents by recording system and network traffic. The growing volume and complexity of log data do not allow traditional analytical methods to be used, which led to the need for the development of more advanced analytical tools. This chapter shows a new method to infer practical information from the log file analysis using machine learning algorithms combined with Python programming. The technique has the following structure: Data preprocessing, Feature extraction, and then using multiple machine learning models such as RandomForestClassifier, Gradient Boosting Classifier, SVM, XGBoostClassifier, and MLPClassifier. Adding Python greatly improves these advanced models' accuracy and efficiency in analyzing log files. The XGBoostClassifier achieved the highest accuracy, which was 0.9198 as precision, and it indicates good applicability to complicated log data compared to another model in our test. This section compares the machine learning models using the UNSWNb15 dataset, which provides a broad range of network traffic data. The chapter contains some visualizations of flagship results and a detailed discussion about the results, discussing the challenges and limitations of the proposed approach. It also suggests future research directions. The results also typify the specifics of how Python and machine learning can be disrupted to develop digital forensics incident response practicability, bringing forth such innovations that cater to solving the cyber world's rapidly transitioning threat landscapes and tooling up valued scientific knowledge in the domain. 2026 selection and editorial matter, Vinay Aseri, Sumit Kumar Choudhary, and Adarsh Kumar; individual chapters, the contributors. -
Enhancing Learning and Societal Innovation with Cyber-Physical Systems: Education and Society
Cyber-Physical Systems (CPS) are evolving rapidly and can significantly impact education and society. In this paper, we explore the various technologies and applications of CPS in the context of education and social concerns. Through the integration of computation, networking, and physical processes, CPS can enhance educational experiences, foster social inclusion, and address societal challenges. Using CPS in education allows for intelligent learning environments, personalized learning experiences, and real-time feedback systems that meet the diverse needs of students and encourage them to engage in their learning. With real-time monitoring and response systems, CPS can help develop smart communities, improve accessibility for disabled individuals, and enhance public safety. This paper provides a comprehensive analysis of CPS technologies and their applications, highlighting their transformative potential in education and society, motivating further research and policy development. The implementation of CPS can transform education and society, but enhanced security measures must accompany their implementation. Integrating CPS in real-world applications requires safeguarding sensitive data and safeguarding against cyber-threats. This collaboration ensures that diverse perspectives are considered, leading to more comprehensive solutions that address the multifaceted challenges of CPS deployment. It also enhances the effectiveness and sustainability of CPS applications by combining different expertise. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Enhancing language teaching materials through artificial intelligence: Opportunities and challenges
Incorporating artificial intelligence (AI) into language education signifies a paradigm shift that promotes originality and inclusiveness. The partnership between AI developers and educators effectively tackles obstacles and establishes a foundation for continuous progress. Anticipating the future, the progression of AI holds the potential to deliver intricate customization, customizing educational encounters to suit the unique requirements of each individual. Responsible incorporation of AI into teaching methodologies transforms them into a collaborative model that empowers educators to engage in individualized interactions. Ethics remain of the utmost importance, encompassing bias mitigation and privacy. In essence, the integration of AI into language education signifies an impending era in which the combined powers of technology and human proficiency foster the development of capable individuals who are prepared to navigate an interconnected, digitally globalized society. 2024, IGI Global. All rights reserved. -
Enhancing Kubernetes Auto-Scaling: Leveraging Metrics for Improved Workload Performance
Kubernetes is an open-source production-grade container orchestration platform, that can enable high availability and scalability for various types of workloads. Maximizing the performance and reducing the cost are two major challenges modern applications encounter. To achieve this, resource management and proactively deploying resources to meet specific application requirements becomes utmost important. Adopting Kubernetes auto-scaler to fit one's needs are important to maximize the performance. This study aims to perform a comprehensive analysis of Kubernetes auto-scaling policies. This paper also lists out the various parameters considered for auto-scaling, and prediction methods used to efficiently handle resource requirements of applications. The research findings reveal a scarcity in the existing work regarding the variety of workload based auto-scaling and custom metrics. This paper provides a concise overview of a forthcoming research endeavor that explores the utilization of custom metrics in conjunction with auto-scaling. 2023 IEEE. -
Enhancing Kannada Handwritten Text Processing: A Deep Learning Approach to Optimized Recognition and Segmentation
Digitalization ensures that information is available in diverse regional languages, empowering more cultures and perspectives to be heard and understood. One of the regional languages considered for empowering information access is the Handwritten Kannada document. Extracting text from these documents requires overcoming several obstacles, such as deciphering diverse handwriting styles, accommodating inconsistencies in character size, and the presence of multiple touches between characters. The present paper explored recognizing and segmenting Kannada handwritten characters using a deep learning model, specifically YOLOv8. While YOLOv8 is primarily known for real-time object detection, the paper suggests its potential for character detection tasks. The model achieved a promising mean Average Precision (mAP) of 96.8% at a threshold of 0.5 on a hybrid dataset consisting of 2476 images and 95.0% on character segmentation. This experiment adds to the growing body of research exploring YOLOv8s capabilities beyond traditional real-time object detection and instance segmentation. 2025 The Authors. Published by Elsevier B.V. -
Enhancing IoT Security Through Multilayer Unsupervised Learning and Hybrid Models
This research addresses the challenge of limited unsupervised learning in current IoT security research, which heavily relies on labelled datasets, hindering the detection of unknown threats. To overcome this constraint, the study proposes a sophisticated methodology integrating K-means clustering, autoencoders, and a hybrid model (combining both). The aim is to enhance detection capabilities without being reliant on prior labelled data. Emphasizing the need to go beyond traditional models, the research underscores the significance of incorporating a diverse range of smart home IoT devices to gain comprehensive insights. Tests conducted on the N-BaIoT dataset, which incorporates authentic traffic data from nine commercial IoT devices afflicted with Mirai and BASH-LITE infections, demonstrate the effectiveness of the suggested models. K-means clustering demonstrates excellence in precision, recall, and F1-scores, particularly in Doorbell and Thermostat categories. The Hybrid model consistently achieves high precision and recall metrics across various device categories by leveraging the strengths of both Kmeans and autoencoder techniques. Notably, the Autoencoder model stands out for its exceptional ability to achieve a perfect 100% detection rate for anomalies across all devices. This study highlights the robust performance of the proposed unsupervised learning models, emphasizing their strengths and potential areas for refinement in enhancing IoT network security. 2024 IEEE. -
Enhancing IoT Security Through Deep Learning-Based Intrusion Detection
The Internet of Things (IoT) has revolutionized the way we interact with technology by connecting everyday devices to the internet. However, this increased connectivity also poses new security challenges, as IoT devices are often vulnerable to intrusion and malicious attacks. In this paper, we propose a deep learning-based intrusion detection system for enhancing IoT security. The proposed work has been experimented on IoT-23 dataset taken from Zenodo. The proposed work has been tested with 10 machine learning classifiers and two deep learning models without feature selection and with feature selection. From the results it can be inferred that the proposed work performs well with feature selection and in deep learning model named as Gated Recurrent Units (GRU) and the GRU is tested with various optimizers namely Follow-the-Regularized-Leader (Ftrl), Adaptive Delta (Adadelta), Adaptive Gradient Algorithm (Adagrad), Root Mean Squared Propagation (RmsProp), Stochastic Gradient Descent (SGD), Nesterov-Accelerated Adaptive Moment Estimation (Nadam), Adaptive Moment Estimation (Adam). Each evaluation is done with the consideration of highest performance metric with low running time. 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG. -
Enhancing Investment Advisory with Machine Learning for a New Era in Financial Services
The current financial service environment, where the volatility of markets and the need to offer flexible solutions is growing, is starting to challenge the traditional investment advisory models. This paper implements a new framework, which incorporates the most advanced methods of machine learning, to make investment advising a process driven by real data. This is unlike the current models which are overly dependent on historical trends or fixed risk profiles, our system allows us to use real time behavior analytics, sentiment analysis and dynamic portfolio optimization to give hyper personalized investment recommendations. The framework feeds the ensemble learning, attention-based neural networks, explainable AI (XAI) to make sure the transparency, regulatory, and investor trust. The innovation in particular is based on the constant interaction between client and adjustment of the model in terms of a ready and sensitive advisory intervention. The study will not only improve the relevance and precision of financial advice, but will with its informed automation of advisor-client relationship led to a redefinition of the advisor-client relationship. The insights guide to a world of advisory services where ML and machine learning complement strategic decision-making with unheard levels of specificity and individuality. 2025 IEEE. -
Enhancing instructional effectiveness using the metaverse: An empirical analysis of the role of attitude and experience of participants
The Metaverse has been gaining importance, with businesses looking to adopt the same for processes rangingfrom onboarding to customer experience. The current study has been conducted to evaluate the impact of learner characteristics on motivation to participate in metaverse-based training programs across various organizations. Based on literature and theory, two main characteristics were identified: attitude towards the metaverse and experience with the technology. Data for the study was collected using a structured questionnaire and 103 responses were collected from employees belonging to various organizations in India. The analysis and interpretation of the data was done using statistical techniques through the tool of SPSS. The study found out that both the learner characteristics have a strong positive relationship with each other, and attitude towards metaverse has a stronger relationship with learner motivation than the experience of use. The findings suggest organizations focus more on the manner in which they should introduce metaverse at the workplaces and need to keep the employee attitude towards any kind of change; more of a technological change in mind when they are strategizing to implement metaverse-based training programs. 2024, IGI Global. All rights reserved. -
Enhancing Industrial Equipment Reliability: Advanced Predictive Maintenance Strategies Using Data Analytics and Machine Learning
In today's dynamic industrial landscape, optimizing machinery performance and minimizing downtime are paramount for sustained operational excellence. This paper presents advanced predictive maintenance strategies, with a focus on leveraging machine learning and data analytics to enhance the reliability and efficiency of industrial equipment. The study explores the key components of predictive maintenance, including data collection, condition monitoring, predictive models, failure prediction, optimized maintenance scheduling and the extension of equipment longevity. The paper discusses how predictive maintenance aligns with modern industrial paradigms. The study evaluated the performance of five popular forecasting models like Random Forest, Linear Regression, Exponential Smoothing, ARIMA, and LSTM, to estimate maintenance for industrial equipment. The effectiveness of each model was evaluated using a number of performance metrics. The percentage of the variation in the real data that the model can explain is shown by the R-squared number. The lowest MSE, RMSE, and greatest R-squared values indicate a model's accuracy. The study highlights practical implications across diverse industries, showcasing the transformative impact of predictive maintenance on minimizing unplanned downtime, reducing maintenance costs, and maximizing the lifespan of critical machinery. When it comes to predictive maintenance for industrial machinery, the LSTM model has been shown to be the most accurate and efficient model with the highest R-squared value, indicating a better fit and higher predictive ability. As technology continues to evolve, the paper discusses future directions, including the integration of artificial intelligence and advanced analytics, and emphasizes the importance of continuous improvement in refining predictive maintenance strategies for the evolving needs of industries worldwide. 2024 IEEE. -
Enhancing image compression through a novel Structural Fidelity Weighted Ensemble (SFWE) model
With the explosion of digital images across multiple sectors like social media, health care, medical imaging, and remote sensing, there is a demand to optimise the storage and transmission of images. In this paper, a novel Structural Fidelity Weighted Ensemble model is proposed to dynamically adjust the weights between SVD and PCA outputs to enhance the quality of reconstructed images.Unlike traditional static fusion techniques, the proposed SFWE deploys a fast bounded scalar optimization strategy so as to dynamically estimate the optimal fusion weights thereby ensuring non-negativity and simplex constraints while significantly reducing computational overhead compared to Sequential Quadratic Programming(SQP) or constrained gradient descent methods.Validation was done across multiple benchmarks datasets namely, USC-SIPI Sequences (grayscale TIFF), Kodak, BSDS500, DRIVE (Digital Retinal Images for Vessel Extraction), and ISPRS Potsdam which cover natural, medical, and remote-sensing images. Per-image processing, runtime measurement, and compressed ratio (CR) were produced automatically by the provided evaluation pipeline;The SFWE method provides greater image quality and structural fidelity across diverse datasets, attaining a PSNR of 40 dB and SSIM of 0.95, outperforming existing approaches such as Discrete Cosine Transform (DCT), Wavelet Transform, Singular Value Decomposition (SVD), and Principal Component Analysis and JPEG2000 + CNN models. In addition, it also maintains a good compression ratio leading to an effective balance between the reduction in file size as well as visual quality of the images, which confirms enhanced structural preservation across diverse image types. To implement a novel ensemble model (SFWE) that optimally balances the outputs of SVD and PCA for doing effective image compression. To achieve a higher SSIM (0.95) and good PSNR (40 dB) compared to compression techniques such as DCT, Wavelet, SVD, PCA, and JPEG2000 + CNN. To ensure adaptive high-quality reconstruction across multiple datasets, demonstrating its suitability for diverse image-intensive applications. 2025 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license. http://creativecommons.org/licenses/by/4.0/ -
Enhancing Image Classification Performance through Hybrid Self-Supervised Learning Strategies
Image classification is a cornerstone of computer vision, with the applications spanning healthcare, autonomous driving and security. The dependence on large labeled datasets for supervised learning poses significant challenges, particularly in specialized fields where the labeled data is scarce and expensive to obtain. Self-supervised learning (SSL) has emerged as a promising paradigm, enabling models to learn useful representations from unlabelled data by designing pretext tasks that generate pseudo-labels. SSL faces limitations in handling complex data distributions and achieving robust generalization. This paper explores hybrid self-supervised learning strategies that combine multiple SSL techniques, such as contrastive learning, masked image modeling, and clustering, to enhance image classification performance and reduce dependence on labeled data. This study proposes a comprehensive framework that integrates data augmentation, feature extraction, and hybrid learning mechanisms, evaluated on the CIFAR-100 dataset. The experimental results demonstrate that hybrid SSL approaches achieve significant improvements in performance. The combination of SimCLR and masked image modeling (MAE) achieves a Top-1 accuracy of 77.8% on the clean test set and 71.4% on the domain-shifted set, and self-distillation with contrastive learning (DINO) achieves the highest Top-1 accuracy of 78.4% on the clean test set and 72.1% on the domain-shifted set. Advanced data augmentation techniques, such as CutMix and RandAugment, additionally enhance model robustness, with SwAV (contrastive clustering) achieving 76.5% Top-1 accuracy on the clean test set and 70.1% on the domain-shifted set. The findings highlight the effectiveness of hybrid SSL methods in addressing the challenges of limited labelled data, offering valuable insights for future research and applications in image classification. 2025 Seventh Sense Research Group. -
Enhancing Human-Computer Interaction with a Low-Cost Air Mouse and Sign Language Recognition System
The purpose of this study is to investigate the development of assistive technologies that are designed to empower people with disabilities by increasing their level of freedom and accessibility. Voice assistants, air mice, and software that recognizes sign language are some of the topics that are specifically covered in this. Those who have impaired fine motor skills can benefit from using air mice since they allow controls to be made by hand gestures. Using machine learning algorithms, sign language recognition software is able to decipher signs with an accuracy rate of over 90 percent, making it easier for people who are deaf or hard of hearing to communicate themselves. By relying solely on vocal instructions, voice assistants like Alexa make it possible to control devices without using your hands. Not only do these technologies have the potential to be revolutionary, but they also confront obstacles in terms of improving identification accuracy and integrating them into common gadgets. In this study, the development and impact of voice assistants, sign language software, and air mice are discussed. More specifically, the paper highlights the potential for these technologies to help millions of people with disabilities all over the world. Additionally, it examines potential enhancements that could be made to these technologies in the future in order to further improve accessibility and inclusivity. This research integrates computer vision and machine learning to create a multimodal system blending air mouse functionality with real-time sign language translation. Achieving 95% accuracy in gesture recognition for air mouse control and 98% accuracy in sign language letter classification using a basic webcam, the system promotes accessible interaction without specialized hardware. Despite limitations in vocabulary and lighting sensitivity, future efforts aim to broaden data training and explore mobile deployment. These advancements hold promise for enhancing natural human-computer interaction, particularly for users with disabilities, by enabling intuitive, hands-free control and communication. 2024 IEEE. -
Enhancing Human Resource Management With Fuzzy Logic and Neural Networks for Personalized Performance Management
Human resource management (HRM) encounters that is making more challenging some exact, fair and person related performance appraisals on a large scale. Traditional methods often fail to capture the richness of human behaviour and tend to be opaque to interpretation. The proposed study contributes a new hybrid approach of Fuzzy Logic and Neural Network for enhanced personalized performance management. The facts are presented qualitatively by the fuzzy inference system in linguistic terms while for numerical features, the neural network analyses such that it can find complex relationship patterns. This methodology ensures the simplicity and high predictability. The model trained on Kaggle dataset achieved an accuracy of 94.7%, F1-score of 0.942, precision of 0.945, recall of 0.940 and AUC-ROC of. 976 which were higher compared to baseline approaches like Logistic Regression and Decision Trees respectively. The solution helps HR professionals make sense of relevant information into employee performance and developmental needs, which are highlighted in real time. The results suggest that combining rule-based reasoning and machine learning enhances personalisation and offers more transparent human resources practices. This study provides a foundation for the next generation of intelligent HRM systems enabling adaptive decision support in various organizational settings. 2026 IEEE.