E-analysis and Notarization of Social Media based on Blockchain Technology Machine Learning and Blockchain Challenges Future Trends and Sustainable Technologies, 2026
Governance, Security, and Ethical Considerations in AI-Driven Motion Control Systems K. Selvi, P. Anbarasan, G. Madhumita, L. Janaki, K. K. Devi Methodologies and Applications of Intelligent Motion Control Systems, 2025 Motion control systems based on AI are revolutionising industries with their accuracy, flexibility, and efficiency but pose serious governance, security and ethical issues. The chapter focuses on the intersection of institutional frameworks, cybersecurity practises and ethical principles in the development of responsible adoption. It presents the connections between governance, resilience, and ethics as interdependent based on interdisciplinary theories, mixed-method analysis, and case studies. Among the crucial findings, there is the necessity to have adaptive regulations, strong security-by-design, and ethical alignment to provide transparency, accountability, and social justice. The chapter suggests the combined solutions and describes the future research directions to ensure the sustainable and reliable innovation in AI-driven motion control.
A Machine Learning Model for Predicting Workplace Spirituality Levels Based on Bhagavad Gita Stress Management Parameters K.S. Sivakumar, G. Madhumita 2025 IEEE 5th International Conference on ICT in Business Industry and Government Ictbig 2025, 2025 Spirituality in the workplace is essential in facilitating the welfare and motivation of employees as well as harmony in the organization. Nevertheless, the majority of the current methods are based on subjective evaluation and do not have quantitative predictive practices. To overcome this weakness, it proposes a machine learning model, KarmaNet, to estimate Workplace Spirituality Levels (WSL) based on Bhagavad Gita-based parameters of stress management, including Equanimity, Karma Orientation, Attachment Control, Desire Regulation, and Anger Modulation. A special dataset of 820 records of employees was trained and preprocessed on the KarmaNet neural framework. The test accuracy of the model was 92.15%, the validation accuracy was 93.42%, and the Spiritual Harmony Index (SHI) was 0.918, which was better than the conventional algorithms such as SVM, Random Forest, and KNN. Findings have shown that Equanimity and Karma Orientation are the most effective features in the prediction of spirituality. The proposed framework represents a new combination of the philosophy of spirituality and artificial intelligence to increase well-being in the workplace and forecast human resource analytics.
Design of an AI-Based Decision Support System for Stress Reduction and Workplace Spirituality Enhancement in Educational Institutions K.S. Sivakumar, G. Madhumita 2025 IEEE 5th International Conference on ICT in Business Industry and Government Ictbig 2025, 2025 Rising stress levels and a decline in workplace spirituality among educators and students demand sophisticated and holistic well-being interventions. Although the existing systems focus on wearable-based monitoring and workshop-based intervention, these are relatively freestanding and suffer from limited personalization, long lag times, and short-term benefits. The propose an AI-Based Decision Support System (AI-DSS) that uses gradient boosting and temporal transformer model modalities to predict stress and recommend adaptive interventions that combine spirituality practices with stress-reduction techniques. The proposed system was initially implemented over 16 weeks with 412 participants, resulting in 89.5 % accuracy, an F1-score of 0.78, and an AUC of 0.86. The traditional techniques resulted in a 27 % reduction in stress markers, a 19 % decrease in burnout, and a 22 % increase in workplace spirituality. The results indicate that artificial intelligence-based close, personalized, and continuous monitoring significantly increases well-being, engagement, and institutional synergy, establishing an observational, data-linked structure for continuous, sustainable educational improvement.
Implementing and Managing Green IT Strategies to Enhance Corporate Sustainability K. Sudharson, N. Vijayakumar, L. Anitha, V. Subhashini, G. Madhumita, A. SureshKumar 2025 IEEE International Students Conference on Electrical Electronics and Computer Science Sceecs 2025, 2025 Importance of Green IT practices is that it improves corporate sustainability through conserving the natural environment and minimizing the use of resource. This paper focuses on next generation IT management for power-optimized hardware, virtualization, cloud computing, and intelligent system through SITOF. Some of the key technologies are: ARM-based low power servers, vSphere-server visualization, Docker- Containerization, Solar/wind hybrid power. It shows that the main benefits of the IT of smart buildings are a 35% saving in energy and 40% reduction in carbons, as well as a quarter decrease in operation costs when compared to traditional IT practices. Moreover, data analytic improve performance measurement and management and hence contributing to an improvement in sustainability issues. These results also show that SITOF is feasible to assist firms in attaining corporate sustainability objectives while embracing the best practice of technology management.
Effect of Office Automation on Enhancing Quality of Life of Employees in IT/Printing Industry Quality Access to Success, 2024 The objective of this study was to investigate the association among office automation and staff members' quality of life and self-efficacy in Information Technology Parks / IT Companies and printing industry.The investigation was conducted in the field using correlational descriptive data collection technique keeping in mind the practical objective.The whole employees (N=50) of IT parks/printing industry were represented in the data population.Also, 384 individuals were randomly selected as the sample of the study, and the selection strategy of the study included Stratified Random Sampling and Morgan tables to estimate the sample size.According to the data of Cranach's alpha, the reliability of the questionnaire was evaluated by administering it to 30 publics.The results of work life office automation =0.80, self-efficacy =0.78, and quality questionnaire =0.8 respectively, indicating the importance of the questionnaire.For inferential analysis of results and hypotheses using SPSS software version 22, Kolmogorov-Smirnov statistical models, linear regression, Shapiro-Wilk, Pearson coefficient were used.According to the results of linear regression, office automation does not significantly affect the self-efficacy of employees (p=0.19,t=0.142), but it significantly affects the quality of life of employees (P>0.001,For SQ (t)= 11.562,), and according to the coefficient of determination (R2=0.837).However, an agreed office automation analysis with reliability analysis is good.
AI-powered Performance Management: Driving Employee Success and Organizational Growth G Madhumita, P. Dolly Diana, Neena PC, P B Narendra Kiran, Swati Aggarwal, Amarja Satish Nargunde 5th International Conference on Recent Trends in Computer Science and Technology Icrtcst 2024 Proceedings, 2024 As organizations navigate the dynamic landscape of the modern workplace, the need for effective performance management becomes increasingly critical. Traditional performance management systems often fall short in providing real-time insights, personalized feedback, and data-driven decision-making. This research explores the integration of artificial intelligence (AI) into performance management practices as a transformative approach to enhance employee success and fuel organizational growth. The advent of AI technologies has ushered in a new era in which data analytics, machine learning, and natural language processing can be harnessed to optimize performance management processes. This research reviews the current challenges in traditional performance management, such as subjectivity, infrequent feedback, and reliance on past data. It then delves into the ways AI can address these challenges by offering continuous monitoring, predictive analytics, and personalized recommendations. The role of AI in performance management extends beyond mere efficiency improvements. By leveraging AI algorithms, organizations can gain deeper insights into employee strengths, weaknesses, and potential areas for development. Furthermore, the paper explores the impact of AI-powered performance management on employee engagement and motivation. The potential benefits extend to talent retention and attraction, as employees thrive in an ecosystem that values their contributions and supports their professional growth. In conclusion, this paper advocates for the integration of AI into performance management as a strategic initiative for organizations aiming to stay competitive in the evolving business landscape. AI-powered performance management systems have the potential to revolutionize the way organizations nurture talent, drive employee success, and ultimately achieve sustainable organizational growth. The insights presented in this research serve as a guide for organizations seeking to harness the transformative power of AI in their pursuit of excellence in performance management.
Detecting Learning Patterns and Student Engagement in Online Courses using Deep Learning V. Subhashini, A. Rahamath Nisha, V. Radhalakshmi, G. Madhumita, K Selvi, K. Sudharson Proceedings of 2024 International Conference on Science Technology Engineering and Management Icstem 2024, 2024 This study introduces LearnTrans, a novel model architecture that integrates the Transformer architecture with attention mechanisms to discern learning patterns and gauge student engagement in online courses. LearnTrans employs Transformer encoder layers with self-attention mechanisms to capture dependencies within the sequential interactions of students with course content. Through rigorous experimentation on a diverse dataset collected from prominent online learning platforms, including Coursera, Udemy, and edX, LearnTrans demonstrates significant performance improvements over baseline methods. Specifically, the model achieves an average accuracy increase of 33% in learning pattern detection and 29% in student engagement prediction tasks. These findings underscore the efficacy of the proposed LearnTrans model in capturing intricate patterns and dependencies within online learning data, offering promising avenues for enhancing educational outcomes in digital learning environments.
IoT and AI for Real-Time Customer Behavior Analysis in Digital Banking G Madhumita, Tapas Das, Seshanwita Das, Eti Khatri, P. Ravisankar, P. Hemachandu 5th International Conference on Recent Trends in Computer Science and Technology Icrtcst 2024 Proceedings, 2024 Digital transformation has revolutionized the banking industry, ushering in an era of enhanced customer experiences and operational efficiency. The convergence of Internet of Things (IoT) and Artificial Intelligence (AI) technologies has further propelled this evolution by providing real-time insights into customer behavior. This research explores the integration of IoT and AI for real-time customer behavior analysis in the context of digital banking. The proliferation of connected devices, ranging from smart phones to wearables, has generated an unprecedented volume of data. IoT facilitates the collection of diverse data points, such as transaction history, location information, and device interactions, creating a comprehensive digital footprint for each customer. Simultaneously, AI algorithms leverage this wealth of data to analyze, predict, and respond to customer behavior dynamically. In the realm of digital banking, understanding and adapting to customer behavior in real-time is crucial for providing personalized services, preventing fraud, and optimizing operational processes. This research delves into the mechanisms by which IoT sensors and devices, coupled with AI algorithms, enable banks to gain deeper insights into customer behavior patterns. Key components of the proposed system include data acquisition through IoT devices, secure data transmission protocols, and AI-driven analytics engines. In conclusion, this research advocates for the symbiotic relationship between IoT and AI in digital banking to enable real-time customer behavior analysis.
Smart grid – introduction, advantages and implementation status in India with a focus on Tamil Nadu: A systematic review. International Journal of Advanced Science and Technology, 2020
Social media effect on students academic performance based on their usage International Journal of Scientific and Technology Research, 2019
Collision of social network sites among college students academic performance International Journal of Recent Technology and Engineering, 2019
Prognostic analysis of purchase experience of women professional towards facial cream brands Journal of Advanced Research in Dynamical and Control Systems, 2018
Imperative variables, discriminating the influence of dermatologist towards the usage of facial cream brands Man in India, 2017
Viability of using factor analysis to investigate the impact on purchase experience with facial creams among women professionals International Journal of Applied Business and Economic Research, 2017
