Citation

Akila, D. and Pal, Souvik and Vijayarani, M. and Sarkar, Bikramjit and Anbananthen, Kalaiarasi Sonai Muthu and Muthaiyah, Saravanan (2026) IoT-Driven Emotional Data Analytics for Medical Applications: Insights and Innovations. Emerging Science Journal, 10 (1). pp. 100-121. ISSN 2610-9182

Text 5.pdf - Published Version Restricted to Repository staff only Download (1MB)

Abstract

This study introduces the Internet of Things-based Emotional State Detection Model (IoT-ESDM), a comprehensive and intelligent emotional computing framework aimed at detecting and managing anxiety-related behavior in healthcare environments. The model leverages a multi-modal approach that combines facial expression analysis, physiological signal monitoring, and AI-driven classification to accurately identify emotional states in real time. Core components of the system include fuzzy color filtering, histogram analysis, and virtual face modeling, which work together to extract relevant emotional features from input data. These features are then analyzed to provide adaptive, personalized feedback to patients or caregivers, enhancing emotional well-being support. Experimental results demonstrate the superior performance of IoT-ESDM over existing emotion detection systems. The model achieved a feedback ratio of 97.54%, accessibility ratio of 95.3%, detection accuracy of 92.7%, and a classification accuracy of 98.13%. Additionally, it showed a quality assurance rate of 94.13%, contributed to a 29.1% reduction in anxiety levels, and yielded a health outcome ratio of 94.5%. These metrics validate the system's effectiveness in clinical and real-world applications. The success of IoT-ESDM highlights its potential as a powerful tool for emotion-aware AI interventions, paving the way for future advancements in mental health monitoring and personalized healthcare solutions.

Item Type:	Article
Uncontrolled Keywords:	Emotional State Detection, Internet of Things, Image Processing, Data Analytics
Subjects:	Q Science > QA Mathematics > QA801-939 Analytic mechanics
Divisions:	Faculty of Information Science and Technology (FIST)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	03 Mar 2026 02:00
Last Modified:	03 Mar 2026 02:00
URII:	http://shdl.mmu.edu.my/id/eprint/15417

Downloads

Edit (login required)