Ai-Powered Wearable Iot Devices for Mental Health Assessment, Stress Prediction and Personalised Health Care Recommendation Systems
Main Article Content
Abstract
The growing burden of psychological stress and the limitations of episodic self-reporting have increased interest in wearable Internet of Things (IoT) systems for continuous, context-aware mental well-being support. This paper proposes an AI-powered wearable IoT framework that combines physiological sensing, secure edge-to-cloud communication, personalised machine learning and recommendation logic to support stress assessment and early identification of elevated stress patterns. The framework integrates photoplethysmography-derived heart rate and heart-rate variability, electrodermal activity, skin temperature, motion and sleep-related indicators. A personal-baseline mechanism is incorporated to reduce reliance on population-level thresholds, while contextual filtering is used to distinguish physiological arousal associated with physical activity from patterns potentially associated with psychological stress. A synthetic evaluation scenario is presented to demonstrate the proposed reporting and comparison methodology. The results compare logistic regression, support vector machine, random forest and a multimodal personalised model using discrimination, sensitivity, specificity and calibration metrics. These values are simulated for methodological demonstration and are not measurements from participants or a deployed device. The paper further discusses recommendation safety, privacy, fairness, usability and the distinction between wellness support and clinical diagnosis. The proposed system is intended as an assistive monitoring framework, not a substitute for validated mental-health assessment or professional care.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
References
A. Pinge, V. Gad, D. Jaisighani, S. Ghosh, and S. Sen, “Detection and monitoring of stress using wearables: A systematic review,” Frontiers in Computer Science, vol. 6, Art. no. 1478851, 2024, doi:
10.3389/fcomp.2024.1478851.
M. Bolpagni, S. Pardini, M. Dianti, and S. Gabrielli, “Personalized stress detection using biosignals from wearables: A scoping review,” Sensors, vol. 24, no. 10, Art. no. 3221, 2024, doi: 10.3390/s24103221.
Fusing wearable biosensors with artificial intelligence for mental health monitoring: A systematic review,” Biosensors, vol. 15, no. 4, Art. no. 202, 2025, doi: 10.3390/bios15040202.
O. Pataca, E. Zdravevski, P. J. Coelho, N. M. Garcia, M. Deruyck, C. Albuquerque, and I. M. Pires, “Use of machine learning for predicting stress episodes based on wearable sensor data: A systematic review,” Computers in Biology and Medicine, vol. 198, Art. no. 111166, 2025, doi:
10.1016/j.compbiomed.2025.111166.
Wearable devices for anxiety assessment: A systematic review,” Communications Medicine, 2025, doi:
10.1038/s43856-025-01234-6.
Machine learning and deep learning techniques to detect mental stress using various physiological signals: A critical insight,” WIREs Data Mining and Knowledge Discovery, vol. 15, no. 3, Art. no. e70035, 2025, doi: 10.1002/widm.70035.
Task Force of the European Society of Cardiology and the North American Society of Pacing and Electrophysiology, “Heart rate variability: Standards of measurement, physiological interpretation and clinical use,” Circulation, vol. 93, no. 5, pp. 1043–1065, 1996.
World Health Organization, Ethics and Governance of Artificial Intelligence for Health: WHO Guidance. Geneva, Switzerland: WHO, 2021.
J. Kumar, “Changing paradigm of employee relations in India after independence,” South Asian Journal of Human Resources Management, vol. 10, no. 1, 2023. doi: 10.1177/26314541221134853.
A. Venkataraman, “Employment relations past, present and future: Demise or resurrection in India?” South Asian Journal of Human Resources Management, vol. 10, no. 1, 2023. doi: 10.1177/26314541221134861.
Rosy, C. P., Indhumathi, R., Lalli, S., & Kanimozhi, R. (2026). Real-time eye movement detection for vision-based interfaces. In Recent advancements in computational intelligence: Concepts, methodologies and applications (Part 2, pp. 268–279). Bentham Science Publishers.
Subashini, D., Vairavan, S., P., P., Bostani, A., K., S. J., Naveenkumar, R., & Edpuganti, S. K. (2026). Deep learning–based prediction and classification of minerals from soil images using computer vision techniques. International Journal of Artificial Intelligence and Machine Learning, 6(2s), 536–543.
https://doi.org/10.51483/IJAIML.6.2s.2026.536-543.
Idhumathi, R., Jeyalakshmi, S., Hemalatha, N., Shrivastava, A., & Alasady, H. (2025). Hybrid fuzzy neural systems for real time decision making in autonomous vehicles. Journal of Machine and Computing, 2544–2556.
Kirthika, B., Sudarmozhi, K., & Akanni, J. O. (2026). SHAP enabled knowledge distilled deep learning framework for explainable intrusion prevention in IoT wireless sensor networks. Discover Internet of Things.
Rehman A., Bin Saad, A. A., Kamaludin, S., Sudarmozhi, K., & Khan, D. (2025). Mathematical simulation for energy transfer in a couple stress ternary hybrid nanofluid flow passing through a 3D surface, considering the impact of MHD and viscous dissipation. Journal of Applied and Computational Mechanics, e19512.
Rehman A., Inc, M., & Sudarmozhi, K. (2026). New research on ternary hybrid nanofluid flow across a surface with the influence of thermal radiation using semi-numerical simulation. Open Engineering, 16(1), 20250157.
Rehman, A., Saad, A. A., Khan, D., Jan, R., & Sudarmozhi, K. (2026). Unsteady MHD mixed convection flow of hybrid nanofluid over a rotating sphere in a Darcy-Forchheimer with slip effects. International Journal of Mechanics and Materials in Design, 22(3), 167.
Rehman, A., Saad, A. A., Inc, M., Abas, S. S. B., Jawo, E., & Sudarmozhi, K. (2026). Semi-numerical simulation for the thermal performance of unsteady squeezing non-Newtonian MHD couple stress ternary hybrid nanofluid flow between parallel surfaces. International Journal of Thermofluids, 31, 101516.
Koneti, Chaitanya, Rajiv Aserkar, and Vanita Bhoola. "AI-Based Predictive Analytics for Demand Forecasting and Inventory Efficiency." Advances in Consumer Research 3.1 (2026). https://acr-journal.com/article/ai-based-predictive-analytics-for-demand-forecasting-and-inventory-efficiency-2425/
Koneti, Chaitanya, A. Seetharaman, and K. Maddulety. "Understanding the supply chain efficiency in e-commerce using the blockchain technology." Library of Progress-Library Science, Information Technology & Computer 44.3 (2024): 3147.https://doi.org/10.48165/bapas.2024.44.2.1
Koneti, Chaitanya, A. Seetharaman, and K. Maddulety. "Understanding the supply chain efficiency in e-commerce using the blockchain technology." Library of Progress-Library Science, Information Technology & Computer 44.3 (2024): 3147.https://doi.org/10.48165/bapas.2024.44.2.1
Koneti, Chaitanya, A. Seetharaman, and K. Maddulety. "Evaluating the effectiveness of influencer marketing in niche markets." Journal of Marketing & Social Research 2 (2025): 65-79. https://jmsr-online.com/article/evaluating-the-effectiveness-of-influencer-marketing-in-niche-markets-247/
Koneti, C., Pingat, S. P., Santos, C. P., Alos, L. G., Parida, P., & Fernández-Rodríguez, J. C. (2025). From engagement to retention: The power of gamification in digital marketing. Journal of Information Systems Engineering & Management, 10(4), 25-35.https://doi.org/10.52783/jisem.v10i4.8382
Neha Sharma, Mukesh Soni, Sumit Kumar, Rajeev Kumar, Anurag Shrivastava, Supervised Machine Learning Method for Ontology-based Financial Decisions in the Stock Market, ACM Transactions on Asian and Low-Resource Language InformationProcessing, Volume 22, Issue 5, Article No.: 139, Pages 1 – 24, https://doi.org/10.1145/3554733
Rathinavelu, G. (2023). Federated Learning and Privacy-Preserving AI for Cross-Institutional Financial Fraud Detection. Journal of Computational Analysis and Applications (JoCAAA), 31(4), 3239–3263.
Rathinavelu, G. (2024). Continual Learning Systems for Adaptive Fraud-Pattern Detection in High-Velocity Transaction Streams. Journal of Computational Analysis and Applications (JoCAAA), 33(4), 1239–1264.
Rathinavelu, G. (2025). Early-Stage Consumer Credit Risk Detection Using Multimodal Deep Learning and Behavioral AI. International Journal of Computer Information Systems and Industrial Management Applications, 17, 1–27.
Rathinavelu, G. (2026). Real-Time Cross-Border Anti-Money Laundering (AML) Detection Using Graph Neural Networks and Machine Learning. International Journal of Computer Information Systems and Industrial Management Applications, 18(5s), 1217–1242.
P. William, A. Shrivastava, U. S. Asmal, M. Gupta, and A. K. Rosa, "Framework for Implementation of Android Automation Tool in Agro Business Sector," 4th International Conference on Intelligent Engineering and Management (ICIEM), 2023.
H. Douman, M. Soni, L. Kumar, N. Deb, and A. Shrivastava, "Supervised Machine Learning Method for Ontology-based Financial Decisions in the Stock Market," ACM Transactions on Asian and Low Resource Language Information Processing, vol. 22, no. 5, p. 139, 2023.
A. V. A. B. Ahmad, D. K. Kurmu, A. Khullia, S. Purafis, and A. Shrivastova, "Framework for Cloud Based Document Management System with Institutional Schema of Database," International Journal of Intelligent Systems and Applications in Engineering, vol. 12, no. 3, pp. 692–678, 2024.