Keywords:-
Article Content:-
Abstract
Stress is a leading cause of declining mental health and reduced productivity in modern life. Wearable sensors and smart devices generate massive streams of physiological, behavioral, and contextual data, offering opportunities for real-time stress detection. However, existing machine learning (ML) systems face limitations in explain ability, adaptability, and handling heterogeneous data sources. This paper proposes a Composite AI framework that integrates machine learning, knowledge-based reasoning, and graph-based data structures for personalized stress detection and management. The system leverages deep learning models for physiological pattern recognition, a knowledge graph for contextual reasoning, and a rule-based engine for adaptive recommendations. Experimental results on benchmark stress datasets demonstrate improved prediction accuracy, interpretability, and personalized adaptability compared to conventional ML approaches. The proposed architecture provides a pathway for building human-centric, explainable, and intelligent stress management systems.
References:-
References
2. Kaholokula JK, Look M, Mabellos T, Zhang G, de Silva M, Yoshimura S, et al. Cultural dance program improves hypertension management for Native Hawaiians and Pacific Islanders: a pilot randomized trial. J Racial Ethn Health Disparities. 2017;4(1):35-46. [FREE Full text] [CrossRef] [Medline]
3. Mohamad Jawad, H.; Bin Hassan, Z.; Zaidan, B.; Mohammed Jawad, F.; Mohamed Jawad, D.; Alredany, W. A Systematic Literature Review of Enabling IoT in Healthcare: Motivations, Challenges, and Recommendations. Electronics 2022, 11, 3223. [Google Scholar] [CrossRef]
4. Mattioli, V.; Davoli, L.; Belli, L.; Gambetta, S.; Carnevali, L.; Sgoifo, A.; Raheli, R.; Ferrari, G. IoT-Based Assessment of a Driver’s Stress Level. Sensors 2024, 24, 5479. [Google Scholar] [CrossRef] [PubMed]
5. Muñoz Arteaga, J.; Hernádez, Y. Temas de Diseño En Interacción Humano-Computadora; Iniciativa Latinoamericana de Libros de Texto Abiertos (LATIn): São Paulo, Brazil, 2014. [Google Scholar]
6. Hindu, A.; Bhowmik, B. An IoT-Enabled Stress Detection Scheme Using Facial Expression. In Proceedings of the 2022 IEEE 19th India Council International Conference (INDICON), Kerala, India, 24–26 November 2022; pp. 1–6. [Google Scholar]
7. Vinod H. Patil, Sheela Hundekari, Anurag Shrivastava, Design and Implementation of an IoT-Based Smart Grid Monitoring System for Real-Time Energy Management, Vol. 11 No. 1 (2025): IJCESEN. https://doi.org/10.22399/ijcesen.854
8. Disease GBD, Injury I, Prevalence C. Global, regional, and national incidence, prevalence, and years lived with disability for 354 diseases and injuries for 195 countries and territories, 1990–2017: a systematic analysis for the Global Burden of Disease Study 2017. Lancet. 2018;392(10159):1789–858.
9. Obermeyer Z, Emanuel EJ. Predicting the future—big data, machine learning, and clinical medicine. N Engl J Med. 2016;375(13):1216–9.
10. Al-Badarneh, M.B.; Shatnawi, H.S.; Alananzeh, O.A.; Al-Mkhadmehd, A.A. Job Performance Management: The Burnout Inventory Model and Intention to Quit their Job among Hospitality Employees. Int. J. Innov. Creat. Chang. 2019, 5, 1355–1375. [Google Scholar]
11. Schmidt et al., WESAD: A Multimodal Dataset for Wearable Stress and Affect Detection, IEEE T-Affective Computing, 2018.
12. Aggarwal, Data Streams: Models and Algorithms, Springer, 2007.
13. Russell & Norvig, Artificial Intelligence: A Modern Approach, Pearson, 2020.