International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | AI Based Student Health Support System |
|---|---|
| ABSTRACT | Student health, including physical fitness, mental well-being, and posture integrity, is a key factor in determining academic performance and overall life quality. Conventional health monitoring in educational institutions is challenged by subjective evaluation, manual data analysis, poor scalability, and the inability to offer personalized interventions. This paper proposes an AI-assisted Student Health Support System that leverages the synergy of diverse AI approaches to offer comprehensive, scalable, and personalized health support to students. The system comprises three primary modules: physical fitness analysis via BP neural networks and CNN-LSTM models that attain 98.45% classification accuracy for grade estimation; posture analysis via a Southeast Asia-fine-tuned pose estimation model that maintains mean absolute error below 2.3° for forward head angle estimation; and mental health risk estimation via multimodal smartphone sensing data that maintains balanced accuracies of 0.71-0.77 for depression, anxiety, eating disorders, and suicidal thoughts. A common dashboard offers real-time visualization, early warning signs, and personalized intervention strategies. Comparative analysis clearly indicates that AI-assisted solutions are substantially more accurate, efficient, and personalized compared to conventional solutions. The proposed system fills a significant gap in student health monitoring and provides a scalable solution for educational institutions to actively promote student well-being. |
| AUTHOR | S. VIMALA, DEEPAK S, ROSHAN KUMAR S, TAMIL SELVAN D Assistant Professor, Department of Artificial Intelligence and Data Science, Kongunadu College of Engineering and Technology, Trichy, India Department of Artificial Intelligence and Data Science, Kongunadu College of Engineering and Technology, Trichy, India |
| VOLUME | 182 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1403015 |
| pdf/15_AI Based Student Health Support System.pdf | |
| KEYWORDS | |
| References | [1]. B. Rahman and I. Sutedja, "AI based sagittal spinal posture assessment for adolescent screening in low resource school settings," Scientific Reports, 2026. doi: 10.1038/s41598-026-36634-8 [2]. "An AI-based algorithm for analyzing physical activity and health-related fitness in youth," Scientific Reports, vol. 16, p. 5105, 2026. doi: 10.1038/s41598-026-35514-5 [3]. S. Nyakhar and H. Wang, "Mental health AI chatbots tailored to college students: A systematic review," Frontiers in Psychiatry, 2026. [4]. "A Comparative Study of Traditional Machine Learning, Deep Learning, and Large Language Models for Mental Health Forecasting using Smartphone Sensing Data," arXiv preprint arXiv:2601.03603, 2026. [5]. "Using AI Chatbot to Assist Students' Behavior Management for Obesity Prevention in Middle Schools: Feasibility Study," Journal of Medical Internet Research, vol. 10, p. e83630, 2026. doi: 10.2196/83630 [6]. "Digital Phenotyping for Adolescent Mental Health: Feasibility Study Using Machine Learning to Predict Mental Health Risk From Active and Passive Smartphone Data," Journal of Medical Internet Research, vol. 28, 2026. doi: 10.2196/72501 [7]. Montgomery Public Schools, "AI-Powered Student Mentorship Pilot," Feb. 2026. [8]. "Optimization of academic performance and mental health in college students through an AI-driven personalized physical exercise and mindfulness intervention system," Scientific Reports, vol. 16, p. 6024, 2026. doi: 10.1038/s41598-026-37028-6 [9]. R. Lopez et al., "Student Mental Health Screening via Fitbit Data Collected During the COVID-19 Pandemic," arXiv preprint arXiv:2601.16324, 2026. [10]. "How AI Supports Student Mental Health in Higher Education," EdTech Magazine, Jan. 2026. [11]. World Health Organization, "Digital screen time and health in adolescents: Global policy brief," WHO, 2023. [12]. D. Sutanto, T. Mahendra, and L. Puspitasari, "Spine deformity trends in post-COVID school-aged children in Indonesia," Indonesian Journal of Orthopedics, vol. 11, no. 2, pp. 113–122, 2023. [13]. Y. Zhou and M. Patel, "Radiographic evidence of postural degeneration in early adolescents linked to device usage," Clinical Spine Journal, vol. 30, no. 6, pp. 455–461, 2021. [14]. H. J. Lee, J. W. Park, and S. H. Sohn, "Pediatric kyphosis progression linked to digital screen usage: A cohort study," Journal of Pediatric Orthopaedics, vol. 42, no. 1, pp. e21–e28, 2022. [15]. Kemenkes RI, "Kebijakan Nasional Kesehatan Digital 2024: Wellness dan Deteksi Dini," Kementerian Kesehatan Republik Indonesia, 2023. [16]. B. Rahman et al., "Optimizing Customer Satisfaction Through Sentiment Analysis: A BERT-Based Machine Learning Approach to Extract Insights," IEEE Access, vol. 12, pp. 151476–151489, 2024. [17]. T. Q. Nguyen, A. Wijaya, and R. Gunawan, "Anthropometric bias in deep learning pose estimation: A Southeast Asian case study," Pattern Recognition Letters, vol. 154, pp. 34–40, 2022. [18]. World Bank, "Education technology and school accessibility report," 2022. [19]. B. L. Tan and S. M. Lee, "Smartphone-based scoliosis screening using machine learning: A field deployment in Malaysian schools," IEEE Journal of Biomedical and Health Informatics, vol. 28, no. 4, pp. 1234–1242, 2024. [20]. N. Gupta and A. L. Rodriguez, "Cost-effectiveness of AI in rural health screening: a case study in Indonesia," Health Economics Review, vol. 15, no. 1, p. 15, 2025. |
