PosePal: An AI-Powered Human Posture Tracking and Real-Time Alert System
Article Sidebar
Main Article Content
Musculoskeletal discomfort caused by prolonged sitting and unmonitored poor posture habits has become a serious occupational health concern among university employees. Without any real-time corrective mechanism, postural deviations accumulate silently into chronic back pain, neck strain, and shoulder tension — conditions widely reported among faculty and staff at Pangasinan State University – Alaminos City Campus (PSU-ACC). Survey results further confirmed that 95% of employees experience posture-related discomfort, yet none had previously used a posture monitoring device, and 55% had no specific method to manage their sitting habits. This study developed PosePal: An AI-Powered Human Posture Tracking and Real-Time Alert System to address these persistent ergonomic challenges in an academic workplace setting. The system was built using Python, Dart, and JavaScript, integrating YOLOv11-Pose for real-time human detection and key point-based posture estimation, supported by Firebase as the cloud database. IP cameras serve as the primary input devices, continuously capturing body alignment for AI-based analysis without requiring any wearable equipment. To enhance accuracy, the system integrates multi-object tracking, face recognition, and a rule-based posture classifier with temporal validation. PosePal automatically detects improper sitting positions and instantly alerts users to correct their posture, while providing posture scoring, analytics reports, personalized recommendations, face recognition for secure identification, and an admin dashboard for institutional monitoring and management. The system was developed following Agile methodology and evaluated by 21 respondents comprising faculty, non-teaching staff, and an IT expert. Assessed against ISO/IEC 25010 quality standards, PosePal achieved an overall weighted mean of 4.19 (Excellent), confirming its effectiveness, reliability, and usability in promoting posture awareness and improving workplace wellness. The study concludes with recommendations to refine posture detection and alert mechanisms, continuously evaluate system accuracy and user satisfaction, and conduct further studies to expand system features and ensure PosePal remains adaptive and reliable across diverse real-world settings.
Downloads
References
Abdul Rahim, A. R. A., Zahari, Z., Zainuddin, N. Z., & Nordin, N. A. M. (2022). Risk factors and prevalence of musculoskeletal disorders among teachers and school staff: A review. International Journal of Academic Research in Business and Social Sciences, 12(1), 1612–1624. https://doi.org/10.6007/IJARBSS/v12-i1/12190
Bassino-Riglos, F., Mosqueira-Chacon, C., & Ugarte, W. (2023). AutoPose: Pose estimation for prevention of musculoskeletal disorders using LSTM. Springer, Cham, 223–238. https://link.springer.com/chapter/10.1007/978-3-031-49339-3_14
Cheriyan, S., Sakthivel, S., Regula, T., Kumar, K., & Al Riyami, S. (2025). Smart posture monitoring and predictive health classification for bedridden patients using IoT and AI. IEEE Xplore, 1–5. https://ieeexplore.ieee.org/abstract/document/10845586
Kumar, S. S., Madesh, S., Nikitha, B., & Maheshwari, R. (2025). Intelligent posture monitoring system with real-time notifications using MediaPipe and OpenCV. Springer Nature Link, 145–155.
Mahomed, A. S., & Saha, A. K. (2024). Driver posture recognition: A review. IEEE Xplore, 176301–176345. https://ieeexplore.ieee.org/abstract/document/10750806
Ota, M., Tateuchi, H., Hashiguchi, T., Kato, T., Ogino, Y., Yamagata, M., & Ichihashi, N. (2020). Verification of reliability and validity of motion analysis systems during bilateral squat using human pose tracking algorithm. Gait & Posture, 80, 62–67. https://doi.org/10.1016/j.gaitpost.2020.05.027
Pistolesi, F., Baldassini, M., & Lazzerini, B. (2024). A human-centric system combining smartwatch and LiDAR data to assess the risk of musculoskeletal disorders and improve ergonomics of Industry 5.0 manufacturing workers. Computers in Industry. https://www.sciencedirect.com/science/article/abs/pii/S0166361523001926
Sharma, R., & Rawat, N. (2023). Posture: Its significance in human health. Journal of Health and Allied Sciences NU, 13(1), 48–52. https://doi.org/10.1055/s-0043-1766103
Sreevani, V., Reddy, B. S., Nithin, K., Vardhan, K. H., Mohammed, K. A., Reddy, U., Lakhanpal, S., & Kalra, R. (2024). Advanced interdisciplinary approaches for bad posture detection using computer vision and IoT. E3S Web of Conferences, 507, 01045. https://doi.org/10.1051/e3sconf/202450701045
Szczygiel, E., Fudacz, N., Golec, J., & Golec, E. (2020). The impact of the position of the head on the functioning of the human body: A systematic review. International Journal of Occupational Medicine and Environmental Health, 33(5), 559–568. https://doi.org/10.13075/ijomeh.1896.01550
Tsantili, A. R., Chrysikos, D., & Troupis, T. (2022). Text Neck Syndrome: Disentangling a new epidemic. Acta Medica Academica, 51(2), 123–127. https://doi.org/10.5644/ama2006-124.380
Wang, M., & Deng, W. (2021). Deep face recognition: A survey. Neurocomputing, 429, 215–244. https://doi.org/10.1016/j.neucom.2020.10.081
Zaharuddin, M. S. H., & Shah, S. M. (2025). A smart chair for sitting postures monitoring and seat occupancy detection. Journal of Electronic Voltage and Application. https://penerbit.uthm.edu.my/ojs/index.php/jeva/article/view/18203
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in our journal are licensed under CC-BY 4.0, which permits authors to retain copyright of their work. This license allows for unrestricted use, sharing, and reproduction of the articles, provided that proper credit is given to the original authors and the source.