Design and implementation of a multimodal embedded system for visual fatigue detection in students based on ESP32-CAM and Edge Impulse
DOI:
https://doi.org/10.48082/espacios-a26v47n04i09Keywords:
digital eye fatigue, ESP32-CAMAbstract
Computer Vision Syndrome affects a high proportion of Peruvian university students. A low-cost multimodal embedded system (PEN 125) was designed, implemented, and validated to detect visual fatigue using an ESP32-CAM with TinyML inference (Edge Impulse) and BH1750, MPU6050, and INMP441 sensors. The eye classifier achieved 90.0% accuracy (F1-score: 0.900). End-to-end system functionality was verified through executable firmware and testing with three users.
References
Adi, P. D. P. (2022). Performance evaluation of ESP32 Camera face recognition for various projects. Internet of Things and Artificial Intelligence Journal, 2(1). https://doi.org/10.31763/iota.v2i1.512
Anbesu, E. W., & Lema, A. K. (2023). Prevalence of computer vision syndrome: A systematic review and meta-analysis. Scientific Reports, 13, 1801. https://doi.org/10.1038/s41598-023-28750-6
Beeson, D., Wolffsohn, J. S., Baigum, T., et al. (2024). Digital eye strain symptoms worsen during prolonged digital tasks. Computers in Human Behavior Reports, 16, 100489. https://doi.org/10.1016/j.chbr.2024.100489
Dewi, C., Chen, R.-C., Chang, C.-W., Wu, S.-H., Jiang, X., & Yu, H. (2022). Eye aspect ratio for real-time drowsiness detection to improve driver safety. Electronics, 11(19), 3183. https://doi.org/10.3390/electronics11193183
Estrada Araoz, E. G., Paricahua Peralta, J. N., Zuloaga Araoz, M. C., Gallegos Ramos, N. A., Paredes Valverde, Y., Quispe Herrera, R., & Velásquez Giersch, L. (2022). Prevalence of computer vision syndrome in Peruvian university students during the COVID-19 health emergency. Archivos Venezolanos de Farmacología y Terapéutica, 41(4), 264–270. https://doi.org/10.5281/zenodo.6945062
Gupta, K. C., Kaur, G., & Chaudhary, A. (2023). Drowsiness detection using ESP32CAM. En 2023 3rd Asian Conference on Innovation in Technology (ASIANCON). IEEE. https://doi.org/10.1109/ASIANCON58793.2023.10269977
Huyhua-Gutiérrez, S. C., Zeladita-Huaman, J. A., Díaz-Manchay, R. J., Dominguez-Palacios, A. B., Zegarra-Chapoñan, R., Rivas-Souza, M. A., & Tejada-Muñoz, S. (2023). Digital eye strain among Peruvian nursing students: Prevalence and associated factors. International Journal of Environmental Research and Public Health, 20(6), 5067. https://doi.org/10.3390/ijerph20065067
Kaur, K., Gurnani, B., Nayak, S., et al. (2022). Digital eye strain: A comprehensive review. Ophthalmology and Therapy, 11(5), 1655–1680. https://doi.org/10.1007/s40123-022-00540-9
Kraft, D., Hartmann, F., & Bieber, G. (2022). Camera-based blink detection using 3D-landmarks. En Proceedings IWOAR (pp. 1–7). https://doi.org/10.1145/3558884.3558890
Lapa, I., Ferreira, S., Mateus, C., Rocha, N., & Rodrigues, M. A. (2023). Real-time blink detection as an indicator of computer vision syndrome in real-life settings: An exploratory study. International Journal of Environmental Research and Public Health, 20(5), 4569. https://doi.org/10.3390/ijerph20054569
León-Figueroa, D. A., Barboza, J. J., et al. (2024). Prevalence of computer vision syndrome during the COVID-19 pandemic: A systematic review and meta-analysis. BMC Public Health, 24, 640. https://doi.org/10.1186/s12889-024-17636-5
Lindo-Cano, E. F., García-Monge, V. A., Castillo-Cadillo, K. J., Sánchez-Tirado, E. A., Távara, I. M., & Morales, J. (2022). Computer-digital vision syndrome among university students of Lima city. Open Public Health Journal, 15. https://doi.org/10.2174/18749445-v15-e2208104
Liu, M., Bian, S., Zhao, Z., Zhou, B., & Lukowicz, P. (2024). Energy-efficient, low-latency, and non-contact eye blink detection with capacitive sensing. Frontiers in Computer Science, 6. https://doi.org/10.3389/fcomp.2024.1394397
McKee, C., & Hedge, A. (2022). Ergonomic lighting considerations for the home office workplace. Work, 71(1), 1–9. https://doi.org/10.3233/WOR-210704
Nowroz, S. T., Saleh, N. M., Shakur, S., Banerjee, S., & Amsaad, F. (2025). A benchmark reference for ESP32-CAM module. arXiv:2505.24081. https://doi.org/10.48550/arXiv.2505.24081
Safarov, F., Akhmedov, F., Abdusalomov, A. B., Nasimov, R., & Cho, Y. I. (2023). Real-time deep learning-based drowsiness detection. Sensors, 23(14), 6459. https://doi.org/10.3390/s23146459
Sharmila, A. S., Jennifer, A., Vinodhini, R., & Sabarirajan, M. A. (2024). A review of eye blink detection methods using computer vision techniques for computer vision syndrome prevention. Frontiers in Computer Science, 6, Article 1394397. https://doi.org/10.3389/fcomp.2024.1394397
Witte, A., & Lins, C. (2023). A real-time eye tracking system for the detection of eye blinks. Studies in Health Technology and Informatics, 302, 843–847. https://doi.org/10.3233/SHTI230719
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Los autores conservan sus derechos de autor y ceden a la revista el derecho de primera publicación bajo la licencia Creative Commons Atribución-NoComercial 4.0 Internacional (CC BY-NC 4.0).
