A SOLAR-POWERED CONTEXT-AWARE WEARABLE IOT SYSTEM FOR REAL-TIME MICROSLEEP DETECTION
DOI:
https://doi.org/10.35631/IJIREV.825034Keywords:
Context-Aware Systems, Drowsiness Detection, Microsleep Detection, Sensor Fusion, Solar Energy Harvesting, Wearable IotAbstract
Microsleep episodes, characterised by brief involuntary lapses in consciousness, pose significant risks in safety-critical activities such as driving and industrial operations. Existing microsleep detection systems primarily rely on camera-based vision techniques or electroencephalography (EEG), which often require computationally intensive processing, continuous and unobstructed visual monitoring, or cumbersome electrode placement, thereby limiting their practicality for continuous, long-term wearable applications. This study proposes a solar-powered, context-aware wearable microsleep detection system that integrates lightweight sensor fusion and IoT connectivity for real-time monitoring and multimodal alerting. The proposed system combines infrared-based eye-closure detection, accelerometer-based head-motion analysis, and ambient-light sensing through a brightness-adaptive decision algorithm executed on an ESP32 microcontroller. Sensor data are processed locally to trigger visual, auditory, and vibration alerts and transmit notifications to the Blynk IoT platform. The prototype was evaluated through 40 controlled experimental trials involving predetermined combinations of eye-closure and head-nodding movements performed by one researcher, comprising 20 trials under bright lighting and 20 trials under dark lighting. The system correctly classified 38 of the 40 trials, achieving an overall detection accuracy of 95% and an average response time of 1.68 seconds. The adaptive decision algorithm achieved an overall sensitivity of 95% and specificity of 95%, with no false positives under bright lighting conditions and no false negatives under dark lighting conditions. These findings demonstrate the feasibility of combining context-aware, on-device sensor fusion, real-time IoT alerting, and solar energy harvesting within a wearable microsleep detection prototype.
Downloads
References
Aditya Madane, Alok Singh, Shubham Fargade, & Atrey Dongare. (2025). Real-Time Driver Drowsiness Detection Using Deep Learning and Computer Vision Techniques. International Journal of Scientific Research in Science, Engineering and Technology, 12(3), 222–229. https://doi.org/10.32628/ijsrset2512335
AlArnaout, Z., Zaki, C., Kotb, Y., AlAkkoumi, M., & Mostafa, N. (2025). Exploiting heart rate variability for driver drowsiness detection using wearable sensors and machine learning. Scientific Reports, 15(1). https://doi.org/10.1038/s41598-025-08582-2
Albadawi, Y., Takruri, M., & Awad, M. (2022). A Review of Recent Developments in Driver Drowsiness Detection Systems. In Sensors (Vol. 22, Issue 5). MDPI. https://doi.org/10.3390/s22052069
Biswal, A. K., Singh, D., Pattanayak, B. K., Samanta, D., & Yang, M.-H. (2021). IoT‐Based Smart Alert System for Drowsy Driver Detection. Wireless Communications and Mobile Computing, 2021(1). https://doi.org/10.1155/2021/6627217
Essel, E., Lacy, F., Albalooshi, F., Elmedany, W., & Ismail, Y. (2025). Drowsiness Detection in Drivers Using Facial Feature Analysis. Applied Sciences (Switzerland), 15(1). https://doi.org/10.3390/app15010020
Fu, B., Boutros, F., Lin, C.-T., & Damer, N. (2024). A Survey on Drowsiness Detection: Modern Applications and Methods. IEEE Transactions on Intelligent Vehicles, 9(11), 7279–7300. https://doi.org/10.1109/TIV.2024.3395889
Fujiwara, K., Iwamoto, H., Hori, K., & Kano, M. (2024). Driver Drowsiness Detection Using R-R Interval of Electrocardiogram and Self-Attention Autoencoder. IEEE Transactions on Intelligent Vehicles, 9(1), 2956–2965. https://doi.org/10.1109/TIV.2023.3308575
G Sudha Rani, A. A. A. Y. I. S. R. , C. G. K. C. (2024). Stay Alert: Drowsiness Detection with IoT Technology. International Journal for Modern Trends in Science and Technology, 10(02), 46–52. https://doi.org/10.46501/IJMTST1002007
Hasan, M. M., Hossain, M. M., Sulaiman, N., & Khandaker, S. (2024). Microsleep Predicting Comparison Between LSTM and ANN Based on the Analysis of Time Series EEG Signal. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 16(1), 25–31. https://doi.org/10.54554/jtec.2024.16.01.004
Helmy Ilhamsyah, M., Citra Budi, S., & Prihaswan, I. (2025). MICROSLEEP AND OCCUPATIONAL SAFETY: INTEGRATION OF BIOMETRIC DETECTION, WEARABLE TECHNOLOGY, AND PREVENTIVE POLICIES FOR THE MODERN INDUSTRY. 22(2), 213–218. https://doi.org/10.31964/jkl.v21i2.1035
Lamaazi, H., Alqassab, A., Fadul, R. A., & Mizouni, R. (2023). Smart Edge-Based Driver Drowsiness Detection in Mobile Crowdsourcing. IEEE Access, 11, 21863–21872. https://doi.org/10.1109/ACCESS.2023.3250834
Minhas, R., Peker, N. Y., Hakkoz, M. A., Arbatli, S., Celik, Y., Erdem, C. E., Peker, Y., & Semiz, B. (2025). Improved drowsiness detection in drivers through optimum pairing of EEG features using an optimal EEG channel comparable to a multichannel EEG system. Medical and Biological Engineering and Computing, 63(10), 3019–3036. https://doi.org/10.1007/s11517-025-03375-1
Nurul’aini, A. R., Aprilianto, R. A., & Pribadi, F. S. (2025). Comparative Analysis of Hybrid Intelligent Algorithms for Microsleep Detection and Prevention. Jurnal Teknik Informatika (JUTIF), 6(3). https://doi.org/10.52436/1.jutif.2025.6.3.3540
Perkins, E., Sitaula, C., Burke, M., & Marzbanrad, F. (2023). Challenges of Driver Drowsiness Prediction: The Remaining Steps to Implementation. IEEE Transactions on Intelligent Vehicles, 8(2), 1319–1338. https://doi.org/10.1109/TIV.2022.3224690
Pham, N., Dinh, T., Kim, T., Raghebi, Z., Bui, N., Truong, H., Nguyen, T., Banaei-Kashani, F., Halbower, A., Dinh, T., Nguyen, P., & Vu, T. (2023). Detection of Microsleep Events With a Behind-the-Ear Wearable System. IEEE Transactions on Mobile Computing, 22(2), 841–857. https://doi.org/10.1109/TMC.2021.3090829
Rusli, M. M., Khairul Adilah Ahmad, Ahmadrofi, A. A., Jayadi, P., & Mat Din, M. (2025). Driver Drowsiness Detection using Transfer Learning and Computer Vision. Journal of Advanced Research in Applied Mechanics, 137(1), 176–190. https://doi.org/10.37934/aram.137.1.176190
Saleem, A. A., Siddiqui, H. U. R., Raza, M. A., Rustam, F., Dudley, S., & Ashraf, I. (2023). A systematic review of physiological signals based driver drowsiness detection systems. Cognitive Neurodynamics, 17(5), 1229–1259. https://doi.org/10.1007/s11571-022-09898-9
Shah, J., Chougule, A., Chamola, V., & Hussain, A. (2023). Novel welch-transform based enhanced spectro-temporal analysis for cognitive microsleep detection using a single electrode EEG. Neurocomputing, 549. https://doi.org/10.1016/j.neucom.2023.126387
Shankara Chari, G. S., & Prashant, J. A. (2024). Scaling effectivity in manifold methodologies to detect driver’s fatigueness and drowsiness state. IAES International Journal of Artificial Intelligence (IJ-AI), 13(2), 1227. https://doi.org/10.11591/ijai.v13.i2.pp1227-1240
