|
Vol.14, No.3, August 2025. ISSN: 2217-8309 eISSN: 2217-8333
TEM Journal
TECHNOLOGY, EDUCATION, MANAGEMENT, INFORMATICS Association for Information Communication Technology Education and Science |
Automatic Microsleep Detection Approach for Car Drivers Using YOLO5 Based on Image Feature
Lilik Anifah, Nurhayati Nurhayati, Haryanto Haryanto, Muhamad Syariffuddien Zuhrie
© 2025 Lilik Anifah, published by UIKTEN. This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License. (CC BY-NC-ND 4.0)
Citation Information: TEM Journal. Volume 14, Issue 3, Pages 1984-1991, ISSN 2217-8309, DOI: 10.18421/TEM143-07, August 2025.
Received: 23 October 2024. Revised: 12 March 2025.
Abstract:
Microsleep is a condition that indicates a transition from drowsiness to sleep characterized by temporary eye closure, a condition where if there is stimulation from outside the body can not respond properly, and is sometimes or often characterized by head nodding. The problem formulation in this research is how to identify car drivers' microsleep using artificial intelligence. This research purpose is to propose a microsleep identification system for car drivers using artificial intelligence. The originality of this research is trying to apply facial data of car drivers, based on this data it is then identified whether the driver is in microsleep or not using You Only Live Once 5 (YOLO5). The method used is artificial intelligence. This research stage includes taking microsleep data, dividing learning data and testing data, learning process, testing process, and performance analysis. It can be concluded that by using YOLO5 the system can identify whether the car driver is in microsleep.
Keywords – Microsleep, detection, YOLO5, image, feature. |
|
----------------------------------------------------------------------------------------------------------- ----------------------------------------------------------------------------------------------------------- |