Citation

Jian, Jordan Chew Ding and Yogarayan, Sumendra and Ganesan, Thinesh (2025) Fatigue Detection Using Machine Learning Approach. In: 6th International Conference on Advanced Information Technologies, ICAIT 2025, 3 November 2025, Yangon.

Text 88.pdf - Published Version Restricted to Repository staff only Download (3MB)

Abstract

Facial expressions are one of the reliable indicators of a person’s physiological state. For drivers, behavioral cues such as lip yawning, eyelid closure, and head movement patterns provide signals of fatigue, which is a leading cause of road accidents worldwide. Fatigue-related crashes often result in severe injuries and fatalities, making early detection an urgent research priority. This study investigates the application of machine learning for real-time driver fatigue detection, where a system that could be practical for everyday use. The Driver Fatigue Dataset (DFD) was utilised, consisting of two categories: “Drowsy” and “Non-Drowsy.” Each category contains 9,200 labeled images, totaling 18,400 images. These were used to train and test machine learning models, enabling the system to differentiate between fatigued and normal states. Data preprocessing and feature extraction were applied to improve recognition of facial cues, while classification models were optimized to achieve prediction accuracy. The experimental results demonstrated that the system achieved performance with precise differentiation between drowsy and non-drowsy states, showing potential for real-world deployment. By reliably identifying signs of fatigue, the proposed system can serve as an assistive safety tool, alerting drivers before their drowsiness leads to impaired driving. The findings contribute to the broader goal of reducing accident rates caused by fatigue and improving road safety standards, particularly in regions where driver exhaustion is a significant concern.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Driver fatigue detection, machine learning algorithm
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics
Divisions:	Faculty of Information Science and Technology (FIST)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	18 Mar 2026 08:05
Last Modified:	19 Mar 2026 01:10
URII:	http://shdl.mmu.edu.my/id/eprint/15574

Downloads

Edit (login required)