Abstract :

Driver Drowsiness Is One Of The Major Causes Of Road Accidents Worldwide, Leading To Significant Loss Of Life, Injuries, And Property Damage. Detecting Driver Fatigue At An Early Stage Is Essential For Improving Road Safety And Preventing Accidents Caused By Reduced Alertness. Traditional Drowsiness Detection Methods Often Rely On Physiological Sensors Or Manual Monitoring, Which May Be Intrusive, Expensive, Or Inconvenient For Real-world Deployment. This Paper Presents A Driver Drowsiness Detection System Based On Convolutional Neural Network (CNN) Architecture Optimization Using A Genetic Algorithm (GA). The Proposed Framework Utilizes Facial Images Captured Through An Invehicle Camera To Monitor Driver Behavior And Identify Signs Of Drowsiness, Such As Eye Closure, Blinking Frequency, And Yawning. A CNN Model Is Employed For Feature Extraction And Classification, While A Genetic Algorithm Is Used To Optimize Network Architecture Parameters, Including The Number Of Layers, Filter Sizes, And Learning Configurations. The Optimization Process Enhances Detection Accuracy And Computational Efficiency. Experimental Analysis Demonstrates That The Proposed CNN-GA Framework Achieves High Accuracy In Detecting Driver Drowsiness And Provides Real-time Monitoring Capabilities. The Developed System Offers An Intelligent, Non-intrusive, And Reliable Solution For Enhancing Road Safety And Reducing Fatigue-related Traffic Accidents.

Published:

26-9-2026

Issue:

Vol. 26 No. 9 (2026)

Page Nos:

421-424

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite