Abstract :

Drowsiness While Performing Attention-critical Activities Such As Driving, Operating Machinery, Or Monitoring Systems Is A Major Cause Of Accidents And Productivity Loss Worldwide. With The Rapid Growth Of Intelligent Vision Systems, Deep Learning Has Emerged As A Powerful Tool For Detecting Human Fatigue And Reduced Alertness In Real Time. This Research Presents An Attention Deep Learning Framework Based Drowsiness Detection Model That Leverages Convolutional Neural Networks (CNNs) Integrated With Attention Mechanisms To Accurately Identify Drowsy States From Visual And Behavioral Cues. The Proposed Framework Focuses On Automatically Learning Discriminative Facial Features Such As Eye Closure, Blink Duration, Yawning Frequency, And Head Posture From Image Or Video Streams. By Incorporating An Attention Layer, The Model Selectively Emphasizes The Most Relevant Facial Regions And Temporal Patterns Associated With Drowsiness, Improving Robustness Under Varying Lighting Conditions, Facial Expressions, And Individual Differences. The System Is Designed To Operate In Real Time With Minimal Computational Overhead, Making It Suitable For Deployment In Embedded And Mobile Platforms. Experimental Evaluations Demonstrate That The Attention-enhanced CNN Significantly Outperforms Traditional Machine Learning And Plain CNN Models In Terms Of Accuracy, Precision, Recall, And Stability. This Work Contributes A Scalable And Intelligent Solution For Early Drowsiness Detection, Aiming To Reduce Accidents And Enhance Safety In Real-world Applications.

Published:

02-9-2026

Issue:

Vol. 26 No. 9 (2026)

Page Nos:

1-5

Section:

Articles

License:

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

How to Cite