Abstract
Driver drowsiness is a major contributor to road accidents, often resulting from delayed reaction times and impaired cognitive performance. This study introduces EffRes-DrowsyNet, a hybrid deep learning model that integrates the architectural efficiencies of EfficientNetB0 with the deep representational capabilities of ResNet50. The model is designed to detect early signs of driver fatigue through advanced video-based analytics by leveraging both computational scalability and deep feature learning. Extensive experiments were conducted on three benchmark datasets-SUST-DDD, YawDD, and NTHU-DDD-to validate the model's performance across a range of environmental and demographic variations. EffRes-DrowsyNet achieved 97.71% accuracy, 98.07% precision, and 97.33% recall on the SUST-DDD dataset. On the YawDD dataset, it sustained a high accuracy of 92.73%, while on the NTHU-DDD dataset, it reached 95.14% accuracy, 94.09% precision, and 95.39% recall. These results affirm the model's superior generalization and classification performance in both controlled and real-world-like settings. The findings underscore the effectiveness of hybrid deep learning models in real-time, safety-critical applications, particularly for automotive driver monitoring systems. Furthermore, EffRes-DrowsyNet's architecture provides a scalable and adaptable solution that could extend to other attention-critical domains such as industrial machinery operation, aviation, and public safety systems.