<![CDATA[This study presents a systematic literature review (SLR) on the application of Convolutional Neural Networks (CNNs) for vision-based driver drowsiness detection. A total of 23 peer-reviewed studies published between 2021 and 2025 were analyzed using the PICOC framework and PRISMA 2020 guidelines. The review aims to identify trends in model architectures, datasets, preprocessing strategies, and performance outcomes. The findings show that transfer learning models, such as MobileNetV2, ResNet, and InceptionV3, along with hybrid architectures like CNN–LSTM, dominate recent research, achieving accuracies predominantly above 90%. However, performance varies significantly depending on dataset characteristics and experimental conditions. Key challenges include sensitivity to low-light environments, occlusion (e.g., glasses), and head pose variations. In addition, most studies rely on controlled datasets, limiting real-world applicability and generalization. Emerging trends emphasize lightweight architectures, temporal modeling, and efficiency-oriented optimization for real-time deployment. This review highlights the need for cross-dataset evaluation, more diverse and representative data, and robust model design to ensure reliable performance in real-world driving scenarios.]]>
Copyrights © 2026
