Real- Time Driver Emotion Recognition Using CNN-LSTM for Enhanced Road Safety and Accident Prevention

Road safety remains a critical global concern, with driver emotions such as drowsiness, stress, and anger significantly contributing to road accidents. Real-time driver emotion recognition can play a crucial role in accident prevention by identifying risky emotional states and triggering timely interventions. This study proposes a CNN-LSTM-based driver emotion recognition system that integrates Convolutional Neural Networks (CNN) for spatial feature extraction and Long Short-Term Memory (LSTM) networks for temporal sequence learning. The model is trained on a combination of two dataset, ensuring comprehensive emotion classification. The experimental results demonstrate an impressive 98.6% accuracy in classifying five key driver emotional states, Drowsy, Alert, Stressed, Angry, and Neutral. Additionally, real-time testing shows that the system efficiently detects emotions with minimal latency, making it highly suitable for in-vehicle deployment. The proposed model enhances road safety by providing real-time alerts to drivers when dangerous emotions are detected. This research contributes to the field of intelligent driver monitoring systems by offering a robust, real-time, and highly accurate emotion recognition framework that can be integrated with ADAS (Advanced Driver Assistance Systems) for enhanced accident prevention.