Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{185773,
        author = {Chitrapu Aruna Sri and Mrs. R. Shweta Balkrishna},
        title = {Towards Transparent Multimodal Emotion and Drowsiness Detection: An Explainable AI Approach},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {5},
        pages = {2642-2646},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=185773},
        abstract = {This paper presents a multimodal emotion and drowsiness detection system designed to enhance driver safety in autonomous vehicles. The system combines facial emotion recognition, speech emotion analysis, and a drowsiness detection module, fusing their outputs to provide real-time alerts. Experimental results show that the facial model (CNN) achieves 90% accuracy, the speech module (BiLSTM) reaches 85%, the drowsiness model (CNN) yields 92%, and the multimodal fusion attains 93%. A prototype console interface demonstrates real-time operation and alerting. This integrated approach reduces false alarms and improves robustness under varying environmental conditions.},
        keywords = {multimodal fusion, emotion detection, drowsiness detection, CNN, BiLSTM, driver safety.},
        month = {October},
        }