Explainable AI in emotion and drowsiness detection for ADAS
DOI:
https://doi.org/10.17979/ja-cea.2025.46.12074Keywords:
Machine Learning, Fuzzy and neural systems relevant to control and identification, Decision-making support, Intelligent driver aids, Perception and sensingAbstract
Advanced Driver Assistance Systems (ADAS) are crucial for enhancing road safety. This work explores the application of Explainable Artificial Intelligence (XAI) to analyze and compare the behavior of deep learning models, specifically Convolutional Neural Networks (CNN), in detecting driver emotions and drowsiness states. Using XAI techniques, the decision-making processes of the models are investigated, offering transparency and interpretability. Findings on how models identify relevant facial features for each task and the inherent differences between emotion and drowsiness detection are discussed. Finally, the implications of these findings for the development and trust in future ADAS are analyzed, highlighting XAI’s potential to refine these systems and reduce the number of traffic accidents.
References
Ghoddoosian, R., Galib, M., Athitsos, V., 2019. A realistic dataset and baseline temporal model for early drowsiness detection.
Goodfellow, I. J., Erhan, D., Carrier, P. L., Courville, A., Mirza, M., Hamner, B., Cukierski, W., Tang, Y., Thaler, D., Lee, D.-H., Zhou, Y., Ramaiah, C., Feng, F., Li, R., Wang, X., Athanasakis, D., Shawe-Taylor, J., Milakov, M., Park, J., Ionescu, R., Popescu, M., Grozea, C., Bergstra, J., Xie, J., Romaszko, L., Xu, B., Chuang, Z., Bengio, Y., 2013. Challenges in representation learning: A report on three machine learning contests.
Ioffe, S., Szegedy, C., 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift.
Jeon, M., 2016. Don’t cry while you’re driving: Sad driving is as bad as angry driving. International Journal of Human–Computer Interaction 32 (10), 777–790. DOI: 10.1080/10447318.2016.1198524
Jeon, M., Roberts, J., Raman, P., Yim, J.-B., Walker, B. N., 2011. Participatory design process for an in-vehicle affect detection and regulation system for various drivers. In: The Proceedings of the 13th International ACM SIGACCESS Conference on Computers and Accessibility. ASSETS ’11. Association for Computing Machinery, New York, USA, p. 271–272. DOI: 10.1145/2049536.2049602
Kapishnikov, A., Bolukbasi, T., Vi´egas, F., Terry, M., 2019. Xrai: Better attributions through regions.
Lorente, M. P. S., Lopez, E. M., Florez, L. A., Espino, A. L., Mart´ ınez, J. A. I., de Miguel, A. S., 2021. Explaining deep learning-based driver models. Applied Sciences 11 (8). DOI: 10.3390/app11083321
Magán, E., Sesmero, M. P., Alonso-Weber, J. M., Sanchis, A., 2022. Driver drowsiness detection by applying deep learning techniques to sequences of images. Applied Sciences 12 (3).
Sheykhivand, S., Mousavi, Z., Rezaii, T. Y., Farzamnia, A., 2020. Recognizing emotions evoked by music using cnn-lstm networks on eeg signals. IEEE Access 8, 139332–139345. DOI: 10.1109/ACCESS.2020.3011882
Simonyan, K., Zisserman, A., 9 2014. Very deep convolutional networks for large-scale image recognition. 3rd International Conference on Learning Representations, ICLR 2015- Conference Track Proceedings.
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R., 2014. Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research 15 (56), 1929–1958.
Tamanani, R., Muresan, R., Al-Dweik, A., 2021. Estimation of driver vigilance status using real-time facial expression and deep learning. IEEE Sensors Letters 5 (5), 1–4. DOI: 10.1109/LSENS.2021.3070419
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L. u., Polosukhin, I., 2017. Attention is all you need. In: Guyon, I., Luxburg, U. V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (Eds.), Advances in Neural Information Processing Systems. Vol. 30. Curran Associates, Inc.
Verma, B., Choudhary, A., 11 2018. A framework for driver emotion recognition using deep learning and grassmann manifolds. pp. 1421–1426. DOI: 10.1109/ITSC.2018.8569461
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Diego Caballero García-Alcaide, Paz Sesmero Lorente, José Antonio Iglesias Martínez, Araceli Sanchis de Miguel
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
