Enhanced Real-Time Driver Fatigue Detection Using Hybrid SVM ‎and Multi-Feature Analysis for Improved Accuracy and ‎Road Safety

  • Authors

    • Lakshmi Devi S Department of Computer Science, Research Scholar, Sri Krishna Adithya College of Arts & Science, Kovaipudur, Coimbatore, 641042, ‎TamilNadu, India
    • Vinoth A Department of Information Technology, Assistant Professor, Sri Krishna Adithya College of Arts & Science, Kovaipudur, Coimbatore, ‎‎641042, TamilNadu, India‎
    https://doi.org/10.14419/hd63bz13

    Received date: June 10, 2025

    Accepted date: July 7, 2025

    Published date: July 24, 2025

  • Image Projection Function; Multi-layer Perceptron; Principal Component Analysis; Radial Basis Function; Support Vector Machine

  • Abstract

    Fatigue and distraction are two of the main causes of traffic accidents, so it's critical to maintain focused attention when driving. A ‎reliable real-time fatigue detection system based on driver visual ‎analysis is proposed in the present research. Yet, features like interference from eyewear and low illumination can affect the precision ‎of detection. A machine learning-based technique for detecting and ‎classifying driver fatigue in real-time is presented in this research. ‎Along with blinking, additional indicators of fatigue include yawning, nodding, and variances in pupil size. To extract multiple visual ‎cues, the Image Projection Function (IPF) is used to quantify pupil ‎size, optical flow is employed for assessing head position, and eye ‎and mouth dimension ratios are measured. Normalization is per-‎formed to ensure data consistency. Multiple facial fatigue ‎markers are incorporated into the system to improve classification ‎accuracy and robustness. Principal Component Analysis (PCA) is ‎applied for dimensionality reduction to optimize classification performance. The Euclidean distance gauge is used to evaluate three ‎machine learning models: Support Vector Machine (SVM), Multi-layer Perceptron (MLP), and K-Nearest Neighbors (KNN). Outperforming KNN and MLP, SVM with the Radial Basis Function ‎‎(RBF) kernel obtains the best accuracy of 91.6% among them. The ‎classification performance is enhanced by the RBF kernel's ability ‎to capture non-linear fatigue-related patterns. The efficiency of the ‎proposed method for detecting fatigue in the real world has been ‎verified by experimental results, which indicate the attributes obtained ‎can reliably differentiate between fatigued and non-fatigued states‎.

  • References

    1. Pratama, B. G., Ardiyanto, I., & Adji, T. B. (2017). A review on driver drowsiness based on image, bio-signal, and driver behavior. 2017 3rd Inter-national Conference on Science and Technology-Computer (ICSTC), 70–75. https://doi.org/10.1109/ICSTC.2017.8011855.
    2. Triyanti, V., & Iridiastadi, H. (2017). Challenges in detecting drowsiness based on driver’s behavior. IOP Conference Series: Materials Science and Engineering, 277(1), 012042. https://doi.org/10.1088/1757-899X/277/1/012042.
    3. National Highway Traffic Safety Administration. (2021). Drowsy driving. https://www.nhtsa.gov/risky-driving/drowsy-driving
    4. Bajaj, J. S., Kumar, N., & Kaushal, R. K. (2021). Comparative study to detect driver drowsiness. 2021 International Conference on Advanced Computing and Innovative Technologies in Engineering (ICACITE), 678–683. https://doi.org/10.1109/ICACITE51222.2021.9404761.
    5. Yu, J., Park, S., Lee, S., & Jeon, M. (2019). Drivers drowsiness detection using condition-adaptive representation learning framework. arXiv. https://arxiv.org/abs/1910.09722
    6. Ghourabi, A., Ghazouani, H., & Barhoumi, W. (2021). Driver drowsiness detection based on joint monitoring of yawning, blinking and nodding. 2020 International Conference on Control, Automation and Diagnosis (ICCAD). https://doi.org/10.1109/ICCP51029.2020.9266160.
    7. Deng, W., & Wu, R. (2021). Real-time driver-drowsiness detection system using facial features. IEEE Access, 7, 118727–118738. https://doi.org/10.1109/ACCESS.2019.2936663.
    8. Zhuang, Q., Zhang, K., Wang, J., & Chen, Q. (2020). Driver fatigue detection method based on eye states with pupil and iris segmentation. IEEE Access, 8, 173440–173449. https://doi.org/10.1109/ACCESS.2020.3025818.
    9. Dreißig, M., Baccour, M. H., Schack, T., & Kasneci, E. (2020). Driver drowsiness classification based on eye blink and head movement features using the k-NN algorithm. arXiv. https://arxiv.org/abs/2009.13276. https://doi.org/10.1109/SSCI47803.2020.9308133
    10. Sahin, M. E. (2023). Real-time driver drowsiness detection and classification on embedded systems using machine learning algorithms. Traitement du Signal, 40(3), 847–856. https://doi.org/10.18280/ts.400302.
    11. Pasieczna, A. H., & Korczak, J. J. (2016). Classification algorithms in sleep detection—A comparative study. Annals of Computer Science and In-formation Systems, 8, 113–120. https://doi.org/10.15439/2016F187.
    12. Savaş, B. K., & Becerikli, Y. (2018). Real time driver fatigue detection based on SVM algorithm. 2018 9th International Conference on Infor-mation and Communication Systems (ICICS). https://doi.org/10.1109/CEIT.2018.8751886.
    13. Shen, Q., Zhao, S., & Zhang, R. (2020). Robust two-stream multi-features network for driver drowsiness detection. ACM International Conference Proceedings, 271–277. https://doi.org/10.1145/3438872.3439093.
    14. Fu, H.-Y., Guo, J.-W., & Yu, Y.-J. (2016). A simple multi-scale Gaussian smoothing-based strategy for automatic chromatographic peak extraction. Journal of Chromatography A. https://doi.org/10.1016/j.chroma.2016.05.018.
    15. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet classification with deep convolutional neural networks. Advances in Neural In-formation Processing Systems, 25, 1097–1105.
    16. Donahue, J., Hendricks, L., Guadarrama, S., Rohrbach, M., Venugopalan, S., Darrell, T., & Saenko, K. (2015). Long-term recurrent convolutional networks for visual recognition and description. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2625–2634. https://doi.org/10.1109/CVPR.2015.7298878.
    17. Park, S., Pan, F., Kang, S., & Yoo, C. D. (2017). Driver drowsiness detection system based on feature representation learning using various deep networks. Asian Conference on Computer Vision (ACCV), 154–164. https://doi.org/10.1007/978-3-319-54526-4_12.
    18. Yu, J., Park, S., Lee, S., & Jeon, M. (2019). Drivers drowsiness detection using condition-adaptive representation learning framework. arXiv. https://arxiv.org/abs/1910.09722. https://doi.org/10.1007/978-3-319-54526-4_13.
    19. Asian Conference on Computer Vision. (2017). Representation learning, scene understanding, and feature fusion for drowsiness detection. In ACCV 2016 (pp. 165–177). https://doi.org/10.1007/978-3-319-54526-4_13
    20. Rajahrajasingh, H. (2017). Driver drowsiness detection using MATLAB. International Journal of Engineering Applied Sciences and Technology, 4(7), 80–87. https://doi.org/10.33564/IJEAST.2019.v04i07.012.
    21. Park, S.-M., Choi, I.-H., & Kim, Y.-G. (2016). Study of wearing sunglass driver drowsiness state monitoring. ACM Conference Proceedings, 444–448. https://doi.org/10.17210/hcik.2016.01.444.
    22. Agustina, I., Nasir, F., & Setiawan, A. (2017). The implementation of image smoothing to reduce noise using Gaussian filter. International Journal of Computer Applications, 7, 15–19. https://doi.org/10.5120/ijca2017915755.
    23. Yu, J., Park, S., Lee, S., & Jeon, M. (2019). Drivers drowsiness detection using condition-adaptive representation learning framework. arXiv, 1–14. https://arxiv.org/abs/1910.09722.
    24. Zhang, J., & Jin, J. (2023). Lightweight object detection algorithm based YOLOv5 for unmanned surface vehicles. Frontiers in Marine Science, 9. https://doi.org/10.3389/fmars.2022.1058401.
    25. Bochkovskiy, A., & Liao, H.-Y. M. (2022). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv.
    26. Soni, M. B., Patel, D., & Shah, S. R. (2024). Real time driver drowsiness detection using facial landmark features and machine learning algorithms. Sensors, 24(3), 812. https://doi.org/10.3390/s24030812.
    27. Gopi, M., & Pillai, S. N. (2025). Webcam based eye aspect ratio analysis for real time drowsiness detection using SVM. International Journal of Engineering Research in Science & Technology, 11(5), 45–51.
    28. Wu, D. (2024). Comparative study of machine learning and deep learning for driver distraction and drowsiness detection. arXiv. https://arxiv.org/abs/2401.10213.
    29. Maior, R., Silva, A. F., & Lima, C. D. (2024). Benchmarking machine learning models for driver drowsiness detection: SVM, MLP, and random forest analysis. Symmetry, 15(6), 1274. https://doi.org/10.3390/sym15061274.
    30. Menon, R. K., & Kumar, S. D. (2024). Optimized PCA based driver fatigue detection using embedded systems. Sensors, 24(5), 1023.

  • Downloads

  • How to Cite

    S, L. D. ., & A, V. . (2025). Enhanced Real-Time Driver Fatigue Detection Using Hybrid SVM ‎and Multi-Feature Analysis for Improved Accuracy and ‎Road Safety. International Journal of Basic and Applied Sciences, 14(3), 232-241. https://doi.org/10.14419/hd63bz13