Comparative Analysis of Machine Learning and Deep Learning Models for Real-Time Driver Drowsiness Detection.

Drowsy driving is among the major factors leading to accidents on roads, especially in scenarios where long hours of traveling or working are involved. The current paper performs a comparative analysis between traditional machine learning (ML) techniques and lightweight deep learning (DL) methods concerning driver drowsiness detection using the YawDD Dataset (a yawning detection dataset). This Dataset consists of 322 videos from the mirror (rear-view mirror camera position) subset and 29 videos from its Dash (dashboard) subset, recorded from 107 drivers of diverse ages, gender and ethnicities. The videos are presented in various levels of illumination and facial occlusions (glasses and sunglasses) as well as poses. Frames were extracted from the videos at regular intervals resulting in thousands of labelled images.

This study evaluates two types of algorithms based on their performance through several parameters such as accuracy, precision, recall, and F1 score while simultaneously considering the efficiency of computation measured by inference time, CPU usage, memory, and frames per second (FPS).

According to the findings, while DL models like the convolutional neural network based on EfficientNet and TinyCNN offer better classification performance with accuracy levels surpassing 93%, these models exhibit inferior inference rates. Consequently, these DL models cannot be employed in real-time situations since they require hardware accelerators. On the other hand, traditional ML models, mainly the combination of Random Forest and Support Vector Machine, offer a good balance between accuracy and efficiency. Logistic regression provides the best processing rate but with limited accuracy.

Conclusively, the results imply that traditional ML models are still applicable for real-time tasks in resource-constrained environments compared to DL models. However, DL models are recommended for implementations where hardware accelerators are available.

Driver Drowsiness Detection, Machine Learning, Deep Learning, Real-Time Systems, Low-Power Devices, Computer Vision.

1. Abe, T. (2023). PERCLOS-based technologies for detecting drowsiness: current evidence and future directions. SLEEP Advances, 4(1), 1–13. https://doi.org/10.1093/SLEEPADVANCES/ZPAD006 [Google Scholar] [Crossref]

2. Abtahi, S., Omidyeganeh, M., Shirmohammadi, S., & Hariri, B. (2014). YawDD: A yawning detection dataset. Proceedings of the 5th ACM Multimedia Systems Conference, MMSys 2014, 24–28. https://doi.org/10.1145/2557642.2563678 [Google Scholar] [Crossref]

3. Arakawa, T. (2021). Trends and Future Prospects of the Drowsiness Detection and Estimation Technology. Italian National Conference on Sensors, 21(23). https://doi.org/10.3390/S21237921 [Google Scholar] [Crossref]

4. Blom, J., Sam, E. F., Egner, L. E., Nævestad, T. O., & Fiangor, A. (2025). Fatigue among bus drivers in Ghana and Norway: Examining the influence of working conditions and national road safety culture. Transportation Research Procedia, 89, 394–403. https://doi.org/10.1016/j.trpro.2025.05.070 [Google Scholar] [Crossref]

5. Deepika, C. N. J., Jithendra, K., Poojitha, B., Ranganath, R. M., Vaithilingam, C. A., & Sivaraman, K. (2025). Driver drowsiness detection using machine learning algorithms. AIP Conference Proceedings, 3253(1). https://doi.org/10.1063/5.0252639 [Google Scholar] [Crossref]

6. Dharshini R, ; Janani V, & Bharanidharn, ; C. (2024). DRIVER DROWSINESS DETECTION USING MACHINE LEARNING. www.tijer.org [Google Scholar] [Crossref]

7. Dinges, D. F., Mallis, M. M., Maislin, G., Powell, J. W., & Administration, U. States. D. of Transportation. N. H. T. S. (1998). Evaluation of techniques for ocular measurement as an index of fatigue and as the basis for alertness management. https://doi.org/10.21949/1503647 [Google Scholar] [Crossref]

8. Elidrissi, M. E., Essoukaki, E., Taleb, L. Ben, Mouhsen, A., & Harmouchi, M. (2023). Drivers’ drowsiness detection based on an optimized random forest classification and single-channel electroencephalogram. International Journal of Electrical and Computer Engineering, 13(3), 3398–3406. https://doi.org/10.11591/ijece.v13i3.pp3398-3406 [Google Scholar] [Crossref]

9. Essahraui, S., Lamaakal, I., El Hamly, I., Maleh, Y., Ouahbi, I., El Makkaoui, K., Filali Bouami, M., Pławiak, P., Alfarraj, O., & Abd El-Latif, A. A. (2025). Real-Time Driver Drowsiness Detection Using Facial Analysis and Machine Learning Techniques. Sensors 2025, Vol. 25, Page 812, 25(3), 812. https://doi.org/10.3390/S25030812 [Google Scholar] [Crossref]

10. Fonseca, T., & Ferreira, S. (2025). Drowsiness Detection in Drivers: A Systematic Review of Deep Learning-Based Models. Applied Sciences 2025, Vol. 15, Page 9018, 15(16), 9018. https://doi.org/10.3390/APP15169018 [Google Scholar] [Crossref]

11. Ibrahim, A. (2022, May 6). Driver fatigue primary cause of road crashes in Ghana - Road Safety Authority. CITI NEWSROOM. https://citinewsroom.com/2022/05/driver-fatigue-primary-cause-of-road-crashes-in-ghana-road-safety-authority/ [Google Scholar] [Crossref]

12. Jasim, S. S., Karim, A., & Hassan, A. (2022). Modern Drowsiness Detection in Deep Learning: A review. Journal of Al-Qadisiyah for Computer Science and Mathematics, 14(3), 119–129. https://doi.org/10.29304/jqcm.2022.14.3.1023 [Google Scholar] [Crossref]

13. Kaundal, S., Chauhan, K., & Rana, A. (2025). A Comprehensive Literature Review on Driver Drowsiness Detection and Alert System. International Journal of Electrical, Electronics ISSN No, 14(2), 32–35. www.researchtrend.net [Google Scholar] [Crossref]

14. Khanehshenas, F., Mazloumi, A., Nahvi, A., Nickabadi, A., Sadeghniiat, K., Rahimiforoushani, A., & Aghamalizadeh, A. (2024). A hybrid approach for driver drowsiness detection utilizing practical data to improve performance system and applicability. Work, 77(4), 1165–1177. https://doi.org/10.3233/WOR-230179 [Google Scholar] [Crossref]

15. Moradi, A., Nazari, S. S. H., & Rahmani, K. (2019). Sleepiness and the risk of road traffic accidents: A systematic review and meta-analysis of previous studies. Transportation Research Part F: Traffic Psychology and Behaviour, 65, 620–629. https://doi.org/10.1016/J.TRF.2018.09.013 [Google Scholar] [Crossref]

16. National Road Safety Authority. (2025). January–March 2025 Crash Report Summary. Government of Ghana. https://www.nrsa.gov.gh/ [Google Scholar] [Crossref]

17. Schwarz, C., Gaspar, J., & Yousefian, R. (2023). Multi-sensor driver monitoring for drowsiness prediction. Traffic Injury Prevention, 24(S1), S100–S104. https://doi.org/10.1080/15389588.2023.2164839 [Google Scholar] [Crossref]

18. Srinivas, K., V M U Vinay Karthik, G. V, Suhas, I., Surendra, A., & Sujith, B. (n.d.). Driver Drowsiness Detection using Machine Learning and Deep Learning. https://doi.org/10.48175/IJARSCT-17442 [Google Scholar] [Crossref]

19. SSATP. (2025). Africa Status Report on Road Safety. SSATP. https://www.ssatp.org/sites/default/files/publication/SSATP_Africa%20Status%20Report%20on%20Road%20Safety%202025_single.pdf [Google Scholar] [Crossref]

20. Wierwille, W. W., Wreggit, S. S., Kirn, C. L., Ellsworth, L. A., & Fairbanks, R. J. (1994). Research on Vehicle-Based Driver Status/Performance Monitoring; Development, Validation, and Refinement of Algorithms For Detection of Driver Drowsiness. https://rosap.ntl.bts.gov/view/dot/2578 [Google Scholar] [Crossref]

• Enhancing Formation Control of Multi Agent Systems Using Ann Based Technique
• Improving Sliding Mode Control with Chattering Reduction using Fuzzy Based Technique
• Cooking Quality, Fasting Blood Glucose, Glycemic Index and Load of High–Fiber Noodles Made from Wheat, Tiger Nut Residue and Cassava Flour Blends
• Matrix Rhythm Therapy Versus Interferential Therapy Combined with Lumbar Stabilization Exercises in Chronic Non-Specific Low Back Pain: A Randomized Comparative Trial
• Formulation and Sensory Evaluation of Functional Cake Prepared from Sweet Potato Powder