10.57647/mjee.2026.2002.15

A Real-Time Driver Drowsiness Detection Method Using a Hybrid of Deep Learning and Fuzzy Logic

PDF
  • Amir Sohrabinezhad1,
  • Reza Sabbaghi-Nadooshan*1,
  • Nasser Talebi2,
  • Roohollah Barzamini1,
  • Fardad Farokhi3,
  1. Department of Electrical Engineering, CT.C, Islamic Azad University, Tehran, Iran
  2. Department of Electrical Engineering, YI.C, Islamic Azad University, Tehran, Iran
  3. Department of Biomedical Engineering, CT.C, Islamic Azad University, Tehran, Iran

Received: 2025-08-31

Revised: 2025-11-26

Accepted: 2026-01-01

Published Online: 2026-04-21

Copyright (c) 2026 Amir Sohrabinezhad, Reza Sabbaghi-Nadooshan, Nasser Talebi, Roohollah Barzamini, Fardad Farokhi (Author)

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Sohrabinezhad, A., Sabbaghi-Nadooshan, R., Talebi, N., Barzamini, R., & Farokhi, F. A Real-Time Driver Drowsiness Detection Method Using a Hybrid of Deep Learning and Fuzzy Logic. Majlesi Journal of Electrical Engineering. https://doi.org/10.57647/mjee.2026.2002.15
Crossref
Scopus
Google Scholar
Europe PMC

PDF views: 27

Abstract

Driver drowsiness contributes to approximately 21% of traffic accidents. Three deep neural networks were trained, with ResNet50 achieving the best performance: 99.74% training accuracy, 99.62% validation accuracy, an average test F1-score of 0.99, no overfitting, and real-time inference at 0.023 seconds per frame on an RTX 3060 laptop GPU with 6GB RAM. Following drowsiness detection, a fuzzy inference system integrating Eye Aspect Ratio (EAR) and Mouth Aspect Ratio (MAR) is applied to determine the drowsiness severity. The system was tested with an infrared camera on 453 volunteers from various Middle Eastern ethnic groups under different lighting conditions. A local database was compiled from these tests, recording 31 misclassifications and achieving an overall accuracy of 93.16%. The findings demonstrate that the system performs reliably under both day and night conditions and across diverse ethnicities, supporting its suitability for integration into advanced driver-assistance systems (ADAS).

Keywords

  • Real-time Drowsiness Detection,
  • Determining the degree of drowsiness,
  • Deep Learning,
  • Fuzzy Inference Systems
PDF

References

  1. H. A. Madni, A. Raza, R. Sehar, N. Thalji and L. Abualigah, “Novel Transfer Learning Approach for Driver Drowsiness Detection Using Eye Movement Behavior,” in IEEE Access, vol. 12, pp. 64765-64778, 2024, doi: 10.1109/ACCESS.
  2. A. Jarndal, H. Tawfik, A. I. Siam, I. Alsyouf and A. Cheaitou, “A Real-Time Vision Transformers-Based System for Enhanced Driver Drowsiness Detection and Vehicle Safety,” in IEEE Access, vol. 13, pp. 1790-1803, 2025, doi: 10.1109/ACCESS.2024.3522111.
  3. S. A. El-Nabi et al., “Driver Drowsiness Detection Using Swin Transformer and Diffusion Models for Robust Image Denoising,” in IEEE Access, vol. 13, pp. 71880-71907, 2025, doi: 10.1109/ACCESS.2025.3561717.
  4. M. Ramzan, A. Abid, M. Fayyaz, T. J. Alahmadi, H. Nobanee and A. Rehman, “A Novel Hybrid Approach for Driver Drowsiness Detection Using a Custom Deep Learning Model,” in IEEE Access, vol. 12, pp. 126866-126884, 2024, doi: 10.1109/ACCESS.2024.3438617.
  5. F. You, X. Li, Y. Gong, H. Wang and H. Li, “A Real-time Driving Drowsiness Detection Algorithm with Individual Differences Consideration,” in IEEE Access, vol. 7, pp. 179396-179408, 2019, doi: 10.1109/ACCESS.2019.2958667.
  6. M. Ngxande, J. -R. Tapamo and M. Burke, “Bias Remediation in Driver Drowsiness Detection Systems Using Generative Adversarial Networks,” in IEEE Access, vol. 8, pp. 55592-55601, 2020, doi: 10.1109/ACCESS.2020.2981912.
  7. M. Venkateswarlu and V. Rami Reddy Ch, “DrowsyDetectNet: Driver Drowsiness Detection Using Lightweight CNN With Limited Training Data,” in IEEE Access, vol. 12, pp. 110476-110491, 2024, doi: 10.1109/ACCESS.2024.3440585.
  8. S. Priyanka, S. Shanthi, A. Saran Kumar and V. Praveen, “Data fusion for driver drowsiness recognition: A multimodal perspective,” in Egyptian Informatics Journal Access, vol. 27, 2024, doi: 10.1016/j.eij.2024.100529.
  9. W. Deng and R. Wu, “Real-Time Driver-Drowsiness Detection System Using Facial Features,” in IEEE Access, vol. 7, pp. 118727-118738, 2019, doi: 10.1109/ACCESS.2019.2936663.
  10. A. Nomura, A. Yoshida, K. Nagumo and A. Nozawa, “Reducing the effect of face orientation using FaceMesh landmarks in drowsiness estimation based on facial thermal images,” in Springer Nature: Artificial Life and Robotics Access, vol. 30, pp. 317-324, 2025, doi: 10.1007/s10015-024-01001-1.
  11. H. Lamaazi, A. Alqassab, R. A. Fadul and R. Mizouni, “Smart Edge-Based Driver Drowsiness Detection in Mobile Crowdsourcing,” in IEEE Access, vol. 11, pp. 21863-21872, 2023, doi: 10.1109/ACCESS.2023.3250834.
  12. D. Salem and M. Waleed, “Drowsiness detection in real-time via convolutional neural networks and transfer learning,” in Journal of Engineering and Applied Science Access, vol. 71, 2024, doi: 10.1186/s44147-024-00457-z.
  13. Y. Xuan Chew, S. F. Abdul Razak, S. Yogarayan and S. N. M. Sayed Ismail, “Dual-Modal Drowsiness Detection to Enhance Driver Safety,” in Computers, Materials & Continua Access, vol. 81, pp. 4397-4417, 2024, doi: 10.32604/cmc.2024.056367.
  14. M. Ramzan, H. U. Khan, S. M. Awan, A. Ismail, M. Ilyas and A. Mahmood, “A Survey on State-of-the-Art Drowsiness Detection Techniques,” in IEEE Access, vol. 7, pp. 61904-61919, 2019, doi: 10.1109/ACCESS.2019.2914373.
  15. V. U. Maheswari, R. Aluvalu, M. P. Kantipudi, K. K. Chennam, K. Kotecha and J. R. Saini, “Driver Drowsiness Prediction Based on Multiple Aspects Using Image Processing Techniques,” in IEEE Access, vol. 10, pp. 54980-54990, 2022, doi: 10.1109/ACCESS.2022.3176451.
  16. A. Yadav, R. Hussain, M. Shukla, J. B, R. Kalia, S. Prince Mary, C. Hsu, M. K. Mishra, K. Saleem, and M. El-Meligy, “Enhancing convolutional neural networks in electroencephalogram driver drowsiness detection using human inspired optimizers,” in Scientific reports Access, vol. 15. 2025, doi: 10.1109/ACCESS.2022.3187995.
  17. A. Murata, T. Doi and W. Karwowski, “Sensitivity of PERCLOS70 to Drowsiness Level: Effectiveness of PERCLOS70 to Prevent Crashes Caused by Drowsiness,” in IEEE Access, vol. 10, pp. 70806-70814, 2022, doi: 10.1109/ACCESS.2022.3187995.
  18. J. Cai, X. Liao, J. Bai, Z. Luo, L. Li and J. Bai, “Face Fatigue Feature Detection Based on Improved D-S Model in Complex Scenes,” in IEEE Access, vol. 11, pp. 101790-101798, 2023, doi: 10.1109/ACCESS.2023.3314665.
  19. A. Z. Mohammed, E. A. Mohammed and A. M. Aaref, “Real-Time Driver Awareness Detection System,” in IOP Conference Series: Materials Science and Engineering Access, vol. 745, 2020, doi: 10.1088/1757-899X/745/1/012053.
  20. S. Nagdeote, H. Pendhari, M. John and S. Agrawal, “An Approach to Detect Driver Drowsiness in Real Time using Facial Landmarks,” in SAMRIDDHI: A Journal of Physical Sciences, Engineering and Technology Access, vol. 15, 2023, doi: 10.18090/samriddhi.v15i01.21.
  21. S. Titare, S. Chinchghare and K. N. Hande, “Driver Drowsiness Detection and Alert System,” in International Journal of Scientific Research in Computer Science, Engineering and Information Technology (ISJRCSEIT) Access, vol. 7, pp: 583-588, 2021, doi: 10.32628/CSEIT2173171.
  22. R. Alshamrani, F. Alshehri and H. Kurdi, “A Preprocessing Technique for Fast Convex Hull Computation,” in Procedia Computer Science Access, vol. 170, pp. 317-324, 2020, doi: 10.1016/j.procs.2020.03.046.
  23. G. Adarsh, V. Singh, S. Singh and B. Hazela, “Drowsiness Detection System in Real Time Based on Behavioral Characteristics of Driver using Machine Learning Approach,” in Journal of informatics Electrical and Electronics Engineering (JIEEE) Access, vol. 04, pp. 1-10, 2023, doi: 10.54060/jieee.v4i1.84.
  24. B. Asdyo, B. Kanigoro and Rojali, “Drowsy Detection System by Facial Landmark and Light Gradient Boosting Machine Method,” in Procedia Computer Science Access, vol. 227, pp. 500-507, 2023, doi: 10.1016/j.procs.2023.10.551.
  25. L. Wang, H. Wang and J. Liu, “Discrimination of Driver Fatigue Based on Distortion Energy Density Theory and Multiple Physiological Signals,” in IEEE Access, vol. 9, pp. 151824-151833, 2021, doi: 10.1109/ACCESS.2021.3125052.
  26. A. Celecia, K. Figueiredo, M. Vellasco and R. Gonzalez, “A Portable Fuzzy Driver Drowsiness Estimation System,” in Sensors Access, vol. 20, 2020, doi: 10.3390/s20154093.
  27. M. Arava and D. M. Sundaram, “Multi-Ftigure Selection and Fuzzy Logic-Based Intelligent Driver Drowsiness Detection,” in The Institution of Engineering and Technology (IET) Access, vol. 19, 2025, doi: 10.1049/ipr2.70052.
  28. W. Alkishri, A. Abualkishik and M. Al-Bahri, “Enhanced Image Processing and Fuzzy Logic Approach Optimizing Driver Drowsiness Detection,” in Applied Computational Intelligence and Soft Computing Access, vol. 2022, 2022, doi: 10.1155/2022/9551203.
  29. A. Sorourkhah, “Coping Uncertainty in the Supplier Selection Problem Using a Scenario-Based Approach and Distance Measure on Type-2 Intuitionistic Fuzzy Sets,” in Fuzzy Optimization and Modelling Access, vol. 3, pp. 1-8, 2022, doi: 10.30495/fomj.2022.1953705.1066.
  30. M. A. L. Khaniki, M. B. Hadi and M. Manthouri, “Tuning of Novel Fractional Order Fuzzy PID Controller for Automatic Voltage Regulator using Grasshopper Optimization Algorithm,” in Majlesi Journal of Electrical Engineering Access, vol. 15, 2012, doi: 10.52547/mjee.15.2.39.
  31. M. Jalali, R. Kardehi and N. Pariz, “Maximum Energy Absorbed from the Persian Gulf Waves Considering Uncertainty in Power Take off Parameters,” in Majlesi Journal of Electrical Engineering Access, vol. 16, 2022, doi: 10.30486/mjee.2022.696491.
  32. D. N. M. Abadi, A. Moarefianpopur and N. M. Dehkordi, “Finite-Time Bounded Model-Based Event-Triggered Control for Distributed Fuzzy T-S Systems,” in Majlesi Journal of Electrical Engineering Access, vol. 18, 2024, doi: 10.30486/mjee.2023.1994207.1226.
  33. S. Boulanouar and Fengal Boualem, “Solar panel fault diagnosis based on the intelligent recursive method,” in Majlesi Journal of Electrical Engineering Access, vol. 19, 2025, doi: 10.57647/j.mjee.2025.1902.28.
  34. N. Z. Janah and B. Baharudin, “Genetic Fuzzy Filter Based on MAD and ROAD to Remove Mixed Impulse Noise,” in Majlesi Journal of Electrical Engineering Access, vol. 4, 2010, doi: 10.1234mjee.v4i2.283.
  35. S. MR. Soroushmehr, “A New Fuzzy Based Motion Estimation Algorithm in Video Compression,” in Majlesi Journal of Electrical Engineering, vol. 4, 2010, doi: 10.1234mjee.v4i2.197.
  36. O. D. Ghaleh, V. Maihami and K. Khamforoosh, “A Hybrid Method for Medical Image Denoising and Segmentation Using Optimized Fuzzy Clustering and Autoencoder,” in Fuzzy Optimization and Modeling Journal (FOMJ) Access, vol. 6, 2025, doi: 10.57647/j.fomj.2025.0602.10.
  37. S. F. Sakhaei, A. J. Afshari, A. Bosaghzade and M. H. M. Jahromi, “Intelligent Image-Based Recognition of Rice Cultivars Using PSO-Optimized ANFIF,” in Fuzzy Optimization and Modeling Journal (FOMJ) Access, vol. 6, 2025, doi: 10.57647/j.fomj.2025.0603.17.