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: 2025-11-28

Accepted: 2026-01-01

Published in Issue 2026-06-30

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. (2026). A Real-Time Driver Drowsiness Detection Method Using a Hybrid of Deep Learning and Fuzzy Logic. Majlesi Journal of Electrical Engineering, 20(2 (June 2026). https://doi.org/10.57647/mjee.2026.2002.15
Crossref
Scopus
Google Scholar
Europe PMC

PDF views: 66

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. Madni HA, Raza A, Sehar R, Thalji N, and Abuali-gah L. “Novel Transfer Learning Approach for Driver Drowsiness Detection Using Eye Movement Behavior.” IEEE 2024; 12:64765–78. doi: 10.1109/ACCESS
  2. Jarndal A, Tawfik H, Siam AI, Alsyouf I, and Cheaitou A. “A Real-Time Vision Transformers-Based System for Enhanced Driver Drowsiness Detection and Vehicle Safety.” IEEE 2025; 13:1790–803. doi: 10 . 1109 / ACCESS . 2024 .3522111
  3. El-Nabi SA et al. “Driver Drowsiness Detection Using Swin Transformer and Diffusion Models for Robust Image Denoising.” IEEE 2025; 13:71880–907. doi: 10.1109/ACCESS.2025.3561717
  4. Ramzan M, Abid A, Fayyaz M, Alahmadi TJ, Noba-nee H, and Rehman A. “A Novel Hybrid Approach for Driver Drowsiness Detection Using a Custom Deep Learning Model.” IEEE 2024; 12:126866–84. doi: 10.1109/ACCESS.2024.3438617
  5. You F, Li X, Wang YGH, and Li H. “A Real-time Driving Drowsiness Detection Algorithm with Individual Differences Consideration.” IEEE 2019; 7:179396–408. doi: 10.1109/ACCESS.2019.2958667
  6. Ngxande M, Tapamo JR, and Burke M. “Bias Re-mediation in Driver Drowsiness Detection Systems Using Generative Adversarial Networks. ” IEEE 2020; 8:55592–601. doi: 10.1109/ACCESS. 2020.2981912
  7. Venkateswarlu M and Ch VRR. “DrowsyDetectNet: Driver Drowsiness Detection Using Lightweight CNN With Limited Training Data.” IEEE 2024; 12:110476–91. doi: 10.1109/ACCESS.2024.3440585
  8. Priyanka S, Shanthi S, Kumar AS, and Praveen V. “Data fusion for driver drowsiness recognition: A multimodal perspective.” Egyptian Informatics Journal 2024; 27. doi: 10.1016/j.eij.2024.100529
  9. Deng W and Wu R. “Real-Time Driver-Drowsiness Detection System Using Facial Features.” IEEE 2019; 7:118727–38. doi: 10.1109/ACCESS.2019.2936663
  10. Nomura A, Yoshida A, Nagumo K, and Nozawa A. “Reducing the effect of face orientation using FaceMesh landmarks in drowsiness estimation based on facial thermal images. ” Nature 2025; 30:317–24. doi: 10.1007/s10015-024-01001-1
  11. Lamaazi H, Alqassab A, Fadul RA, and Mizouni R. “Smart Edge-Based Driver Drowsiness Detection in Mobile Crowdsourcing.” IEEE 2023; 11:21863–72. doi: 10.1109/ACCESS.2023.3250834
  12. Salem D and Waleed M. “Drowsiness detection in real-time via convolutional neural networks and transfer learning.” Journal of Engineering and Applied Science 2024; 71. doi: 10.1186/s44147-024-00457-z
  13. Chew YX, Razak SFA, Yogarayan S, and Ismail SNMS. “Dual-Modal Drowsiness Detection to Enhance Driver Safety.” Computers, Materials & Continua 2024; 81:4397–417. doi: 10.32604/cmc. 2024.056367
  14. Ramzan M, Khan HU, Awan SM, Ismail A, Ilyas M, and Mahmood A. “A Survey on State-of-the-Art Drowsiness Detection Techniques.” IEEE 2019; 7:61904–19. doi: 10.1109/ACCESS.2019.2914373
  15. Maheswari VU, Aluvalu R, Kantipudi MP, Chen-nam KK, Kotecha K, and Saini JR. “Driver Drowsiness Prediction Based on Multiple Aspects Using Image Processing Techniques.” IEEE 2022; 10:54980–90. doi: 10.1109/ACCESS.2022.3176451
  16. Yadav A, Hussain R, Shukla M, J. B RK, Mary SP, Hsu C, Mishra MK, Saleem K, and El-Meligy M. “Enhancing convolutional neural networks in electroencephalogram driver drowsiness detection using human inspired optimizers.” Scientific Reports 2025; 15. doi: 10.1109/ACCESS.2022.3187995
  17. Murata A, Doi T, and Karwowski W. “Sensitivity of PERCLOS70 to Drowsiness Level: Effectiveness of PERCLOS70 to Prevent Crashes Caused by Drowsiness.” IEEE 2022; 10:70806–14. doi: 10.1109/ACCESS.2022.3187995
  18. Cai J, Liao X, Bai J, Luo Z, Li L, and Bai J. “Face Fatigue Feature Detection Based on Improved D-S Model in Complex Scenes.” IEEE 2023; 11:101790–8. doi: 10.1109/ACCESS.2023.3314665
  19. Mohammed AZ, Mohammed EA, and Aaref AM. “Real-Time Driver Awareness Detection System.” IOP Conference Series: Materials Science and Engineering 2020; 745. doi: 10.1088/1757-899X/ 745/1/012053
  20. Nagdeote S, Pendhari H, John M, and Agrawal S. “An Approach to Detect Driver Drowsiness in Real Time using Facial Landmarks.” SAMRID-DHI: A Journal of Physical Sciences, Engineering and Technology 2023; 15. doi: 10.18090/ samriddhi.v15i01.21
  21. Titare S, Chinchghare S, and Hande KN. “Driver Drowsiness Detection and Alert System.” International Journal of Scientific Research in Computer Science, Engineering and Information Technology (ISJRCSEIT) 2021; 7:583–8. doi: 10.32628/ CSEIT2173171
  22. Alshamrani R, Alshehri F, and Kurdi H. “A Pre-processing Technique for Fast Convex Hull Computation.” Procedia Computer Science 2020; 170:317–24. doi: 10.1016/j.procs.2020.03.046
  23. Adarsh G, Singh V, Singh S, and Hazela B. “Drowsiness Detection System in Real Time Based on Behavioral Characteristics of Driver using Machine Learning Approach.” Journal of informatics Electrical and Electronics Engineering (JIEEE) 2023; 04:1–10. doi: 10.54060/jieee.v4i1. 84
  24. Asdyo B, Kanigoro B, and Rojali. “Drowsy Detection System by Facial Landmark and Light Gradient Boosting Machine Method. ” Procedia Computer Science 2023; 277:500–7. doi: 10.1016/j.procs.2023.10.551
  25. Wang L, Wang H, and Liu J. “Discrimination of Driver Fatigue Based on Distortion Energy Density Theory and Multiple Physiological Signals.” IEEE 2021; 9:151824–33. doi: 10.1109/ACCESS. 2021.3125052
  26. Celecia A, Figueiredo K, Vellasco M, and Gon-zalez R. “A Portable Fuzzy Driver Drowsiness Estimation System.” Sensors 2020; 20. doi: 10.3390/s20154093
  27. Arava M and Sundaram DM. “Multi-Figure Selection and Fuzzy Logic-Based Intelligent Driver Drowsiness Detection.” Institution of Engineering and Technology (IET) 2025; 19. doi: 10.1049/ipr2.70052
  28. Alkishri W, Abualkishik A, and Al-Bahri M. “Enhanced Image Processing and Fuzzy Logic Approach Optimizing Driver Drowsiness Detection.” Applied Computational Intelligence and Soft Computing 2022; 2022. doi: 10.1155/2022/ 9551203
  29. Sorourkhah A. “Coping Uncertainty in the Supplier Selection Problem Using a Scenario-Based Approach and Distance Measure on Type-2 Intuitionistic Fuzzy Sets.” Fuzzy Optimization and Modelling 2022; 3:1–8. doi: 10.30495/fomj.2022.1953705.1066
  30. Khaniki MAL, Hadi MB, and Manthouri M. “Tuning of Novel Fractional Order Fuzzy PID Controller for Automatic Voltage Regulator using Grasshopper Optimization Algorithm.” Ma-jlesi Journal of Electrical Engineering 2012; 15. doi: 10.52547/mjee.15.2.39
  31. Jalali M, Kardehi R, and Pariz N. “Maximum Energy Absorbed from the Persian Gulf Waves Considering Uncertainty in Power Take off Parameters.” Majlesi Journal of Electrical Engineering 2022; 16. doi: 10.30486/mjee.2022.696491
  32. Abadi DNM, Moarefianpopur A, and Dehkordi NM. “Finite-Time Bounded Model-Based Event-Triggered Control for Distributed Fuzzy T-S Systems.” Majlesi Journal of Electrical Engineering 2024; 18. doi: 10.30486/mjee.2023.1994207.1226
  33. Boulanouar S and Boualem F. “Solar panel fault diagnosis based on the intelligent recursive method.” Majlesi Journal of Electrical Engineering 2025; 19. doi: 10.57647/j.mjee.2025.1902.28
  34. Janah NZ and Baharudin B. “Genetic Fuzzy Filter Based on MAD and ROAD to Remove Mixed Impulse Noise.” Majlesi Journal of Electrical Engineering 2010; 4. doi: 10.1234mjee.v4i2.283
  35. Soroushmehr SM. “A New Fuzzy Based Motion Estimation Algorithm in Video Compression.” Majlesi Journal of Electrical Engineering 2010; 4. doi: 10.1234mjee.v4i2.197
  36. Ghaleh OD, Maihami V, and Khamforoosh K. “A Hybrid Method for Medical Image Denoising and Segmentation Using Optimized Fuzzy Clustering and Autoencoder. ” Fuzzy Optimiza-tion and Modeling Journal (FOMJ) 2025; 6. doi: 10.57647/j.fomj.2025.0602.10
  37. Sakhaei SF, Afshari AJ, Bosaghzade A, and Jahromi MHM. “Intelligent Image-Based Recog-nition of Rice Cultivars Using PSO-Optimized ANFIF. ” Fuzzy Optimization and Modeling Jour-nal (FOMJ) 2025; 6. doi: 10.57647/j.fomj.2025. 0603.17