SAFE-DRIVE-AI: A CNN–LSTM–Attention Framework for Drowsiness Detection
Received: 13 June 2025 | Revised: 17 July 2025 and 29 July 2025 | Accepted: 1 August 2025 | Online: 6 October 2025
Corresponding author: Ayoub Alsarhan
Abstract
Driver drowsiness is a major cause of road accidents worldwide, leading to thousands of injuries and fatalities each year. Detecting early signs of fatigue remains a critical challenge in road safety and intelligent transportation systems. This paper proposes a novel deep learning-based framework named SAFE-DRIVE-AI, designed to detect drowsiness in real-time by analyzing visual cues from the driver's eyes. The proposed framework integrates three components: A Convolutional Neural Network (CNN) to extract spatial features from eye images, a Long Short-Term Memory (LSTM) layer for capturing temporal patterns such as blink duration and frequency, and an Attention mechanism to enhance the model’s focus on the most relevant time steps. To validate the effectiveness of Deep Learning (DL) techniques, a comparative analysis was conducted using both traditional Machine Learning (ML) models (Logistic Regression, Decision Trees, Random Forest, and Support Vector Machines) and DL models (CNN, LSTM). The experimental results showed that the DL models significantly outperformed the ML ones in all metrics. The hybrid CNN+LSTM model achieved an accuracy of 97.3% and an F1-score of 96.8%, being the most accurate approach. SAFE-DRIVE-AI is designed for real-world deployment, with potential integration into edge devices, 5G-enabled systems, and real-time alert mechanisms. The proposed method offers a practical and intelligent solution for enhancing driver safety through proactive fatigue monitoring.
Keywords:
drowsiness detection, deep learning, attention mechanism, driver monitoring, real-time systems, SAFE-DRIVE-AIDownloads
References
H. Kulhandjian, "Detecting Driver Drowsiness with Multi-Sensor Data Fusion Combined with Machine Learning," Mineta Transportation Institute Publications, Sep. 2021.
N. R. Widyastuti and D. F. Brilianti, "The Impact of Drowsiness on Road Traffic Accidents in Yogyakarta," Journal of Scientific Research, Education, and Technology (JSRET), vol. 3, no. 4, pp. 1651–1661, Dec. 2024.
K. Lu, A. Sjörs Dahlman, J. Karlsson, and S. Candefjord, "Detecting driver fatigue using heart rate variability: A systematic review," Accident Analysis & Prevention, vol. 178, Dec. 2022, Art. no. 106830.
A. Halin, J. G. Verly, and M. Van Droogenbroeck, "Survey and Synthesis of State of the Art in Driver Monitoring," Sensors, vol. 21, no. 16, Aug. 2021, Art. no. 5558.
S. Manga et al., "Estimation of Physiologic Pressures: Invasive and Non-Invasive Techniques, AI Models, and Future Perspectives," Sensors, vol. 23, no. 12, Jun. 2023, Art. no. 5744.
N. Ahmadzadeh Nobari Azar, N. Cavus, P. Esmaili, B. Sekeroglu, and S. Aşır, "Detecting emotions through EEG signals based on modified convolutional fuzzy neural network," Scientific Reports, vol. 14, no. 1, May 2024, Art. no. 10371.
G. Brauwers and F. Frasincar, "A General Survey on Attention Mechanisms in Deep Learning," IEEE Transactions on Knowledge and Data Engineering, vol. 35, no. 4, pp. 3279–3298, Apr. 2023.
X. Wang, Z. Zhu, G. Huang, X. Chen, J. Zhu, and J. Lu, "DriveDreamer: Towards Real-World-Drive World Models for Autonomous Driving," in Computer Vision – ECCV 2024, 2025, pp. 55–72.
Md. A. Uddin et al., "Abnormal Driving Behavior Detection: A Machine and Deep Learning Based Hybrid Model," International Journal of Intelligent Transportation Systems Research, vol. 23, no. 1, pp. 568–591, Apr. 2025.
H. Liu, Y. Zhou, and C. Jiang, "Classifying metro drivers’ cognitive distractions during manual operations using machine learning and random forest-recursive feature elimination," Scientific Reports, vol. 15, no. 1, Mar. 2025, Art. no. 7564.
P. Sinha, D. Sahu, S. Prakash, T. Yang, R. S. Rathore, and V. K. Pandey, "A high performance hybrid LSTM CNN secure architecture for IoT environments using deep learning," Scientific Reports, vol. 15, no. 1, Mar. 2025, Art. no. 9684.
S. Khan, T. H. M. Siddique, M. S. Ibrahim, A. J. Siddiqui, and K. Huang, "Spatio-temporal deep learning for improved face presentation attack detection," Knowledge-Based Systems, vol. 311, Feb. 2025, Art. no. 113059.
A. Zaini, I. K. E. Purnama, Y. K. Suprapto, E. M. Yuniarno, "Drowsiness Classification Using ResNet50 and Time Series Transformer Based on Blink Pattern Features," International Journal of Intelligent Engineering and Systems, vol. 18, no. 1, pp. 992–1008, Feb. 2025.
S. Jayaraman and A. Mahendran, "CNN-LSTM based emotion recognition using Chebyshev moment and K-fold validation with multi-library SVM," PLOS ONE, vol. 20, no. 4, Apr. 2025, Art. no. e0320058.
Z. Sun, Y. Miao, J. Y. Jeon, Y. Kong, and G. Park, "Facial feature fusion convolutional neural network for driver fatigue detection," Engineering Applications of Artificial Intelligence, vol. 126, Nov. 2023, Art. no. 106981.
J. Shi and K. Wang, "Fatigue driving detection method based on Time-Space-Frequency features of multimodal signals," Biomedical Signal Processing and Control, vol. 84, Jul. 2023, Art. no. 104744.
S. Cao, P. Feng, W. Kang, Z. Chen, and B. Wang, "Optimized driver fatigue detection method using multimodal neural networks," Scientific Reports, vol. 15, no. 1, Apr. 2025, Art. no. 12240.
B. Liu et al., "Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems." arXiv, Aug. 02, 2025.
V. N. Thatha et al., "Optimized machine learning mechanism for big data healthcare system to predict disease risk factor," Scientific Reports, vol. 15, no. 1, Apr. 2025, Art. no. 14327.
M. Shujairi, "Developing IoT Performance in Healthcare Through the Integration of Machine Learning and Software-Defined Networking (SDN)," Babylonian Journal of Internet of Things, vol. 2025, pp. 77–88, Feb. 2025.
S. E. Merzougui, "Investigation of Enabling Mechanisms for Green Driving Via 5G-and-Beyond Mobile Networks," Ph.D. dissertation, University of Padova, Italy, 2025.
H. Li, Y. Sun, and S. Qiao, "Dynamic graph learning-based higher-order graph convolutional networks for fluid classification in oil and gas exploration," Physics of Fluids, vol. 37, no. 2, Feb. 2025, Art. no. 026620.
A. F. Tasnim et al., "Explainable Machine Learning Algorithms to Predict Cardiovascular Strokes," Engineering, Technology & Applied Science Research, vol. 15, no. 1, pp. 20131–20137, Feb. 2025.
"MRL Eye Dataset | MRL." [Online]. Available: https://mrl.cs.vsb.cz/eyedataset.html.
Y. Suresh, R. Khandelwal, M. Nikitha, M. Fayaz, and V. Soudhri, "Driver Drowsiness Detection using Deep Learning," in 2021 2nd International Conference on Smart Electronics and Communication (ICOSEC), Trichy, India, Oct. 2021, pp. 1526–1531.
R. Gandhi, A. Sharma, and A. Mohanta, "Drowsiness Detection Through Physical Cues Using Machine Learning," in Proceedings of Data Analytics and Management, 2025, pp. 317–327.
S. K. Singh, A. B., and S. Koppad, "Driver Drowsiness Detection Using Deep Learning *," in 2024 IEEE Silchar Subsection Conference (SILCON 2024), Agartala, India, Nov. 2024, pp. 1–7.
Downloads
How to Cite
License
Copyright (c) 2025 Ola Nasir, Mohammad Al Jaidi, Ayoub Alsarhan, Sami Aziz Alshammari, Nasser S. Albalawi, Nayef H. Alshammari, Amera Qasem Aldoghmi
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
