Research on driving fatigue detection based on improved dense connection convolutional network

Yixin Zhi; Mengyao Li

doi:10.54254/2977-3903/2025.25535

Advances in Engineering InnovationOpen access

Research on driving fatigue detection based on improved dense connection convolutional network

Research Article

Open Access

Research on driving fatigue detection based on improved dense connection convolutional network

Yixin Zhi ^1* Mengyao Li ²

¹ Henan University of Economics and Law

² Henan University of Economics and Law

^*Corresponding author: zhiyixin2026@163.com

Published on 23 July 2025

AEI Vol.16 Issue 7

ISSN (Print): 2977-3911

ISSN (Online): 2977-3903

Download Cover

Abstract

Driving fatigue is one of the major contributors to traffic accidents and poses a serious threat to road safety. Traditional driving fatigue detection methods suffer from limitations such as low classification accuracy, insufficient generalization ability, and poor noise resistance. To address these issues, this study proposes a novel driving fatigue detection approach based on an improved dense connection convolutional network. This method innovatively utilizes raw Electroencephalogram (EEG) signals as input to the model without requiring any data preprocessing, thereby enabling end-to-end feature extraction and classification. The network enhances information flow within dense blocks to promote feature reuse, employs multi-scale convolutional layers for feature extraction, and integrates an attention mechanism to assign adaptive weights to multi-scale feature channels. After completing primary feature extraction through stacked dense blocks and pooling layers, a multi-class classification function is applied to detect driving fatigue. Experimental results on the SEED-VIG driving fatigue dataset show that the proposed method achieves an accuracy of 97.32%, a precision of 96.43%, a recall of 95.78%, and an F1-score of 96.10%. Compared to traditional approaches such as Convolutional Neural Networks (CNN) and Long Short-Term Memory Networks (LSTM), the accuracy improves by 5.14% and 3.45%, respectively. This study demonstrates that the proposed method has significant practical value: on one hand, the end-to-end architecture greatly simplifies the complex feature engineering required by traditional methods; on the other hand, the incorporation of feature reuse and attention mechanisms substantially enhances the model’s classification performance and generalization capability, providing a new technical perspective for intelligent driving safety monitoring.

Keywords:

driving fatigue, dense connection convolutional network, EEG signals, dense block, accuracy

View PDF

References

[1]. Aravinth, S. S., Nagamani, G., Kumar, C. K., Lasisi, A., Naveed, Q. N., Bhowmik, A., & Khan, W. A. (2025). Dynamic cross-domain transfer learning for driver fatigue monitoring: Multi-modal sensor fusion with adaptive real-time personalizations.Scientific Reports, 15(1), 1–20.

[2]. Yogarayan, S., Razak, S. F. A., Mogan, J. N., Azman, A., & Sivaprakasam, A. (2025). Alertness analytics: AI-enhanced detection of driver fatigue and intoxication. InThe smart life revolution(pp. 21–44). CRC Press.

[3]. Li, D., Zhang, X., Liu, X., Ma, Z., & Zhang, B. (2023). Driver fatigue detection based on comprehensive facial features and gated recurrent unit.Journal of Real-Time Image Processing, 20(2), 19.

[4]. Li, Q. (2024). Advancements in driver fatigue detection: A comprehensive analysis of eye movement and facial feature approaches.Applied and Computational Engineering, 65, 75–80.

[5]. Ekinci, E., Kahraman, K., & Oturakci, M. (2025). Enhancing driver safety: Integrating ECG and CAN-Bus data for accurate drowsiness detection.Traitement du Signal, 42(2), 1057.

[6]. Chang, H., & Park, D. (2020). Potentialities of vehicle trajectory big data for monitoring potentially fatigued drivers and explaining vehicle crashes on motorway sections.Sustainability, 12(15), 5877.

[7]. Li, W. (2024). Driver fatigue detection method based on facial features using deep learning.Applied and Computational Engineering, 57, 190–199.

[8]. Kassem, H. A., Chowdhury, M., & Abawajy, J. H. (2021). Drivers fatigue level prediction using facial and head behavior information.IEEE Access, 9, 121686–121697.

[9]. Wang, J., Cai, M., Zhu, Z., Ding, H., Yi, J., & Du, A. (2025). VTD: Visual and tactile dataset for driver state and behavior detection.IEEE Robotics and Automation Letters.

[10]. Pan, Y., Dong, Y., Wang, D., Cao, S., & Chen, A. (2024). Comparative study on fatigue evaluation of suspenders by introducing actual vehicle trajectory data.Scientific Reports, 14(1), 5165.

[11]. Zhang, T., Chen, J., He, E., & Wang, H. (2021). Sample-entropy-based method for real driving fatigue detection with multichannel electroencephalogram.Applied Sciences, 11(21), 10279.

[12]. Wang, F., Wang, H., Zhou, X., & Fu, R. (2022). A driving fatigue feature detection method based on multifractal theory.IEEE Sensors Journal, 22(19), 19046–19059.

[13]. Han, C., Yang, Y., Sun, X., & Qin, Y. (2018, October). Complexity analysis of EEG signals for fatigue driving based on sample entropy. In2018 11th International Congress on Image and Signal Processing, Biomedical Engineering and Informatics (CISP-BMEI)(pp. 1–9). IEEE.

[14]. Qin, Y., Hu, Z., Chen, Y., Liu, J., Jiang, L., Che, Y., & Han, C. (2022). Directed brain network analysis for fatigue driving based on EEG source signals.Entropy, 24(8), 1093.

[15]. Xiang, W., Wu, X., Li, C., Zhang, W., & Li, F. (2022). Driving fatigue detection based on the combination of multi-branch 3D-CNN and attention mechanism.Applied Sciences, 12(9), 4689.

[16]. Quddus, A., Zandi, A. S., Prest, L., & Comeau, F. J. (2021). Using long short term memory and convolutional neural networks for driver drowsiness detection.Accident Analysis & Prevention, 156, 106107.

[17]. Ed-Doughmi, Y., Idrissi, N., & Hbali, Y. (2020). Real-time system for driver fatigue detection based on a recurrent neuronal network.Journal of Imaging, 6(3), 8.

[18]. Zheng, W. L., & Lu, B. L. (2017). A multimodal approach to estimating vigilance using EEG and forehead EOG.Journal of Neural Engineering, 14(2), 026017.

[19]. Zhou, F., Alsaid, A., Blommer, M., Curry, R., Swaminathan, R., Kochhar, D., ... & Lei, B. (2020). Driver fatigue transition prediction in highly automated driving using physiological features.Expert Systems with Applications, 147, 113204.

[20]. Cao, Z., Chuang, C. H., King, J. K., & Lin, C. T. (2019). Multi-channel EEG recordings during a sustained-attention driving task.Scientific Data, 6(1), 19.

[21]. Nanni, L., Lumini, A., Ghidoni, S., & Maguolo, G. (2020). Stochastic selection of activation layers for convolutional neural networks.Sensors, 20(6), 1626.

[22]. Li, G., Zhang, M., Li, J., Lv, F., & Tong, G. (2021). Efficient densely connected convolutional neural networks.Pattern Recognition, 109, 107610.

[23]. Naidu, G., Zuva, T., & Sibanda, E. M. (2023, April). A review of evaluation metrics in machine learning algorithms. InComputer science on-line conference(pp. 15–25). Cham: Springer International Publishing.

[24]. Xiang, W., Wu, X., Li, C., Zhang, W., & Li, F. (2022). Driving fatigue detection based on the combination of multi-branch 3D-CNN and attention mechanism.Applied Sciences, 12(9), 4689.

[25]. Quddus, A., Zandi, A. S., Prest, L., & Comeau, F. J. (2021). Using long short term memory and convolutional neural networks for driver drowsiness detection.Accident Analysis & Prevention, 156, 106107.

[26]. Kır Savaş, B., & Becerikli, Y. (2022). Behavior-based driver fatigue detection system with deep belief network.Neural Computing and Applications, 34(16), 14053–14065.

[27]. Ed-Doughmi, Y., Idrissi, N., & Hbali, Y. (2020). Real-time system for driver fatigue detection based on a recurrent neuronal network.Journal of Imaging, 6(3), 8.

[28]. Zhang, W., Wang, F., Wu, S., Xu, Z., Ping, J., & Jiang, Y. (2020). Partial directed coherence based graph convolutional neural networks for driving fatigue detection.Review of Scientific Instruments, 91(7).

[29]. Tan, Y. S., Lim, K. M., & Lee, C. P. (2021). Hand gesture recognition via enhanced densely connected convolutional neural network.Expert Systems with Applications, 175, 114797.

[30]. Li, G., Zhang, M., Li, J., Lv, F., & Tong, G. (2021). Efficient densely connected convolutional neural networks.Pattern Recognition, 109, 107610.