PERFORMANCE OPTIMIZATION OF DRIVER FATIGUE CLASSIFICATION USING HYBRID DBN-DQN
DOI:
https://doi.org/10.11113/jurnalteknologi.v87.23193Keywords:
Driver fatigue, electroencephalogram (EEG), modified z-score, hybrid deep learning, deep belief network (DBN), deep Q-network (DQNAbstract
Driver fatigue is one of the significant risk factors that occur on the roads; therefore, there is a need to have efficient detection systems. Existing detection systems face noise interference in EEG data, limited generalizability, and high computational requirements. This paper outlines the procedure to classify driver fatigue into different levels by developing a DBN-DQN model coupled with the improved Morlet wavelet transform and a z-score technique to increase recognition efficiency and address these challenges. The DBN-DQN model achieves outstanding results: 99.95% accuracy, 99. 91% precision, 99. 99% recall rate, while the F1-score was 99.95%. Results of the ROC curve of each fold further validate the model with an AUC of 1.00, distinguishing that the technique proved effective for identifying driver fatigue.
References
Dargan, S., Kumar, M., Ayyagari, M. R., & Kumar, G. 2020. A Survey of Deep Learning and Its Applications: A New Paradigm to Machine Learning. Archives of Computational Methods in Engineering. 27(4): 1071–1092.
Guo, S., Zhang, X., Du, Y., Zheng, Y., & Cao, Z. 2021. Path Planning of Coastal Ships Based on Optimised DQN Reward Function. Journal of Marine Science and Engineering. 9: 210.
Shao, H., Xia, M., Wan, J., & De Silva, C. W. 2022. Modified Stacked Autoencoder Using Adaptive Morlet Wavelet for Intelligent Fault Diagnosis of Rotating Machinery. IEEE/ASME Transactions on Mechatronics. 27(1): 24–33.
Wu, M., Sun, M., Zhang, F., Wang, L., Zhao, N., Wang, J., & Huang, W. 2023. A Fault Detection Method of Electric Vehicle Battery through Hausdorff Distance and Modified Z-score for Real-world Data. Journal of Energy Storage. 60: 106561.
Sheykhivand, S., Rezaii, T. Y., Meshgini, S., Makoui, S., & Farzamnia, A. 2022. Developing a Deep Neural Network for Driver Fatigue Detection Using EEG Signals based on Compressed Sensing. Sustainability. 14(5): 2941.
Abbas, Q. 2020. HybridFatigue: A Real-time Driver Drowsiness Detection using Hybrid Features and Transfer Learning. International Journal of Advanced Computer Science and Applications. 11(1): 585–593.
Ming, Y., Wu, D., Wang, Y. K., Shi, Y., & Lin, C. T. 2021. EEG-Based Drowsiness Estimation for Driving Safety Using Deep Q-Learning. IEEE Transactions on Emerging Topics in Computational Intelligence. 5(4): 583–594.
Zainuddin, A., Mansor, W., Lee, K., & Mahmoodin, Z. 2022. Machine Learning and Deep Learning Performance in Classifying Dyslexic Children’s Electroencephalogram during Writing. International Journal of Electrical and Computer Engineering (IJECE). 12(6): 6614.
Bhardwaj, H., Tomar, P., Sakalle, A., & Ibrahim, W. 2021. EEG-Based Personality Prediction Using Fast Fourier Transform and DeepLSTM Model. Computational Intelligence and Neuroscience. 2021.
Li, R., Lan, Z., Cui, J., Sourina, O., & Wang, L. 2020. EEG-based Recognition of Driver State Related to Situation Awareness Using Graph Convolutional Networks. Proceedings - 2020 International Conference on Cyberworlds, CW 2020. 180–187.
Wang, F., Wan, Y., Li, M., Huang, H., Li, L., Hou, X., Pan, J., Wen, Z., & Li, J. 2022. Recent Advances in Fatigue Detection Algorithm Based on EEG. Intelligent Automation & Soft Computing. 35(3): 3573–3586.
Cui, J., Peng, Y., Ozawa, K., & Kong, W. 2021. A Review of Transfer Learning for EEG-Based Driving Fatigue Detection. Communications in Computer and Information Science. 1369 CCIS: 149–162.
Li, Z., Fields, M., Panov, F., Ghatan, S., Yener, B., & Marcuse, L. 2021. Deep Learning of Simultaneous Intracranial and Scalp EEG for Prediction, Detection, and Lateralization of Mesial Temporal Lobe Seizures. Frontiers in Neurology. 12: 705119.
Yoo, G., Kim, H., & Hong, S. 2023. Prediction of Cognitive Load from Electroencephalography Signals using Long Short-term Memory Network. Bioengineering. 10(3): 361.
Sheykhivand, S., Rezaii, T. Y., Mousavi, Z., Meshgini, S., Makouei, S., Farzamnia, A., Danishvar, S., & Teo Tze Kin, K. 2022. Automatic Detection of Driver Fatigue based on EEG Signals Using a Developed Deep Neural Network. Electronics. 11(14): 2169.
Patil, V., Saxena, J., Vineetha, R., Paul, R., Shetty, D. K., Sharma, S., Smriti, K., Singhal, D. K., & Naik, N. 2023. Age Assessment through Root Lengths of Mandibular Second and Third Permanent Molars Using Machine Learning and Artificial Neural Networks. Journal of Imaging. 9(2).
Xie, Q., Chen, P., Li, Z., & Xie, R. 2023. Automatic Segmentation and Classification for Antinuclear Antibody Images based on Deep Learning. Computational Intelligence and Neuroscience. 2023: 1–9.
Ege, D., Sertturk, S., Acarkan, B., & Ademoglu, A. 2023. Machine Learning Models to Predict the Relationship between Printing Parameters and Tensile Strength of 3d Poly (Lactic Acid) Scaffolds for Tissue Engineering Applications. Biomedical Physics & Engineering Express. 9(6): 065014.
Rashid, M., Mustafa, M., Sulaiman, N., Abdullah, N. R. H., & Samad, R. 2021. Random Subspace K-NN Based Ensemble Classifier for Driver Fatigue Detection Utilising Selected EEG Channels. Traitement Du Signal. 38(5): 1259–1270.
Abdubrani, R., Mustafa, M., & Zahari, Z. L. 2023. Enhancement of Morlet Mother Wavelet in Time–Frequency Domain in Electroencephalogram (EEG) Signals for Driver Fatigue Classification. Lecture Notes in Electrical Engineering. 988.
Abdubrani, R., Mustafa, M., & Zahari, Z. L. 2023. A Robust Framework for Driver Fatigue Detection from EEG Signals Using Enhancement of Modified Z-Score and Multiple Machine Learning Architectures. IIUM Engineering Journal. 24(2): 354–372.
Sedik, A., Marey, M., & Mostafa, H. 2023. WFT-Fati-Dec: Enhanced Fatigue Detection AI System Based on Wavelet Denoising and Fourier Transform. Applied Sciences. 13(5): 2785.
Lee, C., & An, J. 2023. LSTM-CNN Model of Drowsiness Detection from Multiple Consciousness States Acquired by EEG. Expert Systems with Applications. 213: 119032.
Zhu, M., Li, H., Chen, J., Kamezaki, M., Zhang, Z., Hua, Z., & Sugano, S. 2021. EEG-based System Using Deep Learning and Attention Mechanism for Driver Drowsiness Detection. 2021 IEEE Intelligent Vehicles Symposium Workshops (IV Workshops). 280–286.
Latreche, I., Slatnia, S., & Kazar, O. 2022. CNN-LSTM To Identify the Most Informative EEG-based Driver Drowsiness Detection Brain Region. 2022 International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT). 725–730.
Downloads
Published
Issue
Section
License
Copyright of articles that appear in Jurnal Teknologi belongs exclusively to Penerbit Universiti Teknologi Malaysia (Penerbit UTM Press). This copyright covers the rights to reproduce the article, including reprints, electronic reproductions, or any other reproductions of similar nature.
