Driver fatigue is increasingly a contributing factor for traffic accidents, so an effective method to automatically detect driver fatigue is urgently needed. In this study, in order to catch the main characteristics of the EEG signals, four types of entropies (based on the EEG signal of a single channel) were calculated as the feature sets, including sample entropy, fuzzy entropy, approximate entropy and spectral entropy. All feature sets were used as the input of a gradient boosting decision tree (GBDT), a fast and highly accurate boosting ensemble method. The output of GBDT determined whether a driver was in a fatigue state or not based on their EEG signals. Three state-of-the-art classifiers, k-nearest neighbor, support vector machine and neural network were also employed. To assess our method, several experiments including parameter setting and classification performance comparison were performed on 22 subjects. The results indicated that it is possible to use only one EEG channel to detect a driver fatigue state. The average highest recognition rate in this work was up to 94.0%, which could meet the needs of daily applications. Our GBDT-based method may assist in the detection of driver fatigue.
Driver fatigue Electroencephalogram (EEG) Gradient boosted decision tree (GBDT) Entropy
This is a preview of subscription content, log in to check access.
This work was supported by Supported by National Natural Science Foundation of China (61762045), Natural Science Foundation of Jiangxi Province, China (Nos. 20151BBE50079, 20171BAB202031), Educational Commission of Jiangxi Province, China (Nos. GJJ151146, GJJ161143) and Postdoctoral Assistance Project of Jiangxi Province, China (2017KY33). Thanks ZD Mu and P Wang for collecting and preprocessing EEG data.
Compliance with ethical standards
Conflict of interest
The author declares no conflicts of interest.
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.
Azarnoosh M, Nasrabadi AM, Mohammadi MR, Firoozabadi M (2011) Investigation of mental fatigue through EEG signal processing based on nonlinear analysis: symbolic dynamics. Chaos Solitons Fractals 44(12):1054–1062CrossRefGoogle Scholar
Bauer E, Kohavi R (1999) An empirical comparison of voting classification algorithms: Bagging, boosting, and variants. Mach Learn 36(1–2):105–139CrossRefGoogle Scholar
Borg G (1990) Psychophysical scaling with applications in physical work and the perception of exertion. Scand J Work Environ Health 16:55–58CrossRefPubMedGoogle Scholar
Bradley A (1997) The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recogn 30(7):1145–1159CrossRefGoogle Scholar
Chai R, Naik G, Nguyen TN, Ling S, Tran Y, Craig A, Nguyen H (2016) Driver fatigue classification with independent component by entropy rate bound minimization analysis in an EEG-based system. IEEE J of Biomed Health Inf. https://doi.org/10.1109/JBHI.2016.2532354Google Scholar
Correa AG, Orosco L, Laciar E (2014) Automatic detection of drowsiness in EEG records based on multimodal analysis. Med Eng Phys 36(2):244–249CrossRefGoogle Scholar
Craig A, Tran Y, Wijesuriya N, Nguyen H (2012) Regional brain wave activity changes associated with fatigue. Psychophysiology 49:574–582CrossRefPubMedGoogle Scholar
Dietrich A, Kanso R (2010) A review of EEG, ERP, and neuroimaging studies of creativity and insight. Psychol Bull 136(5):822–848CrossRefPubMedGoogle Scholar
Donoghue S, Garcia M, Jordan D et al (2015) Transition dynamics of EEG-based network microstates during mental arithmetic and resting wakefulness reflects task-related modulations and developmental changes. Cogn Neurodyn 9(4):371–387CrossRefGoogle Scholar
Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29(5):1189–1232CrossRefGoogle Scholar
Fu RR, Wang H (2014) Detection of driver fatigue by using noncontact EMG and ECG signals measurement system. Int J Neural Syst 24(24):478–491Google Scholar
Fu RR, Wang H, Zhao WB (2016) Dynamic driver fatigue detection using hidden Markov model in real driving condition. Expert Syst Appl 63:397–411CrossRefGoogle Scholar
Hassan AR, Subasi A (2016) Automatic identification of epileptic seizures from EEG signals using linear programming boosting. Comput Methods Prog Biomed 136:65–77CrossRefGoogle Scholar
Hastie T, Tibshirani R, Friedman JH (2009) Elements of Statistical Learning, vol 2. Springer, BerlinCrossRefGoogle Scholar
Hu JF, Mu ZD, Wang P (2015) Multi-feature authentication system based on event evoked electroencephalogram. J Med Imaging Health Inf 5(4):862–870CrossRefGoogle Scholar
Jo J, Lee SJ, Park KR, Kim IJ, Kim J (2014) Detecting driver drowsiness using feature-level fusion and user-specific classification. Expert Syst Appl 41(4):1139–1152CrossRefGoogle Scholar
Kannathal N, Choo ML, Acharya UR, Sadasivan P (2005) Entropies for detection of epilepsy in EEG. Comput Methods Prog Biomed 80(3):187–194CrossRefGoogle Scholar
Kar S, Bhagat M, Routray A (2010) EEG signal analysis for the assessment and quantification of driver’s fatigue. Transp Res F 13(5):297–306CrossRefGoogle Scholar
Richman JS, Moorman JR (2000) Physiological time-series analysis using approximate entropy and sample entropy. Am J Physiol Heart Circ Physiol 278(6):H2039–H2049CrossRefPubMedGoogle Scholar
Sahayadhas A, Sundaraj K, Murugappan M (2012) Detecting driver drowsiness based on sensors: a review. Sensors 12(12):16937–16953CrossRefPubMedGoogle Scholar
Saini V, Saini R (2014) Driver drowsiness detection system and techniques: a review. Comput Sci Inf Technol 3:4245–4249Google Scholar
Shalbaf R, Behnam H, Jelveh MH (2015) Monitoring depth of anesthesia using combination of EEG measure and hemodynamic variables. Cogn Neurodyn 9(1):41–51CrossRefPubMedGoogle Scholar
Shen KQ, Ong CJ, Li XP, Hui Z (2007) A feature selection method for multilevel mental fatigue EEG classification. IEEE Trans Biomed Eng 54(7):1231–1237CrossRefPubMedGoogle Scholar
Silveira TLTD, Kozakevicius AJ, Rodrigues CR (2016) Automated drowsiness detection through wavelet packet analysis of a single EEG channel. Expert Syst Appl 55:559–565CrossRefGoogle Scholar
Sokolova M, Japkowicz N, Szpakowicz S (2006). Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation. In: AI2006: advances in artificial intelligence. Springer, pp 1015–1021Google Scholar
Song Y, Crowcroft J, Zhang J (2012) Automatic epileptic seizure detection in EEGs based on optimized sample entropy and extreme learning machine. J Neurosci Methods 210(2):132–146CrossRefPubMedGoogle Scholar
Swapna G, Swapna G, Swapna G et al (2013) Automated EEG analysis of epilepsy: a review. Knowl Based Syst 45(3):147–165Google Scholar
Wang H (2015). Detection and alleviation of driving fatigue based on EMG and EMS/EEG using wearable sensor. In: Proceedings of the 5th EAI international conference on wireless mobile communication and healthcare, pp 155–157Google Scholar
Wang H, Dragomir A, Abbasi NI et al (2018) A novel real-time driving fatigue detection system based on wireless dry EEG. Cogn Neurodyn 8:1–12Google Scholar
Xiang J, Li CG, Li HF, Cao R, Han XH, Chen JJ (2015) The detection of epileptic seizure signals based on fuzzy entropy. J Neurosci Methods 243:18–25CrossRefPubMedGoogle Scholar
Xiong Y, Gao J, Yang Y, Yu X, Huang W (2016) Classifying driving fatigue based on combined entropy measure using EEG signals. Int J Control Autom 9(3):329–338CrossRefGoogle Scholar
Yang T, Chen WT, Cao GT (2016) Automated classification of neonatal amplitude-integrated EEG based on gradient boosting method. Biomed Signal Process Control 28:50–57CrossRefGoogle Scholar
Yentes JM, Hunt N, Schmid KK, Kaipust JP, Mcgrath D, Stergiou N (2013) The appropriate use of approximate entropy and sample entropy with short data sets. Ann Biomed Eng 41(2):349–365CrossRefPubMedGoogle Scholar