Using EEG to detect driving fatigue based on common spatial pattern and support vector machine

To investigate the correlation between electroencephalogram (EEG) and driving fatigue states, this study used machine learning algorithms to detect driving fatigue based on EEG. 14 channels of EEG data were collected from thirty-four healthy subjects in this research at Northeastern University. Each subject participated in two scenarios (baseline and fatigue scenarios). Subjective ratings of fatigue levels were also obtained from the subjects using the NASA-Task Load Index (TLX). The common spatial pattern (CSP) algorithm was used to extract features from the raw EEG data. The support vector machine (SVM) was used as the classifier in the design of the machine learning algorithm. A grid search cross validation was exploited to find optimal hyperparameter settings. The best classification result was 90%, obtained by using all 14 EEG channels and linear kernel of SVM. The experimental results proved that a machine learning algorithm was able to reliably classify driving fatigue states using EEG data. This study demonstrated that CSP and SVM were promising in detecting driving fatigue, and therefore, they could be strong foundations for future efforts to reduce traffic accidents and save thousands of human lives.

PDF

___

[1] Taylor AH, Dorn L. Stress, fatigue, health, and risk of road traffic accidents among professional drivers: the contribution of physical inactivity. Public Health 2006; 27: 371-391.
[2] National Highway Traffic Safety Administration. Traffic Safety Facts: Drowsy Driving (Rep. No. DOT-HS-811-449). Washington, DC, USA: NHTSA. 2011.
[3] Craft R, Blower D. The large truck crash causation study. In: 2004 R&T Stakeholder Forum, Arlington, VA. 2004.
[4] Yang G, Lin Y, Bhattacharya P. A driver fatigue recognition model based on information fusion and dynamic Bayesian network. Information Sciences 2010; 180 (10): 1942-54.
[5] Lin Y, “i-DRIVE, are we ready?,” Journal of Automotive Safety and Energy 2016; 7 (1):14-24.
[6] Lin Y. Toward intelligent human machine interactions. Mechanical Engineering 2017; 139 (06): S4-8.
[7] Cai H, Lin Y. Coordinating cognitive assistance with cognitive engagement control approaches in human–machine collaboration. IEEE Transactions on Systems, Man, and Cybernetics 2011; 42 (2): 286-94.
[8] Lal SK, Craig A. A critical review of the psychophysiology of driver fatigue. Biological Psychology 2001; 55(3): 173-94.
[9] Simon M, Schmidt EA, Kincses WE, Fritzsche M, Bruns A et al. EEG alpha spindle measures as indicators of driver fatigue under real traffic conditions. Clinical Neurophysiology 2011; 122 (6): 1168-78.
[10] Kar S, Bhagat M, Routray A. EEG signal analysis for the assessment and quantification of driver’s fatigue. Transportation Research Part F: Traffic Psychology and Behaviour 2010; 13 (5): 297-306.
[11] Yeo MV, Li X, Shen K, Wilder-Smith EP. Can SVM be used for automatic EEG detection of drowsiness during car driving?. Safety Science 2009; 47(1): 115-24.
[12] Lal SK, Craig A, Boord P, Kirkup L, Nguyen H. Development of an algorithm for an EEG-based driver fatigue countermeasure. Journal of Safety Research 2003; 34 (3): 321-8.
[13] Lal SK, Craig A. Driver fatigue: electroencephalography and psychological assessment. Psychophysiology 2002; 39 (3): 313-21.
[14] Lu H, Eng HL, Guan C, Plataniotis KN, Venetsanopoulos AN. Regularized common spatial pattern with aggregation for EEG classification in small-sample setting. IEEE Transactions on Biomedical Engineering 2010; 57 (12): 2936-46.
[15] Ramoser H, Muller-Gerking J, Pfurtscheller G. Optimal spatial filtering of single trial EEG during imagined hand movement. IEEE Transactions on Rehabilitation Engineering 2000; 8 (4): 441-6.
[16] Koles ZJ, Lazar MS, Zhou SZ. Spatial patterns underlying population differences in the background EEG. Brain Topography 1990; 2 (4): 275-84.
[17] Müller-Gerking J, Pfurtscheller G, Flyvbjerg H. Designing optimal spatial filters for single-trial EEG classification in a movement task. Clinical Neurophysiology 1999; 110 (5): 787-98.
[18] Ang KK, Chin ZY, Wang C, Guan C, Zhang H. Filter bank common spatial pattern algorithm on BCI competition IV datasets 2a and 2b. Frontiers in Neuroscience 2012; 6:39.
[19] Wang Y, Gao S, Gao X. Common spatial pattern method for channel selelction in motor imagery based braincomputer interface. In: 2005 IEEE Engineering in Medicine and Biology Conference; 2006. pp. 5392-5395
[20] Ince NF, Gupta R, Arica S, Tewfik AH, Ashe J et al. High accuracy decoding of movement target direction in non-human primates based on common spatial patterns of local field potentials. PloS One 2010; 5 (12): e14384.
[21] Tarabalka Y, Fauvel M, Chanussot J, Benediktsson JA. SVM-and MRF-based method for accurate classification of hyperspectral images. IEEE Geoscience and Remote Sensing Letters 2010; 7 (4): 736-40.
[22] Moavenian M, Khorrami H. A qualitative comparison of artificial neural networks and support vector machines in ECG arrhythmias classification. Expert Systems with Applications 2010; 37 (4): 3088-93.
[23] Palaniappan R, Sundaraj K, Sundaraj S. A comparative study of the svm and k-nn machine learning algorithms for the diagnosis of respiratory pathologies using pulmonary acoustic signals. BMC Bioinformatics 2014; 15 (1): 223.
[24] Fraser GD, Chan AD, Green JR, MacIsaac DT. Automated biosignal quality analysis for electromyography using a one-class support vector machine. IEEE Transactions on Instrumentation and Measurement 2014; 63 (12): 2919-30.
[25] Liu Y, Zhou W, Yuan Q, Chen S. Automatic seizure detection using wavelet transform and SVM in long-term intracranial EEG. IEEE Transactions on Neural Systems and Rehabilitation Engineering 2012; 20 (6): 749-55.
[26] Gardner AB, Krieger AM, Vachtsevanos G, Litt B. One-class novelty detection for seizure analysis from intracranial EEG. Journal of Machine Learning Research 2006; 7 (7): 1025-44.
[27] Wan P, Wu C, Lin Y, Ma X. A recognition model of driving anger based on physiological features by ROC curve analysis. In: Transportation Research Board 95th Annual Meeting, Washington DC, USA; 2016. pp.16-5500
[28] Jasper HH. The ten-twenty electrode system of the International Federation. Electroencephalography and Clinical Neurophysiology 1958; 10: 370-5.
[29] Artaud P, Planque S, Lavergne C, Cara H, Tarriere C, et al. An on-board system for detecting lapses of alertness in car driving. In: International Technical Conference on the Enhanced Safety of Vehicles; 1995. pp. 350-359.
[30] Spring B, Maller O, Wurtman J, Digman L, Cozolino L. Effects of protein and carbohydrate meals on mood and performance: interactions with sex and age. Journal of Psychiatric Research 1982; 17 (2): 155-67.
[31] Lieberman HR. Behavioral Changes Caused by Nutrients1. Nutrition and Neurobiology 1986; 38: 219-224
[32] Hart, SG, Lowell ES. Development of NASA-TLX (Task Load Index): Results of empirical and theoretical research. Advances in Psychology 1988; 52: 139-183.
[33] Boser BE, Guyon IM, Vapnik VN. A training algorithm for optimal margin classifiers. In Proceedings of the fifth annual workshop on Computational Learning Theory 1992; 7(1): 144-152.
[34] Vapnik V. The nature of statistical learning theory. Springer Science & Business Media; 2013.
[35] Cortes C, Vapnik V. Support vector machine. Machine learning 1995; 20 (3): 273-97.
[36] McMonnies CW. Incomplete blinking: exposure keratopathy, lid wiper epitheliopathy, dry eye, refractive surgery, and dry contact lenses. Contact Lens and Anterior Eye 2007; 30 (1): 37-51.
[37] Chaudhuri A, and Routray A. Driver fatigue detection through chaotic entropy analysis of cortical sources obtained from scalp EEG signals. IEEE Transactions on Intelligent Transportation Systems 2019; 21 (1): 185-198.
[38] San PP, Ling SH, Chai R, Tran Y, Craig A et al. EEG-based driver fatigue detection using hybrid deep generic model. In: 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); 2016. pp. 800-803.
[39] Xiong YJ, Zhang R, Zhang C, Yu XL. A novel estimation method of fatigue using EEG based on KPCA-SVM and complexity parameters. Applied Mechanics and Materials 2013; 373: 965-969.
[40] Hu S, Zheng G, Peters B. Driver fatigue detection from electroencephalogram spectrum after electrooculography artefact removal. IET Intelligent Transport Systems 2013; 7 (1): 105-113.
[41] Zhang C, Yu X. Estimating mental fatigue based on electroencephalogram and heart rate variability. Polish Journal of Medical Physics and Engineering 2010; 16 (2): 67-84.