A Novel Method for Classifying Driver Mental Workload Under Naturalistic Conditions With Information From Near-Infrared Spectroscopy

Driver cognitive distraction is a critical factor in road safety, and its evaluation, especially under real conditions, presents challenges to researchers and engineers. We introduce a novel method for classifying cognitive distraction levels by using hemodynamic data recorded with a four-channel near-infrared spectroscopy (NIRS) device. To produce cognitive distraction in a driver, an auditory n-back task was used at three levels by changing the variation in n from 0 to 2. A total of 60 experimental data sets from the NIRS device during two driving tasks were obtained and analyzed by machine-learning algorithms. We used two techniques to prevent overfitting of the classification models: (1) k-fold cross-validation and principal-component analysis, and (2) retaining 25% of the data (holdback data) for testing of the model after classification. Six types of classifier were trained and tested: decision tree, discriminant analysis, logistic regression, the support vector machine, the nearest-neighbor classifier, and the ensemble classifier. Distraction levels were well classified from the NIRS data in the cases of subject-dependent classification (the accuracy of classification increased from 81.30% to 95.40%, and the accuracy of prediction of the holdback data was 82.18% to 96.08%), subject-independent classification (the accuracy of classification increased from 84.90% to 89.50%, and the accuracy of prediction of the holdback data increased from 84.08% to 89.91%), and channel-independent classification (classification 82.90%, prediction 82.74%). NIRS data in conjunction with an artificial-intelligence method can therefore be used to classify cognitive distraction in real time under naturalistic conditions to prevent road accidents.