Wearable Driver Distraction Identification On-The-Road via Continuous Decomposition of Galvanic Skin Responses

Abstract

One of the main reasons for fatal accidents on the road is distracted driving. The continuous attention of an individual driver is a necessity for the task of driving. While driving, certain levels of distraction can cause drivers to lose their attention, which might lead to an accident. Thus, the number of accidents can be reduced by early detection of distraction. Many studies have been conducted to automatically detect driver distraction. Although camera-based techniques have been successfully employed to characterize driver distraction, the risk of privacy violation is high. On the other hand, physiological signals have shown to be a privacy preserving and reliable indicator of driver state, while the acquisition technology might be intrusive to drivers in practical implementation. In this study, we investigate a continuous measure of phasic Galvanic Skin Responses (GSR) using a wristband wearable to identify distraction of drivers during a driving experiment on-the-road. We first decompose the raw GSR signal into its phasic and tonic components using Continuous Decomposition Analysis (CDA), and then the continuous phasic component containing relevant characteristics of the skin conductance signals is investigated for further analysis. We generated a high resolution spectro-temporal transformation of the GSR signals for non-distracted and distracted (calling and texting) scenarios to visualize the associated behavior of the decomposed phasic GSR signal in correlation with distracted scenarios. According to the spectrogram observations, we extract relevant spectral and temporal features to capture the patterns associated with the distracted scenarios at the physiological level. We then performed feature selection using support vector machine recursive feature elimination (SVM-RFE) in order to: (1) generate a rank of the distinguishing features among the subject population, and (2) create a reduced feature subset toward more efficient distraction identification on the edge at the generalization phase. We employed support vector machine (SVM) to generate the 10-fold cross validation (10-CV) identification performance measures. Our experimental results demonstrated cross-validation accuracy of 94.81% using all the features and the accuracy of 93.01% using reduced feature space. The SVM-RFE selected set of features generated a marginal decrease in accuracy while reducing the redundancy in the input feature space toward shorter response time necessary for early notification of distracted state of the driver.

XGBoost Algorithm-Based Monitoring Model for Urban Driving Stress: Combining Driving Behaviour, Driving Environment, and Route Familiarity

“…Emotional changes will lead to changes in sweat gland secretion, which in turn will lead to changes in skin conductivity resulting in changes in the skin electrical index. Electrodermal activity is strongly correlated with mood, attention, and arousal, and researchers have widely used the electrodermal index to describe driver stress levels [46], [47]. Studies have shown that the skin conductance response should be chosen as a parameter to study when the level of psychological change is low, and the present study is a low-strain research on the change of driver stress level under normal driving conditions [48].…”

Detection of Driver Cognitive Distraction Using Machine Learning Methods

“…There are other measures such as sensitivity, precision, and training time that have been considered to compare the algorithms in some studies [25] [27] [28]. However, just accuracy was considered in this study as it was the primary measure in most papers we reviewed [68]. The accuracy metric was chosen because of the balanced nature of the classes coupled with the high numbers for true positives and true negatives in confusion matrices.…”

Human–Machine Interface in Transport Systems: An Industrial Overview for More Extended Rail Applications

“…Significant advances for the prediction of driver drowsiness and workload have been made in association with the use of more sophisticated features of physiological signals, as well as from the application of increasingly sophisticated machine learning models, although extrapolation of such to the context of commercial pilots has not yet been attempted. Some approaches have been based on EDA signal decomposition into tonic and phasic components [66], extraction of features in time, frequency, and time-frequency (wavelet based) domains [67], or the use of signal-entropy related features [68].…”