Computational Intelligence for Detection of Distracted Driving
This study focuses on introducing brain connectivity estimators as features for detecting driver distraction. In Stage One, I examined the statistical differences in these connectivity measures to assess their viability compared to traditional frequency-domain features. Stage Two involved a systematic comparison between the proposed brain connectivity estimators and commonly used EEG features, such as power spectral density, to evaluate their effectiveness in distraction detection. Stage Three and Stage Four is currently under review for journal publication, and the outcomes will be updated here once the findings are published.
Publications
This paper presents comparison of brain connectivity estimators of distracted drivers and non-distracted drivers based on statistical analysis. Twelve healthy volunteers with more than one year of driving experience participated in this experiment. Lane-keeping tasks and the Math problem-solving task were introduced in the experiment and EEGs (electroencephalogram) were used to record the brain waves. Granger-Geweke causality (GGC), directed transfer function (DTF) and partial directed coherence (PDC) brain connectivity estimation methods were used in brain connectivity analysis. Correlation test and a student’s t-test were conducted on the connectivity matrixes. Results show a significant difference between the mean of distracted drivers and non-distracted driver’s brain connectivity matrixes. GGC and DTF methods student’s t-tests shows a p-value below 0.05 with the correlation coefficients varying from 0.
This paper discusses a novel approach to an EEG (electroencephalogram)-based driver distraction classification by using brain connectivity estimators as features. Ten healthy volunteers with more than one year of driving experience and an average age of 24.3 participated in a virtual reality environment with two conditions, a simple math problem-solving task and a lane-keeping task to mimic the distracted driving task and a non-distracted driving task, respectively. Independent component analysis (ICA) was conducted on the selected epochs of six selected components relevant to the frontal, central, parietal, occipital, left motor, and right motor areas. Granger–Geweke causality (GGC), directed transfer function (DTF), partial directed coherence (PDC), and generalized partial directed coherence (GPDC) brain connectivity estimators were used to calculate the connectivity matrixes. These connectivity matrixes were used as features to train the support vector machine (SVM) with the radial basis function (RBF) and classify the distracted and non-distracted driving tasks. GGC, DTF, PDC, and GPDC connectivity estimators yielded the classification accuracies of 82.27%, 70.02%, 86.19%, and 80.95%, respectively. Further analysis of the PDC connectivity estimator was conducted to determine the best window to differentiate between the distracted and non-distracted driving tasks. This study suggests that the PDC connectivity estimator can yield better classification accuracy for driver distractions