Detection of steering direction using EEG recordings based on sample entropy and time-frequency analysis

Monitoring driver's intentions beforehand is an ambitious aim, which will bring a huge impact on the society by preventing traffic accidents. Hence, in this preliminary study we recorded high resolution electroencephalography (EEG) from 5 subjects while driving a car under real conditions along with an accelerometer which detects the onset of steering. Two sensor-level analyses, sample entropy and time-frequency analysis, have been implemented to observe the dynamics before the onset of steering. Thus, in order to classify the steering direction we applied a machine learning algorithm consisting of: dimensionality reduction and classification using principal-component-analysis (PCA) and support-vector-machine (SVM), respectively. The results showed an increase of the sample entropy and the estimated power values in the theta and alpha frequency bands, 100 ms before the onset of steering. The detection of steering direction depicted that sample entropy gives a higher classification accuracy (73.5% ±6.8) as compared to that of using the estimated power for theta and alpha frequency bands (62.6% ±5.6).