Electroencephalography signal processing based on textural features for monitoring the driver's state by a Brain-Computer Interface

TL;DR

This paper introduces a novel EEG signal processing method using 1D-LBP for monitoring driver vigilance, showing promising results in classifying alertness states, though further improvements are needed for real-world application.

Contribution

It proposes a new 1D-LBP based feature extraction technique for EEG signals to detect driver vigilance levels, enhancing classification performance over previous methods.

Findings

1D-LBP improves classification accuracy for vigilance states.

Class transitions can be effectively detected from EEG micro-patterns.

Overall system performance needs enhancement for real-world deployment.

Abstract

In this study we investigate a textural processing method of electroencephalography (EEG) signal as an indicator to estimate the driver's vigilance in a hypothetical Brain-Computer Interface (BCI) system. The novelty of the solution proposed relies on employing the one-dimensional Local Binary Pattern (1D-LBP) algorithm for feature extraction from pre-processed EEG data. From the resulting feature vector, the classification is done according to three vigilance classes: awake, tired and drowsy. The claim is that the class transitions can be detected by describing the variations of the micro-patterns' occurrences along the EEG signal. The 1D-LBP is able to describe them by detecting mutual variations of the signal temporarily "close" as a short bit-code. Our analysis allows to conclude that the 1D-LBP adoption has led to significant performance improvement. Moreover, capturing the class transitions from the EEG signal is effective, although the overall performance is not yet good enough to develop a BCI for assessing the driver's vigilance in real environments.