Drowsiness Detection Using Electroencephalogram Anomaly Based on Spectral Entropy Features and Linear Classifier

Abstract

Sleeping on the wheels due to drowsiness is one of the significant causes of death tolls all over the world. The primary reason for sleepiness is due to the lack of sleep and irregular sleep patterns. Several methods such as unobtrusive sensors, vehicle dynamics and obtrusive physiology sensors are suggested to diagnose drowsiness of drivers. However, the unobtrusive sensors detect drowsiness in the later stage, whereas the physiological methods use obtrusive sensors such as electroocular, electromyogram and electroencephalograms and produce high accuracy in the early detection of drowsiness, which makes them a preferable solution. The objective of this research article is to classify drowsiness with alertness based on the electroencephalographic (EEG) signals using band power and log energy entropy features. The publicly available ULg DROZY database was used in this research. The five EEG channels from the raw multimodal signal are extracted. By using a band-pass filter with the cut-off frequencies of 0.1 and 50 Hz the high-frequency components were removed. Another band-pass filter bank is designed to slice the raw signals into eight sub-bands, namely delta, theta, low alpha, high alpha, low beta, mid beta, high beta and gamma. The preprocessed signals were segmented into an equal number of frames with a frame duration of 2 s using a rectangular time windowing approach with an overlap of 50%. Spectral entropy features were extracted for each frame in the sub-bands. The extracted feature sets were further normalized between 0 and 1 and labeled as drowsy and alert and then combined to form the final dataset. The K-fold cross-validation method is used to divide the dataset into training and testing sets. The processed dataset is then trained using, K-nearest neighbor network, and support vector machine classifiers, and the results are compared. The KNN classifier produces 95% classification accuracy.