Identification of drivers drowsiness based on features extracted from EEG signal using SVM classifier

• Published in: 3C tecnología 2021-11, p.579-595
• Main Authors: Thilagaraj, M., Rajasekaran, M. Pallikonda, Ramani, U.
• Format: Article
• Language: English
• Subjects: Brain; Butterworth filters; Classifiers; Discrete Wavelet Transform; Electroencephalography; Feature extraction; Frequencies; Signal classification; Signal processing; Signal quality; Support vector machines; Wavelet transforms
• ISSN: 2254-4143; 2254-4143
• DOI: 10.17993/3ctecno.2021.specialissue8.579-595

Electroencephalogram (EEG) is a recording machine used for storing the electrical movement of the brain. The brain waves are produced by passing electric current through the brain and that is being recorded by the Electroencephalogram. After taking the EEG signal the process of removing the noise and low-quality signal is carried out by using the Butterworth filter and that process is known as Preprocessing. Then the signal is segmented with the help of Discrete Wavelet Transform (DWT) so that the signals are segmented into five primary frequency bands (delta, theta, alpha, beta, and gamma). Finally, the EEG signals were classified based on the statistical features obtained from the different segments of the EEG signals using Support Vector Machine Classifier. SVM maps input vector to a high dimensional space where a finest hyper plane is developed. Among the numerous hyper planes accessible, there is only one hyper plane that amplifies the separation among itself and the closest information vectors of every class. The identification of the fatigue based on the features extracted using SVM is more efficient compared to the other feature extraction methods employed for the analysis of the signals.