Detection of Schizophrenia from EEG Signals using Dual Tree Complex Wavelet Transform and Machine Learning Algorithms

Abstract

This research was conducted with the aim to detect schizophrenia automatically from EEG signals using machine learning algorithms. The 16 electrode EEG data were collected from the online repository where 43 schizophrenic and 39 healthy persons’ dataset is available. By applying Low Pass Filter and Total Variation Denoising method, raw EEG signals were denoised and were decomposed into beta, alpha, theta and delta waves by using Dual Tree Complex Wavelet Transform. To apply machine learning algorithms, five features: mean, median, standard deviation, energy and kurtosis were considered for all the four wave bands. With Linear Support Vector Machine and Random Forest classifier machine learning algorithms, 12 out of 16 channels were classified with test accuracy above 95% and F1 score above 90%. Among them, 7 channels were predicted with 100% test accuracy. This research thus has the potential to detect schizophrenia unsupervised and within a noticeably short period of time giving the opportunity to real time monitoring of patients. Hence, people living in remote areas or deprived of adequate healthcare professionals can be benefitted through the outcome of this research.
 Bangladesh Journal of Medical Physics Vol.15 No.1 2022 P 8-27