Single Channel Electroencephalogram Feature Extraction Based on Probability Density Function for Synchronous Brain Computer Interface

Abstract

Over recent years, there has been an explosive growth of interest in Electroencephalogram (EEG) based-Brain Computer Interface (BCI). Technically any architecture of a BCI is designed to have the ability of extracting out a set of features from brain signal. This paper demonstrated the extraction process based on Probability Density Function (PDF).A shared control scheme was developed between a mobile robot and subject. In general, subjects were required to synchronously imagine a star rotating and mind relaxation at specific time and direction. The imagination of a star would trigger a mobile robot suggesting that there is an object at certain direction. The mobile robot was then looking for a target based on probability value assigned to it. The result shows that 95% of theta activity was concentrated at target’s direction (during star imagination) and reduced when there is no target (during mind relaxation).

Single channel electroencephalogram (EEG) brain computer interface (BCI) feature extraction and quantization method for support vector machine classification

“…27 subjects were voluntarily participating in this experiment. There was no initial training session provided to all of them Based on previous study by [4] two mental states were used as below:…”

“…One typical work is by Hazim et. al [4], in which probability density function (PSD) was used to classify spectral features between mental task for controlling a mobile robot and Tarmizi et. Al in which [5] spectral features from single channel EEG electrode was classified using Artificial Neural Network (ANN) to determine the subject's intention in controlling an electrical wheelchair.…”