Single channel Electroencephalogram (EEG) brain computer interface (BCI) feature extraction and quantization method for Support Vector Machine classification

Abstract

Over the recent years, there has been a huge interest towards Electroencephalogram (EEG) based brain computer interface (BCI) system. BCI system enables the extraction of meaningful information directly from the human brain via suitable signal processing and machine learning method and thus, many researches have applied this technology towards rehabilitation and assistive robotics. Such application is important towards improving the lives of people with motor diseases such as Amytrophic Lateral Scelorosis (ALS) disease or people with quadriplegia/tetraplegia. This paper introduces features extraction method based on the Fast Fourier Transform (FFT) with logarithmic binning for rapid classification using Support Vector Machine (SVM) algorithm, with an application towards a BCI system with a shared control scheme. In general, subjects wearing a single channel EEG electrode located at F8 (10-20 international standards) 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 exists a target object at certain direction. Based on the proposed algorithm, we showed that our algorithm can distinguish between mind relaxation and mental star rotation with up to 80% accuracy from the single channel EEG signals.