Classifying the EEG Signal through Stimulus of Motor Movement Using New Type of Wavelet

Abstract

Brain Computer Interface (BCI) refers to a system designed to translate the brain signal in controlling a computer application.  The most widely used brain signal is electroencephalograph (EEG) for using the non-invasive method, and having a quite good resolution and relatively affordable equipments. This research purposively is to obtain the characteristics of EEG signals using the motor movement of “turn right” and “turn left” that is by moving the simulation of steering wheel. The characteristic of signal obtained is subsequently used as a reference to create a new type of wavelet for classification. The signal processing, including a 4 – 20 Hz bandpass filter, signal segmentation in 1 to 2 seconds after stimuli and signal correlation,  is used to obtain the characteristic of EEG signal; namely Event–Related Synchronization /Desynchronization (ERS/ERD). The result of test data classification to two new types of wavelet shows that each volunteer has a higher correlation value towards the new type of wavelet that has been designed with various wavelet scales for each individuals.

DOI: http://dx.doi.org/10.11591/ij-ai.v1i3.843