PSD-Based Features Extraction For EEG Signal During Typing Task

Abstract

Abstract Electroencephalograph (EEG) is an electrical field that generated by our brain incessantly. The EEG signal released by the brain is different when a people is performing different activities in their daily life. And such EEG signals consist complicated information that can be interpreted. The aims of this study is to analyse the specific EEG channels of a user when they are performing a typing task with laptop. Meanwhile, this research also aimed to verify the performance of the different sub frequency band which is alpha and beta to recognize the specified tasks. The frequency sampling was set at 1024 Hz and the impedance was kept below 5k ohm of each channels. The Truscan EEG (Deymed, Diagnostic, Czech Republic) device consists of 19 channels and only selected channels which is F3 and F4 is filtered through butterworth bandpass filter (1Hz-80Hz) in the pre-processing stage. Power Spectra Density was calculated by using Welch and Burg Method to extract the features from filtered data. K-Nearest Neighbour (KNN) classifier and Linear Discriminant Analysis (LDA) were used in classification. It is found that the combination of channel F3 and F4 for Alpha frequency using Welch method gives the highest accuracy which is 98.45%.