Classification of EEG Signals Using Support Vector Machine to Distinguish Different Hand Motor Movements

摘要

The Brain Computer Interface (BCI) is an emerging technology that provides an alternative medium of communication where human brain (via Electroencephalography signal) can communicate with the computer and other electronic peripherals. Motor movements e.g., lifting hands also affectthe EEG signals, where different brainwave patterns are detected for different motor movements. In this context, our research objective is to compare between Power Spectral Density (PSD) and Energy Spectral Density (ESD) features extracted from the EEG signals in classifying the differentpatterns to distinguish different motor movement; i.e., lifting left and right hand. The classification will be done by using Support Vector Machine (SVM) classifier. Based on the analysis performed, the result shows that the classification done based on PSD has led to higher accuracy measure(82.7%) when compared to classification based on ESD data as input (78.8%).