ElectrodeEncephaloGraph signal classification using back propagation neural network

Abstract

Someone needs a keyboard or mouse to be able to run a cursor on a computer screen. So that it may be impossible to do against someone who is paralyzed or someone who does not have a hand. ElektrodeEncephalograph Devices (EEG) is usually used to measure the electrical activity of the brain, as a tool to search for information related to the brain. Brain Computer Interface (BCI) is a device that can communicate with humans or animals through the brain. Signal generated by brain waves recorded by the electrical component called electrodes are attached to a specific position in the scalp EEG i s connected to the device can be identified as an instruction to be carried out by the organs. This study was made with the purpose of classifying the EEG signals by retrieving data from BCI competition 2003 — Data set la. Furthermore, the data is processed by taking the feature extraction methods Fast Fourier Transform. The results of the feature extraction method used will be selected before it is used for the clasification process, for clasification used neural network back propagation method. Methods of research obtained by taking the Fast Fourier Transform as extraction features of the Root Mean Square (RMS) and Average Power Spectrum obtain accurate clasification rate of 92.5%.