Motor imagery signal classification using spiking neural network

Abstract

A brain-computer interface (BCI) is both a hardware and software based communication system that allows cerebral activity to control computers or external devices. The instantaneous aim of BCI research is to offer communication abilities to severely disabled people who are ‘locked in’ by neurological disorders such as amyotrophic lateral sclerosis, brain stem stroke or spinal cord injury. “Electroencephalography”, a non-invasive approach, has been widely used for BCI system. In recent times, several classifiers have been used in analyzing EEG signals measured in the planning and relaxed state. The key work addressed is the classification of EEG signals (motor imagery signals) using spiking neural classifier. The dataset (Planning and relaxed state data) is a benchmark data taken from UCI (University of California, Irvine) repository. Online Meta-neuron based Learning Algorithm (OMLA), is a newly evolved network applied for the EEG signal classification task. Spiking neural classifier performs better than the other classifiers due to the use of both global and local information of the network.