Spiking Neural Network for On-line Cognitive Activity Classification Based on EEG Data

摘要

The paper presents a method for the classification of EEG data recorded in two cognitive scenarios, a relaxing and memory task. The method uses a reservoir of spiking neurons that are activated by the spatio-temporal EEG data. The states of the reservoir are periodically read out and classified producing in a continuous classification result over time. After suitable optimization of the model parameters, we achieve a test accuracy of 82% on a small data set. Future applications of the proposed model are discussed including its use for an early detection of a cognitive impairment such as in Alzheimers disease.