抄録
In rehabilitation of patients with motor impairments, brain machine interface are used to provide a direct communication pathway between the brain and an external device. Brain machine interfaces (BMI) are designed using the electrical activity of the brain detected by scalp EEG electrodes. One of the popular techniques for designing BMI is classification of EEG signals extracted during imaginary mental tasks. In this paper a classification algorithm using a Particle Swarm Optimization Neural Network is presented. Five different mental tasks from two subjects were studied; a combination of two tasks is studied for task classification for each subject. Principal component analysis is used to extract the features. These features are used for training and testing the neural network. Classification accuracies varied from 77.5% to 100% for the 10 different task combinations for each of the subjects. The results obtained validate the performance of the PSO algorithm for mental task classification.
