Comparison of static and dynamic neural network classifiers for brain-machine interfaces / Hema C.R. ...[et al.]

Neural network classifiers are one among the popular modes in the design of brain machine interface (BMI). In this study two novel dynamic neural network classifier designs for a four-state BMI are presented. Dynamic neural network based design for a four-state BMI to drive a wheelchair is analyzed. Motor imagery signals recorded noninvasively at the sensorimotor cortex region using two bipolar electrodes is used in the study. The performances of the proposed algorithms are compared with a static feed forward neural classifier. Average classification performance of 97.7% was achievable. Experiment results show that the distributed time delay neural network model out performs the layered recurrent and feed forward neural classifiers for a four-state BMI design.