Synchronous brain machine interface design using focused time delay networks

Abstract

Focused time delay neural network based design for a four-state Brain Machine Interface (BMI) to drive a wheelchair is analyzed. Motor imagery signals recorded noninvasively using two bipolar electrodes are used in the study. The performance of the proposed dynamic classifier is compared with a static feed forward neural classifier. Data collected from 10 subjects is used in this study. Average classification performance in the range of 93% to 100% is achievable. Experiment results show that the focused time delay neural network model is suitable for a four-state BMI design.