Recognizing motor imagery using dynamic cascade feed-forward neural networks

Recognition of Motor Imagery (MI) using a dynamic cascade feed-forward neural network (CFNN) is presented. MI is the mental simulation of a motor act that includes preparation for movement and mental operations of motor representations implicitly or explicitly. The ability of an individual to control his EEG through imaginary motor tasks enables him to control devices through a Brain Machine Interface (BMI). A BMI design using the CFNN is used to discriminate EEG signals acquired during MI for four states namely, relax, forward, left and right. EEG is recorded at the C3 and C4 locations using noninvasive scalp electrodes placed over the motor cortex. The proposed CFNN is tested with data collected from 10 subjects. Average recognition accuracy of 93.3% validates the proposed four-state BMI design using MI and CFNN.