Recurrent convolutional neural network model based on temporal and spatial feature for motor imagery classification

Abstract

Brain computer interface (BCI) could be useful in improving the quality of life for paralyzed patients. Motor imagery classification has recently been a center of research interest in the BCI-based rehabilitation. As of current, spatial features and spectral features were often used independently for motor imagery classification. While few studies attempted to combine the information from varying domains including spectral, spatial and temporal feature, the attempts employed simplistic linear models. In this study, a novel feature extraction method for including spatial and temporal information is proposed. The method uses recurrent convolutional neural network (RCNN) which excels in temporal and spatial classification. The method was tested for classifying wrist twisting-related task classification during manipulation of robotic arm via electroencephalography, and the performance of the method was compared to the conventional motor imagery classifiers with common spatial pattern (CSP) filter. The proposed method showed 73.9% accuracy in the classification of three types of tasks, whereas the highest accuracy achieved by conventional models was 59.5%. Overall, the performance of the proposed RCNN model was greater than the conventional models using the CSP as input features. The findings warrant further application of the proposed methods in varying BCI environment.