Fusion of Convolutional Neural Networks for P300 Based Character Recognition

Abstract

One of the most popular brain-computer interface (BCI) system is P300 speller, which is used for character recognition. For real-time application, the improved character recognition is required for P300 speller. In this work, a deep learning technique based on convolutional neural network (CNN) has been proposed for character recognition. Deep learning techniques based feature set can represent the electroencephalogram (EEG) signal better compared to hand-crafted feature set. In this work, two parallel CNN model with different kernel size is proposed to extract multi-resolution feature from the dataset. The proposed CNN model extracts spatial and temporal feature from the dataset. To mitigate the over-fitting problem, dropout is used before the fully-connected layer of the CNN architecture, which improves the network performance. Rectified linear units (ReLU) is used to accelerate the training process. The scores of these two CNN architectures are fused together for P300 detection. Also, ensemble of CNN (ECNN) architecture is proposed to reduce the variation between the classifiers and enhance the character recognition performance. The proposed method is tested on BCI Competition III dataset and the results are fairly comparable and better with the earlier methods.