Comparative Performance Analysis of Scalp EEG and Ear EEG based P300 Ambulatory Brain-Computer Interfaces using Riemannian Geometry and Convolutional Neural Networks

Brain-Computer Interfaces (BCI) provide the users to communicate with computers via brain signals. Significant research within the BCI is devoted to ElectroEncephaloGraphy (EEG), which picks, on the scalp, immensely frail electrical currents delineating brain activity. This paper presents a new ambulatory classification method for EEG Event Related Poten-tials (ERP) for a Practical Brain Computer Interface (BCI). To be more specific, this paper focuses on enhancing the performance of the ERP classification using Ear EEG along with scalp EEG during walking at 1.6m/s. We demonstrate the signal quality of Ear EEG for targets and non-targets. Through a novel estimation of Covariance matrices, this work extends the use of Riemannian Geometry (RG). In addition, the utility of Ear EEG has been justified by the 5% improvement in ERP detection performance after a novel fusion of Riemannian Geometry attributes from Ear EEG and scalp EEG. Further, we also proposed a fusion of feature attributes of both scalp and Ear EEG obtained from the fully connected layer of trained EEGNet CNN model with autoencoders passed through XGBoost. This method improved the state of the art by 10%. The proposed methods serve as novel adaptations of RG and CNN methods for mobile EEG in a practical BCI setup. The proposed method was also validated on the track 5 of the International BCI competition and achieved third position in the challenge.