Prof. Seong-Whan Lee's paper, "Subject-Independent Brain-Computer Interfaces Based on Deep Convolutional Neural Networks" was accepted in  IEEE Transactions on Neural Networks and Learning Systems (ranked in 1 out of 104 journals in Computer Science, Theory and Methods).


Title:  Subject-Independent Brain-Computer Interfaces Based on Deep Convolutional Neural Networks

 

Abstract:

For a brain-computer interface (BCI) system, a calibration procedure is required for each individual user before he/she can use the BCI. This procedure requires approximately 20-30 minutes to collect enough data to build a reliable decoder. It is, therefore, an interesting topic to build a calibration-free, or subject-independent, BCI. In this paper, we construct a large motor imagery (MI)-based EEG database, and propose a subject-independent framework based on deep convolutional neural networks (CNN). The database is composed of fifty-four subjects performing left and right-hand MI on two different days, resulting in 21,600 trials for the MI task. In our framework, we formulated the discriminative feature representation as a combination of the spectral-spatial input embedding the diversity of the EEG signals, as well as a feature representation learned from the CNN through a fusion technique that integrates a variety of discriminative brain signal patterns. To generate spectralspatial inputs, we first consider the discriminative frequency bands in an information-theoretic observation model that measures the power of the features in two classes. From discriminative frequency bands, spectral-spatial inputs that include the unique characteristics of brain signal patterns are generated and then transformed into a covariance matrix as the input to the CNN. In the process of feature representations, spectral-spatial inputs are individually trained through the CNN and then combined by a concatenation fusion technique. In this study, we demonstrate that the classification accuracy of our subject-independent (or calibrationfree) model outperforms that of subject-dependent models using various methods (CSP, CSSP, FBCSP, and BSSFO).