Compact convolutional neural network (CNN) based on SincNet for end-to-end motor imagery decoding and analysis

ABSTR A C T In the field of human-computer interaction, the detection, extraction and classification of the electroencephalogram (EEG) spectral and spatial features are crucial towards develop-ing a practical and robust non-invasive EEG-based brain-computer interface. Recently, due to the popularity of end-to-end deep learning, the applicability of algorithms such as con-volutional neural networks (CNN) has been explored to achieve the mentioned tasks. This paper presents an improved and compact CNN algorithm for motor imagery decoding based on the adaptation of SincNet, which was initially developed for speaker recognition task from the raw audio input. Such adaptation allows for a compact end-to-end neural network with state-of-the-art (SOTA) performances and enables network interpretability for neurophysiological validation in cortical rhythms and spatial analysis. In order to vali-date the performance of proposed algorithms, two datasets were used; the first is the pub-licly available BCI Competition IV dataset 2a, which was often used as a benchmark in validating motor imagery classification algorithms, and the second is a dataset consists of primary data initially collected to study the difference between motor imagery and mental-task associated motor imagery BCI and was used to test the plausibility of the pro-posed algorithm in highlighting the differences in terms of cortical rhythms. Competitive decoding performance was achieved in both datasets in comparisons with SOTA CNN mod -els, albeit with the lowest number of trainable parameters. In addition, it was shown that the proposed architecture performs a cleaner band-pass, highlighting the necessary fre-quency bands that were crucial and neurophysiologically plausible in solving the classifica-tion tasks. (c) 2021 Nalecz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences. Published by Elsevier B.V. All rights reserved.