Motor imagery recognition with automatic EEG channel selection and deep learning

Abstract

Objective. Modern motor imagery (MI)-based brain computer interface systems often entail a large number of electroencephalogram (EEG) recording channels. However, irrelevant or highly correlated channels would diminish the discriminatory ability, thus reducing the control capability of external devices. How to optimally select channels and extract associated features remains a big challenge. This study aims to propose and validate a deep learning-based approach to automatically recognize two different MI states by selecting the relevant EEG channels. Approach. In this work, we make use of a sparse squeeze-and-excitation module to extract the weights of EEG channels based on their contribution to MI classification, by which an automatic channel selection (ACS) strategy is developed. Further, we propose a convolutional neural network to fully exploit the time-frequency features, thus outperforming traditional classification methods both in terms of accuracy and robustness. Main results. We execute the experiments using EEG signals recorded at MI where 25 healthy subjects performed MI movements of the right hand and feet to generate motor commands. An average accuracy of is obtained, providing a 37.3% improvement with respect to a state-of-the-art channel selection approach. Significance. The proposed ACS method has been found to be significantly advantageous compared to the typical approach of using a fixed channel configuration. This work shows that fewer EEG channels not only reduces computational complexity but also improves the MI classification performance. The proposed method selects EEG channels related to hand and feet movement, which paves the way to real-time and more natural interfaces between the patient and the robotic device.

Classification of lower limb motor imagery based on iterative EEG source localization and feature fusion

“…Compared with other channel selection methods, the mean classification performance of STECS on the three data sets was improved by up to 10.42%, 6.13%, and 3.72% respectively. Zhang et al [9] inserted an automatic channel selection (ACS) layer into a convolutional neural network for MI classification. By introducing the sparse regularization, the output of the ACS layer was constrained to be sparse and the channels corresponding to the nonzero coefficients were retained for MI classification.…”

SincNet-Based Hybrid Neural Network for Motor Imagery EEG Decoding

“…The outputs of SincNet were fed into the squeeze-andexcitation (SE) modules [24,25] for recalibration. The structure of the SE modules is shown in Fig.…”

“…In this study, we used the cross-entropy loss to minimize the classification error between the predicted labels and the groundtruth labels. Moreover, the sparse loss [24] and center loss [26] were used to simplify the neural network and improve the discriminability of different class features, respectively. The objective functions of cross-entropy loss 𝐿 , sparse loss 𝐿 , and center loss 𝐿 are given as follows:…”

Arithmetic Optimization with RetinaNet Model for Motor Imagery Classification on Brain Computer Interface

“…Zhang et al [ 10 ] validate and developed a DL-based algorithm for automatically recognizing two distinct MI states by choosing the related EEG channel. It employs an automated channel selection (ACS) approach.…”