TSPNet: a time-spatial parallel network for classification of EEG-based multiclass upper limb motor imagery BCI

Abstract

The classification of electroencephalogram (EEG) motor imagery signals has emerged as a prominent research focus within the realm of brain-computer interfaces. Nevertheless, the conventional, limited categories (typically just two or four) offered by brain-computer interfaces fail to provide an extensive array of control modes. To address this challenge, we propose the Time-Spatial Parallel Network (TSPNet) for recognizing six distinct categories of upper limb motor imagery. Within TSPNet, temporal and spatial features are extracted separately, with the time dimension feature extractor and spatial dimension feature extractor performing their respective functions. Following this, the Time-Spatial Parallel Feature Extractor is employed to decouple the connection between temporal and spatial features, thus diminishing feature redundancy. The Time-Spatial Parallel Feature Extractor deploys a gating mechanism to optimize weight distribution and parallelize time-spatial features. Additionally, we introduce a feature visualization algorithm based on signal occlusion frequency to facilitate a qualitative analysis of TSPNet. In a six-category scenario, TSPNet achieved an accuracy of 49.1% ± 0.043 on our dataset and 49.7% ± 0.029 on a public dataset. Experimental results conclusively establish that TSPNet outperforms other deep learning methods in classifying data from these two datasets. Moreover, visualization results vividly illustrate that our proposed framework can generate distinctive classifier patterns for multiple categories of upper limb motor imagery, discerned through signals of varying frequencies. These findings underscore that, in comparison to other deep learning methods, TSPNet excels in intention recognition, which bears immense significance for non-invasive brain-computer interfaces.

Investigating critical brain area for EEG-based binocular color fusion and rivalry with EEGNet

“…Features learned through DNNs might also be more effective or expressive than the ones engineered by humans ( Roy et al, 2019 ). Deep learning ( LeCun et al, 2015 ) was also gradually being applied to process EEG data in various fields ( Bi et al, 2023 ) such as emotion recognition, epilepsy diagnosis, and depression diagnosis. Cecotti and Graser (2010) implemented the first classification of P300 event-related potentials using a Convolutional Neural Network (CNN).…”