TFSICNet: A Neural Feature-based Encoder for Visual and Motor Imagery EEG Data

Brain-computer interface (BCI) is a technology that enables direct connection and interaction of brain activity with external devices or systems. The encoding and decoding of neural signals play a crucial role in BCIs. The quality of such encodings are the key to robust and accurate information exchange and control between the brain and external devices. Currently, the limited capabilities of conventional brain signal processing is restricting a wider application of BCIs. In this paper, we propose a deep network encoder, Temporal-Frequency-Spatio-Importance Correlation Network (TFSICNet), to robustly and comprehensively encode the original electroencephalogram (EEG) data. The design of TFSICNet is based on an interpretable understanding of the brain's basic structural and connectivity features. The various submodules in TFSICNet were designed to ensure the different features were taken into account. We evaluated encoder performance on three motion imagery datasets and one picture stimulus dataset. The results show that our encoder performs better than traditional deep encoders and advanced deep neural network models that have excelled in extracting EEG features for classification in recent years.