A Hybrid Brain-Computer Interface Using Motor Imagery and SSVEP Based on Convolutional Neural Network
This work addresses efficiency and accuracy issues for EEG-based BCI systems, though it appears incremental as it builds on existing hybrid paradigms with a novel neural network approach.
The paper tackled the problem of low efficiency and generalizability in hybrid brain-computer interfaces by proposing a two-stream convolutional neural network that fuses motor imagery and SSVEP paradigms, improving decoding accuracy by 25.4% compared to MI mode and 2.6% compared to SSVEP mode.
The key to electroencephalography (EEG)-based brain-computer interface (BCI) lies in neural decoding, and its accuracy can be improved by using hybrid BCI paradigms, that is, fusing multiple paradigms. However, hybrid BCIs usually require separate processing processes for EEG signals in each paradigm, which greatly reduces the efficiency of EEG feature extraction and the generalizability of the model. Here, we propose a two-stream convolutional neural network (TSCNN) based hybrid brain-computer interface. It combines steady-state visual evoked potential (SSVEP) and motor imagery (MI) paradigms. TSCNN automatically learns to extract EEG features in the two paradigms in the training process, and improves the decoding accuracy by 25.4% compared with the MI mode, and 2.6% compared with SSVEP mode in the test data. Moreover, the versatility of TSCNN is verified as it provides considerable performance in both single-mode (70.2% for MI, 93.0% for SSVEP) and hybrid-mode scenarios (95.6% for MI-SSVEP hybrid). Our work will facilitate the real-world applications of EEG-based BCI systems.