Bispectrum-based hybrid neural network for motor imagery classification

Background: The performance of motor imagery electroencephalogram (MI-EEG) decoding systems is easily affected by noise. As a higher-order spectra (HOS), the bispectrum is capable of suppressing Gaussian noise and increasing the signal-to-noise ratio of signals. However, the sum of logarithmic amplitudes (SLA) and the first order spectral moment (FOSM) features extracted from the bispectrum only use the numerical values of the bispectrum, ignoring the related information between different frequency bins. New method: In this study, we proposed a novel framework, termed a bispectrum-based hybrid neural network (BHNN), to make full use of bispectrum for improving the performance of the MI-based brain-computer interface (BCI). Specifically, the BHNN consisted of a convolutional neural network (CNN), gated recurrent units (GRU), and squeeze-and-excitation (SE) modules. The SE modules and CNNs are first used to learn the deep relation between frequency bins of the bispectrum estimated from different time window segmentations of the MI-EEG. Then, we used GRU to seek the overlooked sequential information of the bispectrum. Results: To validate the effectiveness of the proposed BHNN, three public BCI competition datasets were used in this study. The results demonstrated that the BHNN can achieve promising performance in decoding MI-EEG. Comparison with existing methods: The statistical test results demonstrated that the proposed BHNN can significantly outperform other competing methods (p < =0.05). Conclusion: The proposed BHNN is a novel bispectrum-based neural network, which can enhance the decoding performance of MI-based BCIs.

Automated summary

In this study, a novel framework called BHNN was proposed to improve the performance of MI-based BCIs using the bispectrum. The BHNN utilized convolutional neural networks, gated recurrent units, and squeeze-and-excitation modules to extract deep relations and sequential information from the bispectrum. The results demonstrated promising decoding performance in MI-EEG, outperforming other existing methods significantly.