Motor imagery(MI)based electroencephalogram(EEG)represents a frontier in enabling direct neural control of external devices and advancing neural rehabilitation.This study introduces a novel time embedding technique,te...Motor imagery(MI)based electroencephalogram(EEG)represents a frontier in enabling direct neural control of external devices and advancing neural rehabilitation.This study introduces a novel time embedding technique,termed traveling-wave based time embedding,utilized as a pseudo channel to enhance the decoding accuracy of MI-EEG signals across various neural network architectures.Unlike traditional neural network methods that fail to account for the temporal dynamics in MI-EEG in individual difference,our approach captures time-related changes for different participants based on a priori knowledge.Through extensive experimentation with multiple participants,we demonstrate that this method not only improves classification accuracy but also exhibits greater adaptability to individual differences compared to position encoding used in Transformer architecture.Significantly,our results reveal that traveling-wave based time embedding crucially enhances decoding accuracy,particularly for participants typically considered“EEG-illiteracy”.As a novel direction in EEG research,the traveling-wave based time embedding not only offers fresh insights for neural network decoding strategies but also expands new avenues for research into attention mechanisms in neuroscience and a deeper understanding of EEG signals.展开更多
A neural network method for independent source separation (ISS) of multichannel electroencephalogram (EEG) is proposed in this paper.Using the denoising function of wavelet multiscale decomposition,the high-frequency ...A neural network method for independent source separation (ISS) of multichannel electroencephalogram (EEG) is proposed in this paper.Using the denoising function of wavelet multiscale decomposition,the high-frequency noises are removed from the original (raw) EEGs.Then the multichannel EEGs are treated as the weighted mixtures and the expression of weight vector is obtained by seeking the local extrema of the fourth-order cumulants (i.e.kurtosis coefficients) of the mixtures.After these process steps,the weighted mixtures are used as the input of neural network,so the independent source of EEGs can be separated one by one.The experimental results show that our method is effective for ISS of multichannel EEGs.展开更多
文摘Motor imagery(MI)based electroencephalogram(EEG)represents a frontier in enabling direct neural control of external devices and advancing neural rehabilitation.This study introduces a novel time embedding technique,termed traveling-wave based time embedding,utilized as a pseudo channel to enhance the decoding accuracy of MI-EEG signals across various neural network architectures.Unlike traditional neural network methods that fail to account for the temporal dynamics in MI-EEG in individual difference,our approach captures time-related changes for different participants based on a priori knowledge.Through extensive experimentation with multiple participants,we demonstrate that this method not only improves classification accuracy but also exhibits greater adaptability to individual differences compared to position encoding used in Transformer architecture.Significantly,our results reveal that traveling-wave based time embedding crucially enhances decoding accuracy,particularly for participants typically considered“EEG-illiteracy”.As a novel direction in EEG research,the traveling-wave based time embedding not only offers fresh insights for neural network decoding strategies but also expands new avenues for research into attention mechanisms in neuroscience and a deeper understanding of EEG signals.
基金Natural Science Foundation of Fujian Province of Chinagrant number:C0710036 and T0750008
文摘A neural network method for independent source separation (ISS) of multichannel electroencephalogram (EEG) is proposed in this paper.Using the denoising function of wavelet multiscale decomposition,the high-frequency noises are removed from the original (raw) EEGs.Then the multichannel EEGs are treated as the weighted mixtures and the expression of weight vector is obtained by seeking the local extrema of the fourth-order cumulants (i.e.kurtosis coefficients) of the mixtures.After these process steps,the weighted mixtures are used as the input of neural network,so the independent source of EEGs can be separated one by one.The experimental results show that our method is effective for ISS of multichannel EEGs.
