Yang Jun, Liu Lintao, Yu Huijuan, Ma Zhengmin, Shen Tao
School of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China.
Front Neurosci. 2022 Apr 25;16:824471. doi: 10.3389/fnins.2022.824471. eCollection 2022.
Brain-computer interfaces (BCI) based motor imagery (MI) has become a research hotspot for establishing a flexible communication channel for patients with apoplexy or degenerative pathologies. Accurate decoding of motor imagery electroencephalography (MI-EEG) signals, while essential for effective BCI systems, is still challenging due to the significant noise inherent in the EEG signals and the lack of informative correlation between the signals and brain activities. The application of deep learning for EEG feature representation has been rarely investigated, nevertheless bringing improvements to the performance of motor imagery classification. This paper proposes a deep learning decoding method based on multi-hierarchical representation fusion (MHRF) on MI-EEG. It consists of a concurrent framework constructed of bidirectional LSTM (Bi-LSTM) and convolutional neural network (CNN) to fully capture the contextual correlations of MI-EEG and the spectral feature. Also, the stacked sparse autoencoder (SSAE) is employed to concentrate these two domain features into a high-level representation for cross-session and subject training guidance. The experimental analysis demonstrated the efficacy and practicality of the proposed approach using a public dataset from BCI competition IV and a private one collected by our MI task. The proposed approach can serve as a robust and competitive method to improve inter-session and inter-subject transferability, adding anticipation and prospective thoughts to the practical implementation of a calibration-free BCI system.
基于脑机接口（BCI）的运动想象（MI）已成为为中风或退行性病变患者建立灵活通信通道的研究热点。运动想象脑电图（MI-EEG）信号的准确解码对于有效的BCI系统至关重要，但由于EEG信号中固有的大量噪声以及信号与大脑活动之间缺乏信息相关性，仍然具有挑战性。深度学习在EEG特征表示中的应用很少被研究，尽管如此，它仍能提高运动想象分类的性能。本文提出了一种基于多层次表示融合（MHRF）的MI-EEG深度学习解码方法。它由一个由双向长短期记忆网络（Bi-LSTM）和卷积神经网络（CNN）构建的并发框架组成，以充分捕捉MI-EEG的上下文相关性和频谱特征。此外，堆叠式稀疏自动编码器（SSAE）被用于将这两个领域特征集中为一个高级表示，用于跨会话和受试者训练指导。实验分析使用来自BCI竞赛IV的公共数据集和我们的MI任务收集的私有数据集，证明了所提方法的有效性和实用性。所提方法可以作为一种强大且有竞争力的方法来提高跨会话和跨受试者的可转移性，为无校准BCI系统的实际实现增添预期和前瞻性思维。
