Faculty of Information Technology, Beijing University of Technology, Beijing 100124, People's Republic of China.
Beijing Machine and Equipment Institute, Beijing 100854, People's Republic of China.
J Neural Eng. 2022 Jan 25;19(1). doi: 10.1088/1741-2552/ac4852.
Motor imagery-based brain-computer interface (MI-BCI) is one of the most important BCI paradigms and can identify the target limb of subjects from the feature of MI-based Electroencephalography signals. Deep learning methods, especially lightweight neural networks, provide an efficient technique for MI decoding, but the performance of lightweight neural networks is still limited and need further improving. This paper aimed to design a novel lightweight neural network for improving the performance of multi-class MI decoding.A hybrid filter bank structure that can extract information in both time and frequency domain was proposed and combined with a novel channel attention method channel group attention (CGA) to build a lightweight neural network Filter Bank CGA Network (FB-CGANet). Accompanied with FB-CGANet, the band exchange data augmentation method was proposed to generate training data for networks with filter bank structure.The proposed method can achieve higher 4-class average accuracy (79.4%) than compared methods on the BCI Competition IV IIa dataset in the experiment on the unseen evaluation data. Also, higher average accuracy (93.5%) than compared methods can be obtained in the cross-validation experiment.This work implies the effectiveness of channel attention and filter bank structure in lightweight neural networks and provides a novel option for multi-class motor imagery classification.
基于运动想象的脑机接口（MI-BCI）是最重要的脑机接口范式之一，它可以从基于 MI 的脑电图信号的特征中识别受试者的目标肢体。深度学习方法，尤其是轻量级神经网络，为 MI 解码提供了一种有效的技术，但轻量级神经网络的性能仍然有限，需要进一步提高。本文旨在设计一种新的轻量级神经网络，以提高多类 MI 解码的性能。提出了一种混合滤波器组结构，可以提取时域和频域的信息，并结合一种新的通道注意力方法通道组注意力（CGA）来构建轻量级神经网络滤波器组 CGA 网络（FB-CGANet）。伴随着 FB-CGANet，提出了带交换数据增强方法，为具有滤波器组结构的网络生成训练数据。在对未见评估数据的实验中，该方法在 BCI 竞赛 IV IIa 数据集上的 4 类平均准确率（79.4%）高于对比方法。此外，在交叉验证实验中，该方法可以获得比对比方法更高的平均准确率（93.5%）。这项工作表明通道注意力和滤波器组结构在轻量级神经网络中的有效性，并为多类运动想象分类提供了一种新的选择。
