Senior Software Developer, Department of Mathematics & Computer Science, Indiana State University, USA.
Department of Computers and Information Technology, Faculty of sciences and arts, Turaif, Northern Border University, Arar 91431, Kingdom of Saudi Arabia.
J Neurosci Methods. 2024 Jun;406:110128. doi: 10.1016/j.jneumeth.2024.110128. Epub 2024 Mar 28.
In recent times, the expeditious expansion of Brain-Computer Interface (BCI) technology in neuroscience, which relies on electroencephalogram (EEG) signals associated with motor imagery, has yielded outcomes that rival conventional approaches, notably due to the triumph of deep learning. Nevertheless, the task of developing and training a comprehensive network to extract the underlying characteristics of motor imagining EEG data continues to pose challenges.
This paper presents a multi-scale spatiotemporal self-attention (SA) network model that relies on an attention mechanism. This model aims to classify motor imagination EEG signals into four classes (left hand, right hand, foot, tongue/rest) by considering the temporal and spatial properties of EEG. It is employed to autonomously allocate greater weights to channels linked to motor activity and lesser weights to channels not related to movement, thus choosing the most suitable channels. Neuron utilises parallel multi-scale Temporal Convolutional Network (TCN) layers to extract feature information in the temporal domain at various scales, effectively eliminating temporal domain noise.
The suggested model achieves accuracies of 79.26%, 85.90%, and 96.96% on the BCI competition datasets IV-2a, IV-2b, and HGD, respectively.
In terms of single-subject classification accuracy, this strategy demonstrates superior performance compared to existing methods.
The results indicate that the proposed strategy exhibits favourable performance, resilience, and transfer learning capabilities.
近年来，脑机接口（BCI）技术在神经科学领域的快速发展，依靠与运动想象相关的脑电图（EEG）信号，取得了与传统方法相媲美的成果，这主要得益于深度学习的成功。然而，开发和训练一个全面的网络来提取运动想象 EEG 数据的潜在特征的任务仍然具有挑战性。
本文提出了一种基于注意力机制的多尺度时空自注意力（SA）网络模型。该模型旨在通过考虑 EEG 的时间和空间特性，将运动想象 EEG 信号分为四类（左手、右手、脚、舌头/休息）。它被用来自动为与运动相关的通道分配更大的权重，为与运动无关的通道分配更小的权重，从而选择最合适的通道。神经元利用并行多尺度时间卷积网络（TCN）层在不同尺度上提取时间域的特征信息，有效地消除了时间域噪声。
该模型在 BCI 竞赛数据集 IV-2a、IV-2b 和 HGD 上的准确率分别达到了 79.26%、85.90%和 96.96%。
就单个人体分类准确率而言，该策略与现有方法相比表现出更好的性能。
结果表明，所提出的策略表现出良好的性能、弹性和迁移学习能力。
