Hu Zhangfang, Luo Kaixin, Liu Yan
The School of Optoelectronic Engineering and Key Laboratory of Optoelectronic Information Sensing and Technology, Chongqing University of Posts and Telecommunications, Chongqing, China.
Comput Methods Biomech Biomed Engin. 2025 Jul 8:1-12. doi: 10.1080/10255842.2025.2528892.
Brain-computer interface (BIC) decodes electroencephalogram (EEG) signals to realize the interaction between brain and external devices. However, traditional methods show limited performance in motor imagery electroencephalogram (MI-EEG) classification. In this paper, we introduce a multi-scale temporal convolutional network (MS-TCNet) that employs parallel multi-scale convolutions for spatiotemporal feature extraction, efficient channel attention (ECA) for channel weights optimization, and fusion-residual temporal convolution (FR-TCN) for high-level temporal feature capture. Experimental results show that MS-TCNet achieved remarkable decoding accuracies of 87.85% and 92.85% on the BCI IV-2a and BCI IV-2b datasets, respectively. The proposed MS-TCNet surpasses existing baseline models across various performance metrics, demonstrating its effectiveness in advancing MI-EEG decoding.
脑机接口（BIC）对脑电图（EEG）信号进行解码，以实现大脑与外部设备之间的交互。然而，传统方法在运动想象脑电图（MI-EEG）分类中表现有限。在本文中，我们介绍了一种多尺度时间卷积网络（MS-TCNet），该网络采用并行多尺度卷积进行时空特征提取，采用高效通道注意力（ECA）优化通道权重，并采用融合残差时间卷积（FR-TCN）捕获高级时间特征。实验结果表明，MS-TCNet在BCI IV-2a和BCI IV-2b数据集上分别取得了87.85%和92.85%的显著解码准确率。所提出的MS-TCNet在各种性能指标上均超过了现有的基线模型，证明了其在推进MI-EEG解码方面的有效性。
