PDF(Pubmed)
Abstract：
Previous research has primarily employed deep learning models such as Convolutional Neural Networks (CNNs), and Recurrent Neural Networks (RNNs) for decoding imagined character signals. These approaches have treated the temporal and spatial features of the signals in a sequential, parallel, or single-feature manner. However, there has been limited research on the cross-relationships between temporal and spatial features, despite the inherent association between channels and sampling points in Brain-Computer Interface (BCI) signal acquisition, which holds significant information about brain activity. To address the limited research on the relationships between temporal and spatial features, we proposed a Temporal-Spatial Cross-Attention Network model, named TSCA-Net. The TSCA-Net is comprised of four modules: the Temporal Feature (TF), the Spatial Feature (SF), the Temporal-Spatial Cross (TSCross), and the Classifier. The TF combines LSTM and Transformer to extract temporal features from BCI signals, while the SF captures spatial features. The TSCross is introduced to learn the correlations between the temporal and spatial features. The Classifier predicts the label of BCI data based on its characteristics. We validated the TSCA-Net model using publicly available datasets of handwritten characters, which recorded the spiking activity from two micro-electrode arrays (MEAs). The results showed that our proposed TSCA-Net outperformed other comparison models (EEG-Net, EEG-TCNet, S3T, GRU, LSTM, R-Transformer, and ViT) in terms of accuracy, precision, recall, and F1 score, achieving 92.66 % , 92.77 % , 92.70 % , and 92.58 % , respectively. The TSCA-Net model demonstrated a 3.65 % to 7.49 % improvement in accuracy over the comparison models.
摘要：
以前的研究主要采用深度学习模型，如卷积神经网络(CNN)，和递归神经网络(RNN)用于解码想象的字符信号。这些方法处理了信号的时间和空间特征，平行,或单一特征的方式。然而,关于时空特征之间的交叉关系的研究有限，尽管在脑机接口（BCI）信号采集中通道和采样点之间存在固有的关联，其中包含有关大脑活动的重要信息。为了解决时空特征关系研究有限的问题，我们提出了一种时空交叉注意力网络模型，名为TSCA-Net。TSCA-Net由四个模块组成：时间特征（TF），空间特征(SF)，时空交叉(TSCross)，和分类器。TF结合LSTM和Transformer从BCI信号中提取时间特征，而SF捕获空间特征。引入TSCross来学习时间和空间特征之间的相关性。分类器根据BCI数据的特征预测其标签。我们使用公开的手写字符数据集验证了TSCA-Net模型，记录了来自两个微电极阵列(MEAs)的尖峰活动。结果表明，我们提出的TSCA-Net优于其他比较模型(EEG-Net，EEG-TCNet,S3T,GRU,LSTM,R-变压器,和ViT)在准确性方面，精度,召回，和F1得分，达到92.66%，92.77%,92.70%,和92.58%，分别。与比较模型相比，TSCA-Net模型的准确性提高了3.65％至7.49％。
