Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai 200237, People's Republic of China.
g.tec medical engineering GmbH, Schiedlberg, Austria.
J Neural Eng. 2024 Jul 5;21(4). doi: 10.1088/1741-2552/ad558a.
Event-related potentials (ERPs) are cerebral responses to cognitive processes, also referred to as cognitive potentials. Accurately decoding ERPs can help to advance research on brain-computer interfaces (BCIs). The spatial pattern of ERP varies with time. In recent years, convolutional neural networks (CNNs) have shown promising results in electroencephalography (EEG) classification, specifically for ERP-based BCIs.This study proposes an auto-segmented multi-time window dual-scale neural network (AWDSNet). The combination of a multi-window design and a lightweight base network gives AWDSNet good performance at an acceptable cost of computing. For each individual, we create a time window set by calculating the correlation of signed-squared values, which enables us to determine the length and number of windows automatically. The signal data are segmented based on the obtained window sets in sub-plus-global mode. Then, the multi-window data are fed into a dual-scale CNN model, where the sizes of the convolution kernels are determined by the window sizes. The use of dual-scale spatiotemporal convolution focuses on feature details while also having a large enough receptive length, and the grouping parallelism undermines the increase in the number of parameters that come with dual scaling.We evaluated the performance of AWDSNet on a public dataset and a self-collected dataset. A comparison was made with four popular methods including EEGNet, DeepConvNet, EEG-Inception, and PPNN. The experimental results show that AWDSNet has excellent classification performance with acceptable computational complexity.These results indicate that AWDSNet has great potential for applications in ERP decoding.
事件相关电位（ERPs）是大脑对认知过程的反应，也称为认知电位。准确解码 ERPs 有助于推进脑机接口（BCIs）的研究。ERP 的空间模式随时间而变化。近年来，卷积神经网络（CNNs）在脑电图（EEG）分类方面取得了有希望的结果，特别是对于基于 ERP 的 BCIs。本研究提出了一种自动分段多时间窗口双尺度神经网络（AWDSNet）。多窗口设计和轻量级基础网络的结合使 AWDSNet 在可接受的计算成本下具有良好的性能。对于每个个体，我们通过计算符号平方值的相关性来创建时间窗口集，从而能够自动确定窗口的长度和数量。根据获得的窗口集以子加全局模式对信号数据进行分段。然后，将多窗口数据输入到双尺度 CNN 模型中，其中卷积核的大小由窗口大小决定。使用双尺度时空卷积可以专注于特征细节，同时具有足够大的感受野，分组并行性可以减少因双比例而增加的参数数量。我们在公共数据集和自行收集的数据集上评估了 AWDSNet 的性能，并与 EEGNet、DeepConvNet、EEG-Inception 和 PPNN 等四种流行方法进行了比较。实验结果表明，AWDSNet 具有出色的分类性能，同时具有可接受的计算复杂度。这些结果表明，AWDSNet 在 ERP 解码应用中具有很大的潜力。
