Xu Ruitian, Allison Brendan Z, Zhao Xueqing, Liang Wei, Wang Xingyu, Cichocki Andrzej, Jin Jing
Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai 200237, China.
Cognitive Science Department University of California, San Diego 92093, USA.
Neural Netw. 2025 Apr;184:107124. doi: 10.1016/j.neunet.2025.107124. Epub 2025 Jan 7.
Event-related potentials (ERPs) can reveal brain activity elicited by external stimuli. Innovative methods to decode ERPs could enhance the accuracy of brain-computer interface (BCI) technology and promote the understanding of cognitive processes. This paper proposes a novel Multi-Scale Pyramid Squeeze Attention Similarity Optimization Classification Neural Network (MS-PSA-SOC) for ERP Detection. The model integrates a multi-scale architecture, self-attention mechanism, and deep metric learning to achieve a more comprehensive, refined, and discriminative feature representation. The MS module aggregates fine-grained local features and global features with a larger receptive field within a multi-scale architecture, effectively capturing the dynamic characteristics of complex oscillatory activities in the brain at different levels of abstraction. This preserves complementary spatiotemporal representation information. The PSA module continues the multi-scale contextual modeling from the previous module and achieves adaptive recalibration of multi-scale features. By employing effective aggregation and selection mechanisms, it highlights key features while suppressing redundant information. The SOC module jointly optimizes similarity metric loss and classification loss, maintaining the feature space distribution while focusing on sample class labels. This optimization of similarity relationships between samples improves the model's generalization ability and robustness. Results from public and self-collected datasets demonstrate that the command recognition accuracy of the MS-PSA-SOC model is at least 3.1% and 2.8% higher than other advanced algorithms, achieving superior performance. Additionally, the method demonstrates a lower standard deviation across both datasets. This study also validated the network parameters based on Shannon's sampling theorem and EEG "microstates" through relevant experiments.
事件相关电位（ERPs）能够揭示由外部刺激引发的大脑活动。解码ERPs的创新方法可以提高脑机接口（BCI）技术的准确性，并促进对认知过程的理解。本文提出了一种用于ERP检测的新型多尺度金字塔挤压注意力相似性优化分类神经网络（MS-PSA-SOC）。该模型集成了多尺度架构、自注意力机制和深度度量学习，以实现更全面、精细和有区分性的特征表示。MS模块在多尺度架构内聚合具有更大感受野的细粒度局部特征和全局特征，有效捕捉大脑中不同抽象层次复杂振荡活动的动态特征。这保留了互补的时空表示信息。PSA模块延续前一模块的多尺度上下文建模，实现多尺度特征的自适应重新校准。通过采用有效的聚合和选择机制，它突出关键特征，同时抑制冗余信息。SOC模块联合优化相似性度量损失和分类损失，在关注样本类别标签的同时保持特征空间分布。样本间相似性关系的这种优化提高了模型的泛化能力和鲁棒性。来自公共数据集和自收集数据集的结果表明，MS-PSA-SOC模型的指令识别准确率比其他先进算法至少高3.1%和2.8%，表现优异。此外，该方法在两个数据集上的标准差更低。本研究还通过相关实验基于香农采样定理和脑电图“微状态”验证了网络参数。
