用二维卷积提升脑电分类效率，训练更快且结果更可解释。
Spatiotemporal Convolutions on EEG signal -- A Representation Learning Perspective on Efficient and Explainable EEG Classification with Convolutional Neural Nets
- 采用时空二维卷积替代传统分步一维卷积，统一处理空间与时间特征。
- 在22通道脑电信号上，二维模型训练速度显著加快，性能保持不变。
- 模型内部表征差异明显，说明结构设计影响学习过程，适合脑机接口研究者。
使用浅层卷积神经网络（CNN）进行脑电（EEG）信号分类在多个领域广泛应用。现有模型通常沿空间和时间维度分别使用一维（1D）卷积，且两者串联无非线性激活。本文提出一种二维（2D）时空卷积方法，虽在数值上等价于两个串联的1D卷积，但对学习过程的影响尚不明确。我们在3通道与22通道的脑机接口运动想象分类任务中对比了1D、2D CNN及混合CNN+Transformer模型。结果表明：在高维（22通道）任务中，2D卷积显著缩短训练时间，同时保持分类性能。进一步分析发现，两种模型在频谱特征重要性上无差异，但在内部表示相似性上呈现显著不同的几何结构。这说明模型架构影响学习表征，建议采用2D卷积以实现更高效、可解释的脑电信号分类。
原文摘要 · Abstract (English)
Classification of EEG signals using shallow Convolutional Neural Networks (CNNs) is a prevalent and successful approach across a variety of fields. Most of these models use independent one-dimensional (1D) convolutional layers along the spatial and temporal dimensions, which are concatenated without a non-linear activation layer between. In this paper, we investigate an alternative encoding that operates a bi-dimensional (2D) spatiotemporal convolution. While 2D convolutions are numerically identical to two concatenated 1D convolutions along the two dimensions, the impact on learning is still uncertain. We test 1D and 2D CNNs and a CNN+transformer hybrid model in a low-dimensional (3-channel) and a high-dimensional (22-channel) BCI motor imagery classification task. We observe that 2D convolutions significantly reduce training time in high-dimensional tasks while maintaining performance. We investigate the root of this improvement and find no difference in spectral feature importance. However, a clear pattern emerges in representational similarity across models: 1D and 2D models yield vastly different representational geometries. Overall, we suggest an improved model with a 2D convolutional layer for faster training and inference. We also highlight the importance of architecturally-driven encoding when processing complex multivariate signals, as reflected in internal representations rather than purely in performance metrics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。