通过双阶段对齐与自监督实现快速校准，提升脑机接口跨个体适应性。
Online Adaptation via Dual-Stage Alignment and Self-Supervision for Fast-Calibration Brain-Computer Interfaces
- 先在脑电空间做欧氏对齐，再在表征空间更新归一化统计量。
- 仅用单次在线试测即提升稳态视觉诱发电位准确率4.9%、运动想象3.6%。
- 无需标签，适配多种范式与解码器，适合实际部署的快速校准场景。
个体间脑活动差异限制了基于脑电图（EEG）的脑机接口（BCI）系统的在线应用。为此，本研究提出一种针对未见受试者的在线自适应算法，结合双阶段对齐与自监督机制。对齐过程首先在脑电信号空间进行欧氏对齐，随后在表征空间更新批量归一化统计量。同时设计自监督损失，利用解码器生成的软伪标签作为未知真实标签的代理，并通过香农熵进行校准以促进自监督训练。在五个公开数据集和七种解码器上的实验表明，该算法可无缝集成于不同BCI范式与解码器架构中。每次迭代仅需单次在线试测即可更新解码器，平均使稳态视觉诱发电位（SSVEP）准确率提升4.9%，运动想象任务提升3.6%。结果验证了快速校准的可行性，表明该算法在实际BCI应用中具有巨大潜力。
原文摘要 · Abstract (English)
Individual differences in brain activity hinder the online application of electroencephalogram (EEG)-based brain computer interface (BCI) systems. To overcome this limitation, this study proposes an online adaptation algorithm for unseen subjects via dual-stage alignment and self-supervision. The alignment process begins by applying Euclidean alignment in the EEG data space and then updates batch normalization statistics in the representation space. Moreover, a self-supervised loss is designed to update the decoder. The loss is computed by soft pseudo-labels derived from the decoder as a proxy for the unknown ground truth, and is calibrated by Shannon entropy to facilitate self-supervised training. Experiments across five public datasets and seven decoders show the proposed algorithm can be integrated seamlessly regardless of BCI paradigm and decoder architecture. In each iteration, the decoder is updated with a single online trial, which yields average accuracy gains of 4.9% on steady-state visual evoked potentials (SSVEP) and 3.6% on motor imagery. These results support fast-calibration operation and show that the proposed algorithm has great potential for BCI applications.
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。