发表机构
New York University (NYU)（纽约大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
EEG-Fusion提出无标签可靠性估计的决策级融合框架，通过可靠性门控路由专家，在无源运动想象脑电解码中显著提升宏F1并降低崩溃风险。
AI 中文摘要
受试者无关的运动想象（MI）脑电解码即使在平均性能看似可接受的情况下，也可能出现受试者级别的失败：在受试者偏移下，解码器可能变成一个过度自信的近乎单类预测器。这在无源部署中尤其成问题，因为在适应和专家选择期间无法获得目标用户的标签。我们提出了EEG-Fusion，一个基于失败信息的决策级融合框架，将无源MI解码视为对异构专家的无标签可靠性估计。EEG-Fusion应用受试者级别的欧几里得对齐和仅归一化的测试时适应，然后通过一个在源数据留出折上训练的可靠性门控，将每个目标受试者路由到神经、基于协方差或生理特征专家，以从无标签流诊断中预测专家性能和崩溃风险。该门控使用置信度、熵、预测多样性、专家一致性和预测类别平衡；崩溃被衡量为最大预测类别比例。在9折留一受试者（LOSO）评估中，使用三个随机种子，相对于无对齐的原始EEGNet无源锚点，EEG-Fusion在BCI IV-2a本地协议上将受试者宏F1从0.417提高到0.529，在BNCI2014-001上从0.314提高到0.482，在BNCI2014-004上从0.607提高到0.708；相应的崩溃指数降低分别为0.199、0.227和0.169。在9名受试者的Cho2017外部子集中，EEG-Fusion将宏F1从0.516提高到0.630。这些结果表明，无标签可靠性估计可以减少无源MI-EEG部署中的受试者级别失败模式。
英文摘要
Subject-independent motor-imagery (MI) EEG decoding can exhibit subject-level failures even when average performance appears acceptable: under subject shift, a decoder can become an overconfident near-one-class predictor. This is especially problematic in source-free deployment, where target-user labels are unavailable during adaptation and expert selection. We present \textit{EEG-Fusion}, a failure-informed decision-level fusion framework that treats source-free MI decoding as label-free reliability estimation over heterogeneous experts. EEG-Fusion applies subject-wise Euclidean alignment and normalization-only test-time adaptation, then routes each target subject to a neural, covariance-based, or physiological-feature expert using a reliability gate trained on source-held-out folds to predict expert performance and collapse risk from label-free stream diagnostics. The gate uses confidence, entropy, prediction diversity, expert agreement, and predicted class balance; collapse is measured as the maximum predicted class fraction. In 9-fold leave-one-subject-out (LOSO) evaluation with three seeds, relative to a no-alignment raw EEGNet source-free anchor, EEG-Fusion improves subject macro-F1 from 0.417 to 0.529 on BCI IV-2a local protocol, from 0.314 to 0.482 on BNCI2014-001, and from 0.607 to 0.708 on BNCI2014-004; corresponding collapse-index reductions are 0.199, 0.227, and 0.169. In a 9-subject Cho2017 external subset, EEG-Fusion improves macro-F1 from 0.516 to 0.630. These results suggest that label-free reliability estimation can reduce subject-level failure modes in source-free MI-EEG deployment.
CommentsAccepted to IEEE-EMBS BHI'2026, 7 pages
