适用于任意电极 montage 的编码器：基于表面肌电信号的校准无关跨用户手势识别
A Montage-Agnostic Encoder for Calibration-Light Cross-User Gesture Recognition from Surface Electromyography
- Division of Biomedical Engineering, University of Saskatchewan（萨斯喀彻温大学生物医学工程系）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出适用于任意电极 montage 的编码器，实现跨用户表面肌电手势识别，在 DB1、DB2 上性能优于 per-user Hudgins 线性判别分类器，训练池达一定规模后性能趋稳，自监督预训练无额外增益。
AI中文摘要：
模式识别控制有望实现可响应多种预期手势而非一两种的肌电假肢，但该设想仍停留在实验室阶段。针对某一用户训练的识别器极少能迁移至其他用户，且要达到可用性能通常需要终端用户重新进行一轮带标签校准。本文提出一种适用于任意电极 montage 的编码器，该编码器以共享权重读取每个电极，并通过物理坐标而非索引定位电极，因此同一架构可处理任意通道数，无需特定 montage 参数。在跨用户训练时，该编码器在 DB1 上对每个留出受试者的宏 F1 值比 per-user Hudgins 线性判别分类器高 0.234，在 DB2 上高 0.108，在含十名受试者的 DB5 上则低于该分类器。在预算匹配的消融研究中，编码器的三个关键组件各自贡献了其 3 次采样宏 F1 值的一半以上。受控受试者数量扫描显示，训练受试者从 9 名增至 39 名时，性能提升幅度接近平稳，因此训练池仅作为稳定性下限，低于该下限时跨用户训练无法收敛；而在三个数据集上跟踪与基线比较方向的是 per-user 基线的强度，该强度由信号保真度决定。与 LDA 基线的比较取决于模型训练预算及该基线的优劣，且当监督模型得到充分训练后，自监督预训练无增益。
英文摘要：
Pattern-recognition control promises a myoelectric prosthesis that responds to many intended gestures rather than one or two, but the promise has stayed in the laboratory. A recogniser trained on one person rarely transfers to the next, and useful performance usually demands a fresh round of labelled calibration from the end user. A montage-agnostic encoder is introduced that reads each electrode with shared weights and locates it by its physical coordinate rather than its index, so one architecture ingests any channel count without montage-specific parameters. Trained across users, it exceeds a per-user Hudgins and linear-discriminant classifier by 0.234 macro-F1 on DB1 for every held-out subject and by 0.108 on DB2, and falls below it on the ten-subject DB5. Each of the encoder's three key components individually accounts for more than half of its 3-shot macro F1 in an otherwise budget-matched ablation study. A controlled subject-count sweep shows the margin is close to flat from nine training subjects to thirty-nine, so the training pool binds only as a stability floor below which cross-user training fails to converge; what tracks the direction of the comparison across the three databases is instead the strength of the per-user baseline, which signal fidelity sets. Comparing against an LDA baseline depends on budget spent training models and on how good that baseline is, and self-supervised pretraining had no benefits once a supervised model was adequately trained.
