[论文] Bio-PM-Guided Synthetic IMU Generation
论文概要
研究领域: ML
作者: Deepali Singh, Deepesh Parpani, Aviral Gupta
发布时间: 2026-11-19
arXiv: 2611.26607
中文摘要
收集和标注人体活动识别(HAR)的惯性测量单元(IMU)数据成本高昂,且在一组受试者上训练的模型往往无法泛化到未见个体。即使有平衡数据,分类器仍难以区分动态相似的活动类别,需要针对性数据增强。我们探索:在预训练生物信号编码器Bio-PM的表征空间中生成的合成IMU数据能否作为实用的增强来源。我们不合成原始信号,而是利用Bio-PM的冻结编码器将10秒IMU窗口转换为token嵌入序列,并在此空间训练类别条件解码器:(1)自回归Transformer解码器顺序预测token;(2)扩散解码器通过去噪目标学习token分布。我们通过分布指标和嵌入空间可视化分析生成真实性,通过留一受试者HAR分类评估下游效用,并提出PatchDecoder近似重建原始波形。扩散解码器在合成训练真实测试(TSTR)上取得0.68的宏F1,证明生成的token足够真实。将合成token增强与320维重力感知特征表征结合,在WISDM基准51名受试者上将留一宏F1从0.729提升至0.809,统计显著增益集中在最具挑战性的活动类别。这些结果表明,在预训练编码器表征空间中实现高保真生成是可行的,且对跨受试者HAR增强具有实际价值。
原文摘要
Collecting and labeling inertial measurement unit (IMU) data for human activity recognition (HAR) is expensive, and models trained on one group of subjects often fail to generalize to unseen individuals. Even with balanced data, classifiers struggle to distinguish dynamically similar activity classes and benefit from targeted augmentation. We explore whether synthetic IMU data generated in the representation space of a pretrained biosignal encoder, Bio-PM, can serve as a practical augmentation source. Rather than synthesizing raw signals, we leverage Bio-PM's frozen encoder to convert 10-second IMU windows into token embedding sequences and train class-conditional decoders in this space: (1) an autoregressive transformer decoder that predicts tokens sequentially, and (2) a diffusion decode...
自动采集于 2026-11-21
#论文 #arXiv #ML #小凯