用物理规律约束模型，让手机端动作识别更稳定可靠。
PI-TTA: Physics-Informed Source-Free Test-Time Adaptation for Robust Human Activity Recognition on Mobile Devices
- 引入重力、时序连续性等物理约束，稳定无源测试时自适应过程。
- 在长序列测试中准确率最高提升9.13%，物理违规率下降超45%。
- 轻量级设计适合移动端部署，特别适合穿戴设备持续感知场景。
无源测试时自适应（TTA）对移动与可穿戴传感极具吸引力，可在不集中私有数据的前提下实现设备端个性化。但基于传感器的动作识别（HAR）面临时序相关性与会话内漂移（如传感器旋转、位置变化、采样率偏移）等挑战，传统视觉风格的TTA目标在非独立同分布流式设置下易不稳定，导致过度自信错误、表征崩溃和灾难性遗忘。本文提出PI-TTA，一种轻量级无源自适应框架，通过重力一致性、短时序连续性和频谱稳定性三项物理一致约束，稳定在线更新。其仅更新少量参数，计算开销小，适合设备端部署。在USCHAD、PAMAP2和mHealth数据集上，长序列压力测试与分解漂移协议下，PI-TTA显著缓解了信心驱动基线的严重性能退化，在持续流式条件下保持稳定适应能力。相比基线，准确率提升最高达9.13%，在三个数据集上物理违反率分别降低27.5%、24.1%和45.4%。结果表明，物理引导的自适应能有效提升真实移动感知系统的准确性、稳定性和部署可靠性。
原文摘要 · Abstract (English)
Source-free test-time adaptation (TTA) is appealing for mobile and wearable sensing because it enables on-device personalization from unlabeled test streams without centralizing private data. However, sensor-based human activity recognition (HAR) poses challenges that are less pronounced in standard vision benchmarks: behavioral inertial streams are temporally correlated and often exhibit within-session shifts caused by sensor rotation, placement change, and sampling-rate drift. Under this streaming non-i.i.d. setting, widely used vision-style TTA objectives can become unstable, leading to overconfident errors, representation collapse, and catastrophic forgetting. We propose PI-TTA, a lightweight source-free adaptation framework that stabilizes online updates through three physics-consistent constraints: gravity consistency, short-horizon temporal continuity, and spectral stability. PI-TTA updates the same small parameter subset as strong source-free baselines and incurs only modest overhead, making it suitable for on-device deployment. Experiments on USCHAD, PAMAP2, and mHealth under long-sequence stress tests and factorized shift protocols show that PI-TTA mitigates the severe degradation observed in confidence-driven baselines and preserves stable adaptation under sustained streaming conditions. It improves long-sequence accuracy by up to 9.13% and reduces physical-violation rates by 27.5%, 24.1%, and 45.4% on USCHAD, PAMAP2, and mHealth, respectively. These results demonstrate that physics-informed adaptation can improve accuracy, stability, and deployment reliability for real-world mobile sensing systems.
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。