超轻量卷积模型实现穿戴设备上高精度步态检测，节省10倍参数。
Time-Series at the Edge: Tiny Separable CNNs for Wearable Gait Detection and Optimal Sensor Placement
- 用极简分离卷积网络处理三轴加速度数据，适合资源受限设备。
- 最小模型仅305参数，仍达PR-AUC 94.0%、F1 91.0%、MCC 89.1%。
- 胸部和大腿传感器效果最佳，可直接在设备端运行，减少传输开销。
本文研究在资源受限的可穿戴设备与边缘节点上，基于短时三轴加速度信号进行帕金森病步态检测的本地化时间序列分析。对比幅度阈值法与三种一维CNN：文献基准（可分离卷积）及两种超轻量模型——纯可分离与带残差连接的模型。使用BioStampRC21数据集，2秒窗口、30 Hz采样率，16名患者（佩戴胸式IMU）采用留一人排除验证。结果表明，带有残差的可分离模型（模型2，533参数）取得PR-AUC 94.5%、F1 91.2%、MCC 89.4%，性能媲美或超越基准模型（5,552参数；PR-AUC 93.7%、F1 90.5%、MCC 88.5%），参数量减少约10倍。最小模型（模型1，305参数）达PR-AUC 94.0%、F1 91.0%、MCC 89.1%。阈值法虽召回率高（89.0%），但精确率低（76.5%），误报多且个体差异大。传感器位置分析显示胸与大腿最可靠；前臂因非步态动作降低性能；全部位融合未优于最优单部位。两种紧凑模型均能在STM32类微控制器上实现亚10毫秒延迟，支持设备端数据筛选与存储控制。总体而言，超轻量可分离CNN在精度-效率-泛化间表现更优，凸显针对边缘部署定制时间序列模型的价值。
原文摘要 · Abstract (English)
We study on-device time-series analysis for gait detection in Parkinson's disease (PD) from short windows of triaxial acceleration, targeting resource-constrained wearables and edge nodes. We compare magnitude thresholding to three 1D CNNs for time-series analysis: a literature baseline (separable convolutions) and two ultra-light models - one purely separable and one with residual connections. Using the BioStampRC21 dataset, 2 s windows at 30 Hz, and subject-independent leave-one-subject-out (LOSO) validation on 16 PwPD with chest-worn IMUs, our residual separable model (Model 2, 533 params) attains PR-AUC = 94.5%, F1 = 91.2%, MCC = 89.4%, matching or surpassing the baseline (5,552 params; PR-AUC = 93.7%, F1 = 90.5%, MCC = 88.5%) with approximately 10x fewer parameters. The smallest model (Model 1, 305 params) reaches PR-AUC = 94.0%, F1 = 91.0%, MCC = 89.1%. Thresholding obtains high recall (89.0%) but low precision (76.5%), yielding many false positives and high inter-subject variance. Sensor-position analysis (train-on-all) shows chest and thighs are most reliable; forearms degrade precision/recall due to non-gait arm motion; naive fusion of all sites does not outperform the best single site. Both compact CNNs execute within tight memory/latency budgets on STM32-class MCUs (sub-10 ms on low-power boards), enabling on-sensor gating of transmission/storage. Overall, ultra-light separable CNNs provide a superior accuracy-efficiency-generalization trade-off to fixed thresholds for wearable PD gait detection and underscore the value of tailored time-series models for edge deployment.
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。