Guardado en:
Detalles Bibliográficos
Autores principales: Procopio, Andrea, Esposito, Marco, Raggiunto, Sara, Gizdov, Andrey, Belli, Alberto, Pierleoni, Paola
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2512.00396
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908706989408256
author Procopio, Andrea
Esposito, Marco
Raggiunto, Sara
Gizdov, Andrey
Belli, Alberto
Pierleoni, Paola
author_facet Procopio, Andrea
Esposito, Marco
Raggiunto, Sara
Gizdov, Andrey
Belli, Alberto
Pierleoni, Paola
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_00396
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Time-Series at the Edge: Tiny Separable CNNs for Wearable Gait Detection and Optimal Sensor Placement
Procopio, Andrea
Esposito, Marco
Raggiunto, Sara
Gizdov, Andrey
Belli, Alberto
Pierleoni, Paola
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Image and Video Processing
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.
title Time-Series at the Edge: Tiny Separable CNNs for Wearable Gait Detection and Optimal Sensor Placement
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2512.00396