Diffusionref imu improves wearable sensor data translation across locations
DiffusionRef-IMU: Guide-Anchored Residual Diffusion for Cross-Location Inertial Measurement Unit Translation
Machine Learning
Summary
Wearable sensors called inertial measurement units (IMUs) record movement, but signals they capture vary depending on where on the body they are placed. This makes it hard to learn or predict signals in one location if only data from another location is available. The authors propose a two-step method where they first guess the target sensor signal and then use a special refinement method called diffusion to improve the prediction. Their approach works better than related methods in tests, although it has mixed results when applied to completely new datasets without any examples.
What this means in practice
- •For wearable device developers: Improve sensor data prediction at different body locations without collecting new data for each location, enabling better movement tracking with fewer sensors.
- •For sports analytics teams: Enhance accuracy of motion analysis from wearable sensors placed at varied body parts, aiding training and injury prevention without retraining models per location.
Authors
M. M. Golam Hafiz, Safia Akter Simi, Md. Rakibul Islam, M. F. Mridha
Abstract
Cross-location variation in wearable inertial measurement unit (IMU) signals complicates learning when measurements from a desired target body location are unavailable. This study proposes DiffusionRef-IMU, a two-stage cross-location translation framework in which a deterministic Direct network first estimates the target signal and a guide-anchored residual diffusion model refines only the remaining target discrepancy. The evaluation comprises five subject-disjoint activity-location composition-held-out folds, capacity-matched deterministic and flow-based residual baselines, source-only activity conditioning, computational ablation, and true zero-shot evaluation on two independent datasets. DiffusionRef-IMU with 16-step deterministic DDIM achieved a mean nRMSE of 0.087538 +/- 0.004922, compared with 0.090262 for Direct, 0.088847 for deterministic residual refinement, and 0.088417 for eight-step CompFlow, and outperformed each baseline in all five folds. Four-step DDIM retained a mean nRMSE of 0.087820 at 47.62 ms per window, providing a favourable quality-computation trade-off. Replacing ground-truth activity conditioning with a source-only activity predictor (macro-F1 0.8473) increased 16-step DiffusionRef nRMSE only to 0.088190. True zero-shot evaluation produced mixed results: DiffusionRef was marginally favourable on Grouvel2025 but remained worse than Direct on Saldaña2025. Overall, guide-anchored residual diffusion improves controlled cross-location reconstruction while revealing clear limits in zero-shot external transfer.