Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Neurotremor: A wearable Supportive Device for Supporting Upper Limb Muscle Function

Aueaphum Aueawattthanaphisut, Thanyanee Srichaisak, Arissa Ieochai

TL;DR

The paper tackles upper-limb weakness and tremor from myopathies by delivering an embedded, sensor-fused wearable that combines sEMG, IMU, and flex/force sensing with on-device INT8 inference and a control barrier safety envelope. The end-to-end pipeline—from real-time feature extraction (RMS, MAV, ZC, tremor power, TI, fatigue) to INT8-powered assist and safety-bounded control—achieves closed-loop operation at 100 Hz with sub-10 ms latency. In a pilot study with 12 healthy volunteers performing ADL-like tasks, the system reduced tremor prominence (TI), increased range of motion and repetitions, and showed fatigue stabilization, all without adverse events. These findings support the technical feasibility of clinic-to-home embedded assistance for upper-limb function, with future IRB-approved patient trials planned to establish clinical utility.

Abstract

A sensor-fused wearable assistance prototype for upper-limb function (triceps brachii and extensor pollicis brevis) is presented. The device integrates surface electromyography (sEMG), an inertial measurement unit (IMU), and flex/force sensors on an M5StickC plus an ESP32-S3 compute hub. Signals are band-pass and notch filtered; features (RMS, MAV, zero-crossings, and 4-12 Hz tremor-band power) are computed in 250 ms windows and fed to an INT8 TensorFlow Lite Micro model. Control commands are bounded by a control-barrier-function safety envelope and delivered within game-based tasks with lightweight personalization. In a pilot technical feasibility evaluation with healthy volunteers (n = 12) performing three ADL-oriented tasks, tremor prominence decreased (Delta TI = -0.092, 95% CI [-0.102, -0.079]), range of motion increased (+12.65%, 95% CI [+8.43, +13.89]), repetitions rose (+2.99 min^-1, 95% CI [+2.61, +3.35]), and the EMG median-frequency slope became less negative (Delta = +0.100 Hz/min, 95% CI [+0.083, +0.127]). The sensing-to-assist loop ran at 100 Hz with 8.7 ms median on-device latency, 100% session completion, and 0 device-related adverse events. These results demonstrate technical feasibility of embedded, sensor-fused assistance for upper-limb function; formal patient studies under IRB oversight are planned.

Neurotremor: A wearable Supportive Device for Supporting Upper Limb Muscle Function

TL;DR

The paper tackles upper-limb weakness and tremor from myopathies by delivering an embedded, sensor-fused wearable that combines sEMG, IMU, and flex/force sensing with on-device INT8 inference and a control barrier safety envelope. The end-to-end pipeline—from real-time feature extraction (RMS, MAV, ZC, tremor power, TI, fatigue) to INT8-powered assist and safety-bounded control—achieves closed-loop operation at 100 Hz with sub-10 ms latency. In a pilot study with 12 healthy volunteers performing ADL-like tasks, the system reduced tremor prominence (TI), increased range of motion and repetitions, and showed fatigue stabilization, all without adverse events. These findings support the technical feasibility of clinic-to-home embedded assistance for upper-limb function, with future IRB-approved patient trials planned to establish clinical utility.

Abstract

A sensor-fused wearable assistance prototype for upper-limb function (triceps brachii and extensor pollicis brevis) is presented. The device integrates surface electromyography (sEMG), an inertial measurement unit (IMU), and flex/force sensors on an M5StickC plus an ESP32-S3 compute hub. Signals are band-pass and notch filtered; features (RMS, MAV, zero-crossings, and 4-12 Hz tremor-band power) are computed in 250 ms windows and fed to an INT8 TensorFlow Lite Micro model. Control commands are bounded by a control-barrier-function safety envelope and delivered within game-based tasks with lightweight personalization. In a pilot technical feasibility evaluation with healthy volunteers (n = 12) performing three ADL-oriented tasks, tremor prominence decreased (Delta TI = -0.092, 95% CI [-0.102, -0.079]), range of motion increased (+12.65%, 95% CI [+8.43, +13.89]), repetitions rose (+2.99 min^-1, 95% CI [+2.61, +3.35]), and the EMG median-frequency slope became less negative (Delta = +0.100 Hz/min, 95% CI [+0.083, +0.127]). The sensing-to-assist loop ran at 100 Hz with 8.7 ms median on-device latency, 100% session completion, and 0 device-related adverse events. These results demonstrate technical feasibility of embedded, sensor-fused assistance for upper-limb function; formal patient studies under IRB oversight are planned.
Paper Structure (22 sections, 13 equations, 3 figures, 2 tables)

This paper contains 22 sections, 13 equations, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. System Architecture and Sensing
  5. Sampling.
  6. Preprocessing
  7. Feature Extraction
  8. On-Device Inference (INT8)
  9. Control and Safety Envelope
  10. Personalization (On-Device Adaptation)
  11. Outcome Computation
  12. Calibration and Synchronization
  13. Implementation Details
  14. Results and Analysis
  15. Cohorts, Tasks, and Statistical Plan
  16. ...and 7 more sections

Figures (3)

  • Figure 1: Clinical need—upper-limb pain points (weakness, tremor 4–12 Hz, fatigue, limited ROM) and target actions (push, reach, grip/pinch); target muscles: triceps brachii, extensor pollicis brevis.
  • Figure 2: System architecture and processing pipeline
  • Figure 3: Primary outcomes displayed side-by-side: (a) Tremor Index, (b) ROM gain, and (c) personalization curves.