Confidence-gated temporal voting for EMG-based prosthetic arm control: a low-cost end-to-end pipeline with quantified rejection behaviour.
- 1School of Engineering and Science, MIT ADT Campus, MIT Art, Design and Technology University, Pune, Maharashtra, India.
- 2K. J. Somaiya School of Engineering, Somaiya Vidyavihar University, Mumbai, India.
Abstract
Background
Surface electromyography (sEMG) is the dominant non-invasive route to volitional prosthetic control, but a closed-world classifier issues a command for every input, including inputs corresponding to no trained gesture. This study evaluated a low-cost, three-gesture sEMG control pipeline combining a Random Forest classifier with rejection on the maximum Random-Forest class probability and temporal majority voting, and measured the resulting rejection behaviour rather than assuming it.Methods
Three data sources were analysed: modelled synthetic sEMG; Ninapro DB5 (10 subjects, 16 channels at 200 Hz, documented three-channel subset); and live three-channel sEMG from 13 healthy limb-intact adults recorded over three sessions with MyoWare sensors spaced equally around the forearm flexor group. Each of the 117 recordings lasted 120 s, comprising a 60 s continuous phase and four 10 s sustained contractions separated by 5 s of rest, yielding 21,294 windows of which 4,212 were rest. Channel interleaving gave an effective 333.3 Hz per channel. All datasets were segmented in physical time (0.6 s window, 0.2 s overlap) without resampling, and four time-domain features (MAV, RMS, WL, ZC) were classified by a 100-tree Random Forest. Evaluation used repetition-level, cross-session and leave-one-participant-out (LOPO) splits, with calibration and threshold selection confined to a participant-disjoint partition. Models were trained and tested within each domain, so the three accuracies index benchmark difficulty rather than transfer.Results
LOPO accuracy was 80.2% (synthetic), 74.5% (DB5) and 80.2% (live). The pooled window-level split used originally overestimated live accuracy by 7.7 percentage points. Expected calibration error was 0.147 uncalibrated and 0.038 after Platt scaling. Open-set AUROC was 0.842 against rest, 0.784 under electrode displacement and 0.741 for held-out movements, and 7.4% of windows were confidently incorrect. The complete pipeline reduced false actuation from 19.80% to 5.00% and command switching from 0.16 to 0.02 s-1 , while rejecting 18.40% of windows and raising median latency from 0.60 to 1.95 s. The prototype completed 12 of 15 benchtop trials.Conclusion
The results support a benchtop engineering proof of concept with quantified rejection and latency behaviour, not clinical safety or deployment readiness.
Related
- MRCER-DR: Multi-Representation Confidence Entropy Rejection for IoT Open-Set Intrusion Detection
- Proactive early invisible spoilage-risk prediction through uncertainty-quantified temporal microbial growth intelligence
- Similar discrimination, different behaviour under synthetic occlusion: confidence and attribution reproducibility of deep learning models for intraoral ultrasonography
- Bayesian Confidence Recalibration and Research-Equilibrium Criticality: Temporal Support in Robust Portfolios
- Transformer-aided guard: A hybrid spatio-temporal framework for confidence-aware intrusion detection in cyber-physical systems
BibTeX
@article{shinde2026confidencegated,
title = {{Confidence-gated temporal voting for EMG-based prosthetic arm control: a low-cost end-to-end pipeline with quantified rejection behaviour.}},
author = {Anagha Shinde and Virendra Shete and Ninad Mehendale},
journal = {Frontiers in rehabilitation sciences},
year = {2026},
month = oct,
doi = {10.3389/fresc.2026.1864998},
url = {https://europepmc.org/article/MED/42909049},
note = {CC BY},
}
RIS
TY - JOUR
TI - Confidence-gated temporal voting for EMG-based prosthetic arm control: a low-cost end-to-end pipeline with quantified rejection behaviour.
AU - Anagha Shinde
AU - Virendra Shete
AU - Ninad Mehendale
PY - 2026
DA - 2026/10/07
JO - Frontiers in rehabilitation sciences
DO - 10.3389/fresc.2026.1864998
UR - https://europepmc.org/article/MED/42909049
AB - Background Surface electromyography (sEMG) is the dominant non-invasive route to volitional prosthetic control, but a closed-world classifier issues a command for every input, including inputs corresponding to no trained gesture. This study evaluated a low-cost, three-gesture sEMG control pipeline combining a Random Forest classifier with rejection on the maximum Random-Forest class probability and temporal majority voting, and measured the resulting rejection behaviour rather than assuming it.Methods Three data sources were analysed: modelled synthetic sEMG; Ninapro DB5 (10 subjects, 16 channels at 200 Hz, documented three-channel subset); and live three-channel sEMG from 13 healthy limb-intact adults recorded over three sessions with MyoWare sensors spaced equally around the forearm flexor group. Each of the 117 recordings lasted 120 s, comprising a 60 s continuous phase and four 10 s sustained contractions separated by 5 s of rest, yielding 21,294 windows of which 4,212 were rest. Channel interleaving gave an effective 333.3 Hz per channel. All datasets were segmented in physical time (0.6 s window, 0.2 s overlap) without resampling, and four time-domain features (MAV, RMS, WL, ZC) were classified by a 100-tree Random Forest. Evaluation used repetition-level, cross-session and leave-one-participant-out (LOPO) splits, with calibration and threshold selection confined to a participant-disjoint partition. Models were trained and tested within each domain, so the three accuracies index benchmark difficulty rather than transfer.Results LOPO accuracy was 80.2% (synthetic), 74.5% (DB5) and 80.2% (live). The pooled window-level split used originally overestimated live accuracy by 7.7 percentage points. Expected calibration error was 0.147 uncalibrated and 0.038 after Platt scaling. Open-set AUROC was 0.842 against rest, 0.784 under electrode displacement and 0.741 for held-out movements, and 7.4% of windows were confidently incorrect. The complete pipeline reduced false actuation from 19.80% to 5.00% and command switching from 0.16 to 0.02 s-1 , while rejecting 18.40% of windows and raising median latency from 0.60 to 1.95 s. The prototype completed 12 of 15 benchtop trials.Conclusion The results support a benchtop engineering proof of concept with quantified rejection and latency behaviour, not clinical safety or deployment readiness.
SN - 2673-6861
ER -