Salvato in:
Dettagli Bibliografici
Autore principale: Kho, Carl Vincent Ladres
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2601.06516
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917194402627584
author Kho, Carl Vincent Ladres
author_facet Kho, Carl Vincent Ladres
contents Consumer-grade biosensors offer a cost-effective alternative to medical-grade electromyography (EMG) systems, reducing hardware costs from thousands of dollars to approximately $13. However, these low-cost sensors introduce significant signal instability and motion artifacts. Deploying machine learning models on resource-constrained edge devices like the ESP32 presents a challenge: balancing classification accuracy with strict latency (<100ms) and memory (<320KB) constraints. Using a single-subject dataset comprising 1,540 seconds of raw data (1.54M data points, segmented into ~1,300 one-second windows), I evaluate 18 model architectures, ranging from statistical heuristics to deep transfer learning (ResNet50) and custom hybrid networks (MaxCRNN). While my custom "MaxCRNN" (Inception + Bi-LSTM + Attention) achieved the highest safety (99% Precision) and robustness, I identify Random Forest (74% accuracy) as the Pareto-optimal solution for embedded control on legacy microcontrollers. I demonstrate that reliable, low-latency EMG control is feasible on commodity hardware, with Deep Learning offering a path to near-perfect reliability on modern Edge AI accelerators.
format Preprint
id arxiv_https___arxiv_org_abs_2601_06516
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Pareto-Optimal Model Selection for Low-Cost, Single-Lead EMG Control in Embedded Systems
Kho, Carl Vincent Ladres
Human-Computer Interaction
Machine Learning
Signal Processing
H.5.2; I.2.6; C.3
Consumer-grade biosensors offer a cost-effective alternative to medical-grade electromyography (EMG) systems, reducing hardware costs from thousands of dollars to approximately $13. However, these low-cost sensors introduce significant signal instability and motion artifacts. Deploying machine learning models on resource-constrained edge devices like the ESP32 presents a challenge: balancing classification accuracy with strict latency (<100ms) and memory (<320KB) constraints. Using a single-subject dataset comprising 1,540 seconds of raw data (1.54M data points, segmented into ~1,300 one-second windows), I evaluate 18 model architectures, ranging from statistical heuristics to deep transfer learning (ResNet50) and custom hybrid networks (MaxCRNN). While my custom "MaxCRNN" (Inception + Bi-LSTM + Attention) achieved the highest safety (99% Precision) and robustness, I identify Random Forest (74% accuracy) as the Pareto-optimal solution for embedded control on legacy microcontrollers. I demonstrate that reliable, low-latency EMG control is feasible on commodity hardware, with Deep Learning offering a path to near-perfect reliability on modern Edge AI accelerators.
title Pareto-Optimal Model Selection for Low-Cost, Single-Lead EMG Control in Embedded Systems
topic Human-Computer Interaction
Machine Learning
Signal Processing
H.5.2; I.2.6; C.3
url https://arxiv.org/abs/2601.06516