Systematic Evaluation of sEMG Processing Pipelines for Gesture Recognition
Bioengineering · 01.09.2026 · 13 (9) · 1019
DOI: 10.3390/bioengineering13091019 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioengineering, online erschienen am 01.09.2026. Verfasst von Elsa Concha-Pérez und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Engineering and Sciences, Tecnologico de Monterrey, Ave. Eugenio Garza Sada 2501 Sur, Col: Tecnológico, Monterrey 64700, Nuevo León, Mexico. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Tecnológico de Monterrey, Ministry of Sciences, Humanities, Technology and Innovation, Secretaría de Ciencia, Humanidades, Tecnología e Innovación (SECIHTI), Mexico.
Abstract (Originalsprache)
Gesture recognition enables intuitive human–robot communication, where surface electromyography (sEMG) provides a minimally invasive interface for detecting motor activity. However, the lack of systematic evaluation of processing pipelines represents a critical barrier to reliable subject-independent deployment. This work presents a systematic evaluation of sEMG processing pipelines for three-gesture recognition (Neutral, Ask, Take) using a Bagged Trees classifier under Leave-One-Subject-Out (LOSO) cross-validation across ten participants. A mixed-effects ANOVA over 1872 experimental configurations revealed that the preprocessing pipeline is the dominant factor affecting classification accuracy, followed by inter-subject variability, while window size and overlap exhibit smaller but statistically significant effects. A consistency-based elbow analysis identified a compact subset of five features that reduced input dimensionality by 94.79% while improving accuracy from 68.10% to 69.86% and reducing training time by 51.62%. Bayesian hyperparameter optimization was also tested, but it did not yield statistically significant improvements over the five-feature baseline; given the limited cohort (n = 10), this indicates the absence of a detectable difference and points to inter-subject variability as a leading factor limiting performance rather than model configuration. These findings provide empirically grounded guidelines for designing computationally efficient sEMG-based gesture recognition systems for collaborative robotics.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Engineering and Sciences, Tecnologico de Monterrey, Ave. Eugenio Garza Sada 2501 Sur, Col: Tecnológico, Monterrey 64700, Nuevo León, Mexico.
- Instituto Tecnológico de Orizaba, Tecnológico Nacional de México, Orizaba 94320, Veracruz, Mexico.
ORCID-Profile: Elsa Concha-Pérez, Jorge A Reyes-Avendaño, Hugo G Gonzalez-Hernandez, Maricruz Concha-Pérez
Förderung
- Tecnológico de Monterrey
- Ministry of Sciences, Humanities, Technology and Innovation
- Secretaría de Ciencia, Humanidades, Tecnología e Innovación (SECIHTI), Mexico
- Tecnologico de Monterrey
Zitieren
APA
Concha-Pérez, E., Reyes-Avendaño, J. A., Gonzalez-Hernandez, H. G., & Concha-Pérez, M. (2026). Systematic Evaluation of sEMG Processing Pipelines for Gesture Recognition. Bioengineering, 13(9), 1019. https://doi.org/10.3390/bioengineering13091019
Vancouver
Concha-Pérez E, Reyes-Avendaño JA, Gonzalez-Hernandez HG, Concha-Pérez M. Systematic Evaluation of sEMG Processing Pipelines for Gesture Recognition. Bioengineering. 2026;13(9):1019. doi:10.3390/bioengineering13091019
BibTeX
@article{ConchaPrez2026,
author = {Concha-Pérez, Elsa and Reyes-Avendaño, Jorge A and Gonzalez-Hernandez, Hugo G and Concha-Pérez, Maricruz},
title = {Systematic Evaluation of sEMG Processing Pipelines for Gesture Recognition},
journal = {Bioengineering},
year = {2026},
volume = {13},
number = {9},
pages = {1019},
doi = {10.3390/bioengineering13091019}
}
EUVIMED