Objective: Although many advancements have been made on myoelectric pattern-recognition, the control of polyarticulated upper-limb prostheses remains insufficiently robust. Electrode-shift, sweat or fatigue degrade the performance of classifiers over time, resulting in unfruitful device usage and frequent re-calibration. To tackle this issue, here we introduce two models 􀀀 μP6 and μP8 􀀀 that combine Geometric Algebra with nearest-neighbor classification. We aim at reducing both the necessary training data and training time and, unlike most current state-of-the-art algorithms, we exploit an alternative geometric representation (and visualization) of the EMG signal as different polygons for different types of gestures, facilitating the explanation of the decision-making process to a layman. Moreover, we explore four abstention strategies to reduce the number of misclassifications. Methods: We perform an offline analysis on two datasets, alongside two other standard models: nonlinear logistic regression (NLR) and linear discriminant analysis (LDA). Results: Even with few training data, the proposed algorithms achieve high F1-scores (>0.95), significantly higher or non-significantly different from the values obtained with NLR and LDA, while maintaining relatively low abstentions rates and training times (<2 ms). Conclusion: The proposed algorithms allow to reduce the amount of training data and training times without compromising recognition rates. Significance: The proposed algorithms may contribute for a faster prosthesis re-calibration procedure while allowing to re-gain high recognition rates. Furthermore, the decision-making process is explainable and interpretable, potentially improving user trust and acceptance.

Calado, A., Roselli, P., Gruppioni, E., Marinelli, A., Bellingegni, A.d., Boccardo, N., et al. (2024). A geometric algebra-based approach for myoelectric pattern recognition control and faster prosthesis recalibration. EXPERT SYSTEMS WITH APPLICATIONS [10.1016/j.eswa.2024.124373].

A geometric algebra-based approach for myoelectric pattern recognition control and faster prosthesis recalibration

Alexandre Calado
;
Paolo Roselli;Giovanni Saggio
2024-06-01

Abstract

Objective: Although many advancements have been made on myoelectric pattern-recognition, the control of polyarticulated upper-limb prostheses remains insufficiently robust. Electrode-shift, sweat or fatigue degrade the performance of classifiers over time, resulting in unfruitful device usage and frequent re-calibration. To tackle this issue, here we introduce two models 􀀀 μP6 and μP8 􀀀 that combine Geometric Algebra with nearest-neighbor classification. We aim at reducing both the necessary training data and training time and, unlike most current state-of-the-art algorithms, we exploit an alternative geometric representation (and visualization) of the EMG signal as different polygons for different types of gestures, facilitating the explanation of the decision-making process to a layman. Moreover, we explore four abstention strategies to reduce the number of misclassifications. Methods: We perform an offline analysis on two datasets, alongside two other standard models: nonlinear logistic regression (NLR) and linear discriminant analysis (LDA). Results: Even with few training data, the proposed algorithms achieve high F1-scores (>0.95), significantly higher or non-significantly different from the values obtained with NLR and LDA, while maintaining relatively low abstentions rates and training times (<2 ms). Conclusion: The proposed algorithms allow to reduce the amount of training data and training times without compromising recognition rates. Significance: The proposed algorithms may contribute for a faster prosthesis re-calibration procedure while allowing to re-gain high recognition rates. Furthermore, the decision-making process is explainable and interpretable, potentially improving user trust and acceptance.
giu-2024
Pubblicato
Rilevanza internazionale
Articolo
Esperti anonimi
Settore MAT/05
Settore MATH-02/A - Algebra
English
Classifier design; Machine learning; Pattern recognition; Prosthetics; Geometric algebra
Calado, A., Roselli, P., Gruppioni, E., Marinelli, A., Bellingegni, A.d., Boccardo, N., et al. (2024). A geometric algebra-based approach for myoelectric pattern recognition control and faster prosthesis recalibration. EXPERT SYSTEMS WITH APPLICATIONS [10.1016/j.eswa.2024.124373].
Calado, A; Roselli, P; Gruppioni, E; Marinelli, A; Bellingegni, Ad; Boccardo, N; Saggio, G
Articolo su rivista
File in questo prodotto:
File Dimensione Formato  
1-s2.0-S0957417424012399-main.pdf

solo utenti autorizzati

Tipologia: Versione Editoriale (PDF)
Licenza: Copyright dell'editore
Dimensione 4.72 MB
Formato Adobe PDF
4.72 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2108/394800
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact