A Comparative Optimization Procedure to Evaluate Pattern Recognition Algorithms on Hannes Prosthesis

13 Pages Posted: 28 Apr 2023

See all articles by Andrea Marinelli

Andrea Marinelli

Istituto Italiano di Tecnologia

Michele Canepa

Istituto Italiano di Tecnologia

Dario Di Domenico

Istituto Italiano di Tecnologia

Emanuele Gruppioni

affiliation not provided to SSRN

Matteo Laffranchi

Istituto Italiano di Tecnologia

Lorenzo De Michieli

affiliation not provided to SSRN

Michela Chiappalone

affiliation not provided to SSRN

Marianna Semprini

affiliation not provided to SSRN

Nicolò Boccardo

Istituto Italiano di Tecnologia

Abstract

Stability and repeatability of Pattern Recognition (PR) myoelectric control for upper limb prosthetic devices remain unresolved challenges in multi-DoFs systems. In this study, we tested several state-of-the-art classifiers to compare their offline performance in different configurations. Parameters such as realization costs, overall encumbrance, and algorithm complexity were considered for the analysis. The results showed that NLR performed comparably to LDA but with fewer EMG sensors. This study demonstrated that sensor numbers can be reduced to a few units for various algorithms, with NLR being the most tolerant due to its non-linearity. In conclusion, NLR can effectively control the multi-DoFs Hannes system in real-time, offering similar performances to other algorithms while reducing the system's complexity and encumbrance as compared to LDA. It also offers improved tolerance to reduced available information and lower implementation costs.

Keywords: Pattern recognition control, real-time, Hannes system, EMG sensors, NLR and LDA algorithms

Suggested Citation

Marinelli, Andrea and Canepa, Michele and Di Domenico, Dario and Gruppioni, Emanuele and Laffranchi, Matteo and De Michieli, Lorenzo and Chiappalone, Michela and Semprini, Marianna and Boccardo, Nicolò, A Comparative Optimization Procedure to Evaluate Pattern Recognition Algorithms on Hannes Prosthesis. Available at SSRN: https://ssrn.com/abstract=4431994 or http://dx.doi.org/10.2139/ssrn.4431994

Andrea Marinelli (Contact Author)

Istituto Italiano di Tecnologia ( email )

Michele Canepa

Istituto Italiano di Tecnologia ( email )

Dario Di Domenico

Istituto Italiano di Tecnologia ( email )

Emanuele Gruppioni

affiliation not provided to SSRN ( email )

No Address Available

Matteo Laffranchi

Istituto Italiano di Tecnologia ( email )

Lorenzo De Michieli

affiliation not provided to SSRN ( email )

No Address Available

Michela Chiappalone

affiliation not provided to SSRN ( email )

No Address Available

Marianna Semprini

affiliation not provided to SSRN ( email )

No Address Available

Nicolò Boccardo

Istituto Italiano di Tecnologia ( email )

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
56
Abstract Views
240
Rank
789,873
PlumX Metrics