Constrained particle filtering for movement identification in forearm prosthesis

Nesrine Amor, Ghulam Rasool, Nidhal Bouaynaya, Roman Shterenberg

Research output: Contribution to journalArticle

Abstract

We formulate the problem of movement identification for the forearm prosthesis using a nonlinear state-space system and the hypothesis of muscle synergies. The synergy activation coefficients contain task-specific information and can be used to identify limb movements. In the proposed framework, the measurements are EMG data and the system state consists of muscle synergy activation coefficients, which are physiologically constrained to be nonnegative on average. Particle filters are the state-of-the-art techniques for optimal state estimation in nonlinear and non-Gaussian systems. However, the very numerical nature of the particle filters, which constitutes their strength, becomes their major weakness in handling constraints on the state. In this paper, we solve the movement identification problem by introducing a constrained particle filter termed as mean density truncation (MiND). We show that MiND minimally perturbs the unconstrained distribution of the state while simultaneously satisfying the desired constraints on the unknown state. We recorded EMG data from forearm muscles of 12 participants for identification of hand and wrist movements. The proposed particle filtering with MiND provided an accurate stream of synergy activation coefficients (p < 0.001) which were used for movement identification with error rates significantly lower (p < 0.05) than currently used heuristics and Linear Discriminate Analysis.

Original languageEnglish (US)
Pages (from-to)25-35
Number of pages11
JournalSignal Processing
Volume161
DOIs
StatePublished - Aug 1 2019

Fingerprint

Muscle
Chemical activation
State estimation
Prostheses and Implants

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

@article{beb6d858711748d8bc787f2da6d92485,
title = "Constrained particle filtering for movement identification in forearm prosthesis",
abstract = "We formulate the problem of movement identification for the forearm prosthesis using a nonlinear state-space system and the hypothesis of muscle synergies. The synergy activation coefficients contain task-specific information and can be used to identify limb movements. In the proposed framework, the measurements are EMG data and the system state consists of muscle synergy activation coefficients, which are physiologically constrained to be nonnegative on average. Particle filters are the state-of-the-art techniques for optimal state estimation in nonlinear and non-Gaussian systems. However, the very numerical nature of the particle filters, which constitutes their strength, becomes their major weakness in handling constraints on the state. In this paper, we solve the movement identification problem by introducing a constrained particle filter termed as mean density truncation (MiND). We show that MiND minimally perturbs the unconstrained distribution of the state while simultaneously satisfying the desired constraints on the unknown state. We recorded EMG data from forearm muscles of 12 participants for identification of hand and wrist movements. The proposed particle filtering with MiND provided an accurate stream of synergy activation coefficients (p < 0.001) which were used for movement identification with error rates significantly lower (p < 0.05) than currently used heuristics and Linear Discriminate Analysis.",
author = "Nesrine Amor and Ghulam Rasool and Nidhal Bouaynaya and Roman Shterenberg",
year = "2019",
month = "8",
day = "1",
doi = "10.1016/j.sigpro.2019.03.012",
language = "English (US)",
volume = "161",
pages = "25--35",
journal = "Signal Processing",
issn = "0165-1684",
publisher = "Elsevier",

}

Constrained particle filtering for movement identification in forearm prosthesis. / Amor, Nesrine; Rasool, Ghulam; Bouaynaya, Nidhal; Shterenberg, Roman.

In: Signal Processing, Vol. 161, 01.08.2019, p. 25-35.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Constrained particle filtering for movement identification in forearm prosthesis

AU - Amor, Nesrine

AU - Rasool, Ghulam

AU - Bouaynaya, Nidhal

AU - Shterenberg, Roman

PY - 2019/8/1

Y1 - 2019/8/1

N2 - We formulate the problem of movement identification for the forearm prosthesis using a nonlinear state-space system and the hypothesis of muscle synergies. The synergy activation coefficients contain task-specific information and can be used to identify limb movements. In the proposed framework, the measurements are EMG data and the system state consists of muscle synergy activation coefficients, which are physiologically constrained to be nonnegative on average. Particle filters are the state-of-the-art techniques for optimal state estimation in nonlinear and non-Gaussian systems. However, the very numerical nature of the particle filters, which constitutes their strength, becomes their major weakness in handling constraints on the state. In this paper, we solve the movement identification problem by introducing a constrained particle filter termed as mean density truncation (MiND). We show that MiND minimally perturbs the unconstrained distribution of the state while simultaneously satisfying the desired constraints on the unknown state. We recorded EMG data from forearm muscles of 12 participants for identification of hand and wrist movements. The proposed particle filtering with MiND provided an accurate stream of synergy activation coefficients (p < 0.001) which were used for movement identification with error rates significantly lower (p < 0.05) than currently used heuristics and Linear Discriminate Analysis.

AB - We formulate the problem of movement identification for the forearm prosthesis using a nonlinear state-space system and the hypothesis of muscle synergies. The synergy activation coefficients contain task-specific information and can be used to identify limb movements. In the proposed framework, the measurements are EMG data and the system state consists of muscle synergy activation coefficients, which are physiologically constrained to be nonnegative on average. Particle filters are the state-of-the-art techniques for optimal state estimation in nonlinear and non-Gaussian systems. However, the very numerical nature of the particle filters, which constitutes their strength, becomes their major weakness in handling constraints on the state. In this paper, we solve the movement identification problem by introducing a constrained particle filter termed as mean density truncation (MiND). We show that MiND minimally perturbs the unconstrained distribution of the state while simultaneously satisfying the desired constraints on the unknown state. We recorded EMG data from forearm muscles of 12 participants for identification of hand and wrist movements. The proposed particle filtering with MiND provided an accurate stream of synergy activation coefficients (p < 0.001) which were used for movement identification with error rates significantly lower (p < 0.05) than currently used heuristics and Linear Discriminate Analysis.

UR - http://www.scopus.com/inward/record.url?scp=85062953022&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062953022&partnerID=8YFLogxK

U2 - 10.1016/j.sigpro.2019.03.012

DO - 10.1016/j.sigpro.2019.03.012

M3 - Article

AN - SCOPUS:85062953022

VL - 161

SP - 25

EP - 35

JO - Signal Processing

JF - Signal Processing

SN - 0165-1684

ER -