Gait phase detection optimization based on variational bayesian inference of feedback sensor signal

Nebojša Malešević; Jovana Malešević; Thierry Keller

doi:10.1109/NEUREL.2014.7011499

Gait phase detection optimization based on variational bayesian inference of feedback sensor signal

Nebojša Malešević
, Jovana Malešević
, Thierry Keller

Foundation TECNALIA Research & Innovation
University of Belgrade

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Citations (Scopus)

Abstract

Stroke patients often suffer from gait disorders which can remain chronic. Mechanical or electrical aids designed to deal with this problem often rely on accurate estimation of current gait phase as this information is used for active ankle joint control. In this paper we present the method for optimization of the gait phase detection algorithm. The method is based on Variational Bayesian inference which is employed on signals from feedback sensors positioned on both paretic and healthy foot of patient. Main aim of Variational Bayesian inference application was to remove noise and provide smooth sensor signal which is suitable for robust gait phase detection algorithm. We modeled foot trajectory with linear model. Results presented in this paper show significant reduction of high frequency noise in gyroscope signal. The reduction was dominant during transitions between gait phases making our method applicable in any algorithm based on signal features in time domain.

Original language	English
Title of host publication	12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Proceedings
Editors	Branimir Reljin, Srdan Stankovic
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	179-182
Number of pages	4
ISBN (Electronic)	9781479958887
DOIs	https://doi.org/10.1109/NEUREL.2014.7011499
Publication status	Published - 15 Jan 2014
Event	12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Belgrade, Serbia Duration: 25 Nov 2014 → 27 Nov 2014

Publication series

Name	12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Proceedings

Conference

Conference	12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014
Country/Territory	Serbia
City	Belgrade
Period	25/11/14 → 27/11/14

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Bayesian inference
drop foot
FES
gait kinematics
variational

Access to Document

10.1109/NEUREL.2014.7011499

Cite this

Malešević, N., Malešević, J., & Keller, T. (2014). Gait phase detection optimization based on variational bayesian inference of feedback sensor signal. In B. Reljin, & S. Stankovic (Eds.), 12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Proceedings (pp. 179-182). Article 7011499 (12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/NEUREL.2014.7011499

Malešević, Nebojša ; Malešević, Jovana ; Keller, Thierry. / Gait phase detection optimization based on variational bayesian inference of feedback sensor signal. 12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Proceedings. editor / Branimir Reljin ; Srdan Stankovic. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 179-182 (12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Proceedings).

@inproceedings{4d035c5f1fc64bb2964655f4b522b15e,

title = "Gait phase detection optimization based on variational bayesian inference of feedback sensor signal",

abstract = "Stroke patients often suffer from gait disorders which can remain chronic. Mechanical or electrical aids designed to deal with this problem often rely on accurate estimation of current gait phase as this information is used for active ankle joint control. In this paper we present the method for optimization of the gait phase detection algorithm. The method is based on Variational Bayesian inference which is employed on signals from feedback sensors positioned on both paretic and healthy foot of patient. Main aim of Variational Bayesian inference application was to remove noise and provide smooth sensor signal which is suitable for robust gait phase detection algorithm. We modeled foot trajectory with linear model. Results presented in this paper show significant reduction of high frequency noise in gyroscope signal. The reduction was dominant during transitions between gait phases making our method applicable in any algorithm based on signal features in time domain.",

keywords = "Bayesian inference, drop foot, FES, gait kinematics, variational",

author = "Neboj{\v s}a Male{\v s}evi{\'c} and Jovana Male{\v s}evi{\'c} and Thierry Keller",

note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 ; Conference date: 25-11-2014 Through 27-11-2014",

year = "2014",

month = jan,

day = "15",

doi = "10.1109/NEUREL.2014.7011499",

language = "English",

series = "12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "179--182",

editor = "Branimir Reljin and Srdan Stankovic",

booktitle = "12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Proceedings",

address = "United States",

}

Malešević, N, Malešević, J & Keller, T 2014, Gait phase detection optimization based on variational bayesian inference of feedback sensor signal. in B Reljin & S Stankovic (eds), 12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Proceedings., 7011499, 12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 179-182, 12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014, Belgrade, Serbia, 25/11/14. https://doi.org/10.1109/NEUREL.2014.7011499

Gait phase detection optimization based on variational bayesian inference of feedback sensor signal. / Malešević, Nebojša; Malešević, Jovana; Keller, Thierry.
12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Proceedings. ed. / Branimir Reljin; Srdan Stankovic. Institute of Electrical and Electronics Engineers Inc., 2014. p. 179-182 7011499 (12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Gait phase detection optimization based on variational bayesian inference of feedback sensor signal

AU - Malešević, Nebojša

AU - Malešević, Jovana

AU - Keller, Thierry

PY - 2014/1/15

Y1 - 2014/1/15

N2 - Stroke patients often suffer from gait disorders which can remain chronic. Mechanical or electrical aids designed to deal with this problem often rely on accurate estimation of current gait phase as this information is used for active ankle joint control. In this paper we present the method for optimization of the gait phase detection algorithm. The method is based on Variational Bayesian inference which is employed on signals from feedback sensors positioned on both paretic and healthy foot of patient. Main aim of Variational Bayesian inference application was to remove noise and provide smooth sensor signal which is suitable for robust gait phase detection algorithm. We modeled foot trajectory with linear model. Results presented in this paper show significant reduction of high frequency noise in gyroscope signal. The reduction was dominant during transitions between gait phases making our method applicable in any algorithm based on signal features in time domain.

AB - Stroke patients often suffer from gait disorders which can remain chronic. Mechanical or electrical aids designed to deal with this problem often rely on accurate estimation of current gait phase as this information is used for active ankle joint control. In this paper we present the method for optimization of the gait phase detection algorithm. The method is based on Variational Bayesian inference which is employed on signals from feedback sensors positioned on both paretic and healthy foot of patient. Main aim of Variational Bayesian inference application was to remove noise and provide smooth sensor signal which is suitable for robust gait phase detection algorithm. We modeled foot trajectory with linear model. Results presented in this paper show significant reduction of high frequency noise in gyroscope signal. The reduction was dominant during transitions between gait phases making our method applicable in any algorithm based on signal features in time domain.

KW - Bayesian inference

KW - drop foot

KW - FES

KW - gait kinematics

KW - variational

UR - https://www.scopus.com/pages/publications/84922822850

U2 - 10.1109/NEUREL.2014.7011499

DO - 10.1109/NEUREL.2014.7011499

M3 - Conference contribution

AN - SCOPUS:84922822850

T3 - 12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Proceedings

SP - 179

EP - 182

BT - 12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Proceedings

A2 - Reljin, Branimir

A2 - Stankovic, Srdan

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014

Y2 - 25 November 2014 through 27 November 2014

ER -

Malešević N, Malešević J, Keller T. Gait phase detection optimization based on variational bayesian inference of feedback sensor signal. In Reljin B, Stankovic S, editors, 12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2014. p. 179-182. 7011499. (12th Symposium on Neural Network Applications in Electrical Engineering, NEUREL 2014 - Proceedings). doi: 10.1109/NEUREL.2014.7011499

Gait phase detection optimization based on variational bayesian inference of feedback sensor signal

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this