Swing-phase detection from the ankle joint angle using recurrent neural networks

Sho Tokuda; Kunihisa Okano; Yukinori Nakamura; Kentaro Hirata

doi:10.1016/j.ifacol.2021.04.216

Swing-phase detection from the ankle joint angle using recurrent neural networks

Sho Tokuda, Kunihisa Okano, Yukinori Nakamura, Kentaro Hirata

Research output: Contribution to journal › Conference article › peer-review

Abstract

Identifying the current gait phase is a key in the control of ankle-foot orthoses, which assist ankle motion during walking. We address the problem to estimate whether the foot is in a swing or stance phase only from the ankle angle. A recurrent neural network with long-short-term-memory architecture is developed and evaluated with experimental data.

Original language	English
Pages (from-to)	291-296
Number of pages	6
Journal	IFAC-PapersOnLine
Volume	53
Issue number	5
DOIs	https://doi.org/10.1016/j.ifacol.2021.04.216
Publication status	Published - 2020
Event	3rd IFAC Workshop on Cyber-Physical and Human Systems, CPHS 2020 - Beijing, China Duration: Dec 3 2020 → Dec 5 2020

Keywords

Ankle-foot orthosis
gait analysis
long short-term memory
neural networks

ASJC Scopus subject areas

Control and Systems Engineering

Access to Document

10.1016/j.ifacol.2021.04.216

Cite this

@article{cd18442878a0463b9f3a47a0f7a36f5b,

title = "Swing-phase detection from the ankle joint angle using recurrent neural networks",

abstract = "Identifying the current gait phase is a key in the control of ankle-foot orthoses, which assist ankle motion during walking. We address the problem to estimate whether the foot is in a swing or stance phase only from the ankle angle. A recurrent neural network with long-short-term-memory architecture is developed and evaluated with experimental data.",

keywords = "Ankle-foot orthosis, gait analysis, long short-term memory, neural networks",

author = "Sho Tokuda and Kunihisa Okano and Yukinori Nakamura and Kentaro Hirata",

note = "Funding Information: ★measures the ankle angle. The prototype is shown in Fig. 1. ★This work was partially supported by JSPS KAKENHI Grant ★This work was partially supported by JSPS KAKENHI Grant NuTmhbiserw2o0rKk1w47a6s3.partially supported by JSPS KAKENHI Grant NuThismberw20K14763.ork was partially by JSPS KAKENHI Grant Number 20K14763. Publisher Copyright: {\textcopyright}2020 The Authors.This is an open access article under the CC BY-NC-ND license.; 3rd IFAC Workshop on Cyber-Physical and Human Systems, CPHS 2020 ; Conference date: 03-12-2020 Through 05-12-2020",

year = "2020",

doi = "10.1016/j.ifacol.2021.04.216",

language = "English",

volume = "53",

pages = "291--296",

journal = "IFAC-PapersOnLine",

issn = "2405-8963",

publisher = "IFAC Secretariat",

number = "5",

}

TY - JOUR

T1 - Swing-phase detection from the ankle joint angle using recurrent neural networks

AU - Tokuda, Sho

AU - Okano, Kunihisa

AU - Nakamura, Yukinori

AU - Hirata, Kentaro

N1 - Funding Information: ★measures the ankle angle. The prototype is shown in Fig. 1. ★This work was partially supported by JSPS KAKENHI Grant ★This work was partially supported by JSPS KAKENHI Grant NuTmhbiserw2o0rKk1w47a6s3.partially supported by JSPS KAKENHI Grant NuThismberw20K14763.ork was partially by JSPS KAKENHI Grant Number 20K14763. Publisher Copyright: ©2020 The Authors.This is an open access article under the CC BY-NC-ND license.

PY - 2020

Y1 - 2020

N2 - Identifying the current gait phase is a key in the control of ankle-foot orthoses, which assist ankle motion during walking. We address the problem to estimate whether the foot is in a swing or stance phase only from the ankle angle. A recurrent neural network with long-short-term-memory architecture is developed and evaluated with experimental data.

AB - Identifying the current gait phase is a key in the control of ankle-foot orthoses, which assist ankle motion during walking. We address the problem to estimate whether the foot is in a swing or stance phase only from the ankle angle. A recurrent neural network with long-short-term-memory architecture is developed and evaluated with experimental data.

KW - Ankle-foot orthosis

KW - gait analysis

KW - long short-term memory

KW - neural networks

UR - http://www.scopus.com/inward/record.url?scp=85107850441&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85107850441&partnerID=8YFLogxK

U2 - 10.1016/j.ifacol.2021.04.216

DO - 10.1016/j.ifacol.2021.04.216

M3 - Conference article

AN - SCOPUS:85107850441

VL - 53

SP - 291

EP - 296

JO - IFAC-PapersOnLine

JF - IFAC-PapersOnLine

SN - 2405-8963

IS - 5

T2 - 3rd IFAC Workshop on Cyber-Physical and Human Systems, CPHS 2020

Y2 - 3 December 2020 through 5 December 2020

ER -

Swing-phase detection from the ankle joint angle using recurrent neural networks

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this