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

Sho Tokuda, Kunihisa Okano, Yukinori Nakamura, Kentaro Hirata

Research output: Contribution to journalConference articlepeer-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 languageEnglish
Pages (from-to)291-296
Number of pages6
JournalIFAC-PapersOnLine
Volume53
Issue number5
DOIs
Publication statusPublished - 2020
Event3rd IFAC Workshop on Cyber-Physical and Human Systems, CPHS 2020 - Beijing, China
Duration: Dec 3 2020Dec 5 2020

Keywords

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

ASJC Scopus subject areas

  • Control and Systems Engineering

Fingerprint

Dive into the research topics of 'Swing-phase detection from the ankle joint angle using recurrent neural networks'. Together they form a unique fingerprint.

Cite this