Online learning of gait models for calculation of gait parameters

Jamie L.S. Waugh, Anton Trinh, Ryan R. Mohammed, William E. McIlroy, Dana Kulic

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

2 Citations (Scopus)

Abstract

This paper proposes a novel approach for gait analysis from wearable sensing, based on an adaptive periodic model of any gait signal. The proposed method learns a model of the gait cycle during online measurement, using a continuous representation that can adapt to inter and intrapersonal variability by creating an individualized model. Once the algorithm has converged to the input signal, key gait events can be identified relative to the estimated gait phase; these events can then be used to calculate gait parameters. The approach is implemented and tested on a human motion dataset where heel impact and toe takeoff events are extracted with an average error of 0.04 cycles.

Original languageEnglish
Title of host publication2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC 2016)
EditorsJose Principe, Jose Carmena, Justin Sanchez
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages6146-6149
Number of pages4
ISBN (Electronic)9781457702204
ISBN (Print)9781457702198
DOIs
Publication statusPublished - 2016
Externally publishedYes
EventInternational Conference of the IEEE Engineering in Medicine and Biology Society 2016: Empowering Individual Healthcare Decisions through Technology - Walt Disney World Resort, Orlando, United States of America
Duration: 16 Aug 201620 Aug 2016
Conference number: 38th
https://embc.embs.org/2016/

Conference

ConferenceInternational Conference of the IEEE Engineering in Medicine and Biology Society 2016
Abbreviated titleEMBC 2016
CountryUnited States of America
CityOrlando
Period16/08/1620/08/16
Internet address

Cite this