A Deep Learning Model for Exercise-Based Rehabilitation Using Multi-channel Time-Series Data from a Single Wearable Sensor

Ghanashyama Prabhu, Noel E. O’Connor, Kieran Moran

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The ability to accurately and automatically recognize and count the repetitions of exercises using a single sensor is essential for technology-assisted exercise-based rehabilitation. In this paper, we present a single deep learning architecture to undertake both of these tasks based on multi-channel time-series data. The models are constructed and tested using the INSIGHT-LME [1] exercise dataset which consists of ten local muscular endurance (LME) exercises. For exercise recognition, we achieved an overall F1-score measure of 96% and for repetition counting, we were correct within an error of ±1 repetitions in 88% of the observed exercise sets. To the best of our knowledge, our approach of using the same deep learning model for both tasks using raw time-series sensor data information is novel.

Original languageEnglish
Title of host publicationWireless Mobile Communication and Healthcare - 9th EAI International Conference, MobiHealth 2020, Proceedings
EditorsJuan Ye, Michael J. O’Grady, Gabriele Civitarese, Kristina Yordanova
PublisherSpringer Science and Business Media Deutschland GmbH
Pages104-115
Number of pages12
ISBN (Print)9783030705688
DOIs
Publication statusPublished - 2021
Event9th EAI International Conference on Wireless Mobile Communication and Healthcare, MobiHealth 2020 - St Andrews, United Kingdom
Duration: 19-11-202019-11-2020

Publication series

NameLecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
Volume362 LNICST
ISSN (Print)1867-8211
ISSN (Electronic)1867-822X

Conference

Conference9th EAI International Conference on Wireless Mobile Communication and Healthcare, MobiHealth 2020
Country/TerritoryUnited Kingdom
CitySt Andrews
Period19-11-2019-11-20

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'A Deep Learning Model for Exercise-Based Rehabilitation Using Multi-channel Time-Series Data from a Single Wearable Sensor'. Together they form a unique fingerprint.

Cite this