IMU-based solution for automatic detection and classification of exercises in the fitness scenario

Claudio Crema, Alessandro Depari, Alessandra Flammini, Emiliano Sisinni, Thomas Haslwanter, Stefan Salzmann

Research output: Chapter in Book/Report/Conference proceedingsConference contributionpeer-review

43 Citations (Scopus)

Abstract

Causal relationship between physical activity and prevention of several diseases has been known for some time. Recently, attempts to quantify dose-response relationship between physical activity and health show that automatic tracking and quantification of the exercise efforts not only help in motivating people but improve health conditions as well. However, no commercial devices are available for weight training and calisthenics. This work tries to overcome this limit, exploiting machine learning technique (particularly Linear Discriminant Analysis, LDA) for analyzing data coming from wearable inertial measurement units, (IMUs) and classifying/counting such exercises. Computational requirements are compatible with embedded implementation and reported results confirm the feasibility of the proposed approach, offering an average accuracy in the detection of exercises on the order of 85%.

Original languageEnglish
Title of host publicationSAS 2017 - 2017 IEEE Sensors Applications Symposium, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509032020
DOIs
Publication statusPublished - 6 Apr 2017
Event12th IEEE Sensors Applications Symposium, SAS 2017 - Glassboro, United States
Duration: 13 Mar 201715 Mar 2017

Publication series

NameSAS 2017 - 2017 IEEE Sensors Applications Symposium, Proceedings

Conference

Conference12th IEEE Sensors Applications Symposium, SAS 2017
Country/TerritoryUnited States
CityGlassboro
Period13.03.201715.03.2017

Keywords

  • data classification
  • IMU
  • machine learning
  • Mhealth
  • wearables

Fingerprint

Dive into the research topics of 'IMU-based solution for automatic detection and classification of exercises in the fitness scenario'. Together they form a unique fingerprint.

Cite this