Activity recognition in patients with lower limb impairments: Do we need training data from each patient?

Luca Lonini*, Aakash Gupta, Konrad Kording, Aran Jayaraman

*Corresponding author for this work

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

5 Scopus citations

Abstract

Machine learning allows detecting specific physical activities using data from wearable sensors. Such a quantification of patient mobility over time promises to accurately inform clinical decisions for physical rehabilitation. There are two strategies of setting up the machine learning problem: detect one patient's activities using data from the same patient (personal model) or detect their activities using data from other patients (global model), and we currently do not know if personal models are necessary. Here we consider the problem of detecting physical activities from a waist-worn accelerometer in patients who use a knee-ankle-foot orthosis (KAFO) to walk. We show that while a model based on healthy subjects has low accuracy, the global model performs as well as the personal model. This is encouraging because it suggests that condition-specific activity recognition algorithms are sufficient and that no data from individual patients is necessary.

Original languageEnglish (US)
Title of host publication2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3265-3268
Number of pages4
ISBN (Electronic)9781457702204
DOIs
StatePublished - Oct 13 2016
Event38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016 - Orlando, United States
Duration: Aug 16 2016Aug 20 2016

Publication series

NameProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Volume2016-October
ISSN (Print)1557-170X

Other

Other38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
CountryUnited States
CityOrlando
Period8/16/168/20/16

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Fingerprint Dive into the research topics of 'Activity recognition in patients with lower limb impairments: Do we need training data from each patient?'. Together they form a unique fingerprint.

Cite this