Learning Predictive Movement Models from Fabric-mounted Wearable Sensors

Research output: Contribution to journalArticlepeer-review

7 Citations (Scopus)
286 Downloads (Pure)

Abstract

The measurement and analysis of human movement for applications in clinical diagnostics or rehabilitation is often performed in a laboratory setting using static motion capture devices. A growing interest in analysing movement in everyday environments (such as the home), has prompted the development of ”wearable sensors”, with the most current wearable sensors being those embedded into clothing. A major issue however with the use of these fabric-embedded sensors is the undesired effect of fabric motion artefacts corrupting movement signals. In this paper, a non-parametric method is presented for learning body movements, viewing the undesired motion as stochastic perturbations to the sensed motion, and using orthogonal regression techniques to form predictive models of the wearer’s motion that eliminate these errors in the learning process. Experiments in this paper show that standard non-parametric learning techniques under-perform in this fabric motion context, and that improved prediction accuracy can be made by using orthogonal regression techniques. Modelling this motion artefact problem as a stochastic learning problem shows an average 77% decrease in prediction error in a body pose task using fabricembedded sensors, compared to a kinematic model.
Original languageEnglish
Pages (from-to)1395-1404
Number of pages10
JournalIEEE transactions on neural systems and rehabilitation engineering
Volume24
Issue number12
Early online date11 Dec 2015
DOIs
Publication statusPublished - Dec 2016

Fingerprint

Dive into the research topics of 'Learning Predictive Movement Models from Fabric-mounted Wearable Sensors'. Together they form a unique fingerprint.

Cite this