Using domain knowledge for interpretable and competitive multi-class human activity recognition

Simple item page
dc.contributor.authorScheurer, Sebastian
dc.contributor.authorTedesco, Salvatore
dc.contributor.authorBrown, Kenneth N.
dc.contributor.authorO'Flynn, Brendan
dc.contributor.funderScience Foundation Irelanden
dc.contributor.funderEuropean Regional Development Funden
dc.contributor.funderEnterprise Irelanden
dc.contributor.funderSeventh Framework Programmeen
dc.date.accessioned2020-03-13T15:53:37Z
dc.date.available2020-03-13T15:53:37Z
dc.date.issued2020-02-22
dc.date.updated2020-03-13T15:26:38Z
dc.description.abstractHuman activity recognition (HAR) has become an increasingly popular application of machine learning across a range of domains. Typically the HAR task that a machine learning algorithm is trained for requires separating multiple activities such as walking, running, sitting, and falling from each other. Despite a large body of work on multi-class HAR, and the well-known fact that the performance on a multi-class problem can be significantly affected by how it is decomposed into a set of binary problems, there has been little research into how the choice of multi-class decomposition method affects the performance of HAR systems. This paper presents the first empirical comparison of multi-class decomposition methods in a HAR context by estimating the performance of five machine learning algorithms when used in their multi-class formulation, with four popular multi-class decomposition methods, five expert hierarchies—nested dichotomies constructed from domain knowledge—or an ensemble of expert hierarchies on a 17-class HAR data-set which consists of features extracted from tri-axial accelerometer and gyroscope signals. We further compare performance on two binary classification problems, each based on the topmost dichotomy of an expert hierarchy. The results show that expert hierarchies can indeed compete with one-vs-all, both on the original multi-class problem and on a more general binary classification problem, such as that induced by an expert hierarchy’s topmost dichotomy. Finally, we show that an ensemble of expert hierarchies performs better than one-vs-all and comparably to one-vs-one, despite being of lower time and space complexity, on the multi-class problem, and outperforms all other multi-class decomposition methods on the two dichotomous problems.en
dc.description.sponsorshipEnterprise Ireland (European funded project SAFESENS under the ENIAC program in association with Enterprise Ireland under grant number IR20140024)en
dc.description.statusPeer revieweden
dc.description.versionPublished Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.articleid1208en
dc.identifier.citationScheurer, S., Tedesco, S., Brown, K. N. and O'Flynn, B. (2020) 'Using Domain Knowledge for Interpretable and Competitive Multi-Class Human Activity Recognition', Sensors, 2 (5), 1208 (25 pp). doi: 10.3390/s20041208en
dc.identifier.doi10.3390/s20041208en
dc.identifier.endpage25en
dc.identifier.issn1424-8220
dc.identifier.issued5en
dc.identifier.journaltitleSensorsen
dc.identifier.startpage1en
dc.identifier.urihttps://hdl.handle.net/10468/9759
dc.identifier.volume2en
dc.language.isoenen
dc.publisherMDPIen
dc.relation.projectinfo:eu-repo/grantAgreement/SFI/SFI Research Centres/12/RC/2289/IE/INSIGHT - Irelands Big Data and Analytics Research Centre/en
dc.relation.projectinfo:eu-repo/grantAgreement/SFI/SFI Research Centres/13/RC/2077/IE/CONNECT: The Centre for Future Networks & Communications/en
dc.relation.projectinfo:eu-repo/grantAgreement/EC/FP7::SP1::SP1-JTI/621272/EU/Sensor technologies enhanced safety and security of buildings and its occupants/SAFESENSen
dc.relation.urihttps://www.mdpi.com/1424-8220/20/4/1208
dc.rights© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/)en
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.subjectHuman activity recognitionen
dc.subjectMachine learningen
dc.subjectWearable sensorsen
dc.subjectInertial sensors;en
dc.subjectMulti-class classificationen
dc.subjectHierarchical classificationen
dc.subjectError-correcting output codesen
dc.subjectEnsembles of nested dichotomiesen
dc.titleUsing domain knowledge for interpretable and competitive multi-class human activity recognitionen
dc.typeArticle (peer-reviewed)en
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
sensors-20-01208-v2.pdf
Size:
2.05 MB
Format:
Adobe Portable Document Format
Description:
Published version
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Tyndall National Institute - Journal Articles
Computer Science - Journal Articles
Insight Centre for Data Analytics - Journal Articles