Show simple item record

dc.contributor.authorSani, Sadiq
dc.contributor.authorWiratunga, Nirmalie
dc.contributor.authorMassie, Stewart
dc.contributor.authorCooper, Kay
dc.date.accessioned2019-02-04T16:03:57Z
dc.date.available2019-02-04T16:03:57Z
dc.date.issued2018-07-09en
dc.identifier.citationSANI, S., WIRATUNGA, N., MASSIE, S. and COOPER, K. 2018. Study of similarity metrics for matching network-based personalised human activity recognition. In Minor, M. (ed.) Workshop proceedings of the 26th International conference on case-based reasoning (ICCBR 2018), 9-12 July 2018, Stockholm, Sweden. Stockholm: ICCBR [online], pages 91-95. Available from: http://iccbr18.com/wp-content/uploads/ICCBR-2018-V3.pdf#page=91en
dc.identifier.urihttp://hdl.handle.net/10059/3279
dc.description.abstractPersonalised Human Activity Recognition (HAR) models trained using data from the target user (subject-dependent) have been shown to be superior to non personalised models that are trained on data from a general population (subject-independent). However, from a practical perspective, collecting sufficient training data from end users to create subject-dependent models is not feasible. We have previously introduced an approach based on Matching networks which has proved effective for training personalised HAR models while requiring very little data from the end user. Matching networks perform nearest-neighbour classification by reusing the class label of the most similar instances in a provided support set, which makes them very relevant to case-based reasoning. A key advantage of matching networks is that they use metric learning to produce feature embeddings or representations that maximise classification accuracy, given a chosen similarity metric. However, to the best of our knowledge, no study has been provided into the performance of different similarity metrics for matching networks. In this paper, we present a study of five different similarity metrics: Euclidean, Manhattan, Dot Product, Cosine and Jaccard, for personalised HAR. Our evaluation shows that substantial differences in performance are achieved using different metrics, with Cosine and Jaccard producing the best performance.en
dc.language.isoengen
dc.publisherICCBR (ORGANISERS)en
dc.rightshttps://creativecommons.org/licenses/by-nc/4.0en
dc.rightsAttribution-NonCommercial 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by-nc/4.0/*
dc.subjectHuman Activity Recoginition (HAR)en
dc.subjectMatching networksen
dc.subjectDataen
dc.subjectCasebased reasoningen
dc.titleStudy of similarity metrics for matching network-based personalised human activity recognition.en
dc.typeConference publicationsen
dc.publisher.urihttp://iccbr18.com/wp-content/uploads/ICCBR-2018-V3.pdf#page=91en
dcterms.dateAccepted2018-05-21en
dcterms.publicationdate2018-07-12en
refterms.accessExceptionNAen
refterms.dateDeposit2019-02-04en
refterms.dateFCA2019-02-04en
refterms.dateFCD2019-02-04en
refterms.dateFreeToDownload2019-02-04en
refterms.dateFreeToRead2019-02-04en
refterms.dateToSearch2019-02-04en
refterms.depositExceptionNAen
refterms.panelBen
refterms.technicalExceptionNAen
refterms.versionAMen
rioxxterms.publicationdate2018-07-09en
rioxxterms.typeConference Paper/Proceeding/Abstracten
rioxxterms.versionAMen


Files in this item

This item appears in the following Collection(s)

Show simple item record

https://creativecommons.org/licenses/by-nc/4.0
Except where otherwise noted, this item's license is described as https://creativecommons.org/licenses/by-nc/4.0