Show simple item record  

dc.contributor.authorMayo, Michaelen_NZ
dc.contributor.authorOmranian, Saraen_NZ
dc.contributor.editorCao, Huipingen_NZ
dc.contributor.editorLi, Jinyanen_NZ
dc.contributor.editorWang, Ruilien_NZ
dc.coverage.spatialConference held at Auckland, NZen_NZ
dc.date.accessioned2016-07-26T01:53:51Z
dc.date.available2016en_NZ
dc.date.available2016-07-26T01:53:51Z
dc.date.issued2016en_NZ
dc.identifier.citationMayo, M., & Omranian, S. (2016). Towards a new evolutionary subsampling technique for heuristic optimisation of load disaggregators. In H. Cao, J. Li, & R. Wang (Eds.), Trends and Applications in Knowledge Discovery and Data Mining, PAKDD 2016 Workshops, Revised Selected Papers (Vol. LNCS 9794, pp. 3–14). Conference held at Auckland, NZ: Springer. http://doi.org/10.1007/978-3-319-42996-0_1en
dc.identifier.isbn978-3-319-42996-0en_NZ
dc.identifier.urihttps://hdl.handle.net/10289/10560
dc.description.abstractIn this paper we present some preliminary work towards the development of a new evolutionary subsampling technique for solving the non-intrusive load monitoring (NILM) problem. The NILM problem concerns using predictive algorithms to analyse whole-house energy usage measurements, so that individual appliance energy usages can be disaggregated. The motivation is to educate home owners about their energy usage. However, by their very nature, the datasets used in this research are massively imbalanced in their target value distributions. Consequently standard machine learning techniques, which often rely on optimising for root mean squared error (RMSE), typically fail. We therefore propose the target-weighted RMSE (TW-RMSE) metric as an alternative fitness function for optimising load disaggregators, and show in a simple initial study in which random search is utilised that TW-RMSE is a metric that can be optimised, and therefore has the potential to be included in a larger evolutionary subsampling-based solution to this problem.
dc.format.mimetypeapplication/pdf
dc.language.isoen
dc.publisherSpringeren_NZ
dc.rightsThis is an author’s accepted version of an article published in Trends and Applications in Knowledge Discovery and Data Mining, PAKDD 2016 Workshops, LNAI 9794. The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-42996-0_1. © Springer International Publishing Switzerland 2016
dc.sourcePAKDD 2016en_NZ
dc.subjectcomputer scienceen_NZ
dc.subjectnon-intrusive load monitoringen_NZ
dc.subjectdisaggregationen_NZ
dc.subjectimbalanced regressionen_NZ
dc.subjectfitness functionen_NZ
dc.subjectevolutionary undersamplingen_NZ
dc.subjectMachine learning
dc.titleTowards a new evolutionary subsampling technique for heuristic optimisation of load disaggregatorsen_NZ
dc.typeConference Contribution
dc.identifier.doi10.1007/978-3-319-42996-0_1en_NZ
dc.relation.isPartOfTrends and Applications in Knowledge Discovery and Data Mining, PAKDD 2016 Workshops, Revised Selected Papersen_NZ
pubs.begin-page3
pubs.elements-id139901
pubs.end-page14
pubs.finish-date2016-04-19en_NZ
pubs.publisher-urlhttp://download.springer.com/static/pdf/833/chp%253A10.1007%252F978-3-319-42996-0_1.pdf?originUrl=http://link.springer.com/chapter/10.1007/978-3-319-42996-0_1&token2=exp=1468985881~acl=/static/pdf/833/chp%25253A10.1007%25252F978-3-319-42996-0_1.pdf?originUrl=http%253A%252F%252Flink.springer.com%252Fchapter%252F10.1007%252F978-3-319-42996-0_1*~hmac=1072071cd757533546637c49fa19858e51c389097d6844e9d80205218d382611en_NZ
pubs.start-date2016-04-19en_NZ
pubs.volumeLNCS 9794en_NZ


Files in this item

This item appears in the following Collection(s)

Show simple item record