Embedding-based real-time change point detection with application to activity segmentation in smart home time series data

Vista sencilla de ítem
dc.contributor.authorBermejo Fernández, Unai
dc.contributor.authorAlmeida, Aitor
dc.contributor.authorBilbao Jayo, Aritz
dc.contributor.authorAzkune, Gorka
dc.date.accessioned2024-11-07T10:26:20Z
dc.date.available2024-11-07T10:26:20Z
dc.date.issued2021-12-15
dc.date.updated2024-11-07T10:26:20Z
dc.description.abstractHuman activity recognition systems are essential to enable many assistive applications. Those systems can be sensor-based or vision-based. When sensor-based systems are deployed in real environments, they must segment sensor data streams on the fly in order to extract features and recognize the ongoing activities. This segmentation can be done with different approaches. One effective approach is to employ change point detection (CPD) algorithms to detect activity transitions (i.e. determine when activities start and end). In this paper, we present a novel real-time CPD method to perform activity segmentation, where neural embeddings (vectors of continuous numbers) are used to represent sensor events. Through empirical evaluation with 3 publicly available benchmark datasets, we conclude that our method is useful for segmenting sensor data, offering significant better performance than state of the art algorithms in two of them. Besides, we propose the use of retrofitting, a graph-based technique, to adjust the embeddings and introduce expert knowledge in the activity segmentation task, showing empirically that it can improve the performance of our method using three graphs generated from two sources of information. Finally, we discuss the advantages of our approach regarding computational cost, manual effort reduction (no need of hand-crafted features) and cross-environment possibilities (transfer learning) in comparison to others.en
dc.description.sponsorshipThis work was carried out with the financial support of FuturAALEgo (RTI2018-101045-A-C22) granted by Spanish Ministry of Science, Innovation and Universities.en
dc.identifier.citationBermejo, U., Almeida, A., Bilbao-Jayo, A., & Azkune, G. (2021). Embedding-based real-time change point detection with application to activity segmentation in smart home time series data. Expert Systems with Applications, 185. https://doi.org/10.1016/J.ESWA.2021.115641
dc.identifier.doi10.1016/J.ESWA.2021.115641
dc.identifier.issn0957-4174
dc.identifier.urihttp://hdl.handle.net/20.500.14454/1689
dc.language.isoeng
dc.publisherElsevier Ltd
dc.rights© 2021 The Authors
dc.subject.otherActivity transition detection
dc.subject.otherChange point detection
dc.subject.otherActivity segmentation
dc.subject.otherSmart homes
dc.subject.otherAction embeddings
dc.subject.otherSensor embeddings
dc.titleEmbedding-based real-time change point detection with application to activity segmentation in smart home time series dataen
dc.typejournal article
dcterms.accessRightsopen access
oaire.citation.titleExpert Systems with Applications
oaire.citation.volume185
oaire.licenseConditionhttps://creativecommons.org/licenses/by-nc-nd/4.0/
oaire.versionVoR
Ficheros en el ítem
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
bermejo_embedding_2021.pdf
Tamaño:
1.53 MB
Formato:
Adobe Portable Document Format
Descargar
Colecciones
Artículos