An active adaptation strategy for streaming time series classification based on elastic similarity measures
dc.contributor.author | Oregi, Izaskun | |
dc.contributor.author | Pérez, Aritz | |
dc.contributor.author | Del Ser, Javier | |
dc.contributor.author | Lozano, Jose A. | |
dc.contributor.institution | Quantum | |
dc.contributor.institution | IA | |
dc.date.issued | 2022-08 | |
dc.description | Publisher Copyright: © 2022, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature. | |
dc.description.abstract | In streaming time series classification problems, the goal is to predict the label associated to the most recently received observations over the stream according to a set of categorized reference patterns. In on-line scenarios, data arise from non-stationary processes, which results in a succession of different patterns or events. This work presents an active adaptation strategy that allows time series classifiers to accommodate to the dynamics of streamed time series data. Specifically, our approach consists of a classifier that detects changes between events over streaming time series. For this purpose, the classifier uses features of the dynamic time warping measure computed between the streamed data and a set of reference patterns. When classifying a streaming series, the proposed pattern end detector analyzes such features to predict changes and adapt off-line time series classifiers to newly arriving events. To evaluate the performance of the proposed scheme, we employ the pattern end detection model along with dynamic time warping-based nearest neighbor classifiers over a benchmark of ten time series classification problems. The obtained results present exciting insights into the detection accuracy and latency performance of the proposed strategy. | en |
dc.description.sponsorship | This research work has been supported by the Basque Government through the EMAITEK and ELKARTEK funding programs (3KIA, ref. KK-2020/00049), as well as by the Consolidated Research Group MATHMODE (IT1294-19) granted by the Department of Education of this institution. I. Oregi and J. Del Ser would like to thank the Spanish Centro para el Desarrollo Tecnologico Industrial (CDTI, Ministry of Science and Innovation) through the “Red Cervera” Programme (AI4ES project). A. Pérez and J. A. Lozano are supported by the Basque Government through the BERC 2022-2025 program and by the Spanish Ministry of Economy and Competitiveness MINECO through BCAM Severo Ochoa excellence accreditation SEV-2017-0718. A. Pérez also acknowledges funding support from AEI/FEDER (UE) through project TIN2017-82626-R. J. A. Lozano is also supported by Spanish Ministry of Economy and Competitiveness MINECO through TIN2016-78365-R and PID2019-104966GB-I00. | |
dc.description.status | Peer reviewed | |
dc.format.extent | 16 | |
dc.identifier.citation | Oregi , I , Pérez , A , Del Ser , J & Lozano , J A 2022 , ' An active adaptation strategy for streaming time series classification based on elastic similarity measures ' , Neural Computing and Applications , vol. 34 , no. 16 , pp. 13237-13252 . https://doi.org/10.1007/s00521-022-07358-3 | |
dc.identifier.doi | 10.1007/s00521-022-07358-3 | |
dc.identifier.issn | 0941-0643 | |
dc.identifier.other | researchoutputwizard: 11556/1365 | |
dc.identifier.other | researchoutputwizard: 11556/1364 | |
dc.identifier.url | http://www.scopus.com/inward/record.url?scp=85130288331&partnerID=8YFLogxK | |
dc.language.iso | eng | |
dc.relation.ispartof | Neural Computing and Applications | |
dc.relation.projectID | BERC, 2022-2025 | |
dc.relation.projectID | U.S. Department of Education, ED | |
dc.relation.projectID | Centro para el Desarrollo Tecnológico Industrial, CDTI | |
dc.relation.projectID | Federación Española de Enfermedades Raras, FEDER, TIN2017-82626-R-PID2019-104966GB-I00-TIN2016-78365-R | |
dc.relation.projectID | Eusko Jaurlaritza, KK-2020/00049-IT1294-19 | |
dc.relation.projectID | Ministerio de Economía y Competitividad, MINECO | |
dc.relation.projectID | Ministerio de Ciencia e Innovación, MICINN | |
dc.relation.projectID | Agencia Estatal de Investigación, AEI | |
dc.rights | info:eu-repo/semantics/openAccess | |
dc.subject.keywords | Deep learning | |
dc.subject.keywords | Dynamic time warping | |
dc.subject.keywords | Streaming data | |
dc.subject.keywords | Time series classification | |
dc.subject.keywords | Time series classification | |
dc.subject.keywords | Streaming data | |
dc.subject.keywords | Deep learning | |
dc.subject.keywords | Dynamic time warping | |
dc.subject.keywords | Software | |
dc.subject.keywords | Artificial Intelligence | |
dc.subject.keywords | Funding Info | |
dc.subject.keywords | Funding was provided by Eusko Jaurlaritza (KK-2020/00049, MATHMODE (IT1294-19), BERC 2022-2025), _x000D_ Ministerio de Economı´a y Competitividad (Severo Ochoa SEV-2017-0718,TIN2016-78365-R), _x000D_ Agencia Estatal de Investigacio´n (TIN2017-82626-R) | |
dc.subject.keywords | Funding was provided by Eusko Jaurlaritza (KK-2020/00049, MATHMODE (IT1294-19), _x000D_ BERC 2022-2025), Ministerio de Economía y Competitividad (Severo Ochoa SEV-2017-0718, TIN2016-78365-R), _x000D_ Agencia Estatal de Investigación (TIN2017-82626-R) | |
dc.subject.keywords | Funding was provided by Eusko Jaurlaritza (KK-2020/00049, MATHMODE (IT1294-19), BERC 2022-2025), _x000D_ Ministerio de Economı´a y Competitividad (Severo Ochoa SEV-2017-0718,TIN2016-78365-R), _x000D_ Agencia Estatal de Investigacio´n (TIN2017-82626-R) | |
dc.subject.keywords | Funding was provided by Eusko Jaurlaritza (KK-2020/00049, MATHMODE (IT1294-19), _x000D_ BERC 2022-2025), Ministerio de Economía y Competitividad (Severo Ochoa SEV-2017-0718, TIN2016-78365-R), _x000D_ Agencia Estatal de Investigación (TIN2017-82626-R) | |
dc.title | An active adaptation strategy for streaming time series classification based on elastic similarity measures | en |
dc.type | journal article |