Logo do repositório
 
Publicação

TSFEL: Time Series Feature Extraction Library

2020-01-01Artigo científico Acesso aberto
Ver registo simples
dc.contributor.authorBarandas, Marília
dc.contributor.authorFolgado, Duarte
dc.contributor.authorFernandes, Letícia
dc.contributor.authorSantos, Sara
dc.contributor.authorAbreu, Mariana
dc.contributor.authorBota, Patrícia
dc.contributor.authorLiu, Hui
dc.contributor.authorSchultz, Tanja
dc.contributor.authorGamboa, Hugo
dc.contributor.institutionDF – Departamento de Física
dc.contributor.institutionLIBPhys-UNL
dc.contributor.pblElsevier BV
dc.date.accessioned2021-05-06T22:45:29Z
dc.date.available2021-05-06T22:45:29Z
dc.date.issued2020-01-01
dc.descriptionPOCI-01-0247-FEDER-038436
dc.description.abstractTime series feature extraction is one of the preliminary steps of conventional machine learning pipelines. Quite often, this process ends being a time consuming and complex task as data scientists must consider a combination between a multitude of domain knowledge factors and coding implementation. We present in this paper a Python package entitled Time Series Feature Extraction Library (TSFEL), which computes over 60 different features extracted across temporal, statistical and spectral domains. User customisation is achieved using either an online interface or a conventional Python package for more flexibility and integration into real deployment scenarios. TSFEL is designed to support the process of fast exploratory data analysis and feature extraction on time series with computational cost evaluation.en
dc.description.versionpublishersversion
dc.description.versionpublished
dc.format.extent660067
dc.identifier.doi10.1016/j.softx.2020.100456
dc.identifier.otherPURE: 29589862
dc.identifier.otherPURE UUID: e7e44c8b-661d-4817-bc1e-c9b1ad98f03c
dc.identifier.otherScopus: 85081936815
dc.identifier.otherWOS: 000549940500009
dc.identifier.otherORCID: /0000-0002-4022-7424/work/93428591
dc.identifier.urihttp://hdl.handle.net/10362/117283
dc.identifier.urlhttps://www.scopus.com/pages/publications/85081936815
dc.language.isoeng
dc.peerreviewedyes
dc.subjectFeature extraction
dc.subjectMachine learning
dc.subjectPython
dc.subjectTime series
dc.subjectSoftware
dc.subjectComputer Science Applications
dc.titleTSFEL: Time Series Feature Extraction Libraryen
dc.typejournal article
degois.publication.titleSoftwareX
degois.publication.volume11
dspace.entity.typePublication
rcaap.rightsopenAccess

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
TSFEL_Time_Series_Feature_Extraction_Library.pdf
Tamanho:
644.6 KB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

FCT: DF - Artigos em revista internacional com arbitragem científica