TSFEL: Time Series Feature Extraction Library

被引：297

作者：

Barandas, Marilia ^{[1
]}

Folgado, Duarte ^{[1
]}

Fernandes, Leticia ^{[1
]}

Santos, Sara ^{[1
]}

Abreu, Mariana ^{[1
]}

Bota, Patricia ^{[1
]}

Liu, Hui ^{[2
]}

Schultz, Tanja ^{[2
]}

Gamboa, Hugo ^{[1
,3
]}

机构：

[1] Assoc Fraunhofer Portugal Res, Rua Alfredo Allen 455-461, Porto, Portugal

[2] Univ Bremen, Cognit Syst Lab, Bremen, Germany

[3] Univ Nova Lisboa, Fac Ciencias & Tecnol, Dept Fis, Lab Instrumentacao Engn Biomed & Fis Radiacao LIB, P-2892516 Monte De Caparica, Caparica, Portugal

来源：

SOFTWAREX | 2020年 / 11卷

关键词：

Time series; Machine learning; Feature extraction; !text type='Python']Python[!/text; TRANSFORM; ENTROPY;

D O I：

10.1016/j.softx.2020.100456

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

Time 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 scien-tists 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. (C) 2020 The Authors. Published by Elsevier B.V.

引用

页数：7

共 24 条

[1] Detailed Human Activity Recognition based on Multiple HMM [J].

Abreu, Mariana ;

Barandas, Marilia ;

Leonardo, Ricardo ;

Gamboa, Hugo .

BIOSIGNALS: PROCEEDINGS OF THE 12TH INTERNATIONAL JOINT CONFERENCE ON BIOMEDICAL ENGINEERING SYSTEMS AND TECHNOLOGIES, VOL 4: BIOSIGNALS, 2019, :171-178

[2] A Semi-Automatic Annotation Approach for Human Activity Recognition [J].

Bota, Patricia ;

Silva, Joana ;

Folgado, Duarte ;

Gamboa, Hugo .

SENSORS, 2019, 19 (03)

[3] Time Series FeatuRe Extraction on basis of Scalable Hypothesis tests (tsfresh - A Python']Python package) [J].

Christ, Maximilian ;

Braun, Nils ;

Neuffer, Julius ;

Kempa-Liehr, Andreas W. .

NEUROCOMPUTING, 2018, 307 :72-77

[4]

Das O., 2016, TECH REP

[5] A Few Useful Things to Know About Machine Learning [J].

Domingos, Pedro .

COMMUNICATIONS OF THE ACM, 2012, 55 (10) :78-87

[6]

Fernandes LS., 2019, THESIS

[7]

Figueira Carina, 2016, BIOSTEC 2016. 9th International Joint Conference on Biomedical Engineering Systems and Technologies. Proceedings: Biosignals, P190

[8] hctsa: A Computational Framework for Automated Time-Series Phenotyping Using Massive Feature Extraction [J].

Fulcher, Ben D. ;

Jones, Nick S. .

CELL SYSTEMS, 2017, 5 (05) :527-+

[9]

Henriksson U., 2003, TECH REP

[10]

Kocaman C, 2009, INT C EL EL ENG ELEC, DOI 10.1109/ELECO.2009

← 1 2 3 →