Unsupervised feature based algorithms for time series extrinsic regression

Áreas de investigación:

• Methodology - Time series

Año:

2024

Tipo de publicación:

Artículo

Palabras clave:

Time series, extrinsic regression, unsupervised feature based algorithms, regression

Autores:

• Guijo-Rubio, David
• Middlehurst, Matthew
• Arcencio, Guilherme
• Silva, Diego Furtado
• Bagnall, Anthony

Journal:

Data Mining and Knowledge Discovery

Páginas:

1-45

Mes:

Mayo

ISSN:

1384-5810

BibTex:

@article{TSERDavid2024, author = "David Guijo-Rubio and Matthew Middlehurst and Guilherme Arcencio and Diego Furtado Silva and Anthony Bagnall", abstract = "Time Series Extrinsic Regression (TSER) involves using a set of training time series to form a predictive model of a continuous response variable that is not directly related to the regressor series. The TSER archive for comparing algorithms was released in 2022 with 19 problems. We increase the size of this archive to 63 problems and reproduce the previous comparison of baseline algorithms. We then extend the comparison to include a wider range of standard regressors and the latest versions of TSER models used in the previous study. We show that none of the previously evaluated regressors can outperform a regression adaptation of a standard classifier, rotation forest. We introduce two new TSER algorithms developed from related work in time series classification. FreshPRINCE is a pipeline estimator consisting of a transform into a wide range of summary features followed by a rotation forest regressor. DrCIF is a tree ensemble that creates features from summary statistics over random intervals. Our study demonstrates that both algorithms, along with InceptionTime, exhibit significantly better performance compared to the other 18 regressors tested. More importantly, DrCIF is the only one that significantly outperforms a standard rotation forest regressor.", awards = "JCR (2023): 2.8, Position: 98/197 (Q2), Category: COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE", comments = "JCR (2023): 2.8, Position: 98/197 (Q2), Category: COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE", doi = "10.1007/s10618-024-01027-w", issn = "1384-5810", journal = "Data Mining and Knowledge Discovery", keywords = "Time series, extrinsic regression, unsupervised feature based algorithms, regression", month = "Mayo", note = "JCR (2023): 2.8, Position: 98/197 (Q2), Category: COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE", pages = "1-45", title = "{U}nsupervised feature based algorithms for time series extrinsic regression", url = "link.springer.com/article/10.1007/s10618-024-01027-w", year = "2024", }

Nota:

JCR (2023): 2.8, Position: 98/197 (Q2), Category: COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Abstract:

Time Series Extrinsic Regression (TSER) involves using a set of training time series to form a predictive model of a continuous response variable that is not directly related to the regressor series. The TSER archive for comparing algorithms was released in 2022 with 19 problems. We increase the size of this archive to 63 problems and reproduce the previous comparison of baseline algorithms. We then extend the comparison to include a wider range of standard regressors and the latest versions of TSER models used in the previous study. We show that none of the previously evaluated regressors can outperform a regression adaptation of a standard classifier, rotation forest. We introduce two new TSER algorithms developed from related work in time series classification. FreshPRINCE is a pipeline estimator consisting of a transform into a wide range of summary features followed by a rotation forest regressor. DrCIF is a tree ensemble that creates features from summary statistics over random intervals. Our study demonstrates that both algorithms, along with InceptionTime, exhibit significantly better performance compared to the other 18 regressors tested. More importantly, DrCIF is the only one that significantly outperforms a standard rotation forest regressor.

Comentarios:

JCR (2023): 2.8, Position: 98/197 (Q2), Category: COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE