Home > Research > Publications & Outputs > Time series clustering using the total variatio...

Research

Text available via DOI:

View graph of relations

Time series clustering using the total variation distance with applications in oceanography

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Published

Standard

Time series clustering using the total variation distance with applications in oceanography. / Euan Campos, Carolina De Jesus.
In: Environmetrics, 30.09.2016, p. 355-369.

Research output: Contribution to Journal/Magazine › Journal article › peer-review

Harvard

Euan Campos, CDJ 2016, 'Time series clustering using the total variation distance with applications in oceanography', Environmetrics, pp. 355-369. https://doi.org/10.1002/env.2398

APA

Euan Campos, C. D. J. (2016). Time series clustering using the total variation distance with applications in oceanography. Environmetrics, 355-369. https://doi.org/10.1002/env.2398

Vancouver

Euan Campos CDJ. Time series clustering using the total variation distance with applications in oceanography. Environmetrics. 2016 Sept 30;355-369. doi: 10.1002/env.2398

Author

Euan Campos, Carolina De Jesus. / Time series clustering using the total variation distance with applications in oceanography. In: Environmetrics. 2016 ; pp. 355-369.

Bibtex

@article{c7f6b3495ff64d2cb1a7f25a8e556c37,
title = "Time series clustering using the total variation distance with applications in oceanography",
abstract = "A clustering procedure for time series based on the use of the total variation distance between normalized spectral densities is proposed in this work. The approach is thus based on classifying time series in the frequency domain by consideration of the similarity between their oscillatory characteristics. As an application of this procedure, an algorithm for determining stationary periods for time series of random sea waves is developed, a problem in which changes between stationary sea states is usually slow. The proposed clustering algorithm is compared to several other methods which are also based on features extracted from the original series, and the results show that its performance is comparable to the best methods available, and in some tests, it performs better. This clustering method may be of independent interest. Copyright {\textcopyright} 2016 John Wiley & Sons, Ltd.",
author = "{Euan Campos}, {Carolina De Jesus}",
year = "2016",
month = sep,
day = "30",
doi = "10.1002/env.2398",
language = "English",
pages = "355--369",
journal = "Environmetrics",
issn = "1180-4009",
publisher = "John Wiley and Sons Ltd",

}

RIS

TY - JOUR

T1 - Time series clustering using the total variation distance with applications in oceanography

AU - Euan Campos, Carolina De Jesus

PY - 2016/9/30

Y1 - 2016/9/30

N2 - A clustering procedure for time series based on the use of the total variation distance between normalized spectral densities is proposed in this work. The approach is thus based on classifying time series in the frequency domain by consideration of the similarity between their oscillatory characteristics. As an application of this procedure, an algorithm for determining stationary periods for time series of random sea waves is developed, a problem in which changes between stationary sea states is usually slow. The proposed clustering algorithm is compared to several other methods which are also based on features extracted from the original series, and the results show that its performance is comparable to the best methods available, and in some tests, it performs better. This clustering method may be of independent interest. Copyright © 2016 John Wiley & Sons, Ltd.

AB - A clustering procedure for time series based on the use of the total variation distance between normalized spectral densities is proposed in this work. The approach is thus based on classifying time series in the frequency domain by consideration of the similarity between their oscillatory characteristics. As an application of this procedure, an algorithm for determining stationary periods for time series of random sea waves is developed, a problem in which changes between stationary sea states is usually slow. The proposed clustering algorithm is compared to several other methods which are also based on features extracted from the original series, and the results show that its performance is comparable to the best methods available, and in some tests, it performs better. This clustering method may be of independent interest. Copyright © 2016 John Wiley & Sons, Ltd.

UR - http://dx.doi.org/10.1002/env.2398

U2 - 10.1002/env.2398

DO - 10.1002/env.2398

M3 - Journal article

SP - 355

EP - 369

JO - Environmetrics

JF - Environmetrics

SN - 1180-4009

ER -