Journal of Computational Science, volume 53, pages 101385

Generalization of Change-Point Detection in Time Series Data Based on Direct Density Ratio Estimation

Publication typeJournal Article
Publication date2021-07-01
Quartile SCImago
Q1
Quartile WOS
Q2
Impact factor3.3
ISSN18777503
Theoretical Computer Science
General Computer Science
Modeling and Simulation
Abstract
The goal of the change-point detection is to discover changes of time series distribution. One of the state of the art approaches of change-point detection is based on direct density ratio estimation. In this work, we show how existing algorithms can be generalized using various binary classification and regression models. In particular, we show that the Gradient Boosting over Decision Trees and Neural Networks can be used for this purpose. The algorithms are tested on several synthetic and real-world datasets. The results show that the proposed methods outperform classical RuLSIF algorithm. Discussion of cases where the proposed algorithms have advantages over existing methods is also provided.

Citations by journals

1
Frontiers in Physics
Frontiers in Physics, 1, 14.29%
Frontiers in Physics
1 publication, 14.29%
European Physical Journal Plus
European Physical Journal Plus, 1, 14.29%
European Physical Journal Plus
1 publication, 14.29%
International Journal of Data Science and Analytics
International Journal of Data Science and Analytics, 1, 14.29%
International Journal of Data Science and Analytics
1 publication, 14.29%
Applied Intelligence
Applied Intelligence, 1, 14.29%
Applied Intelligence
1 publication, 14.29%
Engineering Applications of Artificial Intelligence
Engineering Applications of Artificial Intelligence, 1, 14.29%
Engineering Applications of Artificial Intelligence
1 publication, 14.29%
1

Citations by publishers

1
2
3
Springer Nature
Springer Nature, 3, 42.86%
Springer Nature
3 publications, 42.86%
Frontiers Media S.A.
Frontiers Media S.A., 1, 14.29%
Frontiers Media S.A.
1 publication, 14.29%
Elsevier
Elsevier, 1, 14.29%
Elsevier
1 publication, 14.29%
1
2
3
  • We do not take into account publications that without a DOI.
  • Statistics recalculated only for publications connected to researchers, organizations and labs registered on the platform.
  • Statistics recalculated weekly.
Metrics
Share
Cite this
GOST |
Cite this
GOST Copy
Hushchyn M., Ustyuzhanin A., Ustyuzhanin A. Generalization of Change-Point Detection in Time Series Data Based on Direct Density Ratio Estimation // Journal of Computational Science. 2021. Vol. 53. p. 101385.
GOST all authors (up to 50) Copy
Hushchyn M., Ustyuzhanin A., Ustyuzhanin A. Generalization of Change-Point Detection in Time Series Data Based on Direct Density Ratio Estimation // Journal of Computational Science. 2021. Vol. 53. p. 101385.
RIS |
Cite this
RIS Copy
TY - JOUR
DO - 10.1016/j.jocs.2021.101385
UR - https://doi.org/10.1016%2Fj.jocs.2021.101385
TI - Generalization of Change-Point Detection in Time Series Data Based on Direct Density Ratio Estimation
T2 - Journal of Computational Science
AU - Hushchyn, Mikhail
AU - Ustyuzhanin, Andrey
AU - Ustyuzhanin, Andrey
PY - 2021
DA - 2021/07/01 00:00:00
PB - Elsevier
SP - 101385
VL - 53
SN - 1877-7503
ER -
BibTex
Cite this
BibTex Copy
@article{2021_Hushchyn,
author = {Mikhail Hushchyn and Andrey Ustyuzhanin and Andrey Ustyuzhanin},
title = {Generalization of Change-Point Detection in Time Series Data Based on Direct Density Ratio Estimation},
journal = {Journal of Computational Science},
year = {2021},
volume = {53},
publisher = {Elsevier},
month = {jul},
url = {https://doi.org/10.1016%2Fj.jocs.2021.101385},
pages = {101385},
doi = {10.1016/j.jocs.2021.101385}
}
Found error?