2022 IEEE Congress on Evolutionary Computation, CEC 2022 - Conference Proceedings

Evolutionary Automated Machine Learning for Multi-Scale Decomposition and Forecasting of Sensor Time Series

Sarafanov Mikhail ¹

Pokrovskii Valerii ¹

Nikitin Nikolay O ¹

Hide authors affiliations Show authors affiliations: 1 affiliation

National Center for Cognitive Research ITMO University,Saint Petersburg,Russia |

Publication type: Proceedings Article

Publication date: 2022-07-18

—

DOI: 10.1109/CEC55065.2022.9870347

Copy DOI

Abstract

In the paper, we discuss the applicability of automated machine learning for the effective multi-scale modeling of the industrial sensors time series. The proposed approach is based on the evolutionary generative design of the composite modeling pipelines. The iterative data decomposition algorithm is proposed in the paper to improve the quality of the sensor time series forecasting. To effectively use it in an automated way, the boosting-like mutation operators have been implemented for graphs-based genotypes. The proposed approach reduced the forecast error by 10% compared to the competitor library AutoTS. Also, the proposed modifications of the evolutionary algorithm resulted in better metrics in 78% of the cases where they were used.

By date By citations

Citations by journals

	1
Doklady Mathematics	Doklady Mathematics, 1, 25% Doklady Mathematics 1 publication, 25%
Information (Switzerland)	Information (Switzerland), 1, 25% Information (Switzerland) 1 publication, 25%
	1

Citations by publishers

	1 2
IEEE	IEEE, 2, 50% IEEE 2 publications, 50%
Pleiades Publishing	Pleiades Publishing, 1, 25% Pleiades Publishing 1 publication, 25%
Multidisciplinary Digital Publishing Institute (MDPI)	Multidisciplinary Digital Publishing Institute (MDPI), 1, 25% Multidisciplinary Digital Publishing Institute (MDPI) 1 publication, 25%
	1 2

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.

{"yearsCitations":{"type":"bar","data":{"show":true,"labels":[2022,2023,2024],"ids":[0,0,0],"codes":[0,0,0],"imageUrls":["","",""],"datasets":[{"label":"Citations number","data":[1,2,1],"backgroundColor":["#3B82F6","#3B82F6","#3B82F6"],"percentage":["25","50","25"],"barThickness":null}]},"options":{"indexAxis":"x","maintainAspectRatio":true,"scales":{"y":{"ticks":{"precision":0,"autoSkip":false,"font":{"family":"Montserrat"},"color":"#000000"}},"x":{"ticks":{"stepSize":1,"precision":0,"font":{"family":"Montserrat"},"color":"#000000"}}},"plugins":{"legend":{"position":"top","labels":{"font":{"family":"Montserrat"},"color":"#000000"}},"title":{"display":true,"text":"Citations per year","font":{"size":24,"family":"Montserrat","weight":600},"color":"#000000"}}}},"journals":{"type":"bar","data":{"show":true,"labels":["Doklady Mathematics","Information (Switzerland)"],"ids":[12175,4512],"codes":[0,0],"imageUrls":["\/storage\/images\/resized\/oZgeErrVFhuDksyqFURLvYS1wtVSBWczh001igGo_medium.webp","\/storage\/images\/resized\/MjH1ITP7lMYGxeqUZfkt2BnVLgjkk413jwBV97XX_medium.webp"],"datasets":[{"label":"","data":[1,1],"backgroundColor":["#3B82F6","#3B82F6"],"percentage":[25,25],"barThickness":13}]},"options":{"indexAxis":"y","maintainAspectRatio":false,"scales":{"y":{"ticks":{"precision":0,"autoSkip":false,"font":{"family":"Montserrat"},"color":"#000000"}},"x":{"ticks":{"stepSize":null,"precision":0,"font":{"family":"Montserrat"},"color":"#000000"}}},"plugins":{"legend":{"position":"top","labels":{"font":{"family":"Montserrat"},"color":"#000000"}},"title":{"display":true,"text":"Journals","font":{"size":24,"family":"Montserrat","weight":600},"color":"#000000"}}}},"publishers":{"type":"bar","data":{"show":true,"labels":["IEEE","Pleiades Publishing","Multidisciplinary Digital Publishing Institute (MDPI)"],"ids":[6953,101,202],"codes":[0,0,0],"imageUrls":["\/storage\/images\/resized\/6scCJegesojp2jubwY3uKCzTAmgsaH2GIFlg6Hfk_medium.webp","\/storage\/images\/resized\/oZgeErrVFhuDksyqFURLvYS1wtVSBWczh001igGo_medium.webp","\/storage\/images\/resized\/MjH1ITP7lMYGxeqUZfkt2BnVLgjkk413jwBV97XX_medium.webp"],"datasets":[{"label":"","data":[2,1,1],"backgroundColor":["#3B82F6","#3B82F6","#3B82F6"],"percentage":[50,25,25],"barThickness":13}]},"options":{"indexAxis":"y","maintainAspectRatio":false,"scales":{"y":{"ticks":{"precision":0,"autoSkip":false,"font":{"family":"Montserrat"},"color":"#000000"}},"x":{"ticks":{"stepSize":null,"precision":0,"font":{"family":"Montserrat"},"color":"#000000"}}},"plugins":{"legend":{"position":"top","labels":{"font":{"family":"Montserrat"},"color":"#000000"}},"title":{"display":true,"text":"Publishers","font":{"size":24,"family":"Montserrat","weight":600},"color":"#000000"}}}}}

Metrics

Cite this

GOST |

Cite this

GOST Copy

Sarafanov M., Pokrovskii V., Nikitin N. O. Evolutionary Automated Machine Learning for Multi-Scale Decomposition and Forecasting of Sensor Time Series // 2022 IEEE Congress on Evolutionary Computation, CEC 2022 - Conference Proceedings. 2022.

GOST all authors (up to 50) Copy

RIS |

Cite this

RIS Copy

TY - CPAPER

DO - 10.1109/CEC55065.2022.9870347

UR - https://doi.org/10.1109%2FCEC55065.2022.9870347

TI - Evolutionary Automated Machine Learning for Multi-Scale Decomposition and Forecasting of Sensor Time Series

T2 - 2022 IEEE Congress on Evolutionary Computation, CEC 2022 - Conference Proceedings

AU - Sarafanov, Mikhail

AU - Pokrovskii, Valerii

AU - Nikitin, Nikolay O

PY - 2022

DA - 2022/07/18 00:00:00

ER -

BibTex

Cite this

BibTex Copy

@inproceedings{2022_Sarafanov,

author = {Mikhail Sarafanov and Valerii Pokrovskii and Nikolay O Nikitin},

title = {Evolutionary Automated Machine Learning for Multi-Scale Decomposition and Forecasting of Sensor Time Series},

year = {2022},

month = {jul}

}

Found error?

Publisher

—

Profiles