The Library

MuSDRI : Multi-seasonal decomposition based recurrent imputation for time series

Tools

Zhou, Yujue, Jiang, Jie, Yang, Shuang-Hua, He, Ligang and Ding, Yulong (2021) MuSDRI : Multi-seasonal decomposition based recurrent imputation for time series. IEEE Sensors Journal, 21 (20). pp. 23213-23223. doi:10.1109/jsen.2021.3107836

Preview

PDF
WRAP-MuSDRI-multi-seasonal-decomposition-based-recurrent-imputation-time-series-2021.pdf - Accepted Version - Requires a PDF viewer.
Download (1327Kb) | Preview

Official URL: https://doi.org/10.1109/JSEN.2021.3107836

Request Changes to record.

Abstract

Missing values are a common problem of time series such as sensor-generated data due to issues of data collection, transmission, and storage. To deal with this problem, various data imputation methods have been proposed. Among these methods, variants of recurrent neural networks (RNNs) have attracted a lot of attention as they provide a natural representation of temporal dynamics. Though such methods have been shown to achieve higher imputation accuracy, they mostly focus on the modeling of temporal dynamics from a short-term perspective while ignoring the long-term features such as trend and seasonal information embedded in time series data. In this paper, we investigate different paradigms of time series imputation methods to capture temporal dynamics from both long-term and short-term perspectives. In particular, we propose a new learning paradigm called MuSDRI which combines the time series decomposition method Seasonal Trend decomposition using Loess (STL) with RNNs. Specifically, STL is used to decompose long sequences of time series into trend, seasonal, and remainder components such that long-term dynamics can be revealed; RNNs are used to capture local patterns from the remainder component extracted by STL such that short-term dynamics can be refined. Moreover, MuSDRI is able to handle time series with multiple seasonal patterns by learning their contributions with respect to the imputation task. We evaluate the proposed imputation methods on three real-world datasets. Experimental results show that the imputation methods considering both the long-term and short-term dynamics achieve higher imputation accuracy, and among them MuSDRI in general achieves the best performance.

Item Type:

Journal Article

Subjects:

Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software

Divisions:

Faculty of Science > Computer Science

SWORD Depositor:

Library Publications Router

Library of Congress Subject Headings (LCSH):

Neural networks (Computer science), Time series analysis, Sensor networks, Data mining, Machine learning

Journal or Publication Title:

IEEE Sensors Journal

Publisher:

Institute of Electrical and Electronics Engineers (IEEE)

ISSN:

1558-1748

Official Date:

15 October 2021

Dates:

Date	Event
15 October 2021	Published
2021	Available

Volume:

Number:

Page Range:

pp. 23213-23223

DOI:

10.1109/jsen.2021.3107836

Status:

Peer Reviewed

Publication Status:

Published

Publisher Statement:

© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Access rights to Published version:

Restricted or Subscription Access

RIOXX Funder/Project Grant:

Project/Grant ID	RIOXX Funder Name	Funder ID
61873119	[NSFC] National Natural Science Foundation of China	http://dx.doi.org/10.13039/501100001809
92067109	[NSFC] National Natural Science Foundation of China	http://dx.doi.org/10.13039/501100001809
2019YFC0810705	National Key Research and Development Program of China	UNSPECIFIED
KQJSCX20180322151418232	Science, Technology and Innovation Commission of Shenzhen Municipality	http://dx.doi.org/10.13039/501100010877