Skip to main navigation Skip to search Skip to main content

Mining dynamic association rules from multiple time-series data based on data of power plant

  • Harbin Institute of Technology Shenzhen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Plenty of data are generated from sectors such as industrial manufacture, financial service, e-commerce, satellite remote sensing, sensor network and so on. Normally these data are often with time tags, which are called as time series steams. In this paper sliding window is used to limit the time series data; pretreatment process proceeds linear approximation to the sequences; the sequences after linearization are cut. In the sliding window we maintaining a global SWIU-tree (Incremental Updating tree based on Sliding Window) to store the synopsis structures of scanned datasets, to get rid of the unfrequent patterns and outdated patterns by pruning strategy. With the comparation between the existing algorithm and SWIU-tree algorithm on the data of actual thermal power plant, illustrating that SWIU-tree algorithm is effective and which is able to quickly and precisely dig the association rules among multiple time series streams.

Original languageEnglish
Title of host publicationProceedings of 2016 IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2016
EditorsBing Xu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1968-1972
Number of pages5
ISBN (Electronic)9781467396127
DOIs
StatePublished - 28 Feb 2017
Externally publishedYes
Event2016 IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2016 - Xi'an, China
Duration: 3 Oct 20165 Oct 2016

Publication series

NameProceedings of 2016 IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2016

Conference

Conference2016 IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference, IMCEC 2016
Country/TerritoryChina
CityXi'an
Period3/10/165/10/16

Keywords

  • Association Rules
  • Sliding Window
  • Support Threshold
  • Time-Series Data

Fingerprint

Dive into the research topics of 'Mining dynamic association rules from multiple time-series data based on data of power plant'. Together they form a unique fingerprint.

Cite this