A real-time anomaly detection algorithm/or water quality data using dual time-moving windows

Jin Zhang, Xiaohui Zhu*, Yong Yue, Prudence W.H. Wong

*Corresponding author for this work

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

14 Citations (Scopus)

Abstract

Anomaly data in real-time water quality monitoring systems can cause false alarms and significantly decrease system stability and reliability. We propose a novel anomaly detection algorithm for water quality data using dual time-moving windows, which can identify anomaly data from historical patterns in real-time. The algorithm is based on an autoregressive linear combination model, a prediction interval with dual time-moving windows and a backtracking verification strategy. We have tested the algorithm using 3-month water quality data of PH from a real water quality monitoring station in a river system. Experimental results show that our novel anomaly detection algorithm can significantly decrease the rate of false positive and has better anomaly detection performance than AD and ADAM algorithms.

Original languageEnglish
Title of host publication7th International Conference on Innovative Computing Technology, INTECH 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages36-41
Number of pages6
ISBN (Electronic)9781509039883
DOIs
Publication statusPublished - 8 Nov 2017
Event7th International Conference on Innovative Computing Technology, INTECH 2017 - Luton, United Kingdom
Duration: 16 Aug 201718 Aug 2017

Publication series

Name7th International Conference on Innovative Computing Technology, INTECH 2017

Conference

Conference7th International Conference on Innovative Computing Technology, INTECH 2017
Country/TerritoryUnited Kingdom
CityLuton
Period16/08/1718/08/17

Keywords

  • anomaly data detection
  • autoregressive linear combination model
  • backtracking verification
  • dual time-moving windows

Fingerprint

Dive into the research topics of 'A real-time anomaly detection algorithm/or water quality data using dual time-moving windows'. Together they form a unique fingerprint.

Cite this