Skip to main navigation Skip to search Skip to main content

Trend-adaptive multi-scale PCA for data fault detection in IoT networks

  • Thien Binh Dang
  • , Manh Hung Tran
  • , Duc Tai Le
  • , Vyacheslav V. Zalyubovskiy
  • , Hyohoon Ahn
  • , Hyunseung Choo

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

Abstract

A wide range of IoT applications use information collected from networks of sensors for monitoring and controlling purposes. In such applications, the frequent appearance of fault data makes it difficult to extract correct information, thereby making confuses in interpreting and analyzing collected data. To address this problem, it is necessary to have a mechanism to detect fault data. In this paper, we present a Trend-adaptive Multi-Scale Principal Component Analysis (Trend-adaptive MS-PCA) model for data fault detection. The proposed model inherits advantages of Discrete Wavelet Transform (DWT) in capturing time-frequency information and advantages of PCA in extracting correlation among sensors' data. Experimental results on a real dataset show the high effectiveness of the proposed model in data fault detection. Moreover, the Trend-adaptive MS-PCA shows that it outperforms fault detection techniques using PCA and MS-PCA in term of fault sensitiveness.

Original languageEnglish
Title of host publication32nd International Conference on Information Networking, ICOIN 2018
PublisherIEEE Computer Society
Pages744-749
Number of pages6
ISBN (Electronic)9781538622896
DOIs
StatePublished - 19 Apr 2018
Event32nd International Conference on Information Networking, ICOIN 2018 - Chiang Mai, Thailand
Duration: 10 Jan 201812 Jan 2018

Publication series

NameInternational Conference on Information Networking
Volume2018-January
ISSN (Print)1976-7684

Conference

Conference32nd International Conference on Information Networking, ICOIN 2018
Country/TerritoryThailand
CityChiang Mai
Period10/01/1812/01/18

Keywords

  • Anomaly detection
  • Discrete wavelet transform
  • Fault detection
  • IoT
  • Outlier detection
  • Principal component analysis
  • Security

Fingerprint

Dive into the research topics of 'Trend-adaptive multi-scale PCA for data fault detection in IoT networks'. Together they form a unique fingerprint.

Cite this