• Home
  • Browse
    • Current Issue
    • By Issue
    • By Author
    • By Subject
    • Author Index
    • Keyword Index
  • Journal Info
    • About Journal
    • Aims and Scope
    • Editorial Board
    • Advisory Board
    • Editorial Staff
    • Publication Ethics
    • Indexing and Abstracting
    • Related Links
    • FAQ
    • Peer Review Process
    • News
  • Guide for Authors
  • Submit Manuscript
  • Reviewers
  • Contact Us
 
  • Login
  • Register
Home Articles List Article Information
  • Save Records
  • |
  • Printable Version
  • |
  • Recommend
  • |
  • How to cite Export to
    RIS EndNote BibTeX APA MLA Harvard Vancouver
  • |
  • Share Share
    CiteULike Mendeley Facebook Google LinkedIn Twitter Telegram
Scientia Iranica
Articles in Press
Current Issue
Journal Archive
Volume Volume 25 (2018)
Volume Volume 24 (2017)
Issue Issue 6
Transactions on Civil Engineering (A)
Issue Issue 6
Transactions on Mechanical Engineering (B)
Issue Issue 6
Transactions on Chemistry and Chemical Engineering (C)
Issue Issue 6
Transactions on Computer Science & Engineering and Electrical Engineering (D)
Issue Issue 6
Transactions on Industrial Engineering (E)
Issue Issue 6
Transactions on Nanotechnology (F)
Issue Issue 5
Transactions on Civil Engineering (A)
Issue Issue 5
Transactions on Mechanical Engineering (B)
Issue Issue 5
Transactions on Industrial Engineering (E)
Issue Issue 4
Transactions on Civil Engineering (A)
Issue Issue 4
Transactions on Mechanical Engineering (B)
Issue Issue 4
Transactions on Industrial Engineering (E)
Issue Issue 3
Transactions on Civil Engineering (A)
Issue Issue 3
Transactions on Mechanical Engineering (B)
Issue Issue 3
Transactions on Chemistry and Chemical Engineering (C)
Issue Issue 3
Transactions on Computer Science & Engineering and Electrical Engineering (D)
Issue Issue 3
Transactions on Industrial Engineering (E)
Issue Issue 3
Transactions on Nanotechnology (F)
Issue Issue 2
Transactions on Civil Engineering (A)
Issue Issue 2
Transactions on Mechanical Engineering (B)
Issue Issue 2
Transactions on Industrial Engineering (E)
Issue Issue 1
Transactions on Civil Engineering (A)
Issue Issue 1
Transactions on Mechanical Engineering (B)
Issue Issue 1
Transactions on Industrial Engineering (E)
Volume Volume 23 (2016)
Volume Volume 22 (2015)
Volume Volume 21 (2014)
Volume Volume 20 (2013)
Volume Volume 17 (2010)
Volume Volume 16 (2009)
Volume Volume 15 (2008)
Volume Volume 14 (2007)
Volume Volume 13 (2006)
Volume Volume 12 (2005)
Volume Volume 11 (2004)
Volume Volume 10 (2003)
Volume Volume 9 (2002)
Volume Volume 8 (2001)
Volume Volume 7 (2000)
Volume Volume 6 (1999)
Volume Volume 5 (1998)
Volume Volume 4 (1997)
Volume Volume 3 (1996)
Volume Volume 2 (1995)
Volume Volume 1 (1994)

Scientia Iranica

Scientia Rank

Mojarad, R., Zarandi, H. (2017). Comparison and Analysis of Three Anomaly Correction Methods in Embedded Systems. Scientia Iranica, 24(6), 3087-3100. doi: 10.24200/sci.2017.4579
Roghayeh Mojarad; Hamid R. Zarandi. "Comparison and Analysis of Three Anomaly Correction Methods in Embedded Systems". Scientia Iranica, 24, 6, 2017, 3087-3100. doi: 10.24200/sci.2017.4579
Mojarad, R., Zarandi, H. (2017). 'Comparison and Analysis of Three Anomaly Correction Methods in Embedded Systems', Scientia Iranica, 24(6), pp. 3087-3100. doi: 10.24200/sci.2017.4579
Mojarad, R., Zarandi, H. Comparison and Analysis of Three Anomaly Correction Methods in Embedded Systems. Scientia Iranica, 2017; 24(6): 3087-3100. doi: 10.24200/sci.2017.4579

Comparison and Analysis of Three Anomaly Correction Methods in Embedded Systems

Article 1, Volume 24, Issue 6, November and December 2017, Page 3087-3100  XML PDF (2594 K)
Document Type: Article
DOI: 10.24200/sci.2017.4579
Authors
Roghayeh Mojarad ; Hamid R. Zarandi
Department of Computer Engineering and Information Technology, Amirkabir University of Technology (Tehran Polytechnic), 424 Hafez Ave, Tehran, Iran
Abstract
This paper proposes and compares three anomaly correction methods in embedded systems: 1) Markov-based, 2) Stide (Sequence Time-Delay Embedding)-based, and 3) Cluster-based correction methods. All these methods work online on data streams coming from sensors of embedded systems. In these methods, detection is first obtained using training on normal data, and next in runtime, the correction mechanisms can be applied. Markov-based method is based on probabilities between states, Stide-based method is based on storing common events and Cluster-based is based on clustering similar members. In detection phase, these methods check normal behavior of input data based on what is learned at train phase. Evaluation are performed using a total of 7000 data sets. The window size and the number of injected anomalies varied between 3 and 5, 1 and 7, respectively. Correction coverage for Markov-based, Stide-based, and Cluster-based methods are on average 77.66%, 60.9%, and 70.36%, respectively. Therefore, Markov-based method is the best in terms of correction coverage. Moreover, area overheads of these methods are 249.64, 63.35 and 2.08 μm2, respectively. As a trade-off, Cluster-based method shows best correction coverage compared to area, power and delay overheads.
Keywords
Anomaly; Anomaly detection; Anomaly Correction; Correction Coverage; Embedded Systems
Main Subjects
Computer Engineering
Statistics
Article View: 60
PDF Download: 171
Home | Glossary | News | Aims and Scope | Sitemap
Top Top

© 2017 scientiairanica

Journal Management System. Designed by sinaweb.