Network structure identification from corrupt data streams

Venkat Ram Subramanian, Andrew Lamperski, Murti V. Salapaka

Research output: Contribution to journalArticlepeer-review

3 Scopus citations


Complex networked systems can be modeled as graphs with nodes representing the agents and links describing the dynamic coupling between them. Previous work on network identification has shown that the network structure of linear time-invariant (LTI) systems can be reconstructed from the joint power spectrum of the data streams. These results assumed that data are perfectly measured. However, real-world data are subject to many corruptions, such as inaccurate time-stamps, noise, and data loss. We show that identifying the structure of linear time-invariant (LTI) systems using corrupt measurements results in the inference of erroneous links. We provide an exact characterization and prove that such erroneous links are restricted to the neighborhood of the perturbed node. We extend the analysis of LTI systems to the case of Markov random fields with corrupt measurements. We show that data corruption in Markov random fields results in spurious probabilistic relationships in precisely the locations, where spurious links arise in LTI systems.

Original languageEnglish (US)
Pages (from-to)5314-5325
Number of pages12
JournalIEEE Transactions on Automatic Control
Issue number11
StatePublished - Nov 1 2021

Bibliographical note

Publisher Copyright:
© 1963-2012 IEEE.


  • Graphical models
  • system identification
  • time series analysis


Dive into the research topics of 'Network structure identification from corrupt data streams'. Together they form a unique fingerprint.

Cite this