SVD-based newborn EEG seizure detection in the time-frequency domain

Hantid Hassanpour, Mostefa Mesbah, Boualem Boashash

Research output: Contribution to journalConference articlepeer-review


This paper utilises the Singular Value Decomposition (SVD) technique applied to the time-frequency representation of Electroencephalogram (EEG) signals for detecting EEG seizures in neonates. Seizure in EEG signal may have signature in different frequency areas. This paper, is concentrated on the low frequency (lower than 10 Hz) signature of the seizures. The proposed technique uses the estimated distribution function of the singular vectors associated with the time-frequency representation of the EEG epoch to characterise the patterns embedded in the signal. The estimated distributed functions related to the seizure and nonseizure epochs were used to train a neural network to discriminate between seizure and nonseizure patterns.

Original languageEnglish
Pages (from-to)329-333
Number of pages5
JournalIFAC Proceedings Volumes (IFAC-PapersOnline)
Issue number15
Publication statusPublished - 2003
Externally publishedYes
Event5th IFAC Symposium on Modelling and Control in Biomedical Systems 2003 - Melbourne, Australia
Duration: Aug 21 2003Aug 23 2003


  • Detection
  • Signal processing
  • Singular Value Decomposition
  • Time-frequency representation

ASJC Scopus subject areas

  • Control and Systems Engineering


Dive into the research topics of 'SVD-based newborn EEG seizure detection in the time-frequency domain'. Together they form a unique fingerprint.

Cite this