HRV feature selection for neonatal seizure detection: A wrapper approach

Malarvili, M. B., Mesbah, M. and Boashash, B. (2007). HRV feature selection for neonatal seizure detection: A wrapper approach. In: Signal Processing and Communication 2007 (ICSPC 2007). IEEE International Conference on Signal Processing and Communication (ICSPC07), Dubai, United Arab Emirates, (864-867). 24-27 November 2007. doi:10.1109/ICSPC.2007.4728456


Author Malarvili, M. B.
Mesbah, M.
Boashash, B.
Title of paper HRV feature selection for neonatal seizure detection: A wrapper approach
Conference name IEEE International Conference on Signal Processing and Communication (ICSPC07)
Conference location Dubai, United Arab Emirates
Conference dates 24-27 November 2007
Convener IEEE
Proceedings title Signal Processing and Communication 2007 (ICSPC 2007)
Place of Publication Piscataway, NJ, U.S.A.
Publisher IEEE - Institute of Electrical Electronics Engineers Inc.
Publication Year 2007
Year available 2007
Sub-type Fully published paper
DOI 10.1109/ICSPC.2007.4728456
ISBN 1-4244-1236-6
978-1-4244-1235-8
Start page 864
End page 867
Total pages 4
Language eng
Abstract/Summary This work addresses the feature selection problem using a wrapper approach to select a feature subset to distinguish between the classes of newborn heart rate variability (HRV) corresponding to seizure and non-seizure. The method utilizes a filter as a pre-step to remove the irrelevant and redundant features from the original set of features to provide a starting feature subset for the wrapper. This reduces the computation load and the severity of the search operations involved in a wrapper approach. The goodness of the feature subset selected is compared over 3 different classifiers, namely linear classifier, quadratic classifier and k-Nearest Neighbour (k-NN) statistical classifiers in a leave-one-out (LOO) cross validation. It was found that the 1-NN outperformed the other classifiers resulting in significant reductions in feature dimensionality and achieving 85.7% sensitivity and 84.6% specificity.
Subjects 090609 Signal Processing
0903 Biomedical Engineering
Keyword Feature extraction
Newborn heart rate variability
Neonatal seizure detection
Statistical classifier
Wrapper approach
Q-Index Code E1

Document type: Conference Paper
Sub-type: Fully published paper
Collections: Excellence in Research Australia (ERA) - Collection
UQ Centre for Clinical Research Publications
 
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 4 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Thu, 26 Mar 2009, 23:28:33 EST by Mary-Anne Marrington on behalf of UQ Centre for Clinical Research