HRV feature selection based on discriminant and redundancy analysis for neonatal seizure detection

M. B. Malarvili, M. Mesbah, B. Boashash

Research output: Chapter in Book/Report/Conference proceedingConference contribution

13 Citations (Scopus)

Abstract

This paper addresses the feature selection problem by using a discriminant and redundancy based method to select a feature subset with high discriminatory power between the classes of newborn heart rate variability (HRV) corresponding to seizure and non-seizure. The proposed method combines the Fast Correlation Based Filter (FCBF) criteria for redundancy analysis with the area under the Receiver Operating Curves (AUC) for discriminant analysis. The classification accuracies of the selected features were compared using 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 a significant reduction in feature dimensionality while achieving 85.7% sensitivity and 84.6% specificity.

Original languageEnglish
Title of host publication2007 6th International Conference on Information, Communications and Signal Processing, ICICS
DOIs
Publication statusPublished - 2007
Event2007 6th International Conference on Information, Communications and Signal Processing, ICICS - Singapore, Singapore
Duration: Dec 10 2007Dec 13 2007

Other

Other2007 6th International Conference on Information, Communications and Signal Processing, ICICS
CountrySingapore
CitySingapore
Period12/10/0712/13/07

Fingerprint

Redundancy
Feature extraction
Classifiers
Discriminant analysis

Keywords

  • Feature extraction
  • Feature selection-filter
  • Heart rate variability
  • Newborn seizure detection
  • Statistical classifier

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Malarvili, M. B., Mesbah, M., & Boashash, B. (2007). HRV feature selection based on discriminant and redundancy analysis for neonatal seizure detection. In 2007 6th International Conference on Information, Communications and Signal Processing, ICICS [4449765] https://doi.org/10.1109/ICICS.2007.4449765

HRV feature selection based on discriminant and redundancy analysis for neonatal seizure detection. / Malarvili, M. B.; Mesbah, M.; Boashash, B.

2007 6th International Conference on Information, Communications and Signal Processing, ICICS. 2007. 4449765.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Malarvili, MB, Mesbah, M & Boashash, B 2007, HRV feature selection based on discriminant and redundancy analysis for neonatal seizure detection. in 2007 6th International Conference on Information, Communications and Signal Processing, ICICS., 4449765, 2007 6th International Conference on Information, Communications and Signal Processing, ICICS, Singapore, Singapore, 12/10/07. https://doi.org/10.1109/ICICS.2007.4449765
Malarvili MB, Mesbah M, Boashash B. HRV feature selection based on discriminant and redundancy analysis for neonatal seizure detection. In 2007 6th International Conference on Information, Communications and Signal Processing, ICICS. 2007. 4449765 https://doi.org/10.1109/ICICS.2007.4449765
Malarvili, M. B. ; Mesbah, M. ; Boashash, B. / HRV feature selection based on discriminant and redundancy analysis for neonatal seizure detection. 2007 6th International Conference on Information, Communications and Signal Processing, ICICS. 2007.
@inproceedings{75aaf0e5bece40a983491d13b326fbd1,
title = "HRV feature selection based on discriminant and redundancy analysis for neonatal seizure detection",
abstract = "This paper addresses the feature selection problem by using a discriminant and redundancy based method to select a feature subset with high discriminatory power between the classes of newborn heart rate variability (HRV) corresponding to seizure and non-seizure. The proposed method combines the Fast Correlation Based Filter (FCBF) criteria for redundancy analysis with the area under the Receiver Operating Curves (AUC) for discriminant analysis. The classification accuracies of the selected features were compared using 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 a significant reduction in feature dimensionality while achieving 85.7{\%} sensitivity and 84.6{\%} specificity.",
keywords = "Feature extraction, Feature selection-filter, Heart rate variability, Newborn seizure detection, Statistical classifier",
author = "Malarvili, {M. B.} and M. Mesbah and B. Boashash",
year = "2007",
doi = "10.1109/ICICS.2007.4449765",
language = "English",
isbn = "1424409837",
booktitle = "2007 6th International Conference on Information, Communications and Signal Processing, ICICS",

}

TY - GEN

T1 - HRV feature selection based on discriminant and redundancy analysis for neonatal seizure detection

AU - Malarvili, M. B.

AU - Mesbah, M.

AU - Boashash, B.

PY - 2007

Y1 - 2007

N2 - This paper addresses the feature selection problem by using a discriminant and redundancy based method to select a feature subset with high discriminatory power between the classes of newborn heart rate variability (HRV) corresponding to seizure and non-seizure. The proposed method combines the Fast Correlation Based Filter (FCBF) criteria for redundancy analysis with the area under the Receiver Operating Curves (AUC) for discriminant analysis. The classification accuracies of the selected features were compared using 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 a significant reduction in feature dimensionality while achieving 85.7% sensitivity and 84.6% specificity.

AB - This paper addresses the feature selection problem by using a discriminant and redundancy based method to select a feature subset with high discriminatory power between the classes of newborn heart rate variability (HRV) corresponding to seizure and non-seizure. The proposed method combines the Fast Correlation Based Filter (FCBF) criteria for redundancy analysis with the area under the Receiver Operating Curves (AUC) for discriminant analysis. The classification accuracies of the selected features were compared using 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 a significant reduction in feature dimensionality while achieving 85.7% sensitivity and 84.6% specificity.

KW - Feature extraction

KW - Feature selection-filter

KW - Heart rate variability

KW - Newborn seizure detection

KW - Statistical classifier

UR - http://www.scopus.com/inward/record.url?scp=50449091090&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50449091090&partnerID=8YFLogxK

U2 - 10.1109/ICICS.2007.4449765

DO - 10.1109/ICICS.2007.4449765

M3 - Conference contribution

SN - 1424409837

SN - 9781424409839

BT - 2007 6th International Conference on Information, Communications and Signal Processing, ICICS

ER -