HRV feature selection for neonatal seizure detection

A wrapper approach

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

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

6 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationICSPC 2007 Proceedings - 2007 IEEE International Conference on Signal Processing and Communications
Pages864-867
Number of pages4
DOIs
Publication statusPublished - 2007
Event2007 IEEE International Conference on Signal Processing and Communications, ICSPC 2007 - Dubai, United Arab Emirates
Duration: Nov 14 2007Nov 27 2007

Other

Other2007 IEEE International Conference on Signal Processing and Communications, ICSPC 2007
CountryUnited Arab Emirates
CityDubai
Period11/14/0711/27/07

Fingerprint

seizure
Feature extraction
Classifiers
Set theory

Keywords

  • Feature extraction
  • Newborn heart rate variability
  • Seizure
  • Statistical classifier
  • Wrapper

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing
  • Communication

Cite this

Malarvili, M. B., Mesbah, M., & Boashash, B. (2007). HRV feature selection for neonatal seizure detection: A wrapper approach. In ICSPC 2007 Proceedings - 2007 IEEE International Conference on Signal Processing and Communications (pp. 864-867). [4728456] https://doi.org/10.1109/ICSPC.2007.4728456

HRV feature selection for neonatal seizure detection : A wrapper approach. / Malarvili, M. B.; Mesbah, M.; Boashash, B.

ICSPC 2007 Proceedings - 2007 IEEE International Conference on Signal Processing and Communications. 2007. p. 864-867 4728456.

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

Malarvili, MB, Mesbah, M & Boashash, B 2007, HRV feature selection for neonatal seizure detection: A wrapper approach. in ICSPC 2007 Proceedings - 2007 IEEE International Conference on Signal Processing and Communications., 4728456, pp. 864-867, 2007 IEEE International Conference on Signal Processing and Communications, ICSPC 2007, Dubai, United Arab Emirates, 11/14/07. https://doi.org/10.1109/ICSPC.2007.4728456
Malarvili MB, Mesbah M, Boashash B. HRV feature selection for neonatal seizure detection: A wrapper approach. In ICSPC 2007 Proceedings - 2007 IEEE International Conference on Signal Processing and Communications. 2007. p. 864-867. 4728456 https://doi.org/10.1109/ICSPC.2007.4728456
Malarvili, M. B. ; Mesbah, M. ; Boashash, B. / HRV feature selection for neonatal seizure detection : A wrapper approach. ICSPC 2007 Proceedings - 2007 IEEE International Conference on Signal Processing and Communications. 2007. pp. 864-867
@inproceedings{8ca4dfafdb474d35b88723d138ef35c0,
title = "HRV feature selection for neonatal seizure detection: A wrapper approach",
abstract = "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.",
keywords = "Feature extraction, Newborn heart rate variability, Seizure, Statistical classifier, Wrapper",
author = "Malarvili, {M. B.} and M. Mesbah and B. Boashash",
year = "2007",
doi = "10.1109/ICSPC.2007.4728456",
language = "English",
isbn = "9781424412365",
pages = "864--867",
booktitle = "ICSPC 2007 Proceedings - 2007 IEEE International Conference on Signal Processing and Communications",

}

TY - GEN

T1 - HRV feature selection for neonatal seizure detection

T2 - A wrapper approach

AU - Malarvili, M. B.

AU - Mesbah, M.

AU - Boashash, B.

PY - 2007

Y1 - 2007

N2 - 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.

AB - 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.

KW - Feature extraction

KW - Newborn heart rate variability

KW - Seizure

KW - Statistical classifier

KW - Wrapper

UR - http://www.scopus.com/inward/record.url?scp=60349132394&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=60349132394&partnerID=8YFLogxK

U2 - 10.1109/ICSPC.2007.4728456

DO - 10.1109/ICSPC.2007.4728456

M3 - Conference contribution

SN - 9781424412365

SP - 864

EP - 867

BT - ICSPC 2007 Proceedings - 2007 IEEE International Conference on Signal Processing and Communications

ER -