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 language | English |
|---|---|
| Title of host publication | ICSPC 2007 Proceedings - 2007 IEEE International Conference on Signal Processing and Communications |
| Pages | 864-867 |
| Number of pages | 4 |
| DOIs | |
| Publication status | Published - 2007 |
| Event | 2007 IEEE International Conference on Signal Processing and Communications, ICSPC 2007 - Dubai, United Arab Emirates Duration: Nov 14 2007 → Nov 27 2007 |
Other
| Other | 2007 IEEE International Conference on Signal Processing and Communications, ICSPC 2007 |
|---|---|
| Country | United Arab Emirates |
| City | Dubai |
| Period | 11/14/07 → 11/27/07 |
Fingerprint
Keywords
- Feature extraction
- Newborn heart rate variability
- Seizure
- Statistical classifier
- Wrapper
ASJC Scopus subject areas
- Computer Networks and Communications
- Signal Processing
- Communication
Cite this
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 proceeding › Conference contribution
}
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 -