Relevant Multi Domain Features Selection Based on Mutual Information for Heart Sound Classification

Rima Touahria, Abdenour Hacine-Gharbi, Philippe Ravier, Messaoud Mostefai

2024

Abstract

Many classification systems of the heart sound signals use a combination of features from different domains. In a former reference paper, 324 multidomain features were used for classifying segmented phonocardiogram signals. However, the large feature dimension requires high memory space, high calculus and probably reduces the classification accuracy caused by the curse of dimensionality. In the present work, we propose to reduce the dimensionality of features vectors by selecting the relevant features using six heuristic strategies of feature selection based on mutual information maximisation criterion. In order to validate the selected subset of features, a k-NN model based-classifier was used and evaluated on the PhysioNet/Computing in Cardiology Challenge2016 dataset using the same features sets described in the reference paper. The results demonstrate that the Joint Mutual Information (JMI) selection strategy increases the classification rate from 85. 57% to 89.28% and simultaneously reduces dimension from 324 to 46. Furthermore, this work demonstrates that systolic segment features are the most relevant for murmur/normal classification. It also demonstrates the capability of feature selection algorithms to emphasize specific key areas in signals, which is helpful for aided diagnostic systems and fundamental research.

Paper Citation

in Harvard Style

Touahria R., Hacine-Gharbi A., Ravier P. and Mostefai M. (2024). Relevant Multi Domain Features Selection Based on Mutual Information for Heart Sound Classification. In Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM; ISBN 978-989-758-684-2, SciTePress, pages 918-923. DOI: 10.5220/0012565300003654

in Bibtex Style

@conference{icpram24,
author={Rima Touahria and Abdenour Hacine-Gharbi and Philippe Ravier and Messaoud Mostefai},
title={Relevant Multi Domain Features Selection Based on Mutual Information for Heart Sound Classification},
booktitle={Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},
year={2024},
pages={918-923},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012565300003654},
isbn={978-989-758-684-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
TI - Relevant Multi Domain Features Selection Based on Mutual Information for Heart Sound Classification
SN - 978-989-758-684-2
AU - Touahria R.
AU - Hacine-Gharbi A.
AU - Ravier P.
AU - Mostefai M.
PY - 2024
SP - 918
EP - 923
DO - 10.5220/0012565300003654
PB - SciTePress