# Statistical feature embedding for heart sound classification

## TL;DR

This paper introduces a novel heart sound classification method using i-vector feature extraction, PCA and VAE for dimension reduction, and GMM/SVM classifiers, achieving significant accuracy improvements on the Physionet dataset.

## Contribution

It is the first to use i-vector features combined with PCA and VAE for heart sound classification, enhancing diagnostic accuracy.

## Key findings

- Achieved 16% improvement in Modified Accuracy over baseline.
- Effective dimension reduction with PCA and VAE.
- Validated on Physionet 2016 dataset.

## Abstract

Cardiovascular Disease (CVD) is considered as one of the principal causes of death in the world. Over recent years, this field of study has attracted researchers' attention to investigate heart sounds' patterns for disease diagnostics. In this study, an approach is proposed for normal/abnormal heart sound classification on the Physionet challenge 2016 dataset. For the first time, a fixed-length feature vector; called i-vector; is extracted from each heart sound using Mel Frequency Cepstral Coefficient (MFCC) features. Afterwards, Principal Component Analysis (PCA) transform and Variational Autoencoder (VAE) are applied on the i-vector to achieve dimension reduction. Eventually, the reduced size vector is fed to Gaussian Mixture Models (GMMs) and Support Vector Machine (SVM) for classification purpose. Experimental results demonstrate the proposed method could achieve a performance improvement of 16% based on Modified Accuracy (MAcc) compared with the baseline system on the Physoinet dataset.