Statistical feature embedding for heart sound classification
This work addresses heart sound classification for medical diagnostics, but it is incremental as it combines existing techniques like i-vectors, PCA, VAE, GMMs, and SVM in a new way for this specific dataset.
The paper tackled heart sound classification for cardiovascular disease diagnostics by proposing a method that extracts i-vectors from MFCC features, reduces dimensions with PCA and VAE, and classifies using GMMs and SVM, achieving a 16% improvement in Modified Accuracy over the baseline on the Physionet 2016 dataset.
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.