An Ensemble of Transfer, Semi-supervised and Supervised Learning Methods for Pathological Heart Sound Classification

TL;DR

This paper introduces an ensemble of machine learning methods, including transfer learning, semi-supervised, and supervised techniques, to classify heart sound abnormalities from phonocardiogram signals, achieving improved accuracy.

Contribution

It presents a novel ensemble framework combining transfer learning, unsupervised feature extraction, and traditional classifiers for heart sound classification.

Findings

Ensemble improves UAR by 11.13% over best single model.

Transfer learning from Physionet enhances feature quality.

Combining multiple approaches yields better classification performance.

Abstract

In this work, we propose an ensemble of classifiers to distinguish between various degrees of abnormalities of the heart using Phonocardiogram (PCG) signals acquired using digital stethoscopes in a clinical setting, for the INTERSPEECH 2018 Computational Paralinguistics (ComParE) Heart Beats SubChallenge. Our primary classification framework constitutes a convolutional neural network with 1D-CNN time-convolution (tConv) layers, which uses features transferred from a model trained on the 2016 Physionet Heart Sound Database. We also employ a Representation Learning (RL) approach to generate features in an unsupervised manner using Deep Recurrent Autoencoders and use Support Vector Machine (SVM) and Linear Discriminant Analysis (LDA) classifiers. Finally, we utilize an SVM classifier on a high-dimensional segment-level feature extracted using various functionals on short-term acoustic features, i.e., Low-Level Descriptors (LLD). An ensemble of the three different approaches provides a relative improvement of 11.13% compared to our best single sub-system in terms of the Unweighted Average Recall (UAR) performance metric on the evaluation dataset.