An Ensemble of Transfer, Semi-supervised and Supervised Learning Methods for Pathological Heart Sound Classification
Ahmed Imtiaz Humayun, Md. Tauhiduzzaman Khan, Shabnam Ghaffarzadegan, Zhe Feng and Taufiq Hasan
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 Sub-Challenge. 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.
Cite as: Humayun, A.I., Khan, M.T., Ghaffarzadegan, S., Feng, Z., Hasan, T. (2018) An Ensemble of Transfer, Semi-supervised and Supervised Learning Methods for Pathological Heart Sound Classification. Proc. Interspeech 2018, 127-131, DOI: 10.21437/Interspeech.2018-2413.
BiBTeX Entry:
@inproceedings{Humayun2018,
author={Ahmed Imtiaz Humayun and Md. Tauhiduzzaman Khan and Shabnam Ghaffarzadegan and Zhe Feng and Taufiq Hasan},
title={An Ensemble of Transfer, Semi-supervised and Supervised Learning Methods for Pathological Heart Sound Classification},
year=2018,
booktitle={Proc. Interspeech 2018},
pages={127--131},
doi={10.21437/Interspeech.2018-2413},
url={http://dx.doi.org/10.21437/Interspeech.2018-2413} }