A Semi-Supervised Approach For Identifying Abnormal Heart Sounds Using Variational Autoencoder

Abnormal heart sounds may have diverse frequency characteristics depending upon underlying pathological conditions. Designing a binary classifier for predicting normal and abnormal heart sounds using supervised learning requires a lot of training data, covering different types of cardiac abnormaliti...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) S. 1249 - 1253
Hauptverfasser: Banerjee, Rohan, Ghose, Avik
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.05.2020
Schlagworte:
Convolutional Neural Network
Heart
Heart sounds
Phonocardiography
Semi-supervised learning
Spectrogram
Speech processing
Supervised learning
Training
Training data
Variational Autoencoder
ISSN:2379-190X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Abnormal heart sounds may have diverse frequency characteristics depending upon underlying pathological conditions. Designing a binary classifier for predicting normal and abnormal heart sounds using supervised learning requires a lot of training data, covering different types of cardiac abnormalities. In this paper, we propose a semi-supervised approach to solve the problem. A convolutional Variational Autoencoder (VAE) structure is defined for learning the probability distribution of the spectrogram properties of normal heart sounds. The Kullback-Leibler (KL) divergence between the known prior distribution of the VAE and the encoded distribution is taken as an anomaly score for detecting abnormal heart sounds. The proposed approach is evaluated on open access and in-house datasets of Phonocardiogram (PCG) signals, recorded from normal subjects and patients, having cardiovascular diseases, cardiac murmurs and extra heart sounds. Results show that an improved classification performance is achieved in comparison to the existing approaches.
ISSN:2379-190X
DOI:10.1109/ICASSP40776.2020.9054632