Deep Learning Framework Applied for Predicting Anomaly of Respiratory Sounds

TL;DR

This paper introduces a deep learning framework that classifies respiratory sound anomalies using spectrogram features and ensemble neural networks, achieving competitive results on a benchmark dataset.

Contribution

The work presents a novel combination of spectrogram-based feature extraction with ensemble deep neural networks for respiratory anomaly classification.

Findings

Achieved an average score of 0.49 on ICBHI benchmark

Achieved a harmonic score of 0.42 on ICBHI benchmark

Demonstrated competitive performance with existing methods

Abstract

This paper proposes a robust deep learning framework used for classifying anomaly of respiratory cycles. Initially, our framework starts with front-end feature extraction step. This step aims to transform the respiratory input sound into a two-dimensional spectrogram where both spectral and temporal features are well presented. Next, an ensemble of C- DNN and Autoencoder networks is then applied to classify into four categories of respiratory anomaly cycles. In this work, we conducted experiments over 2017 Internal Conference on Biomedical Health Informatics (ICBHI) benchmark dataset. As a result, we achieve competitive performances with ICBHI average score of 0.49, ICBHI harmonic score of 0.42.