Singapore Institute of Technology
An_Ensemble_of_Deep_Learning_Frameworks_for_Predicting_Respiratory_Anomalies.pdf (373 kB)

An Ensemble of Deep Learning Frameworks for Predicting Respiratory Anomalies

Download (373 kB)
conference contribution
posted on 2023-10-01, 00:58 authored by Lam Pham, Dat Ngo, Khoa Tran, Truong Hoang, Alexander Schindler, Ian McLoughlinIan McLoughlin

This paper evaluates a range of deep learning frameworks for detecting respiratory anomalies from input audio. Audio recordings of respiratory cycles collected from patients are transformed into time-frequency spectrograms to serve as front-end two-dimensional features. Cropped spectrogram segments are then used to train a range of back-end deep learning networks to classify respiratory cycles into predefined medically-relevant categories. A set of those trained high-performance deep learning frameworks are then fused to obtain the best score. Our experiments on the ICBHI benchmark dataset achieve the highest ICBHI score to date of 57.3%. This is derived from a late fusion of inception based and transfer learning based deep learning frameworks, easily outperforming other state-of-the-art systems. Clinical relevance--- Respiratory disease, wheeze, crackle, inception, convolutional neural network, transfer learning.


Journal/Conference/Book title

2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)

Publication date



  • Published

Usage metrics


    No categories selected