An Inception-Residual-based Architecture with Multi-objective Loss for Detecting Respiratory Anomalies

Dat Ngo (Speaker, Invited), Lam Pham (Author, Invited), Huy Phan (Author, Invited), Minh Tran (Author, Invited), Delaram Jarchi (Author, Invited), Sefki Kolozali (Author, Invited)

Research output: Chapter in Book or Conference ProceedingsConference Proceedings with Oral Presentationpeer-review

Abstract

This paper presents a deep learning system applied for detecting anomalies from respiratory sound recordings. Initially, our system begins with audio feature extraction using Gammatone and Continuous Wavelet transformation. This step aims to transform the respiratory sound input into a two-dimensional spectrogram where both spectral and temporal features are presented. Then, our proposed system integrates Inception-residual-based backbone models combined with multi-head attention and multi-objective loss to classify respiratory anomalies. Instead of applying a simple concatenation approach by combining results from various spectrograms, we propose a linear combination, which has the ability to regulate equally the contribution of each individual spectrogram throughout the training process. To evaluate the performance, we conducted experiments over the benchmark dataset of SPRSound (The Open-Source SJTU Paediatric Respiratory Sound) proposed by the IEEE BioCAS 2022 challenge. As regards the Score computed by an average between the average score and harmonic score, our proposed system gained significant improvements of 9.7%, 15.8%, 17.8%, and 16.1% in Task 1–1, Task 1–2, Task 2–1, and Task 2–2, respectively, compared to the challenge baseline system. Notably, we achieved the Top-1 performance in Task 2–1 and Task 2–2 with the highest Score of 74.5% and 53.9%, respectively.
Original languageEnglish
Title of host publicationThe IEEE 25th International Workshop on Multimedia Signal Processing
Number of pages6
ISBN (Electronic)979-8-3503-3893-5
DOIs
Publication statusPublished - Jul 2023
Event2023 IEEE 25th International Workshop on Multimedia Signal Processing (MMSP) - Poitiers, France, Poitiers, France
Duration: 27 Sept 202329 Sept 2023

Conference

Conference2023 IEEE 25th International Workshop on Multimedia Signal Processing (MMSP)
Country/TerritoryFrance
CityPoitiers
Period27/09/2329/09/23

Research Field

  • Former Research Field - Data Science

Fingerprint

Dive into the research topics of 'An Inception-Residual-based Architecture with Multi-objective Loss for Detecting Respiratory Anomalies'. Together they form a unique fingerprint.

Cite this