Respiratory Disease Detection Using Lung Sound with CNN

DOI

10.2991/978-94-6463-471-6_84How to use a DOI?

Keywords

Respiratory disease classification; convolutional neural network; deep learning; MFCC; mel-spectrogram features

Abstract

Every year, respiratory disorders affect millions of people worldwide and pose a serious threat to public health. For treatment and therapy to be effec- tive, a timely and accurate diagnosis is essential. In this work, we present a unique method that uses examination of lung sounds to improve the classifica- tion of pulmonary ailments. Our framework provides a comprehensive solution for autonomous respiratory audio analysis by utilizing cutting-edge deep learn- ing techniques, namely a mixed convolutional neural network model that incor- porates MFCC, or Mel-Frequency Cepstral Coefficients, chroma characteris- ticsand Mel-Spectrogram features. Our architecture focuses on speed optimiza- tion, ensuring rapid clinical application without sacrificing classification accu- racy. It does this by using a lightweight combination of neural network models. By conducting extensive testing on several datasets, such as the chest wall lung sound database and the ICBHI 2017 competition database, our approach shows mastery in categorizing respiratory illnesses into several groups. Extensive as- sessment indicators, including recall, accuracy, precision, and F1 score, offer deep insights into our models’ effectiveness. These results highlight how deep learning approaches may transform pulmonary diagnostics, giving medical per- sonnel the essential tools they need to intervene quickly and improve patient outcomes in the process. With 95% accuracy, this model predicts respiratory illness.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Sk. Nageena Jani
AU  - J. Vidya
AU  - M. Sneha
AU  - K. Jaya Shankar
AU  - N. Narendra Babu
AU  - K. Sathish
PY  - 2024
DA  - 2024/07/30
TI  - Respiratory Disease Detection Using Lung Sound with CNN
BT  - Proceedings of the International Conference on Computational Innovations and Emerging Trends (ICCIET- 2024)
PB  - Atlantis Press
SP  - 884
EP  - 896
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-471-6_84
DO  - 10.2991/978-94-6463-471-6_84
ID  - Jani2024
ER  -