Pulmonary Sound Analysis with Deep Learning for Efficient Respiratory Disease Categorization

DOI

10.2991/978-94-6463-252-1_9How to use a DOI?

Keywords

Respiratory sounds; Pulmonary sounds; Convolutional neural network (CNN); Mel spectrogram

Abstract

Lung Disease treatment is crucial in the medical industry since it is the third most prevalent cause of mortality worldwide. Recently, assistive solutions have greatly benefited from the use of technologies like deep learning and machine learning. This involves the use of a variety of technologies, including Magnetic resonance imaging (MRI), isotopes, X-rays, and CT scans. Unfortunately, using auscultation to identify these disorders requires qualified doctors, and this approach is insufficiently objective. So, it is essential to have a mechanism for accurately recognizing. The proposed method successfully converts recorded audio signals into spectrogram images utilizing the time-frequency approach and deep convolutional neural network (CNN) with prior training which achieved a 94% validation accuracy. The primary objective of this project is to identify healthy lungs and respiratory conditions using ICBHI 2017 data set. As this project considered all seven classes of respiratory sounds at once, the findings based on this framework are superior to those obtained using earlier methods.

Copyright

© 2023 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  - V. Ricky Deeven
AU  - V. Naveen Kumar
AU  - Y. Padma Sai
AU  - N. Akshitha
AU  - M. Kaivalya
PY  - 2023
DA  - 2023/11/09
TI  - Pulmonary Sound Analysis with Deep Learning for Efficient Respiratory Disease Categorization
BT  - Proceedings of the Second International Conference on Emerging Trends in Engineering (ICETE 2023)
PB  - Atlantis Press
SP  - 68
EP  - 78
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-252-1_9
DO  - 10.2991/978-94-6463-252-1_9
ID  - Deeven2023
ER  -