Inhale Calm: Convolutional Neural Network Model for Accurate Detection of Respiratory Anomalies in Pulmonary Disease Diagnosis

DOI

10.2991/978-94-6463-858-5_233How to use a DOI?

Keywords

Inhale Calm; Deep learning; Convolutional Neural Networks (CNNs); Mel-Frequency Cepstral Coefficients (MFCC)

Abstract

Respiratory infections are the third most common cause of mortality worldwide, and successful treatment and prevention of their spread depend on early identification. This application proposes a unique, lightweight inception network intended to identify a wide spectrum of respiratory disorders by monitoring lung sound data. Preprocessing the sound data, extracting mel spectrograms and transforming them into three-channel pictures, and then utilizing the lightweight inception network to categorize these spectrogram images into different pathological categories are the three main steps in the suggested system’s operation. To enable respiratory sound analysis on any device, we developed an algorithm that is both afford- able and easy to use. Our exceptional classification accuracy values of 96.6% for seven-class classification, 99.6% for six-class classification, and 94.0% for distinguishing between healthy individuals and those with asthma were achieved with this system. As far as we are aware, this is the first study to use lung sounds to categorize seven different respiratory disease types. For six-class and binary classification problems, our method also outperforms all previously published work. Using deep learning techniques, this frame- work provides a reliable evaluation mechanism with high classification accuracy. By concentrating solely on lung sounds, our research is leading the way in the diagnosis of various respiratory conditions. The suggested system can be used in clinical settings in real time, opening the door for automated screening of respiratory health using analysis of lung sounds.

Copyright

© 2025 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  - A. Durga Praveen Kumar
AU  - V. Sindhu
AU  - P. Yogitha
AU  - V. Sahith
AU  - A. Kousik
PY  - 2025
DA  - 2025/11/04
TI  - Inhale Calm: Convolutional Neural Network Model for Accurate Detection of Respiratory Anomalies in Pulmonary Disease Diagnosis
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 2790
EP  - 2796
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_233
DO  - 10.2991/978-94-6463-858-5_233
ID  - Kumar2025
ER  -