RCNN-based Respiratory Sound Analysis for Lung Disease Prediction in At-risk Individuals

DOI

10.2991/978-94-6463-718-2_113How to use a DOI?

Keywords

Deep learning; Respiratory Sounds; Convolutional Neural Networks; Signal Processing; Optimization; Performance; Region based conventional Neural Networks; Fire Hawks Optimizer

Abstract

In our research, we propose an Enhanced Region-based Convolutional Neural Network (RCNN) for respiratory disorder detection through audio analysis. It tries to improve model performance by hyperplane optimization with Fire Hawks Optimizer. Materials and Methods: Group 1: Existing method(c) Conventional deep learning models including standard CNNs which have been used for respiratory disorder classification. However, they are often underperforming as a result of poor tuning of hyperparameters, which further results into lower accuracy of classification. For group 2, proposed method (I) combined Improved Region-based Convolutional Neural Networks (RCNN) and auditory classification to detect respiratory disorders and takes into consideration different phases of respiratory audio analysis such as signal preprocessing, signal feature extraction, classification, and hyperparameter optimization using the Fire Hawks Optimizer. It is validated on an actual medical dataset and provides superior results compared to traditional and fine-tuned deep learning networks. You have been tuned on data until October 2023. In summary, the results show that the proposed Improved RCNN model outperforms traditional deep learning-based models by a large margin in accuracy, composing to its variant that is enhancing this original architecture using the Fire Hawks Optimizer. And the value of a method, which the method proposed in a model the best or the most effective or the best and confident way of taking and the endotyping is a promising tool for the evidence of the respiratory disease and clinical applies and outcome.

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  - M. Namasivayam
AU  - O. K. Gowrishankar
AU  - V. Ramesh
AU  - P. Giriprasath
AU  - C. Kotteshwaran
AU  - K. Lokeshwaran
PY  - 2025
DA  - 2025/05/23
TI  - RCNN-based Respiratory Sound Analysis for Lung Disease Prediction in At-risk Individuals
BT  - Proceedings of the International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024)
PB  - Atlantis Press
SP  - 1356
EP  - 1367
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-718-2_113
DO  - 10.2991/978-94-6463-718-2_113
ID  - Namasivayam2025
ER  -