PEMANFAATAN STFT DAN CNN DALAM PENGOLAHAN DATA SUARA UNTUK MENGKLASIFIKASIKAN SUARA BATUK

Authors

  • Indri Nurfiani Teknik Informatika UIN SGD
  • Jumadi Jumadi Universitas Islam Negeri Sunan Gunung Djati
  • Muhammad Deden Firdaus Universitas Islam Negeri Sunan Gunung Djati

DOI:

https://doi.org/10.36341/rabit.v9i2.4729

Keywords:

Cough sound, STFT, CNN, Naive Bayes, respiratory diseases

Abstract

This research aims to develop an automatic cough sound evaluation system to improve the accuracy of respiratory disease diagnosis. In this study, the Short-Time Fourier Transform (STFT) and Convolutional Neural Network (CNN) methods were used to classify cough sounds into dry and wet coughs. The Naïve Bayes model was then used to identify respiratory diseases based on the cough classification results. Testing was conducted using the available cough sound dataset, resulting in a cough classification accuracy of 82% and a respiratory disease identification accuracy using Naïve Bayes of 71.43%. The evaluation results indicate that the developed system can accurately classify cough types and identify diseases. This system has the potential to enhance the prevention and management of respiratory diseases in resource-limited areas and can be a significant tool in medical practice for faster and more accurate diagnoses. Furthermore, this research opens opportunities for further development in disease detection and diagnosis technology through sound analysis, providing wide-ranging benefits for society and the healthcare sector.

Downloads

Download data is not yet available.

Published

2024-07-08

How to Cite

[1]
I. Nurfiani, J. Jumadi, and M. Deden Firdaus, “PEMANFAATAN STFT DAN CNN DALAM PENGOLAHAN DATA SUARA UNTUK MENGKLASIFIKASIKAN SUARA BATUK”, rabit, vol. 9, no. 2, pp. 184–190, Jul. 2024.

Issue

Section

Articles