Klasifikasi Suara Paru Normal dan Abnormal Menggunakan Discrete Wavelet Transform dan Jaringan Saraf Tiruan yang Dioptimasi dengan Algoritma Genetika
DOI:
https://doi.org/10.35143/elementer.v7i1.4388Abstract
The human body consists of several vital organs that have an important role in humans life. One of the vital organs of humans is the lungs, which is responsible for the respiratory system to meet the body's oxygen needs. Respiratory system disorders can cause death. One method doctors use to diagnose lung disorders is by listening to breathing sounds using a stethoscope. However, the use of a stethoscope can still be misdiagnosed due to several factors, such as the doctor's ability, doctor's experience, doctor's sensitivity, and similar lung sound patterns. In this study, lung sounds classification using the Discrete Wavelet Transform (DWT) method and Artificial Neural Networks were optimized with Genetic Algorithms. Lung sounds are considered as sounds from the respiratory system, then normalized, and the DWT coefficient is calculated. The lung sound signal characteristics are obtained by calculating the entropy at the DWT coefficient. Furthermore, the classification is solved using Artificial Neural Networks and optimized with Genetic Algorithms. Based on this solution, the classification of lung sounds can be completed with an accuracy of up to 63.71%Downloads
Published
Issue
Section
License
Copyright (c) 2021 Achmad Rizal
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
a. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
b. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
c. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
This work is licensed under a Creative Commons Attribution 4.0 International License.
