Abstract: Regardless of age, a significant number of people die from persistent lung diseases every year. A crucial demonstration tool for accurately identifying pulmonary diseases is lung sound analysis. In the past, lung diseases were diagnosed manually, but this method was unreliable for a variety of reasons, including low perceptibility and contrast in the eyes of different clinicians for different sounds. Patients suffering from many types of lung illnesses can now receive better treatment since contemporary research yields outcomes with much higher precision. Asthma, bronchitis, emphysema, tuberculosis, and pneumonia are among these problems. Wheezing, exhaustion, rhonchi, and persistent hacking are a few of the negative symptoms. In this project, we are using respiratory sound datasets to predict a variety of diseases, including asthma, pneumonia, bronchiectasis, and others. In order to complete this task, we first took the respiratory sound dataset and the disease conclusion dataset, separated out the components from all of the sound datasets, and then created a convolution brain organisation (CNN) calculation model. We can integrate any fresh test information to the model after it has been prepared in order to foresee infection from it.
Keywords: Admin, Convolution neural network, Cough Sound, Respiratory Disorder, Feature Extraction.
|
DOI:
10.17148/IJARCCE.2022.11765
