Comparison between the different artificial neural network (ANN)‎ accuracy in diagnosis of asthma

Abstract EN

Asthma is a chronic disease that is caused by inflammation of airways.

diagnosis, predication and classification of asthmatic are one of the major attractive areas of research for decades by using different and recent techniques, however the main problem of asthma is misdiagnosis.

this paper simplifies and compare between different artificial neural network techniques used to solve this problem by using different algorithms to getting a high level of accuracy in diagnosis, prediction, and classification of asthma like: (data mining algorithms, machine learning algorithms, deep machine learning algorithms), depending and passing through three stages: data acquisition, feature extracting, data classification.

according to the comparison of different techniques the high accuracy achieved by ANN was (98.85%), and the low accuracy of it was (80%), despite of the accuracy achieved by support vector machine (SVM) was (86%) when used MEL frequency cepstral coefficient MFCC for feature extraction, while the accuracy was (99.34%) when used relief for extracting feature.

based in our comparison we recommend that if the researchers used the same techniques they should to return to previous studies it to get high accuracy.