Open AccessA Novel Health Model Using NuSVC to Predict Severity of Asthma on The basis Of Cough Audio Signal
Author(s) -
Jyothi Mohan,
Vutukuru Murali Mohan,
Madhusudhanan Sampath
Publication year - 2022
Publication title -
international journal of next-generation computing
Language(s) - English
Resource type - Journals
eISSN - 2229-4678
pISSN - 0976-5034
DOI - 10.47164/ijngc.v13i1.294
Subject(s) - asthma , audio signal , medicine , classifier (uml) , feature selection , support vector machine , speech recognition , training set , artificial intelligence , computer science , machine learning , audiology , speech coding
Cough is the the major symptoms of Asthma patients. The purpose of this research is reliable assessment of cough events using sound processing tools to classify and predict severity of Asthma in patients.The system is trained to be self-learning and thus intelligent. In this research paper, patameters of the cough audio signal are analyzed. Finally, Nu Support Vector Classifier (NuSVC), is chosen as the predictor, due to its superb classification and feature selection ability. Finally, end result of severity of Asthma patients is predicted. However for the research purpose, the cough sound recording of Asthma training data set is created. The trained model is used for further classification and prediction of health severity. The model classified and predicted with 94% accuracy compared to previous work.