Automated Diagnoses of Respiratory Health Problems Using Breathing Sounds

Abstract

Respiratory conditions, such as pneumonia, cold, flu, and bronchitis, are still the leading causes of child mortality in the world. One solution for alleviating this problem is to develop affordable respiratory assessment methods using computerized respiratory-sound analysis. This chapter illustrates how computers can be used to automatically diagnose various respiratory health problems. We use an enhanced perceptual and cepstral feature set (PerCepD) for analysing breathing sounds (BSs) for identification and classification of respiratory health problems. Classification models are developed using support vector machine (SVM) and artificial neural network (ANN) to achieve automatic detection from BS data. The high detection accuracy results validate the performance of the proposed feature sets and classification models. The experimental results also demonstrate that the high accuracy of the pathological BS data can provide reliable diagnostic suggestions for breath disorders, such as flu, pneumonia and bronchitis.