Feature extraction for the differentiation of dry and wet cough sounds

Cough is one of the most common symptoms in all respiratory diseases. It is important to provide the healthcare professionals with useful clinical information such as frequency, severity and nature of cough to have a better diagnosis and hence better treatment. The main objective of this thesis is to analyze cough sounds and extract features that can differentiate dry and wet cough sounds. This thesis proposes two features to achieve this goal. The first feature is the number of peaks of the energy envelope of the cough signal. The second feature is the power ratio of two frequency bands of the second phase of the cough signal. A set of nine highly dry and eight highly wet cough recordings were used in this thesis. Using these two features, a clear separation was observed among the dry and wet cough recordings. Furthermore, a Graphical User Interface (GUI) was designed in this thesis as a tool to analyze the cough signals in both time and frequency domain.