Abstract
Lung sound is a biological signal with the information of respiratory system health. Health lung sound can be differentiated from other pathological sounds by auscultation. This difference can be objectively analyzed by a number of digital signal processing techniques. One method in analyzing the lung sound is signal complexity analysis using fractal dimension. To improve the accuracy of lung sound classification, Fractal Dimension (FD) is calculated in the multiscale signal using the coarse-grained procedure. The combination of FD and multiscale process generates the more comprehensive information of lung sound. This study used seven types of FD and three types of the classifier. The result showed that Petrosian C in signal with the scale of 1-5 and SVM with fine Gaussian kernel had the highest accuracy of 99% for five classes of lung sound data. The proposed method can be used as an alternative method for computerized lung sound analysis to assist the doctors in the early diagnosis of lung disease.
Highlights
Auscultation is an important procedure to establish the diagnosis of various lung disorders (Sarkar et al, 2015)
By implementing SVM, K-NN and Multilayer Perceptron (MLP) as a classifier, we found that Petrosian C Fractal Dimension (FD) and MLP produced the highest accuracy of 5-class lung sound classification
This paper described the implementation of FD as a feature for lung sound classification
Summary
Auscultation is an important procedure to establish the diagnosis of various lung disorders (Sarkar et al, 2015). The sound of airflow through respiratory tract is listened by a doctor using a stethoscope to analyze sound that is different from normal. This process is highly dependent upon the doctor’s skill as it requires more practices for years (Abbas and Fahim, 2010). Gnitecki and Mousavi (2005) tested it using Katz Fractal Dimension (KFD), Sevcik Fractal Dimension (SVD) and Variance Fractal Dimension (VFD). They stated that lung sound has a part of fractal properties. The test of lung sound fractality using the degree of similarity (H) was conducted in by
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
