Abstract
Classification of respiratory sounds between normal and abnormal is very crucial for screening and diagnosis purposes. Lung associated diseases can be detected through this technique. With the advancement of computerized auscultation technology, the adventitious sounds such as crackles can be detected and therefore diagnostic test can be performed earlier. In this paper, Linear Predictive Cepstral Coefficient (LPCC) and Mel-frequency Cepstral Coefficient (MFCC) are used to extract features from normal and crackles respiratory sounds. By using statistical computation such as mean and standard deviation (SD) of cepstral based coefficients it can differentiate between crackles and normal sounds. The statistical computations of the cepstral coefficient of LPCC and MFCC show that the mean LPCC except for the third coefficient and first three statistical coefficient values of MFCC’s SD provide distinctive feature between normal and crackles respiratory sounds. Hence, LPCCs and MFCCs can be used as feature extraction method of respiratory sounds to classify between normal and crackles as screening and diagnostic tool.
Highlights
One of the methods used by physician to diagnose respiratory diseases is by chest auscultation using a stethoscope [1]
Mel-frequency Cepstral Coefficient (MFCC) and Linear Predictive Cepstral Coefficient (LPCC) are used to extract the features of the respiratory sounds
The t-test is calculated from the value of mean and standard deviation (SD) of the LPCCs to define the hypotheses with hypotheses that the statistical value, mean and SD of LPCCs can distinguish between normal and crackles sounds
Summary
One of the methods used by physician to diagnose respiratory diseases is by chest auscultation using a stethoscope [1]. Respiratory sounds can be classified as normal and abnormal or adventitious. There are many types of adventitious sounds, such as crackles, pleural rubs, stridor, and wheezes (ronchi) where the abnormality of the pulmonary system can be the cause of these sounds [2]. Crackles can be detected in lung or heart auscultation of COPD, pneumonia, heart failure and asbestosis patients. Explosive opening of the small airways caused lung and heart to produce this crackle sounds ranging from 100 to 2000 Hz or even higher [5]. The LPCC and MFCC will be used to extract the features of crackles and normal respiratory sound and statistical computation will be performed to evaluate the features extracted
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have