Background: Pulmonary acoustic parameters extracted from recorded respiratory sounds provide valuable information\nfor the detection of respiratory pathologies. The automated analysis of pulmonary acoustic signals can serve as a\ndifferential diagnosis tool for medical professionals, a learning tool for medical students, and a self-management tool for\npatients. In this context, we intend to evaluate and compare the performance of the support vector machine (SVM) and\nK-nearest neighbour (K-nn) classifiers in diagnosis respiratory pathologies using respiratory sounds from R.A.L.E database.\nResults: The pulmonary acoustic signals used in this study were obtained from the R.A.L.E lung sound database. The\npulmonary acoustic signals were manually categorised into three different groups, namely normal, airway obstruction\npathology, and parenchymal pathology. The mel-frequency cepstral coefficient (MFCC) features were extracted from the\npre-processed pulmonary acoustic signals. The MFCC features were analysed by one-way ANOVA and then fed separately\ninto the SVM and K-nn classifiers. The performances of the classifiers were analysed using the confusion matrix technique.\nThe statistical analysis of the MFCC features using one-way ANOVA showed that the extracted MFCC features are\nsignificantly different (p < 0.001). The classification accuracies of the SVM and K-nn classifiers were found to be 92.19%\nand 98.26%, respectively.\nConclusion: Although the data used to train and test the classifiers are limited, the classification accuracies found are\nsatisfactory. The K-nn classifier was better than the SVM classifier for the discrimination of pulmonary acoustic signals\nfrom pathological and normal subjects obtained from the RALE database.
Loading....