A comparative study of the svm and k-nn machine learning algorithms for the diagnosis of respiratory pathologies using pulmonary acoustic signals

• Published in: BMC bioinformatics Vol. 15; no. 1; p. 223
• Main Authors: Palaniappan, Rajkumar, Sundaraj, Kenneth, Sundaraj, Sebastian
• Format: Journal Article
• Language: English
• Published: London BioMed Central 27.06.2014; BioMed Central Ltd; Springer Nature B.V
• Subjects: Acoustic properties; Acoustics; Algorithms; Analysis of Variance; Bioinformatics; Biomedical and Life Sciences; Classifiers; Comparative analysis; Comparative studies; Computational Biology/Bioinformatics; Computer Appl. in Life Sciences; Diagnosis; Diagnosis, Differential; Humans; Knowledge-based analysis; Life Sciences; Lung - pathology; Microarrays; Neural networks; Pathology; Research Article; Respiratory Tract Diseases - diagnosis; Respiratory Tract Diseases - pathology; Signal processing; Signal Processing, Computer-Assisted; Sound; Statistical analysis; Studies; Support Vector Machine; Support vector machines; Variance analysis; Support vector machine; Confusion matrix; K-nearest neighbour; MFCC; Respiratory sounds; One way ANOVA
• ISSN: 1471-2105; 1471-2105
• DOI: 10.1186/1471-2105-15-223

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