Comparison of AR-based algorithms for respiratory sounds classification

✍ Scribed by Bülent Sankur; Yasemin P. Kahya; E. Çağatay Güler; Tanju Engin

• Book ID: 103053753
• Publisher: Elsevier Science
• Year: 1994
• Tongue: English
• Weight: 899 KB
• Volume: 24
• Category: Article
• ISSN: 0010-4825
• DOI: 10.1016/0010-4825(94)90038-8

✦ Synopsis

Respiratory sounds of pathological and healthy subjects were analyzed via autoregressive (AR) models with a view to construct a diagnostic aid based on auscultation. Using the AR vectors, two reference libraries, pathological and healthy, were built. Two classifiers, k-nearest neighbour (k-NN) classifier and a quadratic classifier, were designed and compared. Performances of the classifiers were tested for different model orders. The best classification results were obtained for model order 6.