COMPARISON OF AR-BASED ALGORITHMS FOR RESPIRATORY SOUNDS CLASSIFICATION


SANKUR B., KAHYA Y., GULER E., ENGIN T.

COMPUTERS IN BIOLOGY AND MEDICINE, vol.24, no.1, pp.67-76, 1994 (Journal Indexed in SCI) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 24 Issue: 1
  • Publication Date: 1994
  • Doi Number: 10.1016/0010-4825(94)90038-8
  • Title of Journal : COMPUTERS IN BIOLOGY AND MEDICINE
  • Page Numbers: pp.67-76

Abstract

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.