Concerning the Potential Effectiveness of Spectral Correlation Methods of Classification of Breathing Sound

I. V. Vovk, A. Kalyuzhny

1999

Closed access Metadata (CSL-JSON)
DOI 10.1615/interjfluidmechres.v26.i5-6.170
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

An optimal algorithm for classification of respiratory sound on the basis of spectral-correlation criteria is analyzed and parameters of its effectiveness are determined. These parameters are analyzed numerically of for an idealized model of the human respiratory tract. The comparative diagnostic value of a number of parameters of a model, including conditions of excitation of respiratory sound, and the acoustic parameters of the conducting medium is investigated. The advantages of spectral-correlation methods of classification over purely spectral methods are demonstrated. The stability of qualitative criteria of the classification system to inaccuracies in specifying the parameters of the respiratory tract and errors in determining the location of sound recording points is investigated.