Scheduled System Maintenance:
Some services will be unavailable Sunday, March 29th through Monday, March 30th. We apologize for the inconvenience.
By Topic

Modeling and classification of knee-joint vibroarthrographic signals using probability density functions estimated with Parzen windows

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

The purchase and pricing options are temporarily unavailable. Please try again later.
2 Author(s)
Rangayyan, R.M. ; Department of Electrical and Computer Engineering, Schulich School of Engineering, University of Calgary, AB, Canada ; Yunfeng Wu

Diagnostic information related to the articular cartilage surfaces of knee-joints may be derived from vibro-arthrographic (VAG) signals. Although several studies have proposed many different types of parameters for the analysis and classification of VAG signals, no statistical modeling methods have been explored to represent the fundamental distinctions between normal and abnormal VAG signals. In the present work, we derive models of probability density functions (PDFs), using the Parzen-window approach, to represent the basic statistical characteristics of normal and abnormal VAG signals. The Kullback-Leibler distance (KLD) is then computed between the PDF of the signal to be classified and the PDF models for normal and abnormal VAG signals. A classification accuracy of 73.03% was obtained with a database of 89 VAG signals. The screening efficiency was derived to be 0.6724, in terms of the area under the receiver operating characteristics curve.

Published in:

Engineering in Medicine and Biology Society, 2008. EMBS 2008. 30th Annual International Conference of the IEEE

Date of Conference:

20-25 Aug. 2008