Classification of knee-joint vibroarthrographic signals using time-domain and time-frequency domain features and least-squares support vector machine

Yunfeng Wu, Sridhar Krishnan
2009 2009 16th International Conference on Digital Signal Processing  
Analysis of knee-joint vibration sounds, also known as vibroarthrographic (VAG) signals, could lead to a noninvasive clinical tool for early detection of knee-joint pathology. In this paper, we employed the wavelet matching pursuit (MP) decomposition and signal variability for time-frequency domain and time-domain analysis of VAG signals. The number of wavelet MP atoms and the number of significant turns detected with the fixed threshold from signal variability analysis were extracted as
more » ... extracted as prominent features for the classification over the data set of 89 VAG signals. Compared with the Fisher linear discriminant analysis, the nonlinear least-squares support vector machine (LS-SVM) is able to achieve higher overall accuracy of 73.03%, and the area of 0.7307 under the receiver operating characteristic curve.
doi:10.1109/icdsp.2009.5201156 fatcat:7bl3d5532zbtvfykqyy4ojrhde