Enhanced time-frequency analysis of VAG signals by segmentation and denoising algorithm

An enhanced time-frequency analysis of vibroarthrographic (VAG) signals is devised using segmentation by the dynamic time warping and denoising algorithm by the singular value decomposition, and the normal and abnormal VAG signals are classified by a back-propagation neural network. A total of 1408 VAG segments (normal 1031, abnormal 377) were used for evaluating the performance of the devised method and, consequently, the average accuracy was 92.0 ±1.6 (ranging from 89.4 to 95.4). This method could be used as a complementary tool for the non-invasive diagnosis of joint disorders.