EXTRACTION AND SCREENING OF KNEE JOINT VIBROARTHROGRAPHIC SIGNALS USING THE EMPIRICAL MODE DECOMPOSITION METHOD

摘要

This study presents a method for the extraction and screening of knee joint vibroarthrographic (VAG) signals using an Empirical Mode Decomposition (EMD) technique. The proposed analysis method is based on the Hilbert Huang transform, which is a powerful tool for the analysis of non-stationary and non-linear time series and basically consists of an empirical mode decomposition method and Hilbert spectral analysis. A technique for time-frequency analysis of the extracted vibration signals is proposed with the goal of diagnosing knee joint diseases. The performance of the EMD technique is verified experimentally. The screening accuracy of the statistical pattern classification is 85.3% in Vibroarthrographic signals. The results confirm that the proposed approach is indeed feasible for the noninvasive diagnosis and monitoring of articular cartilage pathology.