This study presents a novel method for the extraction and screening of knee joint vibroarthrographic (VAC) signals using an independent component analysis (ICA) technique. A time-frequency analysis technique of the extracted vibration signals is proposed to carry out knee joint diagnosis. The performance of the ICA technique is verified experimentally. Statistical pattern classification screening accuracy is 82.5% in VAC. The results confirm that ICA is a feasible approach for the noninvasive diagnosis and monitoring of articular cartilage pathology.
|Number of pages||18|
|Journal||International Journal of Innovative Computing, Information and Control|
|State||Published - 2012|
- Independent component analysis