Knee Joint Health Care Monitoring System Using AI - Classification Approach

Knee osteoarthritis is a significant global health concern, 7% of the global population is affected with osteoarthritis problem. Early diagnosis and regular monitoring of knee joint healthcare is crucial to avoid surgeries. Vibroarthrography (VAG) signal records the vibration or acoustic signal of human knee joint while the movement of leg. VAG signal denoising is done by using Variational Mode Decomposition (VMD). This work investigates the effectiveness of VMD in separating a signal into its intrinsic components, followed by the identification and removal of noise-dominated modes. Signal characteristics have been identified using time-domain features, scalograms and spectrograms from the decomposed modes. Machine learning classifiers are then utilized to categorize these signals. Our results indicate that the ensemble voting classifier and AdaBoost achieved an accuracy of 93% in distinguishing between normal and abnormal VAG signals for knee joint healthcare.