Early Detection and Quantification of Osteoarthritis Severity in Knee Using Support Vector Machine with Improved Accuracy Compared to Convolutional Neural Network

This study will make use of a classifier that has improved accuracy for support vector machines in order to build a strategy for the early detection and quantification of osteoarthritis. In terms of both the Materials and Methods: A total of 350 samples were taken, and those were split up between the two groups in a manner that was completely random. Each participant received a total of 175 samples during the course of the study. When it comes to Group 1, the SVM algorithm is in charge, but the CNN algorithm is in charge of Group 2. Results: The significance value of 0.197 indicates that the null hypothesis is correct (p>0.01); this was determined by using an independent sample T test with a confidence interval of 95%, an enrolment ratio defined as 1, g power of 80%, and a threshold value of 0.5G; the test also includes a threshold value of 0.5G. The significance value of 0.197 indicates that the null hypothesis is correct (p>0.01). The fact that the significance value is greater than 0.01 indicates that the hypothesis is correct (p > 0.01); The accuracy of the innovative SVM was determined to be 87%, which was higher than the accuracy of the CNN algorithm, which was determined to be 83%. The significance value also indicates that the hypothesis is correct.