Enhancing Accuracy in the Detection of Chondrosarcoma Using Mobile Net Algorithm and Comparison with Support Vector Machine

A new chondrosarcoma detection system was developed by comparing the mobilenet algorithm with the use of deep learning's SVM. Accuracy was the criterion used to evaluate the system. Methods and Supplies: In this method, forty samples will be used to compare the two groups. The mobile net approach and support vector machine (SVM) are two of these groups that use twenty samples apiece. The python code was run once the dataset was imported into the Google Colab application. To calculate the sample size, we plug the prior research's findings into an online tool for statistical analysis, a pre-test power of 80%, and an alpha value of 0.05. It follows that to the data from the simulations undertaken in this study, the mobile net approach obtains an accuracy of 96.065% and the SVM achieves an accuracy of 81.199%. Variance: 0.002937, Precision: t = 48.260, and Average Distinction: 0.1141750. has been achieved. Statistical testing has shown that mobile net chondrosarcoma detection techniques are not as accurate as SVM based systems. Results show that, on the dataset used, the mobilenet method outperforms the support vector machine in chondrosarcoma detection.