Performance analysis of random forest over multi-class SVM comparison in prediction of breast cancer in mammogram images Available to Purchase

The fundamental objective of this study is to determine the distinctions and parallels that exist between multi- class support vector machines (MSVM) and Rf (random forest) for the purpose of tumor analysis. This is done with the intention of achieving greater precision in image processing. Materials and methods: Through the utilization of a threshold alpha of 0.05%, a g power of 80%, a confidence interval of 95%, and a sample size of 16 for the Multi-class support vector machine and 16 for the Random forest, we were able to collect a wide range of breast tumor images. We retrieved and segmented images, determined the total sample size by using base paper, and extracted textural attributes by using image processing tools. All of these actions were carried out in accordance with the suggestions that were supplied by clinical.com. When analyzing the use of artificial intelligence (AI) for tumor detection and analysis in both groups, the accuracy and sensitivity of the parameters were taken into consideration throughout the evaluation process. This was done in order to conduct an accurate and thorough evaluation. Results: The findings of the independent sample T-test reveal that there is a statistically significant difference of 0.01 (p<0.05) between the two approaches when comparing MSVM with RF for the successful detection of breast cancers. This is supported by the fact that the difference is statistically significant. An example of this would be the fact that the accuracy value in RF is 9.228 percent, whereas in MSVM it is 95.544 percent. Conclusion: Random forest (RF) and multiclass support vector machine (SVM) are two examples of machine learning techniques that are commonly utilized because of their effectiveness in solving classification challenges. Comparatively, RF is an ensemble learning technique that synthesises predictions from a large number of decision trees, whereas SVM is a discriminative classifier that aims to locate the hyperplane that separates the various classes to the greatest extent possible.