Accuracy Comparison of Novel Deep Belief Network Compared over Random Forest in Predicting Uterus Cancer
G. Siva Sai Kumar Reddy, P. Subramanian · 2024
In order to provide an exact comparison between the Novel Deep Belief Networks and the Random Forest based on their ability to detect uterine cancer. Among the groups that are participating in this study, two of them are the Random Forest Algorithm and the Novel Deep Belief Network. Each of these groups seems to have a sample size. A comparison was made between (Group 1) with 10 samples and J48 Decision trees, which resulted in better accuracy. (Group 2) also employed 10 samples at the same time. The study on parameters also includes the following. With a G-Power of 80% and a confidence interval of 95%, the significant findings of the dataset were predicted with the use of a statistical tool designed for the social sciences. Various approaches from the fields of machine learning and Random Forest are used.With an accuracy of 86.44%, the Novel Deep Belief Network is much more accurate than the Random Forest, which has an accuracy of 82.18%. This is a significant improvement over the accuracy of the model that was comparison. In the statistical packages for social sciences statistical analysis, it is shown that there exists a statistically significant difference between Random Forest and Novel Deep Belief Network. The value of p = 0.000 (p < 0.05) indicates that this difference is statistically significant. This demonstrates that there is a difference between two algorithms that is capable of being considered statistically significant. According to the findings of this study, the Novel Deep Belief Network algorithm has a significance of 86.44% on uterine cancer prediction, which is much higher than the random forest method, which has a significance of 82.18%.