Treffer: Evaluating the predictive accuracy of alexnet and X-gradient boosting for detecting polycystic ovary syndrome (PCOD) in women.

The primary goal of the study project is to predict PCOD (Polycystic Ovarian Disease) problem in women from the online PCOD DB dataset using various Deep Learning concepts like X-Gradient Boosting and Novel AlexNet Algorithm to find accuracy. The developed models are used to predict PCOD problem using AlexNet and X-Gradient Boosting. The PCOD dataset instance is applied for an investigational stage, and the suggested model is implemented with the help of python programming software. By using the GPower 3.1 software (g power setting parameters alpha: = 0.05 and G power = 0.8) and CI 95%. Group 1 is taken as AlexNet and group 2 as Novel X-Gradient Boosting was calculated as a total of 15 sample sizes. The outcome of the recommended PCOD disease prediction system in the healthcare monitoring system is assessed. The recommended Novel AlexNet classifier accuracy level is confirmed with 93.0427% and the compared algorithm as 90.1667%. AlexNet and Novel X-Gradient Boosting processing time is also calculated. Statistical significance value difference between Alexnet and X-Gradient algorithm was found to be Independent Samples T-test p=0.000 (p < 0.05) it is significantly different. This recommended research process result says that it is finalized that the developed AlexNet model makes better results in PCOD prediction in online dataset than the X-Gradient Boosting classifier. The recommended AlexNet accuracy value is 93.0427% than the accuracy value of the Novel X-Gradient Boosting Algorithm is 90.1667 %. [ABSTRACT FROM AUTHOR]