Analysis and Comparison of Kidney Stone Detection using Gaussian Maximum Likelihood Classifier and Bayesian Classifier with Improved Accuracy
Aim: The aim of this study is to figure out how to predict and detect kidney stones using Gaussian maximum likelihood classifier and Bayesian classifier and also to compare the results of classification accuracy between Gaussian maximum Likelihood classifier and Bayesian classifier. Materials and Methods: This study data was gathered via the kaggle website. Samples were considered as (N=10) for gaussian maximum likelihood classifier and (N=10) for bayesian classifier according to clinicalc.com, by keeping alpha error-threshold value 0.01, enrollment ratio as 0.1, 95% confidence interval, G power as 80% the total sample size was calculated. The accuracy was calculated using MATLAB with a standard data set. Results: Comparison of accuracy is done by independent sample t test in SPSS software. There is a statistical significant difference between Gaussian maximum Likelihood classifier and Bayesian classifier.Comparison results show that innovative Gaussian maximum Likelihood classifier give better classification with an accuracy of (81.34%) than bayesian classifiers (71.1314%). The gaussian maximum likelihood classifier with p=0.122, p>0.05 hence there is a statistically insignificant difference between gaussian maximum likelihood classifiers and bayesian classifiers. Gaussian classifiers showed better results in comparison to Bayesian classifiers. Conclusion: Gaussian maximum likelihood classifiers showed better accuracy than Bayesian classifiers on kidney stone detection in a faster way.
Kishore U., Ramadevi R.. Analysis and Comparison of Kidney Stone Detection using Gaussian Maximum Likelihood Classifier and Bayesian Classifier with Improved Accuracy. Cardiometry; Issue 25; December 2022; p.799-805; DOI: 10.18137/cardiometry.2022.25.799805; Available from: https://www.cardiometry.net/issues/no25-december-2022/gaussian-maximum-likelihood