Prediction of Chronic kidney cancer using RBF support vector machine compared with Random forest for better accuracy

This research is to predict chronic kidney cancer using RBF SVM compared with random forest algorithm. Materials and Methods: A total of 280 samples are collected from the Vermont Center for Ecostudies (VCE) repository. These samples are divided into two types. They are training samples (n=750 (75 %...

Full description

Saved in:
Bibliographic Details
Published in2022 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES) pp. 1 - 5
Main Authors Pavithra, M., Geetha, B.T.
Format Conference Proceeding
LanguageEnglish
Published IEEE 15.07.2022
Subjects
Accuracy
Chronic kidney cancer
Classification algorithms
Forestry
Kidney
Machine learning
Machine learning classifier
Novel Radial basis function support vector machine algorithm
Prediction algorithms
Random forest
Random forests
Support vector machines
Training
Online AccessGet full text

Cover

More Information
Summary:This research is to predict chronic kidney cancer using RBF SVM compared with random forest algorithm. Materials and Methods: A total of 280 samples are collected from the Vermont Center for Ecostudies (VCE) repository. These samples are divided into two types. They are training samples (n=750 (75 %)) and test samples (n=250 (25 %)). For the total sample size, the minimum power (G-Power) required is 0.8. Accuracy is calculated by a novel RBF SVM algorithm. Results: The value 0.8 is taken as G power. Novel RBF SVM obtained accuracy, recall and F-score of 99.0 %, 98.3 % and 98.9 % and Random forest achieved 98.0 %, 97.2 % and 98.3 %. The significance value is less than 0.05. Conclusion: From results it is observed that proposed radial basis function support vector machine algorithm is good in performance compared with random forest algorithm.
DOI:10.1109/ICSES55317.2022.9914342