Comparative Analysis of Classification Method for Wart Treatment Method

Ananta Rahmat, Genda and Primartha, Rifkie and Sukemi, Sukemi and Wijaya, Adi (2019) Comparative Analysis of Classification Method for Wart Treatment Method. ICONISCSE, 1196.

Text Comparative Analysis of Classification Method for Wart Treatment (merge).pdf Restricted to Repository staff only Download (1MB) | Request a copy

Abstract

Wart disease is a benign tumor that grows in all parts of thebody with varying amounts. There have been many methods of treatment of wart diseases that are found, but not much research leads to proving which treatments are best at treating wart disease. As a result, Patients sometimes need extra costs and time to cure wart disease because they have to be treated with more than one method. The purpose of this study was to compare the method of data mining classification to predict the best treatment of warts for patients between cryotherapy treatment which is the treatment of warts in general and the treatment of immunotherapy which is the latest treatment. Decision tree, random forest and k-nearest neighbor will be used as a classifier in predicting wart treatment in this study. From the research, the results obtained from the comparison of these three algorithms are amazing and promising with the best prediction accuracy on cryotherapy treatment achieved by the k-nearest neighbor algorithm of 95.66% while the best accuracy for immunotherapy treatment is achieved by random forest algorithm with an accuracy of 88.89%. We also predicted by combining the two datasets into 1 part, the result of the comparison for the three algorithms with the combined dataset it was found that the k-nearest neighbor algorithm was the best classifier to predict the wart treatment method with an accuracy of 88.03%

Item Type:	Article
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 55101-Informatics (S2)
Depositing User:	Dr. Sukemi Sukemi
Date Deposited:	11 Sep 2020 12:54
Last Modified:	07 Sep 2021 02:36
URI:	http://repository.unsri.ac.id/id/eprint/34799

Actions (login required)

View Item