Enhancing Decision Tree Classification Accuracy through Genetically Programmed Attributes for Wart Treatment Method Identification

摘要: Abstract Origin: Warts are produced and developed on the human body due to infection induced by Human Papillomavirus. The most influenced zone of warts hands feet particularly, which is bit irritating difficult recoup in later stages. major challenge treating diversity treatment method applicable different patients, so it becomes recognize specific be adopted order treat this infection. Ramifications machine learning techniques medical domain have become crucial nowadays for early disease detection developing expert systems. Objective: This research work focuses enhancing predictive accuracy J48, a binary decision tree based classifier adding attributes genetic programming. These genetically tuned attribute construction not only just upgrades classification capabilities J48 but also additionally expand information space, intending giving more exact predictions wart identification. Method: For their experimental setup, authors chosen immunotherapy cryotherapy datasets from UCI repositories, includes instances patients responses against treated with methods both plantar common warts. investigation has been led help WEKA tool, an open source performing data mining operations. Finding: After experimentation, found after inclusion generated through programming, can increased substantial amount less error rate. result shows significant performance improvements 82.22% 96.66% 93.33% 98.88% datasets, implemented J48+GA respectively.