Classifiers’ Accuracy Based on Breast Cancer Medical Data and Data Mining Techniques
Journal Title: International Journal of Advanced Biotechnology and Research. - Year 2016, Vol 7, Issue 2
Abstract
ABSTRACT Knowledge Data Discovery (KDD) in Breast Cancer data set includes; data collection, data preprocessing, data mining, knowledge extraction, patterns validation, and results visualization. Where, this disease is considered as one of the deadly diseases in the world. The research problem is that there are many machine learning classifiers with different levels of accuracy when applied to Breast Cancer data. The highest accuracy of a classifier model depends upon the nature and the size of the data used to establish this model. To help physicians select the most accurate classifier algorithm to be applied using this kind of data. The paper’s objective is to discover the most accurate classifier among all Data Mining classifiers based on Breast Cancer data set and the WEKA software. The results compared with previous results in other researches and show highly accurate results. It was found that the Bayes Net classifier model is the best classifier among the other types.
Authors and Affiliations
Mohammed Abdullah Hassan Al-Hagery
Phylogenetic analysis of Dengue Virus Serotype 1 Isolated from Clinically Suspected Pediatric Patients in Chennai, Tamilnadu.
ABSTRACT The evolution of Dengue virus has a major impact on their virulence in humans and on the epidemiology of dengue disease around the world. In order to perform disease surveillance and to understand DENV evoluti...
Enhancing Provitamin A of Maize using functional gene markers
PHA Synthase Genes in Oil-Degrading Marine Bacteria from the Colombian Pacific Coast
OPTIMIZATION OF DNA EXTRACTION METHODS FOR SOME IMPORTANT FOREST TREE SPECIES
Isolation, Characterization of Extracellular Bacterial Alkaline Proteases and Its Industrial Applications