Appiah Stephen* and Adebayo Felix Adekoya
One out of eight women over their lifetime will be diagnosed of breast cancer and it is recorded to be the world major cause of women’s deaths. Data mining methods are an effective way to classify data, especially in medical field, where those methods are widely used in diagnosis and analysis to make decisions. In this study, a performance comparison between five different data mining technique: Random forest, random tree, Bayes net, Naïve Bayes and J48 on the breast cancer Wisconsin (Diagnostic) data set is conducted. It is aimed to assess the correctness in classifying data with respect to efficiency and effectiveness of each algorithm in terms of accuracy, precision, sensitivity/recall and specificity. Experimental outcome indicates that Bayes net and random forest gives the highest weighted average accuracy of 97.1% with lowest type I and II error rate. All experiments conducted in WEKA data mining tool.
分享此文章
English 
Spanish 
Russian 
German 
French 
Japanese 
Portuguese 
Hindi 