25 Performance Evaluation of Decision Tree Classifiers and AdaBoost on Cancer Datasets

Classification is one of the most important techniques in Data mining. Various applications apply these classification techniques to extract knowledge from huge amount of data collected from various sources. Gathering data from medical sources is one of the most popular one. Among all these datasets, cancer datasets is a real eye catcher for the researchers. Classifying these cancer dataset is a real challenge because of their high dimensionality and enormous size. Different existing classifiers are handy in classifying these high dimensional datasets. Decision tree classifiers are good candidates for this task while we have used a boosting algorithm (AdaBoost) for classifying along with the decision tree classifiers. In this paper, the performances on the accuracy of classification and time to build the model for decision tree induction classifiers and AdaBoost is analyzed.