期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2013
卷号：2
期号：11
页码：2963-2967
出版社：Shri Pannalal Research Institute of Technolgy
摘要：In Data Mining, Classification is the process of finding and applying a model to describe and distinguish data classes, concepts and values. The model that is built is called a Classifier or Predictor depending upon whether the model finds the unknown data class or data value. Single classifier may not be very much accurate; Ensemble systems use an "ensemble" or group of classifiers to improve the accuracy. Associative classification is an approach in data mining that utilizes the association rule discovery techniques to build classification systems, also known as associative classifiers. Ensemble methods have been called the most powerful development in data mining. They combine multiple classification models into one, usually more accurate one. Here in this thesis an efficient approach for classification using association rule ensemble is proposed. This presents an associative classification algorithm BCAR, which remove the frequent items that cannot generate frequent rules directly by adding the count of class labels. Main purpose is to ensemble association rule classifier without loss of performance & accuracy of the resultant classifier.
