A New Discretization and Pattern Selection Method for Classification in Data Mining using Feedforward Neural Networks

Data mining is the widely used research area in recent years. The results of data mining, represent relations in the data and are usually employed for classifying new data or for describing correlations hidden in the data. The process of classification predicts categorical labels based on the analysis of set of training data. Researchers have proposed many classification algorithms to automate the processing and extraction of knowledge from data. Some of the classification algorithms like CN2 (Clark & Niblett, 1989), AQ (Kaufman & Michalski, 1999) or CLIP (Cios & Kurgan, 2001) can handle only discrete data, while some others (Wu et al., 2006) can