A handwritten numeral character classification using tolerant rough set

This paper proposes a new data classification method based on the tolerant rough set that extends the existing equivalent rough set. Similarity measur e between two data is described by a distance function of all constituent a ttributes and they are defined to be tolerant when their similarity measure exceeds a similarity threshold value. The determination of optimal similar ity threshold value is very important for the accurate classification. So, we determine it optimally by using the genetic algorithm (GA), where the go al of evolution is to balance two requirements such that 1) some tolerant o bjects are required to be included in the same class as many as possible an d 2) some objects in the same class are required to be tolerable as much as possible. After finding the optimal similarity threshold value, a tolerant set of each object is obtained and the data set is grouped into the lower and upper approximation set depending on the coincidence of their classes. We propose a two-stage classification method that all data are classified b y using the lower approximation at the first stage and then the nonclassifi ed data at the first stage are classified again by using the rough membersh ip functions obtained from the upper approximation set. We apply the propos ed classification method to the handwritten numeral character classificatio n problem and compare its classification performance and learning time with those of the feedforward neural network's backpropagation algorithm.