Pattern Recognition Technique based on Adaptive Fuzzy k- mediod Clustering using Domain Knowledge

In the real world problems various pattern recognition technologies process huge amount of pattern to discover relevant knowledge. These techniques are computationally expensive. Additional knowledge also known as domain or background knowledge can help us in reducing the search as well as to optimize the hypotheses by decreasing the size of the search area. In the present paper we discuss the processes of domain knowledge, in effectively discovering knowledge. On the reduced search area we apply the dynamic fuzzy K-mediod technique to clusters these patterns in various clusters, the system is made adaptive to these dynamic changes. This technique finds many applications in various fields, like medical sciences, fraud detection in bank customer etc.