A Modified K-Nearest Neighbor Algorithm to Handle Uncertain Data

Classification is an important technique in data mining. The K-Nearest neighbor (K-NN) algorithm is a memory based algorithm and is capable of producing satisfactory results when applied on certain data but the distance measures used in this algorithm is not capable of handling the data sets containing the uncertain attribute values. Data uncertainty is common in real word applications. In this paper we have proposed an effective distance measure and modified K-NN which can be applied on the data sets containing uncertain numerical attributes and gives satisfactory results.