Detection Of Noise By Efficient Hierarchical Birch Algorithm For Large Data Sets

Abstract: Data mining plays a vital role in Computer Field. A huge and valuable Knowledge is extracted from the large collection of data. Various techniques and algorithms are used for finding patterns from the large datasets.. Finding useful patterns in large datasets has attracted considerable interest recently, and one of the most widely studied problems in this area is the identification of clusters or densely populated regions, in a multi-dimensional dataset. Clustering is one of the main techniques for grouping the data items based on their similarity. Outlier detection is one of the outstanding data mining tasks. Clustering methods have efficient algorithms for finding Outliers. Outlier detection has important applications in various data mining domains such as fraud detection, intrusion detection, customer’s behavior and employee’s performance analysis. In this paper we have taken the agriculture datasets for finding Outlier detection. Hierarchical Clustering methods have been compared and considered BIRCH Algorithm to be the best for finding noise and very effective for large datasets than the other hierarchical algorithms

Keywords: Clustering, Outlier detection Hierarchicalalgorithms, BIRCH