Clustering on Uncertain Data


Pratibha M. Patil , NDMVP,s KBTCOE,Nasik; Trupti R. Nerkar , NDMVP,s KBTCOE,Nasik; Swati R. Sanap, NDMVP,s KBTCOE,Nasik; Sanjeet Nehra, NDMVP,s KBTCOE,Nasik


Clustering, Uncertain Data, UK-Means, Large Margin, Histogram Intersection Kernel (LMHIK)


Recently data is generating in large amount everywhere and the efficient use of data should be done. So, proper techniques and methods should be there for efficient maintenance of data. To classify or cluster the valid or certain data, there are different approaches like DT, Rule based Classification, Naive Bayes Classification and many more techniques. But classification of uncertain data is bit difficult. The uncertainty occurs in the data because of the imprecise measurement of the results, like scientific results, data from sensor network, measuring temperature, humidity, pressure and so on. Main task is to handle the uncertainty of the data in order to classify or cluster it. So we are using UK-means and LMHIK algorithms for clustering of uncertain data. In UK-Means, the Expected Euclidean distance is used to assign the object to cluster and in LMHIK algorithm to create the accurate clusters the large margin is calculated.

Other Details

Paper ID: IJSRDV4I30214
Published in: Volume : 4, Issue : 3
Publication Date: 01/06/2016
Page(s): 113-115

Article Preview

Download Article