Data Reduction with K-Means Clustering

Non-Causal Step

This step applies the K-Means Clustering algorithm to reduce the size of input data set without losing much information.

Input Parameters

1. Large size of input data
2. Specified number of clusters

Output Parameters

1. Reduced data set

Workflow

Algorithm

K-Means Clustering

References

• Z.F. Hao, W. Wen, X.W. Yang, J. Lu, and G.Q. Zhang, A Fast Data Preprocessing Procedure for Support Vector Regression, IDEAL 2006, LNCS 4224, pp. 48-56, 2006.