Modification K-Means Model With Local Deviation Method To Improve The Accuracy In Forming Clusters

. K-Means is one method in data mining that can be used to clustering data (Winda, 2015). But in the process of clustering K-Means Trying to minimize the number of Euclidean distance from the mean (Ismkhan, 2018) and it depends on the selection of cluster starting point (Han & Kamber, 2012). In this paper the authors try to use local deviation in calculating the cluster center based on distance variables are calculated and determined the mean so that will form the result between Σx and Σy. The results obtained from the modification algorithm is able to reduce the level of MSE (Means Square Error) performed on tests 1 and 2 that have a value of 290.95, while at K-Means MSE levels change in test 1 reaches 508.54 and test 2 reached 881.13 which gave MSE results higher than K-Means.

Paper

Full text

PDF

Modification K-Means Model With Local Deviation Method To Improve The Accuracy In Forming Clusters

Semantic Scholar · Computer Science · 2019

Abstract

. K-Means is one method in data mining that can be used to clustering data (Winda, 2015). But in the process of clustering K-Means Trying to minimize the number of Euclidean distance from the mean (Ismkhan, 2018) and it depends on the selection of cluster starting point (Han & Kamber, 2012). In this paper the authors try to use local deviation in calculating the cluster center based on distance variables are calculated and determined the mean so that will form the result between Σx and Σy. The results obtained from the modification algorithm is able to reduce the level of MSE (Means Square Error) performed on tests 1 and 2 that have a value of 290.95, while at K-Means MSE levels change in test 1 reaches 508.54 and test 2 reached 881.13 which gave MSE results higher than K-Means.

Similar papers

© 2026 NYSGPT2525 LLC