Inter Cluster Migration Estimation (ICME) model based on cluster parameters

Rajee, A.M.; Francis, F. Sagayaraj

doi:10.1109/iccic.2013.6724194

Cited by 1 publication

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The new element will become member of its nearest cluster and will either facilitate the movement of other data points between clusters, upsetting the clustering setup or becoming a member of the nearest cluster, without influencing inter cluster movement [3]. This paper is inclined to study the behavior of the clustering system considering the former case.…”

Section: Inter Cluster Movement Estimationmentioning

confidence: 99%

“…The correlation relationship of the new point with the cluster parameters is shown in Table I. The ICME model was built by thoroughly studying the dependence of cluster parameters on the new entrée [3]. Studies have shown that there exists a linear dependency of all the cluster parameters with the position of the new point from its nearest cluster center.…”

Section: Inter Cluster Movement Estimationmentioning

confidence: 99%

“…Feeding the system with a new point makes a re-arrangement of the individual clusters, causing other data points to move between the clusters. This process is known as inter cluster movement (or synonymously migration) of data points [3,4]. This paper gives a brief introduction of Inter Cluster Migration Estimation (ICME) model followed by the experimental setup and analysis of ICME model in multidimensional clusters of varying sizes.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Analysis of Inter Cluster Migration Estimation (ICME) model in multidimensional clusters

Rajee¹,

Francis²

2014

International Journal of Advanced Research in Computer and Comm

View full text Add to dashboard Cite

Abstract:Clustering evolves as an indigenous unsupervised data mining problem. This paper presents an estimation model, when new unclustered information is fed to the clustered system. The soul of this paper is to test the accuracy of the built Inter Cluster Movement Estimation (ICME) model with multi-dimensional clusters. Clusters of varying sizes and dimensions were constructed from synthetic and real data sets taken from UCI repository. On experimental analysis, the accuracy of the approximation model is found to increase with increased cluster sizes of multiple dimensions.

show abstract

Section: Inter Cluster Movement Estimationmentioning

confidence: 99%

Section: Inter Cluster Movement Estimationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation