Performance Improvement of Disk Based K-Means Over K-Means on Large Datasets

Provided by: Journal of Theoretical and Applied Information Technology
Topic: Data Management
Format: PDF
Clustering is a popular necessity having extensive scope for varied applications. The authors apply the k-means task in a situation where the volume of data is large and puts pressure on the access memory. The objective is to use less memory and access data sequentially. This paper proposes a method of making the algorithm more effective and efficient; so as to get better clustering with reduced complexity. Their algorithm is based on recent theoretical results, with significant improvements to make it application friendly. Their approach sufficiently simplifies a recently developed algorithm, both in design and analysis.

Find By Topic