K Means Clustering Algorithm for Partitioning Data Sets Evaluated From Horizontal Aggregations
Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2013, Vol 12, Issue 5
Abstract
Data mining refers to the process of analyzing the data from different perspectives and summarizing it into useful information that is mostly used by the different users for analyzing the data as well as for preparing data sets. A data set is collection of data that is present in the tabular form. Preparing data set involves complex SQL queries, joining tables and aggregate functions. Traditional RDBMS manages the tables with vertical format and returns one number per row. It means that it returns a single value output which is not suitable for preparing a data set. This paper mainly focused on k means clustering algorithm which is used to partition data sets after horizontal aggregations and a small description about the horizontal aggregation methods which returns set of numbers instead of one number per row. This paper consists of three methods that is SPJ, CASE and PIVOT methods in order to evaluate horizontal aggregations. Horizontal aggregations results in large volumes of data sets which are then partitioned into homogeneous clusters is important in the system. This can be performed by k means clustering algorithm
Authors and Affiliations
R. Kumar
Investigating ATM System Accessibility for People with Visual Impairments
The aim of this paper is to draw attention for the evaluation of the accessibility and usability of Automated Teller Machine (ATM) systems from the point of view of visually impaired persons. It suggests that &n...
Twitter Sentiment Classification on Sanders Data using HybridApproach
Abstract : Sentiment analysis is very perplexing and massive issue in the field of social data mining. Twitter isone of the mostly used social media where people discuss on various issues in a dense way. The tweets about...
Implementation of an efficient algorithm to enhance connectivity and lifetime in wireless sensor networks
Abstract: Wireless sensor network is a rapidly growing area for research and commercial development. Wireless Sensor Network (WSN) is a major and very interesting technology, which consists of small battery powered senso...
Monitoring Wireless Sensor Network using Android based Smart Phone Application
Abstract: Wireless Sensor Network application’s is use in detection of natural calamities like forest fire detection, flood detection, , earth quick early detection ,snow detection, traffic congestion and various o...
Edge Adaptive Image Steganography Based on Adaptive Pixel Pair Matching
This paper proposes a new improved steganographic technique based on pixel pair matching which is driven by edge adaptive technique. The cover image is scanned first to explore the edges of the image and is used...