Optimization of Horizontal Aggregation in SQL by using C4.5 Algorithm and K-Means Clustering
Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2014, Vol 16, Issue 5
Abstract
Abstract: Datasets in the horizontal aggregated layout are preferred by most of data mining algorithms, machine learning algorithm. Major efforts are required to compute data in the horizontal aggregated format. There are many inbuilt aggregation functions in SQL, namely, minimum, maximum, average, sum and count. These aggregation functions are used with a query evaluation method to retrieve data in the horizontal aggregation format. Optimization techniques used for vertical aggregation is not appropriate for horizontal aggregation. Standard aggregations are hard to interpret when there are many result rows, especially when grouping attributes having high cardinalities. That is why we proposed C4.5 classification algorithm and K-means clustering algorithm with query evaluation method and aggregation function for optimizing horizontal aggregation. Horizontal aggregation is a method which generates SQL code to return aggregated columns in the horizontal tabular layout. It returns a set of numbers instead of one number per row. There are various applications where the horizontal aggregation is used such as electrical billing, banks, hospital management system, pharmacy, and online library etc. [6].
Authors and Affiliations
Ms. Priti Phalak , Dr. Rekha Sharma
Usage and Research Challenges in the Area of Frequent Pattern in Data Mining
Frequent pattern mining is an important chore in the data mining, which reduces the complexity of the data mining task. The usages of frequent patterns in various verticals of the data mining functionalities are...
An Efficient Resource Allocation with Adaptive Rate Scheduling For WCDMA Networks
Abstract: WCDMA is a spread spectrum technique that uses a unique spreading code to spread the data before transmission based on its orthogonal property. WCDMA is mainly used for 3rd generation cellular and mobilenetwork...
Video Segmentation Using Global Motion Estimation and Compensation
Abstract : Video has to be segmented into objects for content-based processing. A number of video object segmentation algorithms have been proposed such as semiautomatic and automatic. Semiautomatic methods adds burden t...
A Short-Normalized Attack Graph Based Approach for Network Attack Analysis
Abstract: Attack graphs are the graphs which describe attack scenarios, play important roles in analyzing network threats. These attack graphs are able to reveal such potential threats by evaluating the all possibl...
Detection and Prevention of Wormhole Attack in MANET UsingDSR Protocol
Abstract: With the advancement in wireless technologies, wireless networks are developing at a fast rate andso are the MANET’s. Several routing attacks are introduced in the wireless networks due to their dynamical...