The proposed EasyMiner (version 2) will extract knowledge from the data warehouse. The traditional data mining query language (DMQL) requires (a) the set of task-relevant data to be mined, (b) the kind of knowledge to be mined, (c) the background knowledge to be used in the discovery process, (d) the interestingness measures and thresholds for pattern evaluation and (e) the expected representation for visualizing the discovered patterns. These lengthy processes should be minimized so that the query processing time could be reduced. The ultimate goal is to simplify the data mining process by using a simple DMQL through EasyMiner. Normally, DMQL adopt several methodologies at each stage of knowledge mining. But the new DMQL propose some sort of eliminated or updated or simplified model of these methodologies namely concept hierarchy, association rules, classification, data cube, etc., Here the supervised learning ie., classification techniques are used. The user will realize the simplicity of the data mining process through EasyMiner. The outcome of the proposed EasyMiner is that expected knowledge from given data warehouse by saving more amount of query processing time. Further, the level of mining the knowledge might be indicated. The multi-dimensional database could be controlled to 3Ds only in order to maintain the simplification process of the EasyMiner. At last, the EasyMiner will extract the required and/or expected knowledge from the data warehouse by using simplified query processing models.
Data Mart, Data Mining, Data Warehouse, Query Processing
Elmasri R and Navathe S B, Fundamentals of Database Systems, 2ed, 1994 Benjamin and Cummings
Jiawei Han and Micheline Kamber, Data Mining: Concepts and Techniques, 2004, Morgan Kaufmann Publishers
Pieter Adriaans and Dolf Zantinge, Data Mining , 2003, Pearson Education
Silverschatz. A, Korth H R, and Sudarshan S, Database System Concepts, 3ed, 1997, McGraw Hill
Margaret H. Dunham, Data Mining Introductory and Advanced Topics, 2006, Pearson Education