Data Mining Techniques : An MRDM Approach

Ashok K Panda; Rashmita Panigrahi; S. N. Dehuri; M. R. Patra

Data mining techniques with the existing approaches look for data as patterns in a single data table. In recent years, the most common types of patterns and data mining approaches are extended to the multi-relational data. Multi-Relational Data Mining (MRDM) approaches involve multiple tables (relations) from a relational database. MRDM now encompasses association rule discovery, decision trees and distance-based methods among others. Three popular techniques such as classification, clustering and association rules have been explored in propositional and structured data mining. It then provides an insight into various classification methods including Inductive Logic Programming, Relational database, emerging patterns and associative approaches. MRDM approaches have been successfully applied to a number of problems in a variety of areas especially in the area of bioinformatics. This paper discusses some of the characteristics and comparisons in detail and finally on future directions of some applications of MRDM.

Select Volume / Issues:

• Volume 3 Issue 5, Sept. 2012

Year:

2012

Type of Publication:

Article

Keywords:

Classification; decision tree; inductive logic programmig; multi relational data mining

Journal:

IJECCE

Volume:

3

Number:

5

Pages:

1270-1278

Month:

Sept.