Heterogeneous Dataset Management On Decision Support System

Due to the hugeness of our information resource and other aspects, people have speculated about how to improve decision-making without much professional help in developing clarity of action. In recent decades, a number of important supporting fields are integrated to ensure discipline analysis of decision that can help decision makers in all areas of activity:business, engineering, medicine, law, and personal life. Since uncertainty is the most important feature to consider when making decisions, the ability to represent knowledge in terms of probability, to see how to combine this knowledge with preferences in a reasoned way to treat very large and complex decision problems using advanced calculations and avoid common errors of thought are combined to produce insights previously unavailable. Restriction of the practice lies in our desire to use reason rather than any shortcoming on the field. This document will help those who need to pursue in the decision support system development in a new paradigm. By strengthening the weakness of DSS on uncertainty issues, one can have optimized result on decision making.According to many data related issues, we need data mining mechanisms. One of the major reasons we need data mining is for decision making. According to the data we have, a single dataset will not be sufficient for the specific purpose which leads us to processing of several datasets to get the expected result. These datasets, however, will rarely be homogeneous. Therefore, before attending to the actual work with the data, the problem of differences needs to be solved. In addition to this, there is also one big issue which is merging (i.e. on the case of heterogeneity of datasets). Merging could become almost impossible even if we need it so badly. Merging Problem could occur due to several causes but to state one; shortage of resource (i.e. time, process, and space). In general data Heterogeneity problem is a big problem related to decision making process.All around the world there are different kinds of systems invented and used. So, even system designers do their own thing to make it safer. This security parameter makes one system differ from the other. Therefore, one needs to process this all different systems and datasets as one system and one dataset. Which makes sense but, will get harder and harder when the size of the datasets bigger. Because, of resource management, response time and other issues. Especially, response time affect the decision making process.This document covers about rough set theory which is an approach for handling incomplete, vague and uncertain data; includes its basic concepts and it answers the questions such as, how to do data analysis without the need of preliminary or additional information about data? What Advantages of rough set analysis approach? What are the applications of rough set theory? What are the relations between rough set theory and data mining? And it includes the general example to show the basic concepts of rough set theory.Dynamic Reduct concept explained in here. Since it is inter-related with rough set theory, user must understand the example done in the previous chapter. And in this chapter there are answers for, How to find dynamic reduct? How to find dynamic core? And properties of the dynamic reduct.There are proposed mechanism and algorithm for solving the mentioned problems. Those are problems rise on knowledge discovery on heterogeneous dataset environment for decision tables and missing value treatment extension on the previous mechanism. Mechanisms to filter on heterogeneous decision tables and proposed algorithm to synchronies the different decision tables for the sake of finding the reducts and core that are the crucial elements in knowledge discovery.This paper will present methods how to manage heterogeneous decision system datasets. On the view of:how to calculate the core and reduct of two or more heterogeneous datasets that are significant to knowledge discovery.