Knowledge Discovery Query Language (KDQL)

KDD is a rapidly expanding field with promise for great applicability. Knowledge discovery became the new database technology for the incoming years. The need for automated discovery tools caused an explosion in the number and type of tools available commercially and in the public domain. These requirements encouraged us to propose a new KDD model so called ODBC_KDD(2) described in [39] ."One of the ODBC_KDD(2) model requirements is the implementation of a query language that could handle DM rules"[40]. This query language called Knowledge Discovery Query Language (KDQL). KDQL is a companion of two major tasks in KDD such as DM and Data Visualization. These requirements motivates us to think for the possibility of joining the two tasks of KDD commonly known as Data Mining (DM) and Data Visualization (DV) together in one single KDD process. Integrating DM and DV requires a new database concept. This database concept is called “i-extended database“. I-extended database will be retrieved by the use of KDQL. This I-extended database described in details in [42]. KDQL RULES operations were also theoretically proposed in this paper and some examples were given as well. KDQL RULES are used only to find out the association rules in i-extended database we have. The development and results of this paper would contribute to the data mining and visualization fields in several ways. The formulation of a set of heuristics for algorithms selection will help to clarify the matching between a specific problem and the set of bestsuited algorithms or techniques (i.e. association rules) for solving it. These guidelines are expected to be useful and applicable to real DM projects. Key-words: Data Mining (DM), Data Mining Query Language (DMQL), Knowledge Discovery in Databases (KDD),Query Optimization (QO), Rule Mining(RM),Association Rules (AR).