| With the large amount of data stored by many organizations, capitalists have observed that this information is an intangible asset. Unfortunately, handling large databases is a very complex process and traditional learning techniques are expensive to use. Heuristic techniques provide much help in this arena, although little is known about heuristic techniques. Heuristic and Optimization for Knowledge Discovery addresses the foundation of this topic, as well as its practical uses, and aims to fill in the gap that exists in current literature.
The advancement in data collection, storage, and distribution technologies has far outpaced computational advances in techniques for analyzing and understanding data. This encourages researchers and practitioners to develop a new generation of tools and techniques for data mining (DM) and for knowledge discovery in databases (KDD). KDD is a broad area that integrates concepts and methods from several disciplines including the fields of statistics, databases, artificial intelligence, machine learning, pattern recognition, machine discovery, uncertainty modeling, data visualization, high performance computing, optimization, management information systems, and knowledge-based systems.
KDD is a multistep iterative process. The preparatory steps of KDD include data selection and/or sampling, preprocessing and transformation of data for the subsequent steps of the process. Data mining is the next step in the KDD process. Data mining algorithms are used to discover patterns, clusters and models from data. The outcomes of the data mining algorithms are then rendered into operational forms that are easy for people to visualize and understand.
The data mining part of KDD usually uses a model and search based algorithm to find patterns and models of interests. The commonly used techniques are decision trees, genetic programming, neural networks, inductive logic programming, rough sets, Bayesian statistics, optimisation and other approaches. That means, heuristic and optimisation have a major role to play in data mining and knowledge discovery. However, most data mining work resulting from the application of heuristic and optimisation techniques has been reported in a scattered fashion in a wide variety of different journals and conference proceedings. As such, different journal and conference publications tend to focus on a very special and narrow topic. It is high time that an archival book series publishes a special volume which provides critical reviews of the state-of-art applications of heuristic and optimisation techniques associated with data mining and KDD problems. This volume aims at filling in the gap in the current literature. |
