Constructing Hybrid Intelligent Systems for Data Mining from Agent Perspectives

Abstract

Data mining, the central activity in the process of knowledge discovery in databases, is concerned with finding patterns in data. Many data mining techniques/algorithms that are used to look for such patterns have been developed in domains that range from space exploration to financial analysis. However, a single data mining technique has not been proved appropriate for every domain and data set. Instead, several techniques may need to be integrated into hybrid systems and used cooperatively during a particular data mining operation. That is, hybrid solutions are crucial for the success of data mining. On the other hand, the design and development of hybrid intelligent systems is difficult because they have a large number of parts or components that have many interactions. Existing software development techniques (for example, object-oriented analysis and design) cannot manage these complex interactions efficiently as these interactions may occur at unpredictable times, for unpredictable reasons, between unpredictable components. From a multi-agent perspective, agents are autonomous and can engage in flexible, high-level interactions. They are good at complex, dynamic interactions. To this end, an agent-based framework was proposed to facilitate the construction of hybrid intelligent systems. In this chapter, we will present the agent-based framework first. We then discuss how to apply this framework to construct hybrid intelligent systems for data mining based on a case study. Combining these two cutting-edge technologies, it is expected that more and more difficult real-world problems can be solved. This chapter is a firm step in this direction.