领域驱动空间co-location模式挖掘技术研究

空间co-location模式挖掘是空间数据挖掘的一个重要分支，近年来，co-location模式挖掘受到学术界的关注并取得了瞩目的成果。但是，在实际应用中，大量研究成果并没有很好地被应用。究其原因，现有挖掘方法几乎不考虑领域知识、应用背景或约束。领域驱动数据挖掘是数据挖掘中的新方法，目的是挖掘用户感兴趣的、可供决策的知识。本项目拟系统研究领域驱动空间co-location模式挖掘的理论、模型、算法和评价准则。具体研究：（1）带约束co-location模式挖掘理论和方法；（2）高效用co-location模式及挖掘技术；（3）组合co-location模式挖掘概念和方法；（4）领域驱动不确定co-location模式挖掘技术。本研究对现有领域驱动数据挖掘理论、模型和算法不失为一个重要的补充和发展，同时将有力地推动空间co-location模式挖掘技术的应用。

Spatial co-location pattern mining plays an important role in the spatial data mining field. Due to its importance, the topic of finding prevalent co-locations in spatial data sets has been extensively explored and many algorithms and models have been presented. At the same time, we have seen that an extreme imbalance between the number of published algorithms versus those really workable in the real-world environment. Domain-driven data mining aims to develop general principles, methodologies, and techniques for modeling and merging comprehensive domain-related factors and synthesized ubiquitous intelligence surrounding problem domains with the data mining process, and discovering knowledge to support business decision-marking. This project plans to enhance real-world problem solving capabilities of mined co-locations by studing methodology of domain-driven spatial co-location pattern mining. In detail, we plan to make the following investigations: firstly, the theories and methods of the constrained co-location pattern mining will be studied; Secondly, the efficient algorithms for mining high utility co-location patterns will be explored; Thirdly, combined co-location pattern mining techniques will be researched; Finally, domain-driven co-location mining in spatially uncertain data sets will be studied. By this project, the theories, models and algorithms of the domain-driven data mining will be expanded. At the same time, the efficient and effective algorithms and techniques for mining spatial co-location patterns will be used extensively.