Mining High Utility Co-location Patterns Based on Importance of Spatial Region
Mining High Utility Co-location Patterns Based on Importance of Spatial Region
复制标题
DOI：
10.1007/978-981-13-0896-3_5
复制
发表时间：
2017-12
期刊：
影响因子：
--
通讯作者：
Jiasong Zhao;Lizhen Wang;Peizhong Yang;Hongmei Chen
中科院分区：
文献类型：
--
作者：
Jiasong Zhao;Lizhen Wang;Peizhong Yang;Hongmei Chen
共址模式挖掘旨在发现地理空间中实例频繁位于一起的空间特征子集。大多数研究主要集中在空间特征实例是否经常位于一起。然而，空间实例在不同空间区域中的效用是不同的。基于空间区域的重要性，确定了区域的效用值，并定义了一种新的兴趣度测度--效用参与指数。我们提出了一个基本的高效用的同位模式挖掘算法。为了减少计算量，提出了一种带有剪枝策略的改进挖掘算法。在人工数据集和真实的世界数据集上的实验表明，所提方法是有效的。
Co-location pattern mining aims at finding the subsets of spatial features whose instances are frequently located together in geographic space. Most studies mainly focus on whether spatial feature instances are frequently located together. However, the utilities of spatial instances in different space regions are different. Based on the importance of spatial a region, the utility value of the region is determined, and then a utility participation index of co-location patterns as a new interestingness measure is defined. We present a basic high utility co-location pattern mining algorithm. To reduce the computational cost, an improved mining algorithm with pruning strategy is developed by cutting down the search space. The experiments on synthetic and real world datasets show that the proposed methods are effective and efficient.