期刊名称：International Journal of Computer Science & Technology
印刷版ISSN：2229-4333
电子版ISSN：0976-8491
出版年度：2012
卷号：3
期号：4
页码：744-747
语种：English
出版社：Ayushmaan Technologies
摘要：Spatial data mining fulfils real needs of many geomantic applications. Many organizations collected large amounts of spatially referenced data in various application areas such as traffic, banking and marketing areas. Mining spatial data is very valuable and knowledgeable for vital strategic decision making. The geographical databases are useful for avoiding the road accidents, vehicle flow and sometimes on the mobility of inhabitants. These data contain useful information for the traffic control in the busiest areas on the roads like administrative areas, schools and market areas. In this paper a study is made for identifying and predicting the accident risk of the road. The previous article written on decision tree techniques invents the mining accident data and the details of corresponding road sections. Using the accident data, combined to trend data relating to the road network, the traffic flow, population, buildings etc. The existing work used the approach of multilayer spatial data mining, i.e. each layer is combined with another layer dataset using spatial criteria, then applying a standard method to build a decision tree. We propose a new method called spatial auto-regression model. It is a popular spatial data mining technique which has been used in many applications with geo-spatial datasets.
关键词：Spatial Auto-Regression;Spatial Data Mining;Geo-Spatial Datasets
