期刊名称:International Journal of Computational Intelligence Techniques
印刷版ISSN:0976-0466
电子版ISSN:0976-0474
出版年度:2010
期号:567
页码:06-13
出版社:Bioinfo Publications
摘要:Many organizations have collected large amounts of spatially referenced data in various application areas such as geographic information systems (GIS), banking and retailing. These are valuable mines of knowledge vital for strategic decision making and motivate the highly demanding field of spatial data mining i.e., discovery of interesting, implicit knowledge from large amounts of spatial data. Most government local administrations collect and/or use geographical databases on the road accidents, on the road network and sometimes on the vehicle flow and sometimes on the mobility of inhabitants. In addition, other databases provide additional information on the geographical environment - trend layers - like administrative boundaries, buildings, census data, etc. These data contain a mine of useful information for the traffic risk analysis. There was a first study aiming identifying and at predicting the accident risk of the roads. It used a decision tree that learns from the inventoried accident data and the description of the corresponding road sections. However, this method is only based on tabular data and does not exploit geographical location. Using the accident data, combined to trend data relating to the road network, the traffic flow, population, buildings, etc., this project aims at deducing relevant risk models to help in traffic safety task. The existing work provided a pragmatic approach to multi¬layer geo-data mining. The process behind was to prepare input data by joining each layer table using a given spatial criterion, then applying a standard method to build' a decision tree. It allows the end-user to evaluate the results without any assistance by an analyst or statistician. The existing work did no consider multi-relational data mining domain. The efficiency of risk factor evaluation requires automatic filtering of spatial relationships. The quality of a decision tree depends, on the whole, of the quality of the initial data which are incomplete, incorrect or nonrelevant data inevitably leads to erroneous results. The proposed model develops an ant colony algorithm for the discovery of spatial trend patterns found in a GIS traffic risk analysis database. The proposed ant colony based spatial data mining algorithm applies the emergent intelligent behavior of ant colonies to handle the huge search space encountered in the discovery of this knowledge. Genetic algorithm is deployed to evaluate the spatial risk pattern rule sets to its optimization on search phase in quick successions. The experimental results on a geographical traffic (trend layer) spatial database show that our method has higher efficiency in performance of the discovery process and in the quality of trend patterns discovered compared to other existing approaches using non-intelligent decision tree heuristics.