GIS与空间数据挖掘技术在环境污染事故应急处理系统中的应用研究
|
摘要
近年来,环境污染问题日益严重,为有效防范环境污染事故,需要及时合理的处理各类可能发生的突发性环境污染事故。本文根据某市环境污染事故的基本情况,将GIS技术和空间数据挖掘技术应用到环境污染事故应急处理系统中,通过挖掘出一些隐含的规则,从而分析得出环境污染事故影响的主要区域及其原因,并对此提出相应的对策,对提高环境污染事故应急处理能力有重要的现实意义。
本文首先研究了GIS技术和空间数据挖掘技术。然后说明了对空间数据进行数据预处理以提高算法挖掘效率的必要性,详细描述了数据预处理的几种常见方法,对环境污染数据进行了数据概化和数据归约,为反映空间对象属性数据的特征和空间对象之间的空间关系设置了空间谓词,并将谓词数值化；为处理数据库中的大量不完备数据引入了粗糙集理论,并利用粗糙集理论对环境污染数据属性进行了分析。其次,研究了空间关联规则中的Apriori算法,针对空间数据的特点提出了扩充的Apriori算法,并将其应用于环境污染事故应急处理的数据挖掘中,该算法解决了Apriori算法的局限性。
最后介绍了使用Delphi和MapX开发的环境污染事故应急处理系统,给出了系统的总体设计及其各个功能的实现。然后针对本系统的不足对GIS技术及空间数据挖掘技术在环境污染事故应急处理系统中的进一步应用作了展望。
综上所述,将GIS技术和空间数据挖掘技术结合应用到本系统中,可以有效的对空间数据进行分析,得到有价值的关联规则知识,为事故的应急处理提供有效决策。
In recent years, the growing problem of environmental pollution, in order to prevent environmental pollution accident effectively, all types of possible major emergency pollution incidents need handling timely and reasonable. Based on the basic situation of a city environmental pollution accident, the thesis has introduced GIS and spatial data mining into sudden environmental contamination accidents emergency control system,by discovering some implicit rules, and obtain the region where the pollution incidents effect and its reason by analysis, and propose counter measures,it has important practical significance on improving environmental emergency capacity.
The thesis first introduces the research state and its significance of environmental pollution accident, through research GIS technology and spatial data technology, and point out the feasibility of solving environmental pollution accidents problems by spatial data mining and GIS technology. Then describes the need for data pretreatment,it can improve the efficiency of mining algorithm, it particularly describes the method of data pretreatment,through solving the spatial data by data generalization and data reduction,in order to reflect the characteristics of the attribute data of spatial objects and the relationships among them,setting predicate and converting them into integer data; To deal with the database of a large number of incomplete data, we introduce the rough set theory and take advantage of rough set theory to the analysis of environmental data attributes, through the spatial association rules of the Apriori algorithm, we propose expansion of the Apriori algorithm based on the characteristics of spatial data, and applied to the data mining of environmental pollution and emergency control, the algorithm solves the limitations of Apriori algorithm.
Finally, the thesis introduces developing the environmental pollution emergency system by using Delphi and MapX, and show the system's overall design and the implementation of its various function. Then, due to the shortcomings of this system, the system based on GIS and spatial data mining technology in the further application is prospected.
In summary, the GIS technology and spatial data mining combined can be analyze the spatial data effectively, and can obtain valuable knowledge of association rules, and can provide an effective decision-making.
本文首先研究了GIS技术和空间数据挖掘技术。然后说明了对空间数据进行数据预处理以提高算法挖掘效率的必要性,详细描述了数据预处理的几种常见方法,对环境污染数据进行了数据概化和数据归约,为反映空间对象属性数据的特征和空间对象之间的空间关系设置了空间谓词,并将谓词数值化；为处理数据库中的大量不完备数据引入了粗糙集理论,并利用粗糙集理论对环境污染数据属性进行了分析。其次,研究了空间关联规则中的Apriori算法,针对空间数据的特点提出了扩充的Apriori算法,并将其应用于环境污染事故应急处理的数据挖掘中,该算法解决了Apriori算法的局限性。
最后介绍了使用Delphi和MapX开发的环境污染事故应急处理系统,给出了系统的总体设计及其各个功能的实现。然后针对本系统的不足对GIS技术及空间数据挖掘技术在环境污染事故应急处理系统中的进一步应用作了展望。
综上所述,将GIS技术和空间数据挖掘技术结合应用到本系统中,可以有效的对空间数据进行分析,得到有价值的关联规则知识,为事故的应急处理提供有效决策。
In recent years, the growing problem of environmental pollution, in order to prevent environmental pollution accident effectively, all types of possible major emergency pollution incidents need handling timely and reasonable. Based on the basic situation of a city environmental pollution accident, the thesis has introduced GIS and spatial data mining into sudden environmental contamination accidents emergency control system,by discovering some implicit rules, and obtain the region where the pollution incidents effect and its reason by analysis, and propose counter measures,it has important practical significance on improving environmental emergency capacity.
The thesis first introduces the research state and its significance of environmental pollution accident, through research GIS technology and spatial data technology, and point out the feasibility of solving environmental pollution accidents problems by spatial data mining and GIS technology. Then describes the need for data pretreatment,it can improve the efficiency of mining algorithm, it particularly describes the method of data pretreatment,through solving the spatial data by data generalization and data reduction,in order to reflect the characteristics of the attribute data of spatial objects and the relationships among them,setting predicate and converting them into integer data; To deal with the database of a large number of incomplete data, we introduce the rough set theory and take advantage of rough set theory to the analysis of environmental data attributes, through the spatial association rules of the Apriori algorithm, we propose expansion of the Apriori algorithm based on the characteristics of spatial data, and applied to the data mining of environmental pollution and emergency control, the algorithm solves the limitations of Apriori algorithm.
Finally, the thesis introduces developing the environmental pollution emergency system by using Delphi and MapX, and show the system's overall design and the implementation of its various function. Then, due to the shortcomings of this system, the system based on GIS and spatial data mining technology in the further application is prospected.
In summary, the GIS technology and spatial data mining combined can be analyze the spatial data effectively, and can obtain valuable knowledge of association rules, and can provide an effective decision-making.
引文
[1]黄杏元,马劲松,汤勤编著·《地理信息系统概论》.北京：高等教育出版社,2003.
[2]陈述彭等.《地理信息系统导论》.北京：科学出版社,1999.
[3]李玲慧,王庆生MAPGIS在编制旅游区规划图中的应用研究,见：王家耀,地理信息系统与电子地图技术的进展,长沙：湖南地图出版社,1999：11-14
[4]乌仔伦,刘瑜等.地理信息系统—原理、方法和应用[M].北京：科学出版社,2001.
[5]刘光.地理信息系统系统二次开发教程.北京：清华大学出版社,2002.6.
[6]徐国培,邵自强.地理信息系统的理论与应用.环境污染与防治.1994,1明：25-30.
[7]Ester M.er al.,2000.Spatial data mining:databases primitives,algorithms and efficient DBMS support.Data Mining and Knowledge Discovery,4:193-216
[8]Koperski k.,Adhikary J.,Han J.,1996.Spatial data mining:process and challenges survey paper.SIGMOD'96 Workshop on Research Issues on Data Mining and Knowledge Discovery(DMKD'96),Montreal,Canada,June
[9]Miller H.J.,Han J.,2001.Geographic Data Mining and Knowledge Discovery.London:Taylor&Francis
[10]Haining R.,2003.Spatial Data Analysis:Theory and Practice.Cambridge:Cambridge University Press
[11]Zeitouni K.,2002.A survey of spatial data mining methods databases and statistic point of views.In:Data Warehousing and Web Engineering,edited by Becker S.London:IRM Press,229-242
[12]Clark P.,Niblet T.T.,1989.The CN2 induction algorithm.Machine Learing,(3):261-283
[13]Kaufman L.,Rousseew P.J.,1990.Finding Groups in Data:an Introduction to Cluster Analysis.New York:John Wiley&Sons
[14]Gallant S.I.,1993.Neural Network Learing and Expert Systems.Cambridge:MIT Press
[15]Quinlan J.,1986.Introduction of decision trees.Machine Learning,(5):239-266
[16]Gallant S.I.,1993.Neural Network Learning and Expert Systems.Cambridge:MIT Press
[17]Zadeh.L.A.,1965.Fuzzy Sets.Information and Control,8(3):338-353
[18]邸凯昌,2001.空间数据发掘和知识发现。武汉：武汉大学出版社
[19]Frawley W,Piatesky-Shapiro G&Matheus C.1991.Knowledge Discovery in Database:An Overview.In G. Piatesky-Shapiro and W.Frawley(Ed.),Knowledge Discovery in Databases,AAAI/MIT Press
[20]Hernandez M.A.,Stolfo S.J.,1998.Real-world data is dirty:data cleansing and the merge/purge problem.Data Mining and Knowledge Discovery,2:1-31
[21]Wang S.L. et al.,2004,A try for handling uncertainties in spatial data mining,Lecture Notes in Artificial Intelligence,3215:513-520
[22]张艳秋,徐六通,数据集成中不一致性数据相似性比较的加权算法,计算机科学,2003,30(8),P92.
[23]曾黄麟.《粗糙集理论及其应用》.重庆：重庆大学出版社.2001.
[25]Nakamura,Fuzzy rough sets.Note on Multiple_valued Logic in Japan.1998,9:1-8.
[26]Pawlak Z.,1991.Rough sets:theoretical aspects of reasoning about data.London:Kluwer Academic Publishers
[27]Yao Y.Y.,Wong S.K.M.,Lin T.Y,1997,A Review of Rough Sets and Data Mining Analysis for Imprecise Data,edited by Y.LIN and N.CERCONE.London:Kluwer.Academic Publishers,47-75
[28]Ahlqvist Q.,Keukelaar J., Oukbir K.,2000.Rough classification and accuracy assessment.International Journal of Geographical Information Science,14(5):475-496
[29]R.slowinski,D,Vanderpooten.A generalized definition of rough approximations based on similarity.IEEE Transactions on Knowledge and Data Engineering.2000,12:331-336
[30]Theresa Beaubouef,Roy Lander,Frederick E.Petry:Rough set spatial data modeling for data mining.Int.J.Intell.Syst.2004,19(7):568-585
[31]吕曹芳,庞宇,罗永龙.基于GIS空间关联规则的挖掘综述.资源开发与市场.23(4)：323—325.
[32]Binbin He,Cuihua Chen.Spatial Data Mining with Uncertainty.Computer Intelliqence and Security,2006 International Conference.2006.1:797-800
[33]郭平,范丽,叶莲.空间规则的可视化解释.计算机科学,2003,31(5)：169-172
[34]王佐成,汪林林,薛丽霞,李永树.空间关联规则的双向挖掘.计算机科学.2006,33(7)：199-203
[36]张雪伍,苏奋振,石忆邵,张丹丹.空间关联规则挖掘研究进展.地理科学进展.2007,26(6)：119-128
[37]Rakesh AgrawalTomasz Imielinski,Arun Swami.Mining Association Rules between Sets of Items in Large Databases.Proceedings of the 1993 ACM SIGMOD Conference Washington DC,USA,1993,1-10.
[38]Agrawal R,Srikant R,Fast algorithom for mining association rules.proceedings of the 1994 International conference on VLDB,Santiago,Chile.1994,486-500。
[39]史文中,王树良,2002.GIS中属性不确定性的处理方法及其发展。遥感学报,6(5)：393-400
[2]陈述彭等.《地理信息系统导论》.北京：科学出版社,1999.
[3]李玲慧,王庆生MAPGIS在编制旅游区规划图中的应用研究,见：王家耀,地理信息系统与电子地图技术的进展,长沙：湖南地图出版社,1999：11-14
[4]乌仔伦,刘瑜等.地理信息系统—原理、方法和应用[M].北京：科学出版社,2001.
[5]刘光.地理信息系统系统二次开发教程.北京：清华大学出版社,2002.6.
[6]徐国培,邵自强.地理信息系统的理论与应用.环境污染与防治.1994,1明：25-30.
[7]Ester M.er al.,2000.Spatial data mining:databases primitives,algorithms and efficient DBMS support.Data Mining and Knowledge Discovery,4:193-216
[8]Koperski k.,Adhikary J.,Han J.,1996.Spatial data mining:process and challenges survey paper.SIGMOD'96 Workshop on Research Issues on Data Mining and Knowledge Discovery(DMKD'96),Montreal,Canada,June
[9]Miller H.J.,Han J.,2001.Geographic Data Mining and Knowledge Discovery.London:Taylor&Francis
[10]Haining R.,2003.Spatial Data Analysis:Theory and Practice.Cambridge:Cambridge University Press
[11]Zeitouni K.,2002.A survey of spatial data mining methods databases and statistic point of views.In:Data Warehousing and Web Engineering,edited by Becker S.London:IRM Press,229-242
[12]Clark P.,Niblet T.T.,1989.The CN2 induction algorithm.Machine Learing,(3):261-283
[13]Kaufman L.,Rousseew P.J.,1990.Finding Groups in Data:an Introduction to Cluster Analysis.New York:John Wiley&Sons
[14]Gallant S.I.,1993.Neural Network Learing and Expert Systems.Cambridge:MIT Press
[15]Quinlan J.,1986.Introduction of decision trees.Machine Learning,(5):239-266
[16]Gallant S.I.,1993.Neural Network Learning and Expert Systems.Cambridge:MIT Press
[17]Zadeh.L.A.,1965.Fuzzy Sets.Information and Control,8(3):338-353
[18]邸凯昌,2001.空间数据发掘和知识发现。武汉：武汉大学出版社
[19]Frawley W,Piatesky-Shapiro G&Matheus C.1991.Knowledge Discovery in Database:An Overview.In G. Piatesky-Shapiro and W.Frawley(Ed.),Knowledge Discovery in Databases,AAAI/MIT Press
[20]Hernandez M.A.,Stolfo S.J.,1998.Real-world data is dirty:data cleansing and the merge/purge problem.Data Mining and Knowledge Discovery,2:1-31
[21]Wang S.L. et al.,2004,A try for handling uncertainties in spatial data mining,Lecture Notes in Artificial Intelligence,3215:513-520
[22]张艳秋,徐六通,数据集成中不一致性数据相似性比较的加权算法,计算机科学,2003,30(8),P92.
[23]曾黄麟.《粗糙集理论及其应用》.重庆：重庆大学出版社.2001.
[25]Nakamura,Fuzzy rough sets.Note on Multiple_valued Logic in Japan.1998,9:1-8.
[26]Pawlak Z.,1991.Rough sets:theoretical aspects of reasoning about data.London:Kluwer Academic Publishers
[27]Yao Y.Y.,Wong S.K.M.,Lin T.Y,1997,A Review of Rough Sets and Data Mining Analysis for Imprecise Data,edited by Y.LIN and N.CERCONE.London:Kluwer.Academic Publishers,47-75
[28]Ahlqvist Q.,Keukelaar J., Oukbir K.,2000.Rough classification and accuracy assessment.International Journal of Geographical Information Science,14(5):475-496
[29]R.slowinski,D,Vanderpooten.A generalized definition of rough approximations based on similarity.IEEE Transactions on Knowledge and Data Engineering.2000,12:331-336
[30]Theresa Beaubouef,Roy Lander,Frederick E.Petry:Rough set spatial data modeling for data mining.Int.J.Intell.Syst.2004,19(7):568-585
[31]吕曹芳,庞宇,罗永龙.基于GIS空间关联规则的挖掘综述.资源开发与市场.23(4)：323—325.
[32]Binbin He,Cuihua Chen.Spatial Data Mining with Uncertainty.Computer Intelliqence and Security,2006 International Conference.2006.1:797-800
[33]郭平,范丽,叶莲.空间规则的可视化解释.计算机科学,2003,31(5)：169-172
[34]王佐成,汪林林,薛丽霞,李永树.空间关联规则的双向挖掘.计算机科学.2006,33(7)：199-203
[36]张雪伍,苏奋振,石忆邵,张丹丹.空间关联规则挖掘研究进展.地理科学进展.2007,26(6)：119-128
[37]Rakesh AgrawalTomasz Imielinski,Arun Swami.Mining Association Rules between Sets of Items in Large Databases.Proceedings of the 1993 ACM SIGMOD Conference Washington DC,USA,1993,1-10.
[38]Agrawal R,Srikant R,Fast algorithom for mining association rules.proceedings of the 1994 International conference on VLDB,Santiago,Chile.1994,486-500。
[39]史文中,王树良,2002.GIS中属性不确定性的处理方法及其发展。遥感学报,6(5)：393-400