中小城市商业网点选址决策支持系统研究
|
摘要
随着我国经济的快速发展,城市化及城市扩张加快,中小城市由于人口数量、城市规模以及产业发展重点与大中城市不同,商业网点规模的确定和布局也有所不同。对于当前我国600多个中小城镇来说,其商业网点规划不但需要确立自身的发展框架,逐步形成合理的用地开发时序,更要注重商业网点建设和规划的独特性,比如突出地方特色和充分发挥商业中心的人文内涵等,这也是贯彻“科学发展,和谐发展”的体现。如何依据科学理论,充分利用空间信息技术的优势来研究、分析和管理网点数据,并为城镇商业网点分布提供合理的布局和规划,已成为企业迫在眉睫的问题和重大的挑战。然而地理信息系统的空间数据分析与可视化表达与决策支持系统的数据判断能力,计算最优解并进行科学预测能力的相互集成,完美的解决了这一问题。
本文首先从影响中小城市商业网点选址的因子因素入手,对比分析中小城市网点选址与大城市网点选址的相似性和差异性,并通过专家咨询等方式确立选址影响因素及其权重。整个选址过程由粗选和精选两大部分构成,粗选过程涉及到公交便捷度、道路通达性、人口估算等五个影响因素的获取和运算;精选址是在粗选的基础上采用基于K-Means聚类的粒子对搜索算法确定。最后,采用AO+VB二次开发方式,进行“中小城市商业网点选址决策支持系统”开发。文章的主要工作和创新点如下:
(1)查阅国内外相关研究,针对我国中小城网点建设现状及国家对中小城市商业发展规划的重要指示,提出建立市级、区域级和社区级三个级别的商业网点布局框架和粗选、精选技术路线。
(2)对比分析中小城市和大城市网点建设影响因素相似性和差异性,采用定性和定量分析相结合的方法,确立影响因素,并对各影响因素进行作用分值计算。
(3)讨论通过高分辩率遥感影像在地方建筑特色浓厚、居民地分布零散的中小城市城区进行人口数据获取的思路和误差分析方法。结果表明,采用改进的土地利用密度法进行人口估算,其数据精度满足商业网点选址的需要。
(4)把K-Means聚类分析法引入粒子对算法,同时采用“窗口“搜索方法在粗选区域进行最优位置搜索,并以开封市商业网点选址为例实证研究,模拟结果与现实相符。
(5)以Geodatabase数据库为基础,开发中小城市商业网点选址决策支持系统,系统涵盖了数据编辑、矢量数据处理、栅格数据处理、PSO精选址操作和专题图输出五大功能,同时,友好界面及人性化操作使用户可以方便的进行各种影响因素的查询及网点选址操作。
通过以上研究得出,建立在相关理论基础上的中小城市商业网点选址决策支持系统,结合了以往商业网点选址工作的经验成果,具备了较强的操作性。本系统实现了中小城市商业网点选址的自动化和智能化,用计算机处理网点数据和网点因素数据,并对各类数据建表入库,不但有利于新建网点的查询分析,更利于后期的网点规划管理和建设布局,相比传统的图纸操作和人为经验选址更具科学性和准确性。
With China's rapid economic development, urbanization and urban expansion accelerated, however, city planning and rational distribution business to ensure the sound development of urban economy premise. As small and medium cities in population, city size and development of key industries and cities and so different, so, to determine the scale of commercial net sites and distribution are also different. For the current more than 600 small towns in China, its commercial net sites planning is not only necessary to establish its own development framework,and gradually form a reasonable sequence of land developmen, commercial networks have to pay attention to the unique nature of construction and planning,such as prominent local features and give full play to humanistic connotation of business center, which is also carrying out "scientific development, harmonical development" embodied. How scientific theories based on full use of the advantages of spatial information technology to research, analyze and manage network data and to provide a reasonable distribution of urban commercial network layout and planning, have become an urgent problem and a major challenge.GIS spatial data analysis and visualization of expression and decision support system data judgment,to compute the optimal solution and make the mutual integration of science and predictive power, the perfect solution to this problem.
Firstly, from the impact of small city commercial network site factors, we compared small and medium cities and major cities in net sites’similarities and differences, and by way of expert advice to establish site factors and weight. The selection process is composed by two major parts----roughing and cocentration, the roughing process involves public transport convenience, road accessibility, the five factors of population estimates of the acquisition and operation; Concentration is selected on the basis of rough K-Means clustering based on the particle search algorithm. Finally, the use of AO + VB secondary development model, "small urban commercial network site Decision Support System". In a word, the main work and innovations in this article are done as follows:
(1)Recent relevant studies in the construction of our network status in the town and country planning for medium and small urban commercial development an important directives,proposed the establishment of municipal, regional and community level of three levels of commercial network layout framework and roughing, contration technology line.
(2)Comparison of small and medium cities and major cities in the factors affecting network similarities and differences,both qualitative and quantitative analysis methods, the establishment of influencing factors and the role of each factor score were calculated.
(3)Discussion by high-resolution images in the local architectural features strong,, residents of small cities scattered distribution of population in urban areas for data acquisition and error analysis of the idea. The results show that the improved method of land use density of population estimates, the data accuracy can be applied to municipal and regional commercial network site area, and community-level population data because of its small size area can be obtained by field survey.
(4)The K-Means cluster analysis algorithm into particles, while a "window" search method in the optimal position roughing region search, and location of Kaifeng City Commercial outlets empirical case study, simulation results with reality.
(5)To Geodatabase based on small urban commercial network site development decision support system, the system covers five functions,including the data editing, vector data processing,raster data processing, PSO selected site operations and thematic map output function, while human-friendly interface and of operation allows the user to easily query various factors and the net site operation.
Obtained through the above study, based on theories and the location of small city commercial network decision support system, combined with previous experience in commercial network site search results,with a strong operational.The system realizes the location of small city commercial network automation and intelligence with computer network data and network element data, and the construction of various types of data storage table is not only beneficial to the new network of query and analysis,is more conducive to the network later management and construction planning, compared to traditional operations and human experience,drawing more scientific and accurate location.
本文首先从影响中小城市商业网点选址的因子因素入手,对比分析中小城市网点选址与大城市网点选址的相似性和差异性,并通过专家咨询等方式确立选址影响因素及其权重。整个选址过程由粗选和精选两大部分构成,粗选过程涉及到公交便捷度、道路通达性、人口估算等五个影响因素的获取和运算;精选址是在粗选的基础上采用基于K-Means聚类的粒子对搜索算法确定。最后,采用AO+VB二次开发方式,进行“中小城市商业网点选址决策支持系统”开发。文章的主要工作和创新点如下:
(1)查阅国内外相关研究,针对我国中小城网点建设现状及国家对中小城市商业发展规划的重要指示,提出建立市级、区域级和社区级三个级别的商业网点布局框架和粗选、精选技术路线。
(2)对比分析中小城市和大城市网点建设影响因素相似性和差异性,采用定性和定量分析相结合的方法,确立影响因素,并对各影响因素进行作用分值计算。
(3)讨论通过高分辩率遥感影像在地方建筑特色浓厚、居民地分布零散的中小城市城区进行人口数据获取的思路和误差分析方法。结果表明,采用改进的土地利用密度法进行人口估算,其数据精度满足商业网点选址的需要。
(4)把K-Means聚类分析法引入粒子对算法,同时采用“窗口“搜索方法在粗选区域进行最优位置搜索,并以开封市商业网点选址为例实证研究,模拟结果与现实相符。
(5)以Geodatabase数据库为基础,开发中小城市商业网点选址决策支持系统,系统涵盖了数据编辑、矢量数据处理、栅格数据处理、PSO精选址操作和专题图输出五大功能,同时,友好界面及人性化操作使用户可以方便的进行各种影响因素的查询及网点选址操作。
通过以上研究得出,建立在相关理论基础上的中小城市商业网点选址决策支持系统,结合了以往商业网点选址工作的经验成果,具备了较强的操作性。本系统实现了中小城市商业网点选址的自动化和智能化,用计算机处理网点数据和网点因素数据,并对各类数据建表入库,不但有利于新建网点的查询分析,更利于后期的网点规划管理和建设布局,相比传统的图纸操作和人为经验选址更具科学性和准确性。
With China's rapid economic development, urbanization and urban expansion accelerated, however, city planning and rational distribution business to ensure the sound development of urban economy premise. As small and medium cities in population, city size and development of key industries and cities and so different, so, to determine the scale of commercial net sites and distribution are also different. For the current more than 600 small towns in China, its commercial net sites planning is not only necessary to establish its own development framework,and gradually form a reasonable sequence of land developmen, commercial networks have to pay attention to the unique nature of construction and planning,such as prominent local features and give full play to humanistic connotation of business center, which is also carrying out "scientific development, harmonical development" embodied. How scientific theories based on full use of the advantages of spatial information technology to research, analyze and manage network data and to provide a reasonable distribution of urban commercial network layout and planning, have become an urgent problem and a major challenge.GIS spatial data analysis and visualization of expression and decision support system data judgment,to compute the optimal solution and make the mutual integration of science and predictive power, the perfect solution to this problem.
Firstly, from the impact of small city commercial network site factors, we compared small and medium cities and major cities in net sites’similarities and differences, and by way of expert advice to establish site factors and weight. The selection process is composed by two major parts----roughing and cocentration, the roughing process involves public transport convenience, road accessibility, the five factors of population estimates of the acquisition and operation; Concentration is selected on the basis of rough K-Means clustering based on the particle search algorithm. Finally, the use of AO + VB secondary development model, "small urban commercial network site Decision Support System". In a word, the main work and innovations in this article are done as follows:
(1)Recent relevant studies in the construction of our network status in the town and country planning for medium and small urban commercial development an important directives,proposed the establishment of municipal, regional and community level of three levels of commercial network layout framework and roughing, contration technology line.
(2)Comparison of small and medium cities and major cities in the factors affecting network similarities and differences,both qualitative and quantitative analysis methods, the establishment of influencing factors and the role of each factor score were calculated.
(3)Discussion by high-resolution images in the local architectural features strong,, residents of small cities scattered distribution of population in urban areas for data acquisition and error analysis of the idea. The results show that the improved method of land use density of population estimates, the data accuracy can be applied to municipal and regional commercial network site area, and community-level population data because of its small size area can be obtained by field survey.
(4)The K-Means cluster analysis algorithm into particles, while a "window" search method in the optimal position roughing region search, and location of Kaifeng City Commercial outlets empirical case study, simulation results with reality.
(5)To Geodatabase based on small urban commercial network site development decision support system, the system covers five functions,including the data editing, vector data processing,raster data processing, PSO selected site operations and thematic map output function, while human-friendly interface and of operation allows the user to easily query various factors and the net site operation.
Obtained through the above study, based on theories and the location of small city commercial network decision support system, combined with previous experience in commercial network site search results,with a strong operational.The system realizes the location of small city commercial network automation and intelligence with computer network data and network element data, and the construction of various types of data storage table is not only beneficial to the new network of query and analysis,is more conducive to the network later management and construction planning, compared to traditional operations and human experience,drawing more scientific and accurate location.
引文
[1]贾世东.中小城市商业网点的需求预测与布局规划研究――以山西省晋城市为例[D].北京:中国科学院科技政策与管理科学研究所.2005年.
[2]张文忠.经济区位论[M].北京:科学出版社, 2000.
[3] Syed Nasirin, David F. Birks. Geographical Information System(GIS)Success Factors Amongst UK Food Retailers: Comparisons Between Market Leaders and Followers. Proceeding of the Spatial Intormation Research Centre’s 10th Colloquium, 235-246,1998.
[4]孔云峰,林珲.地理信息系统在区域商业和经济中的应用初探[J].经济地理, 1999, 19(5):1-5.
[5]王家耀.关于地理信息系统与决策支持系统的探讨[J].测绘科学, 2003,3,28(1).
[6]杨香花. GIS辅助下的金融网点选址研究—以广州市农业银行网点布局调整为例[D].沈阳:东北师范大学, 2003, 12-15: 1-4.
[7]张超,王远飞,李治洪等.地理信息系统实习教程[M].北京:高等教育出版社, 2001.
[8]葛传滨.商业银行网点选址计算机专家系统初探[ J].中国金融电脑, 2001, (1): 72-75.
[9]杜端甫.运筹图论[M].北京:北京航空航天大学出版社会性, 1990.
[10]雷翔,走向制度化的城市规划决策[M],北京:中国建筑工业出版社,2003.
[11]杨瑛. 20年代以来西方国家商业空间学理论研究进展[J].热带地理, 2000年3月.
[12]崔丽丽,黄涛,王铮.数字城市中决策支持模型研究——以多元韦伯区位模型为例[J].遥感应用与技术,2001(12).
[13]伍少坤,黎夏,刘小平,龚友夫.基于城市扩张的动态选址模型———以深圳垃圾转运站选址为例[J].地理科学, 2008年6月, 28(3).
[14]张伟,刘纯波,周廷刚,黎雯.基于GIS与遥感影像的银行ATM机网点选址方法研究[J].测绘科学, 2007年1月, 32(1).
[15]刘娜,徐京华.基于GIS的商业网点选址研究与实现[J].四川测绘, 2005,6,28(2).
[16]朱轶群. GIS与模糊数学理论在商服中心空间选址中的应用[J].地理空间信息, 2006年2月,4(1).
[17]杜娟,卢潇,焦宁. GIS和RBF网络在直升机机降点选址分析中的应用[C].电脑知识与技术, 120-121.
[18] Hedia Chakroun Goze B,Benie Norman T,O’Neill Jacques Desilets.Spatial analysis weighting algorithm using voronoi diagrams[J]. Geographical Information Science,2000,14(4):319 ~ 336
[19] Okabe A,Boots B,Sugihara K.Nearest neighbor operations with generalize voronoi diagram:A review[J]. International Journal of Geographical Information Systems.1994,8(1):43– 71.
[20]曾文,徐世文.地理信息系统中的常规网络分析功能及相关算法[J].中国地质大学学报(地球科学),1998,23(4):355 -358.
[21] Robert Haining.Designing an health needs GIS with spatial analysis capability[A].In:Massimocraglia,helen couclelis,eds,geographic informationresearch,bridging theatlantic[C].Taylor&Francis,1996,87-113.
[22] ArentzeT,Borgers A,Timmermans H.A knowledge-based system for developing retail location strategies[J]. Computers,Environment and UrbanSystems,2000,(24):489–508.
[23]蔡力群.城市勘测技术成就与展望. URL:http://www.chinacon.com.cn/50year/f105.htm.
[24]高学东,李宗元.物流中心选址模型及一种启发式算法[J].运筹与管理,1994,11(3-4).
[25]龚国华,龚益鸣.生产与运营管理-制造业和服务业[M].上海:复旦大学出版社, 1998.
[26] Reynolds. Flocks,herds,and schools;A distributed behavioral model.Computer Graphic,1987,21(4):25-34.
[27] Boyd R,Recharson P. Culture and the evolutionary process. Chicago:University of Chicago Press,1985.
[28] Kennedy J,Eberhart R. Particle swarm optimization. Proceedings of IEEE International Conference on Neural Networks,Piscataway :IEEE Service Center ,1995,1942-1948.
[29] Shi Y,Eberhart RC. A modified particle swarm optimizer. Proceedings of IEEE International Conference on Evolutionary Computation, Anchorage,1998,69-73.
[30] Mendes R,Kennedy J. The full informed particle swarm: Simpler,maybe better. IEEE Transaction on Evolutionary Computation,2004,8(3):204-210.
[31] Angeline P J. Using selection to improve particle swarm optimization. Proceeding of the 2003 Congress on Evolutionary Computation,Piscataway :IEEEPress ,199:84-89.
[32] Shi,Eberhart RC.A modified particle swarm optimizer.Proceedings of IEEE International Conference on Evolutionary Computation,Anchorage ,1998,69-73.
[33] Mac Queen JB. Some methods for classification and analysis of multivariate observations. Proceedings of 5th Berkeley Symposium on Mathematical Statistics and Probability,Berkeley:University of California Press,1:281-297.
[34] Yeung K Y,Huges JD,Campbell M J. Systematic determiation of genetic network architecture. Nature Genetics,1999,22(3):281-285
[35]纪震,廖惠连,张宏基.基于人工蚁群优化的矢量量化码书设计算法.电子学报,2004,32(3):1082-1085.
[36]付朋辉,康立山.用多目标演化算法解决约束选址问题[J].计算机工程与设计, 2003, 24(13):1-3.
[37] DASP, Chakrabarty N R. Minimax Location for an arbitrary shaped constrained region using the rectilinear norm[J]. Asia-Pacific Journal of Operational Research, 1994,11(2):107-206.
[38]马良,蒋馥.约束多目标选址问题及其算法[J].运筹与管理, 1998, 7(2):7-12.53.
[39] Clerc M. The swarm and the queen: Towards a deterministic and adaptive particle swarmoptimization. Proceedings of the Congress of Evolutionary Computation ,Washington,1999:1951-1957.54.
[40] Yang S, Wang M ,Jiao L. A quantum particle swarm optimization. Proceeding of the 2004 IEEE Congress on Evolutionary Computation ,2004,1:320-324.
[41]高鹰,谢胜利.混沌粒子群优化算法[M].北京:计算机科学, 2004, 31(8): 13-15.
[42]高鹰,谢胜利.基于模拟退火的粒子群优化算法[J].计算机工程与应用, 2004, 1:47-50.
[43]何春阳,史培军,李景刚等.基于DMSP/0LS夜间灯光数据和统计数据的中国大陆20世纪90年代城市化空间过程重建研究[J].科学通报,2006,51(7):856-861.
[44] Fisher P F,Langford M.Modeling the errors in areal interpolation between zonal systems by Monte Carlo simulation[J].Environment and Planning,1995,A 27:21l-224.
[45] Sautton P.Modeling population density with night—times satellite imagery and GIS[J].Comput,Environ,and Urban System,1998,21(3/4):227-244.
[46] David R.Satellite-measuredg growth of the urban heat island of Houston,Tesas[J].Remote Sensing of Environment,2003,85:282-289.
[47] Langford M,Maguire D J,Unwin D J.The areal interpolation problem:estimating population using remote sensing in a GIS framework.In:Masser I,Blakemore M(eds.),Handling Geographical Information,55-77.London:Longman,1991.
[48]卓莉,陈晋,史培军等.基于夜间灯光数据的中国人口密度模拟[J].地理学报,2005, 60(2):266-276.
[49] Wang HH.City population estimation method with satellite imagery.Remote Sensing Technology,1990,(3):48-54.
[50]王发曾.城市人口估算——多光谱遥感影象分析[J].城市环境与城市生态,1990,3(3):33-34.
[51]秦奋,钱乐祥.地理信息系统原理与方法[M].陕西:西安地图出版社,2005.
[52]袁小群,梁虹,刘蕊.基于Arcobject的GeodatabaLse数据导入方法与实现[J].昆明理工大学学报,2005,30(5A):366—369.
[53]陈静,张树文.面向对象空间数据模型——Ge僦aSe及其实现[J].国土与自然资源研究,2003(5):44-46.
[54]叶嘉安,宋小冬,钮心毅,等.地理信息与规划支持系统[M].北京:科学出版社, 2006
[55]龚纯伟,基于ArcObjectS的地理信息系统二次开发与实现——以洱海流域地理信息系统为例[D].昆明:昆明理工大学,2005.
[56]蒋波涛.ArcobjectS开发基础与技巧[M],武汉:武汉大学出版社,2006.
[57]黄猛.ArcGISEngine组件在水土保持决策支持系统开发中的应用研究[D].长春:东北师范大学,2007.
[58] Kennedy J,Eberhart R C.Particle swarm optimiza-tion[A].Proceedings of the 1995 IEEE International Conference on Neural Networks[C].Piscataway NJ:IEEE Press,1995.1942-1948.
[59]杨维,李歧强.粒子群优化算法综述[J].中国工程科学,2004,6(5):87-94. YANG Wei,LI Qi-qiang.Survey on particle swarm optimization algorithm [ J]. Engineering Science,2004,6(5):87-94.
[60] Luis G,Acosta E,Roberto D G.Dual-based heuris-tics for a hierarchical covering location problem [J].Computer and Operations Research,2003,(30):65-180.
[2]张文忠.经济区位论[M].北京:科学出版社, 2000.
[3] Syed Nasirin, David F. Birks. Geographical Information System(GIS)Success Factors Amongst UK Food Retailers: Comparisons Between Market Leaders and Followers. Proceeding of the Spatial Intormation Research Centre’s 10th Colloquium, 235-246,1998.
[4]孔云峰,林珲.地理信息系统在区域商业和经济中的应用初探[J].经济地理, 1999, 19(5):1-5.
[5]王家耀.关于地理信息系统与决策支持系统的探讨[J].测绘科学, 2003,3,28(1).
[6]杨香花. GIS辅助下的金融网点选址研究—以广州市农业银行网点布局调整为例[D].沈阳:东北师范大学, 2003, 12-15: 1-4.
[7]张超,王远飞,李治洪等.地理信息系统实习教程[M].北京:高等教育出版社, 2001.
[8]葛传滨.商业银行网点选址计算机专家系统初探[ J].中国金融电脑, 2001, (1): 72-75.
[9]杜端甫.运筹图论[M].北京:北京航空航天大学出版社会性, 1990.
[10]雷翔,走向制度化的城市规划决策[M],北京:中国建筑工业出版社,2003.
[11]杨瑛. 20年代以来西方国家商业空间学理论研究进展[J].热带地理, 2000年3月.
[12]崔丽丽,黄涛,王铮.数字城市中决策支持模型研究——以多元韦伯区位模型为例[J].遥感应用与技术,2001(12).
[13]伍少坤,黎夏,刘小平,龚友夫.基于城市扩张的动态选址模型———以深圳垃圾转运站选址为例[J].地理科学, 2008年6月, 28(3).
[14]张伟,刘纯波,周廷刚,黎雯.基于GIS与遥感影像的银行ATM机网点选址方法研究[J].测绘科学, 2007年1月, 32(1).
[15]刘娜,徐京华.基于GIS的商业网点选址研究与实现[J].四川测绘, 2005,6,28(2).
[16]朱轶群. GIS与模糊数学理论在商服中心空间选址中的应用[J].地理空间信息, 2006年2月,4(1).
[17]杜娟,卢潇,焦宁. GIS和RBF网络在直升机机降点选址分析中的应用[C].电脑知识与技术, 120-121.
[18] Hedia Chakroun Goze B,Benie Norman T,O’Neill Jacques Desilets.Spatial analysis weighting algorithm using voronoi diagrams[J]. Geographical Information Science,2000,14(4):319 ~ 336
[19] Okabe A,Boots B,Sugihara K.Nearest neighbor operations with generalize voronoi diagram:A review[J]. International Journal of Geographical Information Systems.1994,8(1):43– 71.
[20]曾文,徐世文.地理信息系统中的常规网络分析功能及相关算法[J].中国地质大学学报(地球科学),1998,23(4):355 -358.
[21] Robert Haining.Designing an health needs GIS with spatial analysis capability[A].In:Massimocraglia,helen couclelis,eds,geographic informationresearch,bridging theatlantic[C].Taylor&Francis,1996,87-113.
[22] ArentzeT,Borgers A,Timmermans H.A knowledge-based system for developing retail location strategies[J]. Computers,Environment and UrbanSystems,2000,(24):489–508.
[23]蔡力群.城市勘测技术成就与展望. URL:http://www.chinacon.com.cn/50year/f105.htm.
[24]高学东,李宗元.物流中心选址模型及一种启发式算法[J].运筹与管理,1994,11(3-4).
[25]龚国华,龚益鸣.生产与运营管理-制造业和服务业[M].上海:复旦大学出版社, 1998.
[26] Reynolds. Flocks,herds,and schools;A distributed behavioral model.Computer Graphic,1987,21(4):25-34.
[27] Boyd R,Recharson P. Culture and the evolutionary process. Chicago:University of Chicago Press,1985.
[28] Kennedy J,Eberhart R. Particle swarm optimization. Proceedings of IEEE International Conference on Neural Networks,Piscataway :IEEE Service Center ,1995,1942-1948.
[29] Shi Y,Eberhart RC. A modified particle swarm optimizer. Proceedings of IEEE International Conference on Evolutionary Computation, Anchorage,1998,69-73.
[30] Mendes R,Kennedy J. The full informed particle swarm: Simpler,maybe better. IEEE Transaction on Evolutionary Computation,2004,8(3):204-210.
[31] Angeline P J. Using selection to improve particle swarm optimization. Proceeding of the 2003 Congress on Evolutionary Computation,Piscataway :IEEEPress ,199:84-89.
[32] Shi,Eberhart RC.A modified particle swarm optimizer.Proceedings of IEEE International Conference on Evolutionary Computation,Anchorage ,1998,69-73.
[33] Mac Queen JB. Some methods for classification and analysis of multivariate observations. Proceedings of 5th Berkeley Symposium on Mathematical Statistics and Probability,Berkeley:University of California Press,1:281-297.
[34] Yeung K Y,Huges JD,Campbell M J. Systematic determiation of genetic network architecture. Nature Genetics,1999,22(3):281-285
[35]纪震,廖惠连,张宏基.基于人工蚁群优化的矢量量化码书设计算法.电子学报,2004,32(3):1082-1085.
[36]付朋辉,康立山.用多目标演化算法解决约束选址问题[J].计算机工程与设计, 2003, 24(13):1-3.
[37] DASP, Chakrabarty N R. Minimax Location for an arbitrary shaped constrained region using the rectilinear norm[J]. Asia-Pacific Journal of Operational Research, 1994,11(2):107-206.
[38]马良,蒋馥.约束多目标选址问题及其算法[J].运筹与管理, 1998, 7(2):7-12.53.
[39] Clerc M. The swarm and the queen: Towards a deterministic and adaptive particle swarmoptimization. Proceedings of the Congress of Evolutionary Computation ,Washington,1999:1951-1957.54.
[40] Yang S, Wang M ,Jiao L. A quantum particle swarm optimization. Proceeding of the 2004 IEEE Congress on Evolutionary Computation ,2004,1:320-324.
[41]高鹰,谢胜利.混沌粒子群优化算法[M].北京:计算机科学, 2004, 31(8): 13-15.
[42]高鹰,谢胜利.基于模拟退火的粒子群优化算法[J].计算机工程与应用, 2004, 1:47-50.
[43]何春阳,史培军,李景刚等.基于DMSP/0LS夜间灯光数据和统计数据的中国大陆20世纪90年代城市化空间过程重建研究[J].科学通报,2006,51(7):856-861.
[44] Fisher P F,Langford M.Modeling the errors in areal interpolation between zonal systems by Monte Carlo simulation[J].Environment and Planning,1995,A 27:21l-224.
[45] Sautton P.Modeling population density with night—times satellite imagery and GIS[J].Comput,Environ,and Urban System,1998,21(3/4):227-244.
[46] David R.Satellite-measuredg growth of the urban heat island of Houston,Tesas[J].Remote Sensing of Environment,2003,85:282-289.
[47] Langford M,Maguire D J,Unwin D J.The areal interpolation problem:estimating population using remote sensing in a GIS framework.In:Masser I,Blakemore M(eds.),Handling Geographical Information,55-77.London:Longman,1991.
[48]卓莉,陈晋,史培军等.基于夜间灯光数据的中国人口密度模拟[J].地理学报,2005, 60(2):266-276.
[49] Wang HH.City population estimation method with satellite imagery.Remote Sensing Technology,1990,(3):48-54.
[50]王发曾.城市人口估算——多光谱遥感影象分析[J].城市环境与城市生态,1990,3(3):33-34.
[51]秦奋,钱乐祥.地理信息系统原理与方法[M].陕西:西安地图出版社,2005.
[52]袁小群,梁虹,刘蕊.基于Arcobject的GeodatabaLse数据导入方法与实现[J].昆明理工大学学报,2005,30(5A):366—369.
[53]陈静,张树文.面向对象空间数据模型——Ge僦aSe及其实现[J].国土与自然资源研究,2003(5):44-46.
[54]叶嘉安,宋小冬,钮心毅,等.地理信息与规划支持系统[M].北京:科学出版社, 2006
[55]龚纯伟,基于ArcObjectS的地理信息系统二次开发与实现——以洱海流域地理信息系统为例[D].昆明:昆明理工大学,2005.
[56]蒋波涛.ArcobjectS开发基础与技巧[M],武汉:武汉大学出版社,2006.
[57]黄猛.ArcGISEngine组件在水土保持决策支持系统开发中的应用研究[D].长春:东北师范大学,2007.
[58] Kennedy J,Eberhart R C.Particle swarm optimiza-tion[A].Proceedings of the 1995 IEEE International Conference on Neural Networks[C].Piscataway NJ:IEEE Press,1995.1942-1948.
[59]杨维,李歧强.粒子群优化算法综述[J].中国工程科学,2004,6(5):87-94. YANG Wei,LI Qi-qiang.Survey on particle swarm optimization algorithm [ J]. Engineering Science,2004,6(5):87-94.
[60] Luis G,Acosta E,Roberto D G.Dual-based heuris-tics for a hierarchical covering location problem [J].Computer and Operations Research,2003,(30):65-180.