基于数据挖掘的兵棋推演数据分析方法研究
|
摘要
计算机兵棋系统具备节省训练经费、不受场地限制、接近真实体验等优点，是和平时期战略战役指挥能力训练的有效途径，其发展也越来越受到国内外的重视。对推演数据进行分析是计算机兵棋系统中的一个重要组成部分，可以帮助指挥员找出推演过程中发挥的长处和暴露的不足，充分发挥计算机兵棋系统在指挥能力培养和作战理论探索上的优势；而同时，计算机兵棋系统的大规模、多尺度、高复杂性等特点决定了对推演数据进行分析又是一个难点问题。本文正是在这一背景下，以大型计算机兵棋系统的军事需求为牵引，提出了基于数据挖掘的数据分析方法，论文研究成果可归纳如下：
（1）考虑到兵棋系统结构的复杂性和高性能的运行要求，以及兵棋数据的多样性和大规模性，在分析兵棋系统数据特点的基础上，描述了三种兵棋数据结构，提出了兵棋数据的采集原则，定义了七种基本采集模式，然后根据这些采集模式系统分析和比较了当前主要的采集方法和技术的优缺点及其适用范围，满足了兵棋系统在不同开发阶段的采集需求；提出了三种基于文件的兵棋推演数据存储策略，并依据时空复杂度计算方法对存储策略的访问和存储效率进行了对比分析，较好地解决了高效的数据存储需求等开发与应用中的一些实际问题。
（2）为了能够快速有效地检测兵棋推演过程中对抗各方在兵力部署上的缺陷，以节省指挥员分析战场态势的时间，使其有更多的精力花在施计用谋和排兵布阵上，提出了一种基于密度的QDBSCAN算法。QDBSCAN算法对传统的DBSCAN算法做了一些改进：①在邻近度度量上提出了最短可行路径的概念，使聚类更符合计算机兵棋的规则；②动态设置密度参数，不仅参数的设置方式让指挥员容易接受，同时也使算法的结果更能被指挥员所理解；③采用提出的代表对象选择方法来减少对对象邻域的判断次数，并按区域对数据进行分组，在缩小聚类规模的同时也减少了最短可行路径的计算时间，进一步提高了算法的效率。实验表明，QDBSCAN算法的性能在数据规模较大的情况下，明显优于DBSCAN算法。
（3）通过热区定位，可以帮助指挥员整体审视战场态势，辅助分析对抗方的作战意图。针对计算机兵棋地图和推演数据的特点，结合图论的思想，提出了一种基于连通树的热区检测算法，可检测任意形状的热区。首先从数学的角度明确了热区相关的几个定义，并证明了热区存在于每个最小化分的连通区域中。在此基础上，提出了先构建连通树将数据集按连通区域进行最小划分，再对每棵连通子树进行剪枝处理。通过调整密度阈值可以改变指挥员的观察视角，以适合不同层次指挥员的需要。理论和实验结果均表明了算法的有效性。
（4）通过轨迹聚类可以发现兵棋推演作战实体之间的整体行为模式，进而可以辅助判断指挥员的作战意图。因此，在充分分析作战实体轨迹数据特点的基础上，提出了计算机兵棋作战实体轨迹聚类CTECW算法。整个算法由三个部分组成：轨迹预处理，轨迹分段聚类以及可视化表现。在轨迹预处理阶段，先将实体原始轨迹转化成实体简化轨迹，再进一步处理成轨迹分段；在轨迹分段聚类阶段，引入了DENCLUE算法中密度函数的概念，并基于DBSCAN算法的基本框架采用提出的相似性度量函数对轨迹分段进行聚类，并对参数的优选设置进行了讨论；在可视化表现阶段，将轨迹分段聚类的结果以赋有军事涵义的形式展现给指挥员，使得指挥员对聚类的结果更容易理解和接受。理论和实验结果均表明了算法的有效性。
（5）在分析了数据挖掘系统的发展以及主流数据挖掘系统的体系结构和功能的基础上，设计并实现了基于数据挖掘技术的兵棋推演数据分析原型系统。
In peacetime, the computer wargame is one of the most suitable tools for higherlevels of military command training due to its superiority in terms of money, amount ofsubordinate troops required, land use and approximative realistic experience. And itsdevelopment is receiving increased emphasis. As an important component of thecomputer wargame, analyzing wargaming data can help commanders to findstrongpoints or weakness exploited in the wargaming process, improving its effect inmilitary command training and operation theories exploration. At the same time,analyzing wargaming data is also a difficult problem because of that the computerwargame possesses such characteristics as large-scope, multi-scale, high complexity,and so on. It is under such background that the author effectively studies thecorresponding martial requirements of the computer wargame and proposes some dataanalysis methods based on data mining, the achievements of this dissertation can beconcluded as follows:
(1) Considing the complex structure and high running performance of the computerwargame as well as the diversity and massiveness of wargaming data, based on studyingthe characters of the wargaming data, the author describes three kinds of wargamingdata structure, proposes data collection principles, defines seven basic collection modes,and then analyses forth and compares the merits and defects of current main datacollection methods and technologies and their applicability according to those definedcollection modes, which meets data collection requiements at various developmentstages. Besides that, to solve some practical problems such as efficient data storageneeds in the development and applications of the computer wargame, we provide threedata storage policies based on files and their efficiencies of access and storage arecomparatively analysed using the spatial-temporal complexity computing method.
(2) A clustering algorithm named QDBSCAN is proposed for determining thevulnerability of units’ deployment rapidly by detecting the isolated units in order to savethe time consumed by commaders for analysing the battlefield situation in thewargaming process. Compared with DBSCAN, QDBSCAN made some improvementsin such aspects:①defined the shortest viable path as the similarity measurement tomake the clustering algorithm more coincident with the rules of computer wargames;②set the density parameters dynamically instead of statically;③chose a small numberof representative objects to expand the cluster so that the execution frequency of regionquery was reduced and grouped the whole dataset by divisiory regions in order toreduce the scale of clustering and ulteriorly enhance the efficiency of the algorithm.Experimental results indicate that QDBSCAN is more effective and efficient thanDBSCAN in clustering large datasets.
(3) A hotspot detection algorithm based on connected tree is proposed, which iscapable of detecting arbitrarily shaped hotspots during the wargaming process. Bydetecting the areas with high concentrations of martial events, this algorithm couldassist commaders understanding the whole wargaming battlefield situation andconjecturing the intent of opponents. After making the definition of a hotspot, aconnected tree is built in order to least divide the whole dataset into connected regions,and a pruning procedure is carried out according to the provided density threshold value.Each pruned connected subtree is a hotspot which we would like to acquire. Throughadjusting the density threshold, commanders with different levels can chooseappropriate observational views. Both the theoretical analysis and experimental resultsverify the effectiveness of the algorithm.
(4) By clustering trajectories of the wargame entities, we may find their holisticbehavioral patterns which could help commanders estimate the intent of their opponents.Thereby, in allusion to the characters of trajectory data of the wargame entities atrajectory clustering algorithm named CTECW is proposed. This algorithm is composedof three parts: trajectory pretreatment, trajectory segments clustering and visualpresentation. Trajectory pretreatment transforms original trajectories into simplifiedones which are ulteriorly processed into linear segments. In the second part, the conceptof density function derived from DENCLUE is introduced and trajectory segments areclustered based on our own similarity measure under the framework of DBSCAN.Moreover, how to choose optimal parameters is discussed detailedly. Visualpresentation exhibits clustering results with martial meanings which can be easilycomprehended by commanders. Both the theoretical analysis and experimental resultsverify the effectiveness of the algorithm.
(5) After analysing the development of the data mining system as well asarchitectures and functions of main data mining systems, a wargame data analysisprototype system based on data mining is designed.
（1）考虑到兵棋系统结构的复杂性和高性能的运行要求，以及兵棋数据的多样性和大规模性，在分析兵棋系统数据特点的基础上，描述了三种兵棋数据结构，提出了兵棋数据的采集原则，定义了七种基本采集模式，然后根据这些采集模式系统分析和比较了当前主要的采集方法和技术的优缺点及其适用范围，满足了兵棋系统在不同开发阶段的采集需求；提出了三种基于文件的兵棋推演数据存储策略，并依据时空复杂度计算方法对存储策略的访问和存储效率进行了对比分析，较好地解决了高效的数据存储需求等开发与应用中的一些实际问题。
（2）为了能够快速有效地检测兵棋推演过程中对抗各方在兵力部署上的缺陷，以节省指挥员分析战场态势的时间，使其有更多的精力花在施计用谋和排兵布阵上，提出了一种基于密度的QDBSCAN算法。QDBSCAN算法对传统的DBSCAN算法做了一些改进：①在邻近度度量上提出了最短可行路径的概念，使聚类更符合计算机兵棋的规则；②动态设置密度参数，不仅参数的设置方式让指挥员容易接受，同时也使算法的结果更能被指挥员所理解；③采用提出的代表对象选择方法来减少对对象邻域的判断次数，并按区域对数据进行分组，在缩小聚类规模的同时也减少了最短可行路径的计算时间，进一步提高了算法的效率。实验表明，QDBSCAN算法的性能在数据规模较大的情况下，明显优于DBSCAN算法。
（3）通过热区定位，可以帮助指挥员整体审视战场态势，辅助分析对抗方的作战意图。针对计算机兵棋地图和推演数据的特点，结合图论的思想，提出了一种基于连通树的热区检测算法，可检测任意形状的热区。首先从数学的角度明确了热区相关的几个定义，并证明了热区存在于每个最小化分的连通区域中。在此基础上，提出了先构建连通树将数据集按连通区域进行最小划分，再对每棵连通子树进行剪枝处理。通过调整密度阈值可以改变指挥员的观察视角，以适合不同层次指挥员的需要。理论和实验结果均表明了算法的有效性。
（4）通过轨迹聚类可以发现兵棋推演作战实体之间的整体行为模式，进而可以辅助判断指挥员的作战意图。因此，在充分分析作战实体轨迹数据特点的基础上，提出了计算机兵棋作战实体轨迹聚类CTECW算法。整个算法由三个部分组成：轨迹预处理，轨迹分段聚类以及可视化表现。在轨迹预处理阶段，先将实体原始轨迹转化成实体简化轨迹，再进一步处理成轨迹分段；在轨迹分段聚类阶段，引入了DENCLUE算法中密度函数的概念，并基于DBSCAN算法的基本框架采用提出的相似性度量函数对轨迹分段进行聚类，并对参数的优选设置进行了讨论；在可视化表现阶段，将轨迹分段聚类的结果以赋有军事涵义的形式展现给指挥员，使得指挥员对聚类的结果更容易理解和接受。理论和实验结果均表明了算法的有效性。
（5）在分析了数据挖掘系统的发展以及主流数据挖掘系统的体系结构和功能的基础上，设计并实现了基于数据挖掘技术的兵棋推演数据分析原型系统。
In peacetime, the computer wargame is one of the most suitable tools for higherlevels of military command training due to its superiority in terms of money, amount ofsubordinate troops required, land use and approximative realistic experience. And itsdevelopment is receiving increased emphasis. As an important component of thecomputer wargame, analyzing wargaming data can help commanders to findstrongpoints or weakness exploited in the wargaming process, improving its effect inmilitary command training and operation theories exploration. At the same time,analyzing wargaming data is also a difficult problem because of that the computerwargame possesses such characteristics as large-scope, multi-scale, high complexity,and so on. It is under such background that the author effectively studies thecorresponding martial requirements of the computer wargame and proposes some dataanalysis methods based on data mining, the achievements of this dissertation can beconcluded as follows:
(1) Considing the complex structure and high running performance of the computerwargame as well as the diversity and massiveness of wargaming data, based on studyingthe characters of the wargaming data, the author describes three kinds of wargamingdata structure, proposes data collection principles, defines seven basic collection modes,and then analyses forth and compares the merits and defects of current main datacollection methods and technologies and their applicability according to those definedcollection modes, which meets data collection requiements at various developmentstages. Besides that, to solve some practical problems such as efficient data storageneeds in the development and applications of the computer wargame, we provide threedata storage policies based on files and their efficiencies of access and storage arecomparatively analysed using the spatial-temporal complexity computing method.
(2) A clustering algorithm named QDBSCAN is proposed for determining thevulnerability of units’ deployment rapidly by detecting the isolated units in order to savethe time consumed by commaders for analysing the battlefield situation in thewargaming process. Compared with DBSCAN, QDBSCAN made some improvementsin such aspects:①defined the shortest viable path as the similarity measurement tomake the clustering algorithm more coincident with the rules of computer wargames;②set the density parameters dynamically instead of statically;③chose a small numberof representative objects to expand the cluster so that the execution frequency of regionquery was reduced and grouped the whole dataset by divisiory regions in order toreduce the scale of clustering and ulteriorly enhance the efficiency of the algorithm.Experimental results indicate that QDBSCAN is more effective and efficient thanDBSCAN in clustering large datasets.
(3) A hotspot detection algorithm based on connected tree is proposed, which iscapable of detecting arbitrarily shaped hotspots during the wargaming process. Bydetecting the areas with high concentrations of martial events, this algorithm couldassist commaders understanding the whole wargaming battlefield situation andconjecturing the intent of opponents. After making the definition of a hotspot, aconnected tree is built in order to least divide the whole dataset into connected regions,and a pruning procedure is carried out according to the provided density threshold value.Each pruned connected subtree is a hotspot which we would like to acquire. Throughadjusting the density threshold, commanders with different levels can chooseappropriate observational views. Both the theoretical analysis and experimental resultsverify the effectiveness of the algorithm.
(4) By clustering trajectories of the wargame entities, we may find their holisticbehavioral patterns which could help commanders estimate the intent of their opponents.Thereby, in allusion to the characters of trajectory data of the wargame entities atrajectory clustering algorithm named CTECW is proposed. This algorithm is composedof three parts: trajectory pretreatment, trajectory segments clustering and visualpresentation. Trajectory pretreatment transforms original trajectories into simplifiedones which are ulteriorly processed into linear segments. In the second part, the conceptof density function derived from DENCLUE is introduced and trajectory segments areclustered based on our own similarity measure under the framework of DBSCAN.Moreover, how to choose optimal parameters is discussed detailedly. Visualpresentation exhibits clustering results with martial meanings which can be easilycomprehended by commanders. Both the theoretical analysis and experimental resultsverify the effectiveness of the algorithm.
(5) After analysing the development of the data mining system as well asarchitectures and functions of main data mining systems, a wargame data analysisprototype system based on data mining is designed.
引文
[1]董子峰．信息化战争形态论[M]．中国人民解放军出版社，2004.10．
[2]胡晓峰，司光亚等．战争模拟原理与系统[M]．国防大学出版社，2009．
[3]胡晓峰，司光亚．战争模拟引论(上、下)[M]．国防大学出版社，2004.3．
[4]戴国忠．兵棋推演与军事训练[C]．军队信息化建设与军事运筹研究（下册）—军事运筹学学会2009年学术年会论文集，2009．
[5]杨南征．虚拟演兵—兵棋、作战模拟与仿真[M]．解放军出版社，2007．
[6]胡晓峰．战争复杂系统仿真分析与实验[M]．国防大学出版社，2008.6．
[7]蔡益朝．态势评估中的兵力聚合技术研究[D]．国防科学技术大学．2006．
[8]张义宏，蒋晓原．基于信息优势的决策能力分析[J]．火力与指挥控制．2006，31(12):19-22．
[9]J. Hagelback，S.J. Johansson．Dealing with fog of war in a real time strategygame environment[C]．IEEE Symposium on Computational Intelligence and Games，2008，IEEE:55-62．
[10]韩家炜，坎伯．数据挖掘:概念与技术[M]．北京:机械工业出版社，2001．
[11]吕晓玲，谢邦昌．数据挖掘:方法与应用[M]．中国人民大学出版社，2009．
[12]纪希禹，韩秋明，李微，et al．数据挖掘技术应用实例[M]．机械工业出版社，2009．
[13]胡可云，田凤占，黄厚宽．数据挖掘理论与应用[M]．清华大学出版社，2008．
[14]U.M. Fayyad，G. Piatetsky-Shapiro，P. Smyth，et al．Advances in knowledgediscovery and data mining[M]，1996．
[15]G. Piatetsky-Shapiro．Knowledge discovery in real databases: A report on theIJCAI-89Workshop[J]．AI magazine．1990，11(4):68．
[16]E. Simoudis．Reality check for data mining[J]．IEEE Expert: Intelligentsystems and their applications．1996，11(5):26-33．
[17]Heikki Mannila．Methods and Problems in Data Mining[C]．Proceedings of the6th International Conference on Database Theory，1997．656095，Springer-Verlag:41-55．
[18]B.M. Thuraisingham． Data mining: technologies, techniques, tools, andtrends[M]．CRC，1999．
[19]J.F. Elder，D. Pregibon．A Statistical Perspective on Knowledge Discovery inDatabases[J]．1996．
[20]U. Fayyad，G. Piatetsky-Shapiro，P. Smyth．From data mining to knowledgediscovery in databases[J]．AI magazine．1996，17(3):37．
[21]朱建秋．数据挖掘系统发展综述[EB/OL]．http:∥www.dmgroup.org.cn/zhujianqiu/dmsystem.pdf．
[22]P. Chapman，J. Clinton，T. Khabaza，et al．The CRISP-DM processmodel[J]．The CRIP–DM Consortium．1999，310．
[23]D.S. Tkach．Information mining with the ibm intelligent miner family[J]．AnIBM Software Solutions White Paper．1998:1-29．
[24]J. Han，J.Y. Chiang，S. Chee，et al．DBMiner: A system for data mining inrelational databases and data warehouses[C]，1997，IBM Press:8．
[25]T. Khabaza，C. Shearer．Data mining with Clementine[C]，1995，IET:1/1-1/5．
[26]焦李成．智能数据挖掘与知识发现[M]．西安电子科技大学出版社，2006．
[27]何晓群，统计学．现代统计分析方法与应用[M]．中国人民大学出版社，1998．
[28]R. Agarwal，R. Srikant．Fast algorithms for mining association rules[C]．Proc.of the20th VLDB Conference，1994:487-499．
[29]刘莉，徐玉生，马志新．数据挖掘中数据预处理技术综述[J]．甘肃科学学报．2003，12(1):117-119．
[30]J. Gehrke，V. Ganti，R. Ramakrishnan，et al．BOAT—optimistic decision treeconstruction[C]．ACM SIGMOD Record，1999，ACM:169-180．
[31]M. Mehta，R. Agrawal，J. Rissanen．SLIQ: A fast scalable classifier for datamining[J]．Advances in Database Technology—EDBT'96．1996:18-32．
[32]I.P. Witten，E. Frank．数据挖掘:实用机器学习技术:英文版[M]．机械工业出版社，2005．
[33]陈文伟．数据仓库与数据挖掘教程[M]．清华大学出版社，2006．
[34]任永功，于戈．数据可视化技术的研究与进展[J]．计算机科学．2004，31(12):92-95．
[35]李德毅，杜鹢．不确定性人工智能[M]．国防工业出版社，2005．
[36]杨炳儒．基于内在机理的知识发现理论及其应用[M]．电子工业出版社，2004．
[37]徐慧英，赵建民，岑琴，et al．电子商务环境下基于Multi-Agent的数据挖掘系统[J]．计算机研究与发展．2006(z1):494-498．
[38]熊海亮，白振兴．一种基于多Agent的Web数据挖掘方法[J]．现代电子技术．2010，33(008):83-86．
[39]佟志臣，刘滨，王建军．面向CRM的基于Multi-Agent的数据挖掘模型研究[J]．河北工业科技．2009，26(005):311-314．
[40]毛国君．数据挖掘原理与算法[M]．清华大学出版社，2005．
[41]刘同明．数据挖掘技术及其应用[M]．国防工业出版社，2001．
[42]陈安，陈宁，周龙骧．数据挖掘技术及应用[M]．科学出版社，2006．
[43]B.A. Bodt．Urban Combat Data Mining[R]．Document, DTIC，2004:8．
[44]陈立潮，刘玉树，杨国胜，et al．炮兵阵地选取的空间数据挖掘模型研究[J]．北京理工大学学报．2002，22(4):469-472．
[45]金鑫，李元左．空间军事系统综合集成研讨厅中数据挖掘应用[J]．备指挥技术学院学报．2005，16(04):57-60．
[46]武玉红，刘毅勇．空间数据挖掘及其在军事领域的应用[J]．军事运筹与系统工程．2006，20(002):18-21．
[47]张文明，薛青．粗糙集方法在作战仿真数据挖掘中的应用[J]．系统仿真学报增刊．2006，18(2):179-181．
[48]周红梅，薛青．数据挖掘技术及其在装备作战仿真系统中的应用[J]．第五届全国仿真器学术会论文集．2004．
[49]P.P. Perla． The art of wargaming: a guide for professionals andhobbyists[M]．Naval Inst Pr，1990．
[50]朱元锋，李伟．兵棋经典实战运用大扫描[J]．环球军事．2008(012):41-44．
[51]李学军，王锐华．联合作战兵棋推演系统研究[J]．中国电子学会电子系统工程分会第五届军事信息软件与仿真学术研讨会论文集,北京:电子工业出版社．2006:16-19．
[52]彭春光，鞠儒生，杨建池，et al．现代兵棋推演技术分析[J]．系统仿真学报．2009，21(增刊2):97-100．
[53]韩志军，柳少军，唐宇波，et al．计算机兵棋推演系统公共数据的建模与VV&C研究[J]．系统仿真学报．2011，12．
[54]石崇林，张茂军，吴琳，et al．基于密度的计算机兵棋推演数据快速聚类算法[J]．系统工程与电子技术．2011，33(11):2428-2433．
[55]胡晓峰．美军训练模拟[M]．国防大学出版社，2001．
[56]金伟新．大型仿真系统[M]．电子工业出版社，2004．
[57]U.S.J.F. Command．JTLS Executive Overview[R]，2004．
[58]殷兴良．EADSIM仿真系统概况介绍[J]．现代防御技术．1993，2:47-52．
[59]陈丽，冯润明，姚益平．联合建模与仿真系统研究[J]．电光与控制．2007，14(4):10-12．
[60]V.K. Handley，PM Shea，M. Morano．An Introduction to the Joint Modelingand Simulation System (JMASS)[C]． Proceedings of the Fall2000SimulationInteroperability Workshop，Orlando FL，2000．
[61]李宁，赵存如．美军联合作战系统分析[J]．军事运筹与系统工程．2008，21(4):67-71．
[62]D.T. Maxwell． An Overview of The Joint Warfare System(JWARS)[J]．MORS Phalanx Magazine (S0023-1687)．2000，6(3):12-14．
[63]D. Zedo． Corps Battle Simulation[J]． PEOSTRI web site. RetrievedApril．2004，2:2004．
[64]P. Pike．Tactical Simulation (TACSIM)[J]．Retrieved Nov．2005，15:2005．
[65]R. Smith， G. Allen． After action review in military trainingsimulations[C]．Proceedings of the26th conference on Winter simulation，1994，Society for Computer Simulation International:845-849．
[66]R.W. Bennington． Joint Simulation System (JSIMS)-anoverview[C]． Proceedings of IEEE1995National Aerospace and ElectronicsConference，1995，IEEE:804-809vol.802．
[67]L. Budge，R. Strini，R. Dehncke，et al．Synthetic Theater of War (STOW)97Overview[C]．Simulation Interoperability Workshop，1998．
[68]赵沁平．分布式虚拟战场环境—现代战争的实验场[J]．系统仿真学报．2001，13(11):1-7．
[69]R.L. Wittman Jr． OneSAF: A product line approach to simulationdevelopment[R]，2001．
[70]R.L. Wittman，A.J. Courtemanche．The OneSAF Product Line Architecture:An Overview of the Products and Process[C]，2002，Citeseer．
[71]景民，胡晓峰，吴琳，et al．面向态势回放的两种海量数据采集存储结构分析[J]．系统仿真学报．2011，已录用．
[72]J.W. Gibson．After Action Review System (AARS) design and functionalcapabilities[C]．the27th conference on winter simulation，1995，IEEE ComputerSociety:1267-1273．
[73]J.A. Hixson．Battle command AAR methodology: a paradigm for effectivetraining[C]． Proceedings of the27th conference on winter simulation，1995，IEEE:1274-1279．
[74]P. Lane，V. Schupmann，I. Stuart．Oracle Database Data Warehousing Guide10g Release2(10.2)[J]．Oracle Corporation, Redwood City, CA．2005．
[75]曹海旺，黄建国，韩晶．HLA中的数据收集技术研究[J]．计算机仿真．2006，23(2):113-117．
[76]张志伟，刘登第，蔡建宇，et al．基于HLA的数据采集与重放模型[J]．计算机工程．2010，36(005):255-256．
[77]姚渝春，潘林森，王凡．数据库触发器及应用[J]．重庆建筑大学学报．2003，25(5):128-131．
[78]徐富亮，周祖德．变化数据捕获技术研究[J]．武汉理工大学学报:信息与管理工程版．2009，31(005):740-743．
[79]S. Banerjee，S. Banergee，K. Chintakayala，et al．Oracle C++Call InterfaceProgrammer's Guide,11g Release1(11.1) B28390-03[J]．
[80]J. Melnick． Oracle Call Interface Programmer's Guide,10g Release1(10.1)[J]．Oracle Corporation [pdf-dokumentti]．2003．
[81]李伟，马萍，杨明，et al．基于HLA的仿真数据收集与分析系统研究[J]．系统工程与电子技术．2008，30(010):1949-1952．
[82]顾云锋，杨素霞，王智钢，et al．Oracle数据库中存储过程开发研究[J]．计算机与现代化．2011(10):138-142．
[83]胡怀勇，胡勇军．Oracle数据库访问技术的探讨[J]．现代计算机:下半月版．2002(005):46-50．
[84]徐波，熊萍．ODBC数据库互操作技术综述[J]．计算机应用．1998，18(003):1-3．
[85]G. Reese， A. Oram． Database Programming with JDBC andJAVA[M]．O'Reilly&Associates, Inc.，2000．
[86]王海亮．精通Oracle10g Pro*C/C++编程[M]．中国水利水电出版社，2005．
[87]R. Xu，D. Wunsch．Survey of clustering algorithms[J]．Neural Networks, IEEETransactions on．2005，16(3):645-678．
[88]C. B hm，C. Plant，J. Shao，et al．Clustering by synchronization[C]．Proc.of the16th ACM SIGKDD Conf. on Knowledge Discovery and Data Mining，2010，ACM:583-592．
[89]孙吉贵，刘杰，赵连宇．聚类算法研究[J]．软件学报．2008，19(1):48-61．
[90]J. Han，M. Kamber，J. Pei．Data mining: concepts and techniques[M]．MorganKaufmann，2006．
[91]J. MacQueen．Some methods for classification and analysis of multivariateobservations[C]． Proceedings of the Fifth Symposium on Math, Statistics, andProbability，1967，Berkeley, USA: University of California Press:281-297．
[92]L. Kaufman，P.J. Rousseeuw．Finding groups in data: an introduction to clusteranalysis[M]．Wiley Online Library，1990．
[93]P.S. Bradley， U.M. Fayyad． Refining initial points for k-meansclustering[C]．Proceedings of the15th ICML，1998，San Francisco, CA, USA:91-99．
[94]I.S. Dhillon，Y. Guan，J. Kogan．Refining clusters in high-dimensional textdata[C]．Workshop on Clustering High Demensional Data，2002:71-82．
[95]D. Pelleg，A. Moore．X-means: Extending k-means with efficient estimation ofthe number of clusters[C]． Proceedings of the17th ICML，2000， SanFrancisco:727-734．
[96]I. Sarafis，A. M. S. Zalzala，P. W. Trinder．A genetic rule-based data clusteringtoolkit[C]． Proceedings of the Evolutionary Computation on2002. CEC '02.Proceedings of the2002Congress-Volume02，2002．1252396，IEEE ComputerSociety:1238-1243．
[97]R.T. Ng，J. Han．Clarans: A method for clustering objects for spatial datamining[J]． Knowledge and data Engineering, IEEE Transactions on．2002，14(5):1003-1016．
[98]H.S. Park， C.H. Jun． A simple and fast algorithm for K-medoidsclustering[J]．Expert Systems with Applications．2009，36(2):3336-3341．
[99]R. Pratap，J.R. Devi，K.S. Vani，et al．An Efficient Density based ImprovedK-Medoids Clustering algorithm[J]．International Journal．2011，2(6):49-54．
[100]Tian Zhang，Raghu Ramakrishnan，Miron Livny．BIRCH: an efficient dataclustering method for very large databases[J]．SIGMOD Rec.．1996，25(2):103-114．
[101]Sudipto Guha，Rajeev Rastogi，Kyuseok Shim．CURE: an efficient clusteringalgorithm for large databases[J]．SIGMOD Rec.．1998，27(2):73-84．
[102]． ROCK: A Robust Clustering Algorithm for CategoricalAttributes[C]．Proceedings of the15th International Conference on Data Engineering，1999．847264，IEEE Computer Society:512．
[103]G. Karypis，E.H. Han，V. Kumar．Chameleon: Hierarchical clustering usingdynamic modeling[J]．Computer．1999，32(8):68-75．
[104]M. Ester，H.P. Kriegel，J. Sander，et al．A density-based algorithm fordiscovering clusters in large spatial databases with noise[C]． Proc. of the2ndInternational Conference on Knowledge Discovery and Data Mining，1996，AAAIPress:226-231．
[105]M. Ankerst，M.M. Breunig，H.P. Kriegel，et al．OPTICS: Ordering pointsto identify the clustering structure[C]． Proc. of ACM SIGMOD Int Conf onManagement of Data，1999，Seattle: ACM Press:49-60．
[106]A.H. Daniel，A. Keim．An Efficient Approach to Clustering in LargeMultimedia Databases with Noise[C]．Proc. of the4th International Conference onKnowledge Discovery and Data mining，1998:58-65．
[107]Wei Wang，Jiong Yang，Richard R. Muntz．STING: A Statistical InformationGrid Approach to Spatial Data Mining[C]．Proceedings of the23rd InternationalConference on Very Large Data Bases，1997．758369，Morgan Kaufmann PublishersInc.:186-195．
[108]G. Sheikholeslami，S. Chatterjee，A. Zhang．Wavecluster: A multi-resolutionclustering approach for very large spatial databases[C]．Proceedings of the24rdInternational Conference on Very Large Data Bases，1998， INSTITUTE OFELECTRICAL&ELECTRONICS ENGINEERS:428-439．
[109]Rakesh Agrawal，Johannes Gehrke，Dimitrios Gunopulos，et al．Automaticsubspace clustering of high dimensional data for data mining applications[J]．SIGMODRec.．1998，27(2):94-105．
[110]C. Fraley，A.E. Raftery．Model-based clustering, discriminant analysis, anddensity estimation[J]． Journal of the American Statistical Association．2002，97(458):611-631．
[111]G.J. McLachlan，T. Krishnan．The EM algorithm and extensions[M]．JohnWiley and Sons，2008．
[112]R.S. Michalski．Knowledge acquisition through conceptual clustering: Atheoretical framework and an algorithm for partitioning data into conjunctiveconcepts[J]．Journal of Policy Analysis and Information Systems．1980，4(3):219-244．
[113]J. Stutz，P. Cheeseman．Bayesian classification (autoclass): Theory andresults[J]．Advances in Knowledge Discovery and Data Mining. AAAI Press, MenloPark, CA．1995．
[114]D.H. Fisher． Knowledge acquisition via incremental conceptualclustering[J]．Machine learning．1987，2(2):139-172．
[115]陈泯融，邓飞其．一种基于自组织特征映射网络的聚类方法[J]．系统工程与电子技术．2004，26(12):1864-1866．
[116]N. Liu， B. Zhang， J. Yan， et al． Learning similarity measures innon-orthogonal space[C]．the13th Conf. on Information and Knowledge Management(CIKM2004)，2004，ACM Press:334-341．
[117]Jian Yin，Xianli Fan，Yiqun Chen，et al．High-dimensional shared nearestneighbor clustering algorithm[C]．Proceedings of the Second international conferenceon Fuzzy Systems and Knowledge Discovery-Volume Part II，Changsha, China，2005．2130582，Springer-Verlag:494-502．
[118]S. Openshaw，M. Charlton，C. Wymer，et al．A mark1geographical analysismachine for the automated analysis of point data sets[J]．International Journal ofGeographical Information System．1987，1(4):335-358．
[119]R. Block．Gang activity and overall levels of crime: A new mapping tool fordefining areas of gang activity using police records[J]． Journal of QuantitativeCriminology．2000，16(3):369-383．
[120]M. Kulldorff， L. Huang， L. Pickle， et al． An elliptic spatial scanstatistic[J]．Statistics in medicine．2006，25(22):3929-3943．
[121]GP Patil，C. Taillie．Upper level set scan statistic for detecting arbitrarilyshaped hotspots[J]．Environmental and Ecological Statistics．2004，11(2):183-197．
[122]R. Modarres，GP Patil．Hotspot detection with bivariate data[J]．Journal ofStatistical planning and inference．2007，137(11):3643-3654．
[123]Getis A．Reflections on spatial autocorrelation[J]．Regional Science andUrban Economics．2007，37(4):491-496．
[124]L. Anselin．Local indicators of spatial association—LISA[J]．Geographicalanalysis．1995，27(2):93-115．
[125]J.K. Ord，A. Getis．Local spatial autocorrelation statistics: distributionalissues and an application[J]．Geographical analysis．1995，27(4):286-306．
[126]B. Flahaut，M. Mouchart，E.S. Martin，et al．The local spatial autocorrelationand the kernel method for identifying black zones: a comparative approach[J]．AccidentAnalysis&Prevention．2003，35(6):991-1004．
[127]T. Steenberghen，T. Dufays，I. Thomas，et al．Intra-urban location andclustering of road accidents using GIS: a Belgian example[J]．International Journal ofGeographical Information Science．2004，18(2):169-181．
[128]M. Craglia，R. Haining，P. Wiles．A comparative evaluation of approaches tourban crime pattern analysis[J]．Urban Studies．2000，37(4):711．
[129]A.T. Murray，I. McGuffog，J.S. Western，et al．Exploratory spatial dataanalysis techniques for examining urban crime[J]． British Journal ofCriminology．2001，41(2):309．
[130]T.H. Grubesic．On the application of fuzzy clustering for crime hot spotdetection[J]．Journal of Quantitative Criminology．2006，22(1):77-105．
[131]J.C. Duque，R. Ramos，J. Suri ach．Supervised regionalization methods: Asurvey[J]．International Regional Science Review．2007，30(3):195-220．
[132]D. Zeng，W. Chang，H. Chen．A comparative study of spatio-temporalhotspot analysis techniques in security informatics[C]．Proc. of the7th InternationalIEEE Conference on Intelligent Transportation Systems，2004，IEEE:106-111．
[133]J.G. Lee，J. Han，K.Y. Whang．Trajectory clustering: a partition-and-groupframework[C]．Proc. of SIGMOD'07，2007，ACM:593-604．
[134]J.G. Lee，J. Han，X. Li．Trajectory outlier detection: A partition-and-detectframework[C]．Proc. of24th Intl Conf. on Data Engineering，2008，IEEE:140-149．
[135]S. Dodge，R. Weibel，E. Forootan．Revealing the physics of movement:Comparing the similarity of movement characteristics of different types of movingobjects[J]．Computers, environment and urban systems．2009，33(6):419-434．
[136]N.H. Thach， E. Suzuki． A Symbolic Representation for TrajectoryData[C]．Proc. of24th Annual Conference of the Japanese Society for ArtificialIntelligence，2010．
[137]M. Vlachos，G. Kollios，D. Gunopulos．Discovering similar multidimensionaltrajectories[C]．Proc. of the International Conference on Data Engineering，2002，IEEE:673-684．
[138]Y. Yanagisawa，J. Akahani，T. Satoh．Shape-based similarity query fortrajectory of mobile objects[C]．Proc. of the4th Intl. Conference on MDM，2003，Springer:63-77．
[139]Z. Zhang，K. Huang，T. Tan．Comparison of similarity measures for trajectoryclustering in outdoor surveillance scenes[C]．Proc. of International Conference onPattern Recognition，2006，IEEE:1135-1138．
[140]J.R. Hwang，H.Y. Kang，K.J. Li．Searching for similar trajectories on roadnetworks using spatio-temporal similarity[C]． Proc. of the10th East EuropeanConference on Advances in Databases and Information Systems (ADBIS)，2006，Springer:282-295．
[141]S.J. Gaffney，A.W. Robertson，P. Smyth，et al．Probabilistic clustering ofextratropical cyclones using regression mixture models[J]．Climate dynamics．2007，29(4):423-440．
[142]M. Nanni，D. Pedreschi．Time-focused clustering of trajectories of movingobjects[J]．Journal of Intelligent Information Systems．2006，27(3):267-289．
[143]N. Pelekis，I. Kopanakis，E.E. Kotsifakos，et al．Clustering trajectories ofmoving objects in an uncertain world[C]．Proc. of the Ninth IEEE InternationalConference on Data Mining，2009，IEEE:417-427．
[144]C.S. Chen，C. Eick，N. Rizk．Mining spatial trajectories using non-parametricdensity functions[J]． Machine Learning and Data Mining in PatternRecognition．2011:496-510．
[145]B. Morris， M. Trivedi． Learning trajectory patterns by clustering:Experimental studies and comparative evaluation[C]． IProc. of IEEE Conf. onComputer Vision and Pattern Recognition，2009，IEEE:312-319．
[146]R. Gelbard，O. Goldman，I. Spiegler．Investigating diversity of clusteringmethods: An empirical comparison[J]．Data&Knowledge Engineering．2007，63(1):155-166．
[147]L. Condat，D. Van De Ville，T. Blu．Hexagonal versus orthogonal lattices: Anew comparison using approximation theory[C]．Proc. of the IEEE International ImageProcessing，2005，IEEE:III-1116-1119．
[148]淦文燕，李德毅．基于核密度估计的层次聚类算法[J]．系统仿真学报．2004，16(002):302-305．
[149]J.E. Dennis, R.B. Schnabel． Numerical methods for unconstrainedoptimization and nonlinear equations[M]．Society for Industrial Mathematics，1996．
[150]张成现，李建文．多元非线性函数极值的通用数值解法[J]．西安工程科技学院学报．2005，19(4):507-509．
[151]R.L. Grossman, M.F. Hornick, G. Meyer． Data mining standardsinitiatives[J]．Communications of the ACM．2002,45(8):59-61.
[2]胡晓峰，司光亚等．战争模拟原理与系统[M]．国防大学出版社，2009．
[3]胡晓峰，司光亚．战争模拟引论(上、下)[M]．国防大学出版社，2004.3．
[4]戴国忠．兵棋推演与军事训练[C]．军队信息化建设与军事运筹研究（下册）—军事运筹学学会2009年学术年会论文集，2009．
[5]杨南征．虚拟演兵—兵棋、作战模拟与仿真[M]．解放军出版社，2007．
[6]胡晓峰．战争复杂系统仿真分析与实验[M]．国防大学出版社，2008.6．
[7]蔡益朝．态势评估中的兵力聚合技术研究[D]．国防科学技术大学．2006．
[8]张义宏，蒋晓原．基于信息优势的决策能力分析[J]．火力与指挥控制．2006，31(12):19-22．
[9]J. Hagelback，S.J. Johansson．Dealing with fog of war in a real time strategygame environment[C]．IEEE Symposium on Computational Intelligence and Games，2008，IEEE:55-62．
[10]韩家炜，坎伯．数据挖掘:概念与技术[M]．北京:机械工业出版社，2001．
[11]吕晓玲，谢邦昌．数据挖掘:方法与应用[M]．中国人民大学出版社，2009．
[12]纪希禹，韩秋明，李微，et al．数据挖掘技术应用实例[M]．机械工业出版社，2009．
[13]胡可云，田凤占，黄厚宽．数据挖掘理论与应用[M]．清华大学出版社，2008．
[14]U.M. Fayyad，G. Piatetsky-Shapiro，P. Smyth，et al．Advances in knowledgediscovery and data mining[M]，1996．
[15]G. Piatetsky-Shapiro．Knowledge discovery in real databases: A report on theIJCAI-89Workshop[J]．AI magazine．1990，11(4):68．
[16]E. Simoudis．Reality check for data mining[J]．IEEE Expert: Intelligentsystems and their applications．1996，11(5):26-33．
[17]Heikki Mannila．Methods and Problems in Data Mining[C]．Proceedings of the6th International Conference on Database Theory，1997．656095，Springer-Verlag:41-55．
[18]B.M. Thuraisingham． Data mining: technologies, techniques, tools, andtrends[M]．CRC，1999．
[19]J.F. Elder，D. Pregibon．A Statistical Perspective on Knowledge Discovery inDatabases[J]．1996．
[20]U. Fayyad，G. Piatetsky-Shapiro，P. Smyth．From data mining to knowledgediscovery in databases[J]．AI magazine．1996，17(3):37．
[21]朱建秋．数据挖掘系统发展综述[EB/OL]．http:∥www.dmgroup.org.cn/zhujianqiu/dmsystem.pdf．
[22]P. Chapman，J. Clinton，T. Khabaza，et al．The CRISP-DM processmodel[J]．The CRIP–DM Consortium．1999，310．
[23]D.S. Tkach．Information mining with the ibm intelligent miner family[J]．AnIBM Software Solutions White Paper．1998:1-29．
[24]J. Han，J.Y. Chiang，S. Chee，et al．DBMiner: A system for data mining inrelational databases and data warehouses[C]，1997，IBM Press:8．
[25]T. Khabaza，C. Shearer．Data mining with Clementine[C]，1995，IET:1/1-1/5．
[26]焦李成．智能数据挖掘与知识发现[M]．西安电子科技大学出版社，2006．
[27]何晓群，统计学．现代统计分析方法与应用[M]．中国人民大学出版社，1998．
[28]R. Agarwal，R. Srikant．Fast algorithms for mining association rules[C]．Proc.of the20th VLDB Conference，1994:487-499．
[29]刘莉，徐玉生，马志新．数据挖掘中数据预处理技术综述[J]．甘肃科学学报．2003，12(1):117-119．
[30]J. Gehrke，V. Ganti，R. Ramakrishnan，et al．BOAT—optimistic decision treeconstruction[C]．ACM SIGMOD Record，1999，ACM:169-180．
[31]M. Mehta，R. Agrawal，J. Rissanen．SLIQ: A fast scalable classifier for datamining[J]．Advances in Database Technology—EDBT'96．1996:18-32．
[32]I.P. Witten，E. Frank．数据挖掘:实用机器学习技术:英文版[M]．机械工业出版社，2005．
[33]陈文伟．数据仓库与数据挖掘教程[M]．清华大学出版社，2006．
[34]任永功，于戈．数据可视化技术的研究与进展[J]．计算机科学．2004，31(12):92-95．
[35]李德毅，杜鹢．不确定性人工智能[M]．国防工业出版社，2005．
[36]杨炳儒．基于内在机理的知识发现理论及其应用[M]．电子工业出版社，2004．
[37]徐慧英，赵建民，岑琴，et al．电子商务环境下基于Multi-Agent的数据挖掘系统[J]．计算机研究与发展．2006(z1):494-498．
[38]熊海亮，白振兴．一种基于多Agent的Web数据挖掘方法[J]．现代电子技术．2010，33(008):83-86．
[39]佟志臣，刘滨，王建军．面向CRM的基于Multi-Agent的数据挖掘模型研究[J]．河北工业科技．2009，26(005):311-314．
[40]毛国君．数据挖掘原理与算法[M]．清华大学出版社，2005．
[41]刘同明．数据挖掘技术及其应用[M]．国防工业出版社，2001．
[42]陈安，陈宁，周龙骧．数据挖掘技术及应用[M]．科学出版社，2006．
[43]B.A. Bodt．Urban Combat Data Mining[R]．Document, DTIC，2004:8．
[44]陈立潮，刘玉树，杨国胜，et al．炮兵阵地选取的空间数据挖掘模型研究[J]．北京理工大学学报．2002，22(4):469-472．
[45]金鑫，李元左．空间军事系统综合集成研讨厅中数据挖掘应用[J]．备指挥技术学院学报．2005，16(04):57-60．
[46]武玉红，刘毅勇．空间数据挖掘及其在军事领域的应用[J]．军事运筹与系统工程．2006，20(002):18-21．
[47]张文明，薛青．粗糙集方法在作战仿真数据挖掘中的应用[J]．系统仿真学报增刊．2006，18(2):179-181．
[48]周红梅，薛青．数据挖掘技术及其在装备作战仿真系统中的应用[J]．第五届全国仿真器学术会论文集．2004．
[49]P.P. Perla． The art of wargaming: a guide for professionals andhobbyists[M]．Naval Inst Pr，1990．
[50]朱元锋，李伟．兵棋经典实战运用大扫描[J]．环球军事．2008(012):41-44．
[51]李学军，王锐华．联合作战兵棋推演系统研究[J]．中国电子学会电子系统工程分会第五届军事信息软件与仿真学术研讨会论文集,北京:电子工业出版社．2006:16-19．
[52]彭春光，鞠儒生，杨建池，et al．现代兵棋推演技术分析[J]．系统仿真学报．2009，21(增刊2):97-100．
[53]韩志军，柳少军，唐宇波，et al．计算机兵棋推演系统公共数据的建模与VV&C研究[J]．系统仿真学报．2011，12．
[54]石崇林，张茂军，吴琳，et al．基于密度的计算机兵棋推演数据快速聚类算法[J]．系统工程与电子技术．2011，33(11):2428-2433．
[55]胡晓峰．美军训练模拟[M]．国防大学出版社，2001．
[56]金伟新．大型仿真系统[M]．电子工业出版社，2004．
[57]U.S.J.F. Command．JTLS Executive Overview[R]，2004．
[58]殷兴良．EADSIM仿真系统概况介绍[J]．现代防御技术．1993，2:47-52．
[59]陈丽，冯润明，姚益平．联合建模与仿真系统研究[J]．电光与控制．2007，14(4):10-12．
[60]V.K. Handley，PM Shea，M. Morano．An Introduction to the Joint Modelingand Simulation System (JMASS)[C]． Proceedings of the Fall2000SimulationInteroperability Workshop，Orlando FL，2000．
[61]李宁，赵存如．美军联合作战系统分析[J]．军事运筹与系统工程．2008，21(4):67-71．
[62]D.T. Maxwell． An Overview of The Joint Warfare System(JWARS)[J]．MORS Phalanx Magazine (S0023-1687)．2000，6(3):12-14．
[63]D. Zedo． Corps Battle Simulation[J]． PEOSTRI web site. RetrievedApril．2004，2:2004．
[64]P. Pike．Tactical Simulation (TACSIM)[J]．Retrieved Nov．2005，15:2005．
[65]R. Smith， G. Allen． After action review in military trainingsimulations[C]．Proceedings of the26th conference on Winter simulation，1994，Society for Computer Simulation International:845-849．
[66]R.W. Bennington． Joint Simulation System (JSIMS)-anoverview[C]． Proceedings of IEEE1995National Aerospace and ElectronicsConference，1995，IEEE:804-809vol.802．
[67]L. Budge，R. Strini，R. Dehncke，et al．Synthetic Theater of War (STOW)97Overview[C]．Simulation Interoperability Workshop，1998．
[68]赵沁平．分布式虚拟战场环境—现代战争的实验场[J]．系统仿真学报．2001，13(11):1-7．
[69]R.L. Wittman Jr． OneSAF: A product line approach to simulationdevelopment[R]，2001．
[70]R.L. Wittman，A.J. Courtemanche．The OneSAF Product Line Architecture:An Overview of the Products and Process[C]，2002，Citeseer．
[71]景民，胡晓峰，吴琳，et al．面向态势回放的两种海量数据采集存储结构分析[J]．系统仿真学报．2011，已录用．
[72]J.W. Gibson．After Action Review System (AARS) design and functionalcapabilities[C]．the27th conference on winter simulation，1995，IEEE ComputerSociety:1267-1273．
[73]J.A. Hixson．Battle command AAR methodology: a paradigm for effectivetraining[C]． Proceedings of the27th conference on winter simulation，1995，IEEE:1274-1279．
[74]P. Lane，V. Schupmann，I. Stuart．Oracle Database Data Warehousing Guide10g Release2(10.2)[J]．Oracle Corporation, Redwood City, CA．2005．
[75]曹海旺，黄建国，韩晶．HLA中的数据收集技术研究[J]．计算机仿真．2006，23(2):113-117．
[76]张志伟，刘登第，蔡建宇，et al．基于HLA的数据采集与重放模型[J]．计算机工程．2010，36(005):255-256．
[77]姚渝春，潘林森，王凡．数据库触发器及应用[J]．重庆建筑大学学报．2003，25(5):128-131．
[78]徐富亮，周祖德．变化数据捕获技术研究[J]．武汉理工大学学报:信息与管理工程版．2009，31(005):740-743．
[79]S. Banerjee，S. Banergee，K. Chintakayala，et al．Oracle C++Call InterfaceProgrammer's Guide,11g Release1(11.1) B28390-03[J]．
[80]J. Melnick． Oracle Call Interface Programmer's Guide,10g Release1(10.1)[J]．Oracle Corporation [pdf-dokumentti]．2003．
[81]李伟，马萍，杨明，et al．基于HLA的仿真数据收集与分析系统研究[J]．系统工程与电子技术．2008，30(010):1949-1952．
[82]顾云锋，杨素霞，王智钢，et al．Oracle数据库中存储过程开发研究[J]．计算机与现代化．2011(10):138-142．
[83]胡怀勇，胡勇军．Oracle数据库访问技术的探讨[J]．现代计算机:下半月版．2002(005):46-50．
[84]徐波，熊萍．ODBC数据库互操作技术综述[J]．计算机应用．1998，18(003):1-3．
[85]G. Reese， A. Oram． Database Programming with JDBC andJAVA[M]．O'Reilly&Associates, Inc.，2000．
[86]王海亮．精通Oracle10g Pro*C/C++编程[M]．中国水利水电出版社，2005．
[87]R. Xu，D. Wunsch．Survey of clustering algorithms[J]．Neural Networks, IEEETransactions on．2005，16(3):645-678．
[88]C. B hm，C. Plant，J. Shao，et al．Clustering by synchronization[C]．Proc.of the16th ACM SIGKDD Conf. on Knowledge Discovery and Data Mining，2010，ACM:583-592．
[89]孙吉贵，刘杰，赵连宇．聚类算法研究[J]．软件学报．2008，19(1):48-61．
[90]J. Han，M. Kamber，J. Pei．Data mining: concepts and techniques[M]．MorganKaufmann，2006．
[91]J. MacQueen．Some methods for classification and analysis of multivariateobservations[C]． Proceedings of the Fifth Symposium on Math, Statistics, andProbability，1967，Berkeley, USA: University of California Press:281-297．
[92]L. Kaufman，P.J. Rousseeuw．Finding groups in data: an introduction to clusteranalysis[M]．Wiley Online Library，1990．
[93]P.S. Bradley， U.M. Fayyad． Refining initial points for k-meansclustering[C]．Proceedings of the15th ICML，1998，San Francisco, CA, USA:91-99．
[94]I.S. Dhillon，Y. Guan，J. Kogan．Refining clusters in high-dimensional textdata[C]．Workshop on Clustering High Demensional Data，2002:71-82．
[95]D. Pelleg，A. Moore．X-means: Extending k-means with efficient estimation ofthe number of clusters[C]． Proceedings of the17th ICML，2000， SanFrancisco:727-734．
[96]I. Sarafis，A. M. S. Zalzala，P. W. Trinder．A genetic rule-based data clusteringtoolkit[C]． Proceedings of the Evolutionary Computation on2002. CEC '02.Proceedings of the2002Congress-Volume02，2002．1252396，IEEE ComputerSociety:1238-1243．
[97]R.T. Ng，J. Han．Clarans: A method for clustering objects for spatial datamining[J]． Knowledge and data Engineering, IEEE Transactions on．2002，14(5):1003-1016．
[98]H.S. Park， C.H. Jun． A simple and fast algorithm for K-medoidsclustering[J]．Expert Systems with Applications．2009，36(2):3336-3341．
[99]R. Pratap，J.R. Devi，K.S. Vani，et al．An Efficient Density based ImprovedK-Medoids Clustering algorithm[J]．International Journal．2011，2(6):49-54．
[100]Tian Zhang，Raghu Ramakrishnan，Miron Livny．BIRCH: an efficient dataclustering method for very large databases[J]．SIGMOD Rec.．1996，25(2):103-114．
[101]Sudipto Guha，Rajeev Rastogi，Kyuseok Shim．CURE: an efficient clusteringalgorithm for large databases[J]．SIGMOD Rec.．1998，27(2):73-84．
[102]． ROCK: A Robust Clustering Algorithm for CategoricalAttributes[C]．Proceedings of the15th International Conference on Data Engineering，1999．847264，IEEE Computer Society:512．
[103]G. Karypis，E.H. Han，V. Kumar．Chameleon: Hierarchical clustering usingdynamic modeling[J]．Computer．1999，32(8):68-75．
[104]M. Ester，H.P. Kriegel，J. Sander，et al．A density-based algorithm fordiscovering clusters in large spatial databases with noise[C]． Proc. of the2ndInternational Conference on Knowledge Discovery and Data Mining，1996，AAAIPress:226-231．
[105]M. Ankerst，M.M. Breunig，H.P. Kriegel，et al．OPTICS: Ordering pointsto identify the clustering structure[C]． Proc. of ACM SIGMOD Int Conf onManagement of Data，1999，Seattle: ACM Press:49-60．
[106]A.H. Daniel，A. Keim．An Efficient Approach to Clustering in LargeMultimedia Databases with Noise[C]．Proc. of the4th International Conference onKnowledge Discovery and Data mining，1998:58-65．
[107]Wei Wang，Jiong Yang，Richard R. Muntz．STING: A Statistical InformationGrid Approach to Spatial Data Mining[C]．Proceedings of the23rd InternationalConference on Very Large Data Bases，1997．758369，Morgan Kaufmann PublishersInc.:186-195．
[108]G. Sheikholeslami，S. Chatterjee，A. Zhang．Wavecluster: A multi-resolutionclustering approach for very large spatial databases[C]．Proceedings of the24rdInternational Conference on Very Large Data Bases，1998， INSTITUTE OFELECTRICAL&ELECTRONICS ENGINEERS:428-439．
[109]Rakesh Agrawal，Johannes Gehrke，Dimitrios Gunopulos，et al．Automaticsubspace clustering of high dimensional data for data mining applications[J]．SIGMODRec.．1998，27(2):94-105．
[110]C. Fraley，A.E. Raftery．Model-based clustering, discriminant analysis, anddensity estimation[J]． Journal of the American Statistical Association．2002，97(458):611-631．
[111]G.J. McLachlan，T. Krishnan．The EM algorithm and extensions[M]．JohnWiley and Sons，2008．
[112]R.S. Michalski．Knowledge acquisition through conceptual clustering: Atheoretical framework and an algorithm for partitioning data into conjunctiveconcepts[J]．Journal of Policy Analysis and Information Systems．1980，4(3):219-244．
[113]J. Stutz，P. Cheeseman．Bayesian classification (autoclass): Theory andresults[J]．Advances in Knowledge Discovery and Data Mining. AAAI Press, MenloPark, CA．1995．
[114]D.H. Fisher． Knowledge acquisition via incremental conceptualclustering[J]．Machine learning．1987，2(2):139-172．
[115]陈泯融，邓飞其．一种基于自组织特征映射网络的聚类方法[J]．系统工程与电子技术．2004，26(12):1864-1866．
[116]N. Liu， B. Zhang， J. Yan， et al． Learning similarity measures innon-orthogonal space[C]．the13th Conf. on Information and Knowledge Management(CIKM2004)，2004，ACM Press:334-341．
[117]Jian Yin，Xianli Fan，Yiqun Chen，et al．High-dimensional shared nearestneighbor clustering algorithm[C]．Proceedings of the Second international conferenceon Fuzzy Systems and Knowledge Discovery-Volume Part II，Changsha, China，2005．2130582，Springer-Verlag:494-502．
[118]S. Openshaw，M. Charlton，C. Wymer，et al．A mark1geographical analysismachine for the automated analysis of point data sets[J]．International Journal ofGeographical Information System．1987，1(4):335-358．
[119]R. Block．Gang activity and overall levels of crime: A new mapping tool fordefining areas of gang activity using police records[J]． Journal of QuantitativeCriminology．2000，16(3):369-383．
[120]M. Kulldorff， L. Huang， L. Pickle， et al． An elliptic spatial scanstatistic[J]．Statistics in medicine．2006，25(22):3929-3943．
[121]GP Patil，C. Taillie．Upper level set scan statistic for detecting arbitrarilyshaped hotspots[J]．Environmental and Ecological Statistics．2004，11(2):183-197．
[122]R. Modarres，GP Patil．Hotspot detection with bivariate data[J]．Journal ofStatistical planning and inference．2007，137(11):3643-3654．
[123]Getis A．Reflections on spatial autocorrelation[J]．Regional Science andUrban Economics．2007，37(4):491-496．
[124]L. Anselin．Local indicators of spatial association—LISA[J]．Geographicalanalysis．1995，27(2):93-115．
[125]J.K. Ord，A. Getis．Local spatial autocorrelation statistics: distributionalissues and an application[J]．Geographical analysis．1995，27(4):286-306．
[126]B. Flahaut，M. Mouchart，E.S. Martin，et al．The local spatial autocorrelationand the kernel method for identifying black zones: a comparative approach[J]．AccidentAnalysis&Prevention．2003，35(6):991-1004．
[127]T. Steenberghen，T. Dufays，I. Thomas，et al．Intra-urban location andclustering of road accidents using GIS: a Belgian example[J]．International Journal ofGeographical Information Science．2004，18(2):169-181．
[128]M. Craglia，R. Haining，P. Wiles．A comparative evaluation of approaches tourban crime pattern analysis[J]．Urban Studies．2000，37(4):711．
[129]A.T. Murray，I. McGuffog，J.S. Western，et al．Exploratory spatial dataanalysis techniques for examining urban crime[J]． British Journal ofCriminology．2001，41(2):309．
[130]T.H. Grubesic．On the application of fuzzy clustering for crime hot spotdetection[J]．Journal of Quantitative Criminology．2006，22(1):77-105．
[131]J.C. Duque，R. Ramos，J. Suri ach．Supervised regionalization methods: Asurvey[J]．International Regional Science Review．2007，30(3):195-220．
[132]D. Zeng，W. Chang，H. Chen．A comparative study of spatio-temporalhotspot analysis techniques in security informatics[C]．Proc. of the7th InternationalIEEE Conference on Intelligent Transportation Systems，2004，IEEE:106-111．
[133]J.G. Lee，J. Han，K.Y. Whang．Trajectory clustering: a partition-and-groupframework[C]．Proc. of SIGMOD'07，2007，ACM:593-604．
[134]J.G. Lee，J. Han，X. Li．Trajectory outlier detection: A partition-and-detectframework[C]．Proc. of24th Intl Conf. on Data Engineering，2008，IEEE:140-149．
[135]S. Dodge，R. Weibel，E. Forootan．Revealing the physics of movement:Comparing the similarity of movement characteristics of different types of movingobjects[J]．Computers, environment and urban systems．2009，33(6):419-434．
[136]N.H. Thach， E. Suzuki． A Symbolic Representation for TrajectoryData[C]．Proc. of24th Annual Conference of the Japanese Society for ArtificialIntelligence，2010．
[137]M. Vlachos，G. Kollios，D. Gunopulos．Discovering similar multidimensionaltrajectories[C]．Proc. of the International Conference on Data Engineering，2002，IEEE:673-684．
[138]Y. Yanagisawa，J. Akahani，T. Satoh．Shape-based similarity query fortrajectory of mobile objects[C]．Proc. of the4th Intl. Conference on MDM，2003，Springer:63-77．
[139]Z. Zhang，K. Huang，T. Tan．Comparison of similarity measures for trajectoryclustering in outdoor surveillance scenes[C]．Proc. of International Conference onPattern Recognition，2006，IEEE:1135-1138．
[140]J.R. Hwang，H.Y. Kang，K.J. Li．Searching for similar trajectories on roadnetworks using spatio-temporal similarity[C]． Proc. of the10th East EuropeanConference on Advances in Databases and Information Systems (ADBIS)，2006，Springer:282-295．
[141]S.J. Gaffney，A.W. Robertson，P. Smyth，et al．Probabilistic clustering ofextratropical cyclones using regression mixture models[J]．Climate dynamics．2007，29(4):423-440．
[142]M. Nanni，D. Pedreschi．Time-focused clustering of trajectories of movingobjects[J]．Journal of Intelligent Information Systems．2006，27(3):267-289．
[143]N. Pelekis，I. Kopanakis，E.E. Kotsifakos，et al．Clustering trajectories ofmoving objects in an uncertain world[C]．Proc. of the Ninth IEEE InternationalConference on Data Mining，2009，IEEE:417-427．
[144]C.S. Chen，C. Eick，N. Rizk．Mining spatial trajectories using non-parametricdensity functions[J]． Machine Learning and Data Mining in PatternRecognition．2011:496-510．
[145]B. Morris， M. Trivedi． Learning trajectory patterns by clustering:Experimental studies and comparative evaluation[C]． IProc. of IEEE Conf. onComputer Vision and Pattern Recognition，2009，IEEE:312-319．
[146]R. Gelbard，O. Goldman，I. Spiegler．Investigating diversity of clusteringmethods: An empirical comparison[J]．Data&Knowledge Engineering．2007，63(1):155-166．
[147]L. Condat，D. Van De Ville，T. Blu．Hexagonal versus orthogonal lattices: Anew comparison using approximation theory[C]．Proc. of the IEEE International ImageProcessing，2005，IEEE:III-1116-1119．
[148]淦文燕，李德毅．基于核密度估计的层次聚类算法[J]．系统仿真学报．2004，16(002):302-305．
[149]J.E. Dennis, R.B. Schnabel． Numerical methods for unconstrainedoptimization and nonlinear equations[M]．Society for Industrial Mathematics，1996．
[150]张成现，李建文．多元非线性函数极值的通用数值解法[J]．西安工程科技学院学报．2005，19(4):507-509．
[151]R.L. Grossman, M.F. Hornick, G. Meyer． Data mining standardsinitiatives[J]．Communications of the ACM．2002,45(8):59-61.