| 计算机兵棋作战实体轨迹聚类算法 |
| |
| 引用本文： | 石崇林,淦文燕,吴琳,张茂军,唐宇波.计算机兵棋作战实体轨迹聚类算法[J].软件学报,2013,24(3):465-475. |
| |
| 作者姓名： | 石崇林 淦文燕 吴琳 张茂军 唐宇波 |
| |
| 作者单位： | 国防科学技术大学 信息系统与管理学院,湖南 长沙 410073;中国人民解放军理工大学 指挥自动化学院,江苏 南京 210007;国防大学 信息作战与指挥训练教研部,北京 100091;国防科学技术大学 信息系统与管理学院,湖南 长沙 410073;国防大学 信息作战与指挥训练教研部,北京 100091 |
| |
| 基金项目： | 中国博士后科学基金(201003746) |
| |
| 摘 要： | 针对计算机兵棋系统的实际应用,提出计算机兵棋实体轨迹聚类算法——CTECW(clustering trajectoriesof entities in computer wargames).算法分为3部分:轨迹预处理、轨迹分段聚类以及可视化表现.轨迹预处理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DBSCAN算法的基本框架下引入DENCLUE算法中密度函数的概念,并基于提出的相似性度量函数对轨迹分段进行聚类;可视化表现将轨迹分段聚类的结果以赋有军事涵义的形式展现给参与兵棋推演的受训指挥员,体现出算法的实际应用价值.理论分析与实验结果表明,CTECW算法能够得到与TRACLUS算法比较接近的聚类结果,但计算效率却比TRACLUS算法要高,并且聚类结果不依赖于用户参数的仔细选择.
|
| 关 键 词： | 计算机兵棋 数据挖掘 轨迹聚类 相似性度量 密度估计熵 |
| 收稿时间： | 8/2/2011 12:00:00 AM |
| 修稿时间： | 4/1/2012 12:00:00 AM |
Clustering Trajectories of Entities in Computer Wargames |
| |
| SHI Chong-Lin,GAN Wen-Yan,WU Lin,ZHANG Mao-Jun and TANG Yu-Bo.Clustering Trajectories of Entities in Computer Wargames[J].Journal of Software,2013,24(3):465-475. |
| |
| Authors: | SHI Chong-Lin GAN Wen-Yan WU Lin ZHANG Mao-Jun and TANG Yu-Bo |
| |
| Affiliation: | School of Information System and Management, National University of Defense Technology, Changsha 410073, China;Institute of Command and Automation, PLA University of Science and Technology, Nanjing 210007, China;Department of Information Operation & Command Training, National Defense University, Beijing 100091, China;School of Information System and Management, National University of Defense Technology, Changsha 410073, China;Department of Information Operation & Command Training, National Defense University, Beijing 100091, China |
| |
| Abstract: | Under the background of a computer wargame system, a trajectory clustering algorithm named CTECW (clustering trajectories of entities in computer wargames) is proposed. The algorithm is composed of three parts: trajectory pretreatment, trajectory segments clustering, and visual presentation. Trajectory pretreatment transforms original trajectories into simplified ones which are ulteriorly processed into linear segments. In the second part, the concept of density function derived from DENCLUE is introduced and trajectory segments are clustered based on similarity measure under the framework of DBSCAN. The visual presentation exhibits clusters of trajectory segments with martial meanings to trainees, which embodies practical values of CTECW. Both theoretical analysis and experimental results indicate that CTECW could acquire approximate clusters more efficiently compared with TRACLUS and requires no input parameters. |
| |
| Keywords: | computer wargame data mining trajectory clustering similarity measure density estimation entropy |
|
| 点击此处可从《软件学报》浏览原始摘要信息 |
|
点击此处可从《软件学报》下载全文 |
|
