| 引用本文: | 赵翔,刘耀林,刘殿锋.基于插件技术的人工免疫智能空间优化平台研究.[J].国防科技大学学报,2013,35(2):164-168.[点击复制] |
| ZHAO Xiang,Liu Yaolin,Liu Dianfeng.A study on artificial immune computing platform for spatial optimization based on plugin technique[J].Journal of National University of Defense Technology,2013,35(2):164-168[点击复制] |
|
| |
|
|
| 本文已被：浏览 7130次 下载 7261次 |
| 基于插件技术的人工免疫智能空间优化平台研究 |
| 赵翔, 刘耀林, 刘殿锋 |
|
(武汉大学 资源与环境科学学院, 湖北 武汉 430079)
|
| 摘要: |
| 采用人工智能方法求解空间优化问题已成为当前地理学研究领域的热点之一。研究目的在于通过设计一个开放的、可扩展的人工免疫空间优化模型框架，开发基于插件技术的优化工具软件，丰富空间优化决策支持的方法和技术体系。研究从空间优化问题的基本特点和计算需求出发，定义了面向空间优化问题求解的克隆选择优化模型框架。在此基础上，采用“插件-宿主平台”结构设计了人工免疫智能空间优化平台的总体架构，定义免疫算子插件与空间优化问题应用插件开发机制。实验结果表明，平台的架构和功能设计充分考虑了计算平台的开放性和扩展性，通过平台标准接口的功能扩展可实现对不同类型空间优化问题的求解。空间优化问题研究者或政府决策部门无需关系人工免疫优化方法的具体内涵即可基于本平台完成其具体空间优化决策支持任务。 |
| 关键词: 空间优化 人工免疫系统 克隆选择 插件技术 |
| DOI： |
| 投稿日期：2012-09-01 |
| 基金项目:国家863高技术研究发展计划资助项目（2011AA120304）; 国家自然科学基金创新团队项目(41021061) |
|
| A study on artificial immune computing platform for spatial optimization based on plugin technique |
| ZHAO Xiang, Liu Yaolin, Liu Dianfeng |
|
(School of Resource and Environment Science, Wuhan University, Wuhan 430079, China)
|
| Abstract: |
| Solving the spatial optimization problems can be a complex and difficult task, since it has to handle some high-dimension, non-linear, complicated relationships. Many efforts have been made with regard to this specific issue, and the strong ability of artificial immune system algorithms has been proven in previous studies. In this study, a novel framework used for spatial optimization based on clonal selection algorithms, which are the most popular immune algorithms in geoscience, is proposed. Then, the spatial optimization platform was designed based on the architecture of “plugins – platform”, and some key technologies about the developing of immune operator plugins and spatial optimization application plugins were described. Based on the standard APIs provided by this platform, researchers can develop their own
problem-specific application plugins to solve the practical problems or to implement some advanced immune operators into the platform to improve the performance of the algorithm. Finally, the functionality, reusability and extensibility of platform were tested by using the Traveling Salesman Problem as a benchmark testing. Experiments show that, the platform is capable of solving various optimization problems, and it is expected to bridging the gap between the immune algorithm researchers, geographers and decision makers. |
| Keywords: spatial optimization artificial immune system clonal selection plug-in |
|
|
|
|
|
