• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文OA文献 >Application of hybrid intelligent agents to modelling a dynamic, locally interacting retail market
【2h】

Application of hybrid intelligent agents to modelling a dynamic, locally interacting retail market

机译：混合智能代理在动态，本地互动零售市场建模中的应用

页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The emergence of agent-based modelling from the field of artificial intelligence (Al) presents a new and alternative approach to geographical modelling. The vast potential offered by agent-based models in representing distributed complex systems, coupled with the increase in available computing power has resulted in agent-based models becoming an increasingly popular and powerful tool within geographical applications. These models offer distinct advantages over traditional empirical techniques through their characteristics of autonomy, flexibility and adaptability. There is an emerging recognition that the power of agent-based systems is enhanced when integrated with other AI-based and conventional approaches. The resulting hybrid models are powerful tools that combine the flexibility of the agent-based methodology with the strengths of more traditional modelling. This research examines the application of a hybrid agent-based model to the case study of the retail petrol market. Detailed analysis of the real data was first performed before the construction of an agent-based model. Model performance was evaluated against real data from the UK for a three month period in 1999. On the basis of this evaluation, the agent model was further developed to incorporate consumer behaviour by the inclusion of a spatial interaction (SI) model and a network model. Suitable parameters for these models were derived through detailed analysis of the real data, numerical experimentation and experimentation on the real data. These developments improved the performance of the model. A genetic algorithm (GA) was constructed to provide an objective approach to deriving optimal parameters. There was a close agreement in the values selected by the GA and those derived by hand. This research clearly demonstrates that agent-based modelling has the ability to improve on existing geographical models. Further investigation is needed if this potential is to be fully realised for a range if geographical problems.
机译：人工智能（Al）领域基于代理的建模的出现为地理建模提出了一种新的替代方法。基于代理的模型在表示分布式复杂系统中提供的巨大潜力，再加上可用计算能力的提高，已经导致基于代理的模型成为地理应用程序中越来越流行和强大的工具。与自主经验，灵活性和适应性相比，这些模型具有优于传统经验技术的独特优势。人们逐渐认识到，与其他基于AI的常规方法集成时，基于代理的系统的功能会增强。最终的混合模型是强大的工具，将基于代理的方法的灵活性与更传统的建模的优势相结合。这项研究探讨了基于混合代理的模型在零售汽油市场案例研究中的应用。在构建基于代理的模型之前，首先对真实数据进行详细分析。在1999年的三个月中，根据英国的真实数据对模型的性能进行了评估。在此评估的基础上，进一步开发了代理模型，以通过包含空间交互（SI）模型和网络模型来纳入消费者行为。 。通过对真实数据的详细分析，数值实验以及对真实数据的实验，得出了这些模型的合适参数。这些发展改善了模型的性能。构建了遗传算法（GA），以提供一种导出最佳参数的客观方法。通用航空选择的值和手工得出的值之间有着密切的共识。这项研究清楚地表明，基于代理的建模具有改进现有地理模型的能力。如果一定范围内的地理问题要充分发挥这种潜力，则需要进一步研究。

著录项

  • 作者

    Heppenstall Alison Jane;

  • 作者单位
  • 年度 2004
  • 总页数
  • 原文格式 PDF
  • 正文语种 English
  • 中图分类

相似文献

  • 外文文献
  • 中文文献
  • 专利

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号