• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>The 8th international conference on optimization: Techniques and Applications >Enhanced Network Interaction in Multi-Objective Immune Optimization Algorithm
【24h】

Enhanced Network Interaction in Multi-Objective Immune Optimization Algorithm

机译：多目标免疫优化算法中的增强网络交互

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Many problems arising from engineering, science or business can be formulated as multiobjective optimization problems. Artificial immune systems (AIS) are considered to be a class of evolutionary techniques that can be deployed to solving multi-objective optimization problems. Owing to the characteristics of learning and adaptability, self-organization and memory capabilities, the contribution from AIS in multi-objective optimization is growing. As rapid convergence and diversity are very crucial aspects in multi-objective optimization, the inherent network operation in AIS provides an effective solution. In the adoption of immune network theory, suppression operation is a common feature to control diversity. Immune network theory consists not only of network suppression operation, but also network activation operation. Activation operation is rarely considered by the research community; however it offers real hope in enhancing the proximity performance to achieve quick convergence by facilitating the exploitation in early phase of the solution process and in the right direction. This paper probes the potential of the network activation operation by introducing a holistic model of the immune network theory for multi-objective optimization. The network activation operation is adopted in immune algorithms and their performance compared in terms of convergence and diversity.
机译：工程，科学或商业引起的许多问题都可以表述为多目标优化问题。人工免疫系统（AIS）被认为是一类进化技术，可用于解决多目标优化问题。由于学习和适应性，自组织性和记忆能力的特点，AIS在多目标优化中的贡献正在增长。由于快速收敛和多样性是多目标优化中非常关键的方面，因此AIS中固有的网络操作提供了有效的解决方案。在采用免疫网络理论时，抑制操作是控制多样性的共同特征。免疫网络理论不仅包括网络抑制操作，还包括网络激活操作。研究界很少考虑激活操作。但是，它通过促进解决方案过程的早期阶段和正确方向的开发，为增强邻近性能以实现快速收敛提供了真正的希望。本文通过引入用于多目标优化的免疫网络理论的整体模型，探讨了网络激活操作的潜力。免疫算法采用网络激活操作，并从收敛性和多样性方面比较它们的性能。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

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