作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2007, Vol. 33 ›› Issue (05): 156-157. doi: 10.3969/j.issn.1000-3428.2007.05.055

• 人工智能及识别技术 • 上一篇    下一篇

基于改进遗传算法的权重发现技术

贾兆红1,2,陈华平2   

  1. (1. 安徽大学计算智能与信号处理教育部重点实验室,合肥 230039;2. 中国科学技术大学信息管理与决策科学系,合肥 230026)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-03-05 发布日期:2007-03-05

Weights Finding Based on Improved Genetic Algorithms

JIA Zhaohong1,2, CHEN Huaping2   

  1. (1. Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui University, Hefei 230039; 2. Department of Information Management and Decision Science, University of Science and Technology of China, Hefei 230026)
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-03-05 Published:2007-03-05

摘要: 范例推理的关键步骤在于相似范例的检索,而范例库中的特征项权重起到重要的作用。文章讨论了用遗传算法来获取范例库上的特征项权重,并用两种改进的遗传算法来发现范例库上的特征项权重,给出了具体的算法,分析了实验结果。该方法可用于权重发现。

关键词: 基于范例的推理, 权重, 遗传算法, Boltzmann

Abstract: In case-based system, the retrieval of similar cases is the key step of the intelligent system, and the attribute weighting of a case base takes important effect. This paper introduces two improved GAs to find the attribute weights, and analyzes the experimental results. This method can be used for weights finding.

Key words: Case-based reasoning, Weight, Genetic algorithms, Boltzmann