计算机工程 ›› 2009, Vol. 35 ›› Issue (11): 210-212,.doi: 10.3969/j.issn.1000-3428.2009.11.072

• 人工智能及识别技术 • 上一篇    下一篇

基于优序图加权的多维稀疏模糊推理方法

刘文远,武丽霞,王宝文   

  1. (燕山大学信息科学与工程学院,秦皇岛 066004)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2009-06-05 发布日期:2009-06-05

Multidimensional Sparse Fuzzy Reasoning Method Based on Weight of Precedence Chart

LIU Wen-yuan, WU Li-xia, WANG Bao-wen   

  1. (School of Information Science and Engineering, Yanshan University, Qinhuangdao 066004)
  • Received:1900-01-01 Revised:1900-01-01 Online:2009-06-05 Published:2009-06-05

摘要: 在稀疏规则库条件下,多数的多维稀疏规则条件近似推理方法都难以保证推理结果的凸性和正规性,且没有考虑到多维变量对结论的影响权值。提出一种基于优序图加权的多维模糊推理方法,运用优序图确定权值,实验结果表明,该方法不仅减小推理结果的误差,而且能较好地保证推理结果的凸性和正规性。

关键词: 多维稀疏模糊推理, 优序图, 权值, 相似性

Abstract: Most interpolative reasoning methods in multi-dimension cannot guarantee the convexity and normality of result, and cannot consider weights of each variable influencing conclusion. This paper proposes a fuzzy multidimensional reasoning method based on weight of Precedence Chart(PC), which confirms the weights by Precedence Chart(PC). Experimental results show that it not only reduces the errors, but also keeps the convexity and normality of the reasoning consequence.

Key words: multidimensional sparse fuzzy reasoning, Precedence Chart(PC), weight, similarity

中图分类号: