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 ›› 2011, Vol. 37 ›› Issue (2): 163-165. doi: 10.3969/j.issn.1000-3428.2011.02.056

• 人工智能及识别技术 • 上一篇    下一篇

基于变长编码遗传算法的K-匿名化

王 莉,宫照煊   

  1. (辽宁科技大学电子与信息工程学院计算机工程系,辽宁 鞍山 114051)
  • 出版日期:2011-01-20 发布日期:2011-01-25
  • 作者简介:王 莉(1973-),女,教授、博士,主研方向:数据挖掘,人工智能;宫照煊,硕士研究生
  • 基金资助:
    辽宁省自然科学基金资助项目(20082189)

K-anonymization Based on Genetic Algorithm of Variable Length Encoding

WANG Li, GONG Zhao-xuan   

  1. (Department of Computer Engineering, School of Electronic and Information Engineering, University of Science and Technology Liaoning, Anshan 114051, China)
  • Online:2011-01-20 Published:2011-01-25

摘要: 针对传统遗传编码存在求解效率低且信息失真大的问题,提出一种基于不定长密歇根编码的遗传算法,采用多种启发式策略进行杂交操作,将基于遗传算法的聚类方法应用到K-匿名化问题中。实验结果表明,该方法可以更好地降低信息失真,从而实现K-匿名化问题。

关键词: K-匿名化, 遗传算法, 信息失真

Abstract: Aiming at the problems that raditional genetic encoding has low efficiency and large information loss, this paper proposes a michigan-based variable-length coding Genetic Algorithm(GA), which adopts various heuristic strategies to select genes for crossover operation. It is applied to the problem of K-anonymization. Experimental results show this method can further reduce the information loss and it is a new way to solve the problem of K-anonymization.

Key words: K-anonymization, Genetic Algorithm(GA), information distortion

中图分类号: