摘要
为了改进传统遗传算法在求解复杂问题上存在早收敛及搜索后期运行效率低等缺点,提出了一种应用于文本分类和信息过滤的模糊遗传算法。首先应用了年龄概念来控制种群规模,使得遗传操作过程更接近于自然进化过程,然后引进参数的模糊调整过程,对遗传算法的参数种群规模、交叉率及变异率3个方面进行动态调整,改进了遗传算法的搜索性能。实验结果表明,相比传统遗传算法,该模糊遗传算法在全局优化能力及收敛速度上均有显著提高。
To deal with premature convergence and running inefficient to the solution on complicated problem at later evolution process of tradition genetic algorithm,a new algorithm is proposed.It is used for text categorization and information,which is called fuzzy genetic algorithm.Firstly,the concept of age is used to control the population size,making the process of genetic operation closer to the natural evolutionary process.Then,the fuzzy parameters of the adjustment process is proposed,with the parameters of the genetic algorithm population size,crossover rate and mutation rate dynamically adjust parameters,improved genetic search algorithm perfor-mance.Compared to tradition genetic algorithm,experimental results show that the proposed approach is effective in the capability of global optimization and significantly improves the convergence rate.
出处
《计算机工程与设计》
CSCD
北大核心
2009年第24期5718-5721,共4页
Computer Engineering and Design
基金
国家自然科学基金项目(60873247)
山东省自然科学基金项目(Y2006G20)
山东省高新自主创新专项工程基金项目(2008ZZ28)
关键词
模糊遗传算法
早收敛
交叉率
变异率
信息过滤
fuzzy genetic algorithm
premature convergence
crossover probability
mutation probability
information filtering
