摘要
利用改进的协同进化遗传算法,使全局搜索与局部搜索、全局收敛性与收敛速度有机地统一起来,并将之应用到主题信息采集的研究中,实例结果表明具有较好的分类预测能力。
This paper improves coordinating operation in co-evolution genetic algorithms,a model based on global coordination and local evolution as well as improved genetic algorithms are proposed.A local evolution method based on neighbor field is adopted for enhancing capability of local search and accelerating convergent speed. At the same time, an improved multi-population co-evolution algorithm is used for the diversity of individuals in populations. The method is used to topic-specific web resource, and experimental results show this algorithm has good predictive ability.
出处
《情报科学》
CSSCI
北大核心
2008年第10期1531-1534,共4页
Information Science
关键词
遗传算法
协同进化
主题信息
收敛
URL
genetic algorithms
co-evolution
topic-specific web resource
convergent
url
