基于混合遗传粒子群优化推荐算法的设计  

Similarity recommendation based on hybrid of GA and PSO

作　　者：吴彦文[1] 王洁[1] WU Yan-wen;WANG Jie(College of Physical Science and Technology, Central China Normal University, Wuhan 430079, China)

机构地区：[1]华中师范大学物理科学与技术学院,湖北武汉430079

出　　处：《计算机工程与设计》2017年第2期405-408,共4页Computer Engineering and Design

摘　　要：在处理大数据方面,针对基本相似度计算方法存在数据稀疏性和推荐效果不明显的问题,对传统相似度算法优势进行研究,引入时间模型和信任度模型进一步过滤,采用分层遗传算法和粒子群算法进行混合优化。在MovieLens数据集上做推荐对比实验,实验结果表明,在得到最近邻用户群的基础上,相比传统相似度算法,使用分层遗传算法和粒子群算法进行混合资源推荐,提高了推荐的质量。In dealing with big data,the basic method to compute the similarity has many problems such as data sparsity and the lack of obvious recommend effects,a research for the advantage of the basic similarity calculation was done,which integrated timing model and trust model,then used HGA(hierarchical genetic algorithm)and PSO(particle swarm optimization)for hy-brid optimization.After that,based on the nearest neighbor users?comparative experiments were carried out using the algorithm in MovieLens date sets,results show that comparing with pure similarity calculation,the algorithm adopting PSO combining hierarchical genetic algorithm for mixed resources recommendation can improve the quality of recommendation.

关 键 词：分层遗传算法 粒子群算法 相似度 优化算法 资源推荐 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]