高级检索
    张付志 常俊风 周全强. 基于模糊C均值聚类的环境感知推荐算法[J]. 计算机研究与发展, 2010, 47(10): 2185-2194.
    引用本文: 张付志 常俊风 周全强. 基于模糊C均值聚类的环境感知推荐算法[J]. 计算机研究与发展, 2010, 47(10): 2185-2194.
    Zhang Fuzhi, Chang Junfeng, and Zhou Quanqiang. Context-Aware Recommendation Algorithm Based on Fuzzy C-Means Clustering[J]. Journal of Computer Research and Development, 2010, 47(10): 2185-2194.
    Citation: Zhang Fuzhi, Chang Junfeng, and Zhou Quanqiang. Context-Aware Recommendation Algorithm Based on Fuzzy C-Means Clustering[J]. Journal of Computer Research and Development, 2010, 47(10): 2185-2194.

    基于模糊C均值聚类的环境感知推荐算法

    Context-Aware Recommendation Algorithm Based on Fuzzy C-Means Clustering

    • 摘要: 针对现有环境感知推荐算法存在的不足,提出一种基于模糊C均值聚类的环境感知推荐算法.首先采用模糊C均值聚类算法对历史环境信息进行聚类,产生聚类及隶属矩阵;然后匹配活动用户环境信息与历史环境信息聚类,采用聚类隶属度作为映射系数将符合条件的非隶属数据映射为隶属数据,最终选择与活动环境匹配的隶属用户评分数据为用户产生推荐.同现有算法相比,该算法不仅解决了因用户环境改变不能准确推荐项目的问题,而且通过采用模糊聚类算法克服了传统硬聚类问题,并且借助于隶属映射函数解决了聚类产生的数据稀疏性问题.在MovieLens数据集上比较了新算法和其他算法的性能,验证了所提算法的有效性.

       

      Abstract: Aiming at the deficiencies of existing context-aware recommendation algorithms, this paper proposes a context-aware recommendation algorithm based on fuzzy C-means clustering. Firstly, the fuzzy C-means clustering algorithm is used to perform clustering of historical contextual information and produce clusters and membership matrix. Then contextual information for the active user is matched with the cluster of historical contextual information, and non-membership data, which accord with the condition, are mapped into membership data by using membership degree of clustering as a mapping coefficient. Finally, we choose ratings of membership users, which conform to the active contextual information, to generate recommendation for the user. Compared with the existing algorithms, the proposed algorithm can not only solve the problem of inaccuracy recommendation due to the change of user context, but also overcome traditional hard clustering by using fuzzy C-means clustering algorithm. Moreover, the problem of data sparseness caused by clustering is solved by using membership mapping function. The experiments are conducted on the MovieLens dataset and the effectiveness of the proposed algorithm is verified.

       

    /

    返回文章
    返回