The existing collaborative recommendation algorithms have lower robustness against shilling attacks.With this problem in mind,in this paper we propose a robust collaborative recommendation algorithm based on k-distanc...The existing collaborative recommendation algorithms have lower robustness against shilling attacks.With this problem in mind,in this paper we propose a robust collaborative recommendation algorithm based on k-distance and Tukey M-estimator.Firstly,we propose a k-distancebased method to compute user suspicion degree(USD).The reliable neighbor model can be constructed through incorporating the user suspicion degree into user neighbor model.The influence of attack profiles on the recommendation results is reduced through adjusting similarities among users.Then,Tukey M-estimator is introduced to construct robust matrix factorization model,which can realize the robust estimation of user feature matrix and item feature matrix and reduce the influence of attack profiles on item feature matrix.Finally,a robust collaborative recommendation algorithm is devised by combining the reliable neighbor model and robust matrix factorization model.Experimental results show that the proposed algorithm outperforms the existing methods in terms of both recommendation accuracy and robustness.展开更多
让 P 是凸的 N-gon N 的一个内部点：A1A2 ANA1 (N3 ) ，和让的 di， k 从点 Ai+k 表示距离到线白族(i=1,2，， N， Ai=Aj() ij (modN )) ，它为 N 的 P 被称为 k-Brocard 距离。我们证明了下列双不平等：如果 P N， k = Ni=1Ai-kAiAi+k...让 P 是凸的 N-gon N 的一个内部点：A1A2 ANA1 (N3 ) ，和让的 di， k 从点 Ai+k 表示距离到线白族(i=1,2，， N， Ai=Aj() ij (modN )) ，它为 N 的 P 被称为 k-Brocard 距离。我们证明了下列双不平等：如果 P N， k = Ni=1Ai-kAiAi+k (1kN/2， i=1,2，， N ) ，并且 r1nN-1n (N-1 )/1n2+2 [1nN-1n (N-1 )] ，那么(1/NNi=1dri， k ) 1/r1/Ncosk/NNi=1 | AiAi+k|sin2k/N/2sin/N (1/NNi=1 | AiAi+1|2 )展开更多
K-means聚类算法随机确定初始聚类数目,而且原始数据集中含有大量的冗余特征会导致聚类时精度降低,而布谷鸟搜索(CS)算法存在收敛速度慢和局部搜索能力弱等问题,为此提出一种基于自适应布谷鸟优化特征选择的K-means聚类算法(DCFSK)。首...K-means聚类算法随机确定初始聚类数目,而且原始数据集中含有大量的冗余特征会导致聚类时精度降低,而布谷鸟搜索(CS)算法存在收敛速度慢和局部搜索能力弱等问题,为此提出一种基于自适应布谷鸟优化特征选择的K-means聚类算法(DCFSK)。首先,为提升CS算法的搜索速度和精度,在莱维飞行阶段,设计了自适应步长因子;为调节CS算法全局搜索和局部搜索之间的平衡、加快CS算法的收敛,动态调整发现概率,进而提出改进的动态CS算法(IDCS),在IDCS的基础上构建了结合动态CS的特征选择算法(DCFS)。其次,为提升传统欧氏距离的计算精确度,设计同时考虑样本和特征对距离计算贡献程度的加权欧氏距离;为了确定最佳聚类数目的选取方法,依据改进的加权欧氏距离构造了加权簇内距离和簇间距离。最后,为克服传统K-means聚类目标函数仅考虑簇内的距离而未考虑簇间距离的缺陷,提出基于中位数的轮廓系数的目标函数,进而设计了DCFSK。实验结果表明,在10个基准测试函数上,IDCS的各项指标取得了较优的结果;相较于K-means、DBSCAN(Density-Based Spatial Clustering of Applications with Noise)等算法,在6个合成数据集与6个UCI数据集上,DCFSK的聚类效果最佳。展开更多
基金National Natural Science Foundation of China under Grant No.61379116，Natural Science Foundation of Hebei Province under Grant No.F2015203046 and No.F2013203124，Key Program of Research on Science and Technology of Higher Education Institutions of Hebei Province under Grant No.ZH2012028
文摘The existing collaborative recommendation algorithms have lower robustness against shilling attacks.With this problem in mind,in this paper we propose a robust collaborative recommendation algorithm based on k-distance and Tukey M-estimator.Firstly,we propose a k-distancebased method to compute user suspicion degree(USD).The reliable neighbor model can be constructed through incorporating the user suspicion degree into user neighbor model.The influence of attack profiles on the recommendation results is reduced through adjusting similarities among users.Then,Tukey M-estimator is introduced to construct robust matrix factorization model,which can realize the robust estimation of user feature matrix and item feature matrix and reduce the influence of attack profiles on item feature matrix.Finally,a robust collaborative recommendation algorithm is devised by combining the reliable neighbor model and robust matrix factorization model.Experimental results show that the proposed algorithm outperforms the existing methods in terms of both recommendation accuracy and robustness.
文摘K-means聚类算法随机确定初始聚类数目,而且原始数据集中含有大量的冗余特征会导致聚类时精度降低,而布谷鸟搜索(CS)算法存在收敛速度慢和局部搜索能力弱等问题,为此提出一种基于自适应布谷鸟优化特征选择的K-means聚类算法(DCFSK)。首先,为提升CS算法的搜索速度和精度,在莱维飞行阶段,设计了自适应步长因子;为调节CS算法全局搜索和局部搜索之间的平衡、加快CS算法的收敛,动态调整发现概率,进而提出改进的动态CS算法(IDCS),在IDCS的基础上构建了结合动态CS的特征选择算法(DCFS)。其次,为提升传统欧氏距离的计算精确度,设计同时考虑样本和特征对距离计算贡献程度的加权欧氏距离;为了确定最佳聚类数目的选取方法,依据改进的加权欧氏距离构造了加权簇内距离和簇间距离。最后,为克服传统K-means聚类目标函数仅考虑簇内的距离而未考虑簇间距离的缺陷,提出基于中位数的轮廓系数的目标函数,进而设计了DCFSK。实验结果表明,在10个基准测试函数上,IDCS的各项指标取得了较优的结果;相较于K-means、DBSCAN(Density-Based Spatial Clustering of Applications with Noise)等算法,在6个合成数据集与6个UCI数据集上,DCFSK的聚类效果最佳。
