模式识别与人工智能
模式識彆與人工智能
모식식별여인공지능
Pattern Recognition and Artificial Intelligence
2015年
10期
903-912
,共10页
软子空间聚类%粒子群优化%惯性权重%有效性函数
軟子空間聚類%粒子群優化%慣性權重%有效性函數
연자공간취류%입자군우화%관성권중%유효성함수
Soft Subspace Clustering%Particle Swarm Optimization%Inertia Weight%Validity Function
目标函数和子空间搜索策略决定软子空间聚类算法的性能,而聚类有效性分析是衡量其性能的主要指标。针对子空间聚类性能,提出基于粒子群优化的软子空间聚类算法(SC-WPSO)。首先,利用 K 均值类型框架,结合类间分散度和特征权重,提出模糊加权软子空间聚类目标函数。然后,为跳出局部最优,将带惯性权重的粒子群算法作为子空间的搜索策略。最后,根据提出的聚类有效性函数,选取最佳聚类数目。在数据集上的实验证实 SC-PSO能提高聚类准确度,同时自动确定最佳聚类数目。
目標函數和子空間搜索策略決定軟子空間聚類算法的性能,而聚類有效性分析是衡量其性能的主要指標。針對子空間聚類性能,提齣基于粒子群優化的軟子空間聚類算法(SC-WPSO)。首先,利用 K 均值類型框架,結閤類間分散度和特徵權重,提齣模糊加權軟子空間聚類目標函數。然後,為跳齣跼部最優,將帶慣性權重的粒子群算法作為子空間的搜索策略。最後,根據提齣的聚類有效性函數,選取最佳聚類數目。在數據集上的實驗證實 SC-PSO能提高聚類準確度,同時自動確定最佳聚類數目。
목표함수화자공간수색책략결정연자공간취류산법적성능,이취류유효성분석시형량기성능적주요지표。침대자공간취류성능,제출기우입자군우화적연자공간취류산법(SC-WPSO)。수선,이용 K 균치류형광가,결합류간분산도화특정권중,제출모호가권연자공간취류목표함수。연후,위도출국부최우,장대관성권중적입자군산법작위자공간적수색책략。최후,근거제출적취류유효성함수,선취최가취류수목。재수거집상적실험증실 SC-PSO능제고취류준학도,동시자동학정최가취류수목。
The performance of soft subspace clustering depends on the objective function and subspace search strategy, and cluster validity analysis is the main indicator of its performance. Aiming at the subspace clustering performance, a soft subspace clustering algorithm based on particle swarm optimization (SC-PSO) is proposed. Firstly, combining inter-cluster separation with feature weight based on K means-type clustering framework, a fuzzy weighting soft subspace objective function is designed. Then, particle swarm optimization with inertia weight is used as a subspace search strategy to jump out of the local optimum. Finally, the optimal cluster number is selected by the proposed cluster validity function. The experimental results demonstrate that SC-PSO improves the clustering accuracy and automatically determines the optimal cluster number.