Title :
Enhanced CABOSFV clustering algorithm based on adaptive threshold
Author :
Zhu, Qin ; Tu, Guoping ; Gao, Xuedong ; Wu, Sen ; Chen, Hua
Author_Institution :
Sch. of Sci., Nanchang Univ., Nanchang, China
Abstract :
In the light of the sensitivity of the order of data input by CABOSFV clustering algorithm, to enhance performance of CABOSFV, this paper puts forward a novel algorithm to gain an adaptive its threshold on the line(APCABOSFV). In the end experiments on artificial l data sets show demonstrate that the accuracy of the proposed APCABOSFV algorithm outperforms existing CABOSFV clustering algorithm for clustering high-dimensional sparse data.
Keywords :
data handling; pattern clustering; APCABOSFV algorithm; adaptive threshold; clustering algorithm based on sparse feature vector; enhanced CABOSFV clustering algorithm; high-dimensional sparse data; Algorithm design and analysis; Clustering algorithms; Data mining; Decision making; Presses; Sensitivity; CABOSFV; Feature Difference-Based; High Dimensional Sparse Feature Data; an adpative threshold;
Conference_Titel :
Computer Science and Automation Engineering (CSAE), 2011 IEEE International Conference on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4244-8727-1
DOI :
10.1109/CSAE.2011.5952924
