Title :
Latent variable study algorithm based on grey cluster relation analysis method
Author :
Qu Ying ; Jia Jian ; Wu Qi-zong
Author_Institution :
HeiBei Univ. of Sci. & Technol., Shijiazhuang, China
Abstract :
A latent variable study algorithm based on grey cluster relation analysis method was proposed. Grey cluster method give a preliminary statistical analysis on existing data, thus the relationship among variables were established and candidate pre-models of Bayesian was built up. Compared with the existing heuristic methods, it could effectively reduce the pre-model search space, decrease the call times of EM Algorithm. The study progress of latent structure is simplified, so the efficiency of it was improved to some extent.
Keywords :
grey systems; heuristic programming; pattern clustering; statistical analysis; grey cluster relation analysis method; heuristic methods; latent variable study algorithm; statistical analysis; Algorithm design and analysis; Bayesian methods; Clustering algorithms; Statistical analysis; Technology management; Bayesian Network; Grey Cluster; Latent Variable; Pre-Model;
Conference_Titel :
Control and Decision Conference, 2009. CCDC '09. Chinese
Conference_Location :
Guilin
Print_ISBN :
978-1-4244-2722-2
Electronic_ISBN :
978-1-4244-2723-9
DOI :
10.1109/CCDC.2009.5192732
