DOI: 10.21276/sjpms.2019.6.1.1

Pages: 1-5

The clique tree expresses dependencies in a high dimensional attribute space and can be used to make probabilistic inferences about data. For the high dimensional data analysis problem, the joint probability distribution is constructed by using the clique tree structure; a joint probability distribution in a high dimensional space can be decomposed into a product of lower dimensional probabilities. Within low dimensional spaces, the data is more concentrated and a probability distribution can be successfully derived.