Discovery of Quantified Hierarchical Censored Production Rules (QHCPR) from Large Data Set

In this paper a fusion algorithm is suggested in between two knowledge bases for discovery of QHCPR. HCPR system is capable of handling trade-off between the precision of an inference and its computational efficiency leading to trade-off between the certainty of a conclusion and its specificity. It is an attempt to use Dempster-Shafer interpretation of the HCPRs for the quantification to discover HCPR in the form: Decision If <pre-conditions> Unless <censor conditions> Generality <general info> Specificity<specific info>, [alpha, beta, gamma, delta]. The discovered quantified HCPRs would facilitate quantitative reasoning and learning. Examples are given to demonstrate the performance of proposed approach.