Mining bridging rules between conceptual clusters

Abstract

Bridging rules take the antecedent and action from different conceptual clusters. They are distinguished from association rules (frequent itemsets) because (1) they can be generated by the infrequent itemsets that are pruned in association rule mining, and (2) they are measured by their importance including the distance between two conceptual clusters, whereas frequent itemsets are measured only by their support. In this paper, we first design two algorithms for mining bridging rules between clusters, and then propose two non-linear metrics to measure their interestingness. We evaluate these algorithms experimentally and demonstrate that our approach is promising.

Dynamic behavioral assessment model based on Hebb learning rule

“…Therefore, as to the behavioral assessment, the research difficult is the complex behavior assessment of multiple elements variable, while the research hot spot of multiple elements variable behavioral assessment is the determination of relative weights of all the variables. The existing methods for determining the relative weights of multiple elements variable are expert assessment method [1,2], experience formula method [3,4], mean-variance method [5,6], and support-confidence method [7,8].…”

“…Arroyo and Fernandez [13] improved the meanvariance assessment method, and proposed the K-means fuzzy assessment method that improved the accuracy of mean-variance assessment method; Luque-Baena et al [14] also proposed the fuzzy assessment method based on K-means and used it to evaluate the robot behavior. Support-confidence method is the one assessing system behavior by the concept of support and confidence, and this method is usually combined with the research of data mining [7,8,[15][16][17]. Zhou et al [18] investigated the architecture and behavioral law of internetware and proposed the internetware behavioral assessment method based on support-confidence method, and this is a novel research direction for complex behavioral assessment based on support-confidence method.…”