Adaptive behavioral control of collaborative robots in hazardous environments
HSI'09 Proceedings of the 2nd conference on Human System Interactions
Active rule learning using decision tree for resource management in Grid computing
Future Generation Computer Systems
| Hi-index | 0.00 |
Rule design is very important for active database system implementation. But, it is also very difficult for us because of lacking methodology and support. In the paper, active rule design is regarded as a whole process and identified to three steps: rule extraction, rule analysis, and rule update. Data mining technique is originally introduced into rule design by us to cope with the problems arisen in active semantic extraction, termination analysis of rules set, and rules update. Rule mining methods are adopted to extract active semantics, and the discovered rules are used to assist active rule specification. Data mining technique is integrated with the triggering graph to improve the accuracy of termination analysis. Finally, data mining technique is used to identify new semantics and determine which rules should be updated.