Mining top-k association rules
Canadian AI'12 Proceedings of the 25th Canadian conference on Advances in Artificial Intelligence
Mining top-K non-redundant association rules
ISMIS'12 Proceedings of the 20th international conference on Foundations of Intelligent Systems
Hi-index | 0.00 |
The real-world data may be usually polluted by uncontrolled factors or contained with noisy. Fault-tolerant frequent pattern can overcome this problem. It may express more generalized information than frequent pattern which is absolutely matched. The present research is integrated with previous research into an integrity new method, called Top-NFTDS, to discover fault-tolerant association rules over stream. It can discover top-k true fault-tolerant rules without minimum support threshold and minimum confidence threshold specified by user. We extend the negative itemsets to fault-tolerant space and disambiguate redundant patterns by this algorithm. Experiment results show that the developed algorithm is an efficient method for mining top-k fault-tolerant association rules in data streams.