Mining association rules between sets of items in large databases
SIGMOD '93 Proceedings of the 1993 ACM SIGMOD international conference on Management of data
Unifying instance-based and rule-based induction
Machine Learning
Improving accuracy by combining rule-based and case-based reasoning
Artificial Intelligence
Lazy Learning of Bayesian Rules
Machine Learning
Introduction to Modern Information Retrieval
Introduction to Modern Information Retrieval
Data Mining: Concepts, Models, Methods and Algorithms
Data Mining: Concepts, Models, Methods and Algorithms
Combining the Strength of Pattern Frequency and Distance for Classification
PAKDD '01 Proceedings of the 5th Pacific-Asia Conference on Knowledge Discovery and Data Mining
Lazy Associative Classification for Content-based Spam Detection
LA-WEB '06 Proceedings of the Fourth Latin American Web Congress
Lazy Associative Classification
ICDM '06 Proceedings of the Sixth International Conference on Data Mining
AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1
Combination of metric-based and rule-based classification
RSFDGrC'05 Proceedings of the 10th international conference on Rough Sets, Fuzzy Sets, Data Mining, and Granular Computing - Volume Part I
Hi-index | 0.00 |
Most classification problems assume that there are sufficient training sets to induce the prediction knowledge. Few studies are focused on the label prediction according to the small knowledge. Hence, a classification algorithm in which the prediction knowledge is induced by only few training instances at the initial stage and is incrementally expanded by following verified instances is presented. We have shown how to integrate kNN and LARM methods to design a multi-strategy classification algorithm. In the experiments on edoc collection, we show that the proposed method improves 4% in accuracy of low-confidence results of kNN prediction and 8% in accuracy of results of the dominant class bias of LARM prediction. We also show experimentally that the proposed method obtains enhanced classification accuracy and achieves acceptable performance efficiency.