Proceedings of the Korean Information Science Society Conference (한국정보과학회:학술대회논문집)
- 1999.10b
- /
- Pages.551-553
- /
- 1999
- /
- 1598-5164(pISSN)
Metalevel Data Mining through Multiple Classifier Fusion
다수 분류기를 이용한 메타레벨 데이터마이닝
Abstract
This paper explores the utility of a new classifier fusion approach to discrimination. Multiple classifier fusion, a popular approach in the field of pattern recognition, uses estimates of each individual classifier's local accuracy on training data sets. In this paper we investigate the effectiveness of fusion methods compared to individual algorithms, including the artificial neural network and k-nearest neighbor techniques. Moreover, we propose an efficient meta-classifier architecture based on an approximation of the posterior Bayes probabilities for learning the oracle.
Keywords