엔트로피 기반 분할과 중심 인스턴스를 이용한 분류기법의 데이터 감소

• 영문명: Data reduction for classification using entropy-based partitioning and center instances
• 발행기관: 한국산업경영시스템학회
• 저자명: 손승현 김재련
• 간행물 정보: 『한국산업경영시스템학회 학술대회』2005년 추계학술대회 논문집, 133~137쪽, 전체 5쪽
• 주제분류: 공학 > 산업공학
• 파일형태: PDF
• 발행일자: 2005.10.01

영문 초록

  Instance-based learning methods like the nearest neighbour classifier have been proven to perform well in pattern classification on many fields. Despite their high classification accuracy, they suffer from high storage requirement, computational cost and sensitivity to noise. In this paper, we present a data reduction method for classification techniques based on entropy-based partitioning and center instances. Experimental results show that the new algorithms achieve a high data reduction rate as well as classification accuracy.

목차

Abstract
1. 서론
2. 제안 알고리듬
3. 실험 결과
4. 결론
참고문헌

키워드

Data reduction Data mining Instance-based learning