지능정보연구 (Journal of Intelligence and Information Systems)

  • 제7권1호
  • /
  • Pages.47-61
  • /
  • 2001
  • /
  • 2288-4866(pISSN)
  • /
  • 2288-4882(eISSN)
한국지능정보시스템학회 (Korea Intelligent Information System Society)
권호 표지

사례기반 추론을 위한 동적 속성 가중치 부여 방법

A Dynamic feature Weighting Method for Case-based Reasoning

  • 발행 : 2001.06.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

사례기반 추론과 같은 사후학습 기법은 인공신경망이나 의사결정나무와 같은 사전학습 기법에 비해서 여러 장점을 가지고 있다. 하지만, 사후학습 기법은 사례 표현에 관련성이 적은 속성이 포함된 경우에는 성능이 저하되는 단점을 가지고 있다. 이러한 단점을 극복하기 위해서, 속성 가중치 부여 방법들이 연구되었다. 기존의 속성 가중치 부여 방법들은 대부분 전역적으로 속성 가중치를 부여하는 것이었다. 본 연구에서는 새로운 지역적 속성 가중치 부여 방법인 CBDFW를 제안한다. CBDFW 기법은 무작위로 생성된 속성 가중치들의 분류 성공 여부를 저장하고 있다가, 새로운 사례가 주어졌을 때에 성공적인 분류 결과를 보인 가중치들을 검색하여 동적으로 새로운 가중치들을 생성해낸다. 신용평가 데이터로 CBDFW의 성능을 실험한 결과, 기존의 연구들에서 제시된 분류 적중률보다 우수한 성능을 보였다.

Lazy loaming methods including CBR have relative advantages in comparison with eager loaming methods such as artificial neural networks and decision trees. However, they are very sensitive to irrelevant features. In other words, when there are irrelevant features, larry learning methods have difficulty in comparing cases. Therefore, their performance can be degraded significantly. To overcome this disadvantage, feature weighting methods for lazy loaming methods have been studied. Most of the existing researches, however, were focused on global feature weighting. In this research, we propose a new local feature weighting method, which we shall call CBDFW. CBDFW stores classification performance of randomly generated feature weight vectors. Then, given a new query case, CBDFW retrieves the successful feature weight vectors and designs a feature weight vector fur the query case. In the test on credit evaluation domain, CBDFW showed better classification accuracy when compared to the results of previous researches.

키워드

참고문헌

  1. Artificial Intelligence Communications v.7 no.1 Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches Aamodt, A.;E. Plaza
  2. Proceedings of the Ninth International Workshop on Machine Learning Generalizing from Case Studies: A Case Study Aha, D. W.
  3. Feature Extraction, Construction and Selection: A Data Mining Perspective Feature Weighting for Lazy Learning Algorithms Aha, D. W.;Liu, H.(ed.);H. Motoda(ed.)
  4. Proceedings of AAAI-94 Workshop on CBR Feature Selection for Case-Based Classification of Cloud Types: An Empirical Comparison Aha, D. W.;R. L. Bankert
  5. Proceedings of the Ninth National Conference on the Cognitive Science Society Concept Learning and Flexible Weighting Aha, D. W.;R. L. Goldstone
  6. UCI Repository of Machine Learning Databases Blake, C.;E. Keogh;C. J. Merz
  7. Proceedings of the Tenth International Conference on Machine Learning Using Decision Trees to Improve Case-Based Reasoning Cardie, C.
  8. Proceedings of the Fourteenth International Conference on Machine Learning Improving Minority Class Prediction Using Case-Specific Feature Weights Cardie, C.;N. Howe
  9. Proceedings of the Eleventh International Conference on Machine Learning Greedy Attribute Selection Caruana, R.;D. Freitag
  10. Intelligent Data Analysis v.3 no.3 Feature Selection for Classification Dash, M.;H. Liu
  11. Machine Learning v.24 Unifying Instance-Based and Rule-Based Induction Domingos, P.
  12. Artificial Intelligence Review v.11 Context-Sensitive Feature Selection for Lazy Learners Domingos, P.
  13. Case-Based Reasoning Research and Development: Second International Conference on Case-Based Reasoning;Lecture Notes in Artificial Intelligence Examining Locally Varying Weights for Nearest Neighbor Algorithms Howe, N.;C. Cardie;Leake, D.(ed.);E. Plaza(ed.)
  14. Proceedings of the Eleventh International Conference on Machine Learning Irrelevant Features and the Subset Selection Problem John, G. H.;R. Kohavi;K. Pfleger
  15. '98 한국전문가시스템학회 추계 학술대회 논문집 Optimizing Retrieval of Precedents in Case-Based Reasoning through a Genetic Algorithm Kim, S. H.;S. Shin
  16. Proceedings of The Ninth International Workshop on Machine Learning A Practical Approach to Feature Selection Kira, A.;L. A. Rendell
  17. Case-Based Reasoning Kolodner, J.
  18. A Practical Guide to Neural Nets Nelson, M. M.;W. T. Illingworth
  19. Machine Learning v.1 no.1 Induction of Decision Trees Quinlan, J. R.
  20. International Journal of Man-Machine Studies v.27 Simplifying Decision Trees Quinlan, J. R.
  21. C4.5: Programs for Machine Learning Quinlan, J. R.
  22. '98 한국경영정보학회/한국전문가시스템학회 춘계 공동학술대회 논문집 A Hybrid Approach Using Case-based Reasoning and Genetic Algorithm for Corporate Bond Rating Shin, K.;I. Han
  23. Communications of the ACM v.29 Toward Memory-Based Reasoning Stanfill, C.;D. Waltz
  24. AI Review v.11 A Review and Empirical Comparison of Feature Weighting Methods for a Class of Lazy Learning Algorithms Wettschereck, D.;D. W. Aha;T. Mohri
  25. IEEE Intelligent Systems Feature Subset Selection Using a Genetic Algorithm Yang, J. H.;V. Honavar