DOI QR코드

DOI QR Code

면 객체 매칭을 위한 판별모델의 성능 평가

Evaluation of Classifiers Performance for Areal Features Matching

  • 김지영 (서울대학교 대학원 공과대학 건설환경공학부) ;
  • 김정옥 (서울대학교 공학연구소) ;
  • 유기윤 (서울대학교 공과대학 건설환경공학부) ;
  • 허용 (서울대학교 공학연구소)
  • 투고 : 2013.01.22
  • 심사 : 2013.02.15
  • 발행 : 2013.02.28

초록

데이터마이닝과 바이오인식 분야의 판별모델의 성능평가 방법을 이종의 공간 데이터 셋의 매칭에 적용함으로써 좋은 매칭결과를 보이는 판별모델을 도출하고자 한다. 이를 위하여 매칭 기준별 매칭 후보객체 쌍의 거리 값을 구하고, 이들 거리 값을 Min-Max 방법과 Tanh 방법으로 정규화하여 유사도를 산출한다. 산출된 유사도를 CRITIC 방법, Matcher Weighting 방법 그리고 Simple Sum 방법으로 결합하여 형상유사도를 도출하는 판별모델을 적용하였다. 각 판별모델을 PR곡선과 AUC-PR로 평가한 결과, Tanh 정규화와 Simple Sum 방법을 적용한 판별모델의 AUC-PR이 0.893으로 가장 높게 나타났다. 따라서 이종의 공간 데이터 셋의 매칭을 위해서는 Tanh 정규화를 이용하여 각 매칭기준별 유사도를 산출하고 Simple Sum 방법으로 형상유사도를 구하는 판별모델이 적합한 것으로 사료된다.

In this paper, we proposed a good classifier to match different spatial data sets by applying evaluation of classifiers performance in data mining and biometrics. For this, we calculated distances between a pair of candidate features for matching criteria, and normalized the distances by Min-Max method and Tanh (TH) method. We defined classifiers that shape similarity is derived from fusion of these similarities by CRiteria Importance Through Intercriteria correlation (CRITIC) method, Matcher Weighting method and Simple Sum (SS) method. As results of evaluation of classifiers performance by Precision-Recall (PR) curve and area under the PR curve (AUC-PR), we confirmed that value of AUC-PR in a classifier of TH normalization and SS method is 0.893 and the value is the highest. Therefore, to match different spatial data sets, we thought that it is appropriate to a classifier that distances of matching criteria are normalized by TH method and shape similarity is calculated by SS method.

키워드

참고문헌

  1. Bengio, S., Marethoz, J. and Keller, M. (2005), The expected performance curve, Proceedings of the ICML'05 workshop on ROC analysis in machine learning, Germany, pp. 43-50.
  2. Davis, J. and Goadrich, M. (2006), The relationship between precision-recall and ROC curves, Proceedings of the 23rd International Conference on Machine Learning, USA, pp. 233-240.
  3. Diakoulaki, D., Mavrotas, G. and Papayannakis, L. (1995), Determing objective weights in multiple criteria problems: the CRITIC method, Computers & Operational Research, Elsevier, Vol. 22, No. 7, pp. 763-770. https://doi.org/10.1016/0305-0548(94)00059-H
  4. Fu, Z. and Wu, J. (2008), Entity matching in vector spatial data, Proceedings of the XXIth ISPRS Congress, ISPRS, China, pp. 1467-1472.
  5. Han, J., Kamber, M. and Pei, J. (2011), Data Mining: Concepts and Techniques, Third Edition, Morgan Kaufmann, USA, pp. 370.
  6. Huang, L., Wang, S., Ye, Y., Wang, B. and Wu, L. (2010), Feature matching in cadastral map integration with a case study of Beijing, Proceedings of 2010 18th International Conference on Geoinformatics, IEEE, China, pp. 1-4.
  7. Jain. A., Nandakumar, K. and Ross, A. (2005), Score normalization in multimodal biometric systems, Pattern Recognition, Elsevier, Vol. 38, No. 12, pp. 2270-2285. https://doi.org/10.1016/j.patcog.2005.01.012
  8. Samal, A., Seth, S. and Cueto, K. (2004), A featurebased approach to conflation of geospatial sources, International Journal of Geographical Information science, Taylor & Francis, Vol. 18, No. 5, pp. 459-489. https://doi.org/10.1080/13658810410001658076
  9. Snelick, R., Uludag, U., Mink, A., Indovina, M. and Jain, A. (2005), Large scale evaluation of multimodal biometric authentication using state-of-the-art systems, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 27, No. 3, pp. 450-455. https://doi.org/10.1109/TPAMI.2005.57
  10. Wenjing, T., Yanling, H., Yuxin, Z. and Ning, L. (2008), Research on areal feature matching algorithm based on spatial similarity, Proceedings of Control and Decision Conference (CCDC 2008), China, pp. 3326-3330.
  11. Woo, N. and Kim, H. (2006), Performance evaluation of various normalization methods and score-level fusion algorithms for multiple-biometric system, Journal of the Korea Institute of Information Security and Cryptology, Vol.16, No. 3, pp. 37-46.
  12. Yang, B., Luan, X. and Li, Q. (2010), An adaptive method for identifying the spatial patterns in road networks, Computers, Environment and Urban Systems, Elsevier, Vol. 34, No. 1, pp. 40-48. https://doi.org/10.1016/j.compenvurbsys.2009.10.002
  13. Zhang, L., Zhang, L., Zhang, D. and Shu, H. (2011), Ensemble of local and global information for fingerknuckle-print recognition, Pattern Recognition, Elsevier, Vol. 44, No. 9, pp. 1990-1998. https://doi.org/10.1016/j.patcog.2010.06.007

피인용 문헌

  1. 계층적 매칭 기법을 이용한 수치지도 건물 폴리곤 데이터의 자동 정합에 관한 연구 vol.33, pp.1, 2015, https://doi.org/10.7848/ksgpc.2015.33.1.45