지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
이용수34
Chapter 1. Introduction 11.1 Background 11.2 Research Purpose 31.3 Research Methods 51.4 Outlines of the dissertation 6Chapter 2. Naive Bayesian Classification 72.1 Naive Bayesian classifier 72.2 Weighted naive Bayesian classifier 92.3 Existing weighting methods 11Chapter 3. Proposed method: Heuristic optimization approach 133.1 Receiver operating characteristics 133.2 Weighting variances 163.3 Selecting attributes by AUC 193.4 Numerical Experiments 203.5 Chapter summary 28Chapter 4. Proposed method: Training error minimization 294.1 Minimizing loss functions 294.2 Comparative studies 344.3 Numerical experiments 374.4 Chapter summary 45Chapter 5. Proposed Method: AUC Maximization 465.1 RankOptAUC 475.2 RankOptNB 495.3 Attribute selection with RNB 515.4 Numerical experiments 555.5 Chapter summary 68Chapter 6. Numerical Experiments 696.1 Experimental design 696.2 Results 72Chapter7. Conclusion 80
0