Rough Sets: Theoretical Aspects of Reasoning about Data
Rough Sets: Theoretical Aspects of Reasoning about Data
Face recognition using a kernel fractional-step discriminant analysis algorithm
Pattern Recognition
Rough set theory with discriminant analysis in analyzing electricity loads
Expert Systems with Applications: An International Journal
Rough Cluster Quality Index Based on Decision Theory
IEEE Transactions on Knowledge and Data Engineering
Three-way decisions with probabilistic rough sets
Information Sciences: an International Journal
Push-Pull marginal discriminant analysis for feature extraction
Pattern Recognition Letters
Projection-pursuit approach to robust linear discriminant analysis
Journal of Multivariate Analysis
RSKT'10 Proceedings of the 5th international conference on Rough set and knowledge technology
Probabilistic model criteria with decision-theoretic rough sets
Information Sciences: an International Journal
Decision-Theoretic rough sets with probabilistic distribution
RSKT'12 Proceedings of the 7th international conference on Rough Sets and Knowledge Technology
Incorporating logistic regression to decision-theoretic rough sets for classifications
International Journal of Approximate Reasoning
Hi-index | 0.00 |
Discriminant analysis is an effective methodology to deal with the classification problem. However, most common methods including binary logistic regression in discriminant analysis rarely consider the semantics explanations such as losses or costs in decision rules. From the idea of three-way decisions in decision-theoretic rough sets (DTRS), we propose a new discriminant analysis approach by combining DTRS and binary logistic regression. DTRS is utilized to systematically calculate the corresponding thresholds with Bayesian decision procedure. Meanwhile, the binary logistic regression is employed to compute the conditional probability of three-way decisions. An empirical study validates the reasonability and effectiveness of the proposed approach.