A classification reliability driven reject rule for multi-expert systems

International Journal of Pattern Recognition and Artificial Intelligence

Volumn 15, Issue 6, 2001, Pages 885-904

  Sansone, C ^a   Tortorella, F ^b   Vento, M ^a  

^a UNIVERSITY OF NAPLES FEDERICO II   (Italy)

^b UNIVERSITY OF CASSINO AND SOUTHERN LAZIO   (Italy)

Author keywords

Classification; Classification cost; Multi expert systems; Reject option; Reliability

Indexed keywords

COMPUTATIONAL COMPLEXITY; DATABASE SYSTEMS; ERROR ANALYSIS; EXPERT SYSTEMS; FUNCTIONS; PROBLEM SOLVING; RELIABILITY THEORY; STATISTICAL METHODS;

CLASSIFICATION COST; MULTI-EXPERT SYSTEM; REJECT OPTION;

PATTERN RECOGNITION;

EID: 0035440291     PISSN: 02180014     EISSN: None     Source Type: Journal    
DOI: 10.1142/S0218001401001210     Document Type: Article

References (27)

1. Combination of classifiers on the decision level for face recognition
2. Democracy in neural nets: Voting schemes for classification
3. UCI repository of machine learning databases
4. Information combination operators for data fusion: A comparative review with classification
5. An optimum character recognition system using decision functions
6. On optimum recognition error and reject tradeoff
7. A method for improving classification reliability of multilayer perceptrons
8. Nearest neighbor pattern classification
9. Comparing generalization and recognition capability of learning vector quantization and multi-layer perceptron architectures
10. To reject or not to reject ... that's the question: An answer in case of neural classifiers
11. Multiclassification: Reject criteria for the Bayesian combiner
12. The optimum class-selective rejection rule
13. Decision combination in multiple classifier systems
14. A method of combining multiple experts for the recognition of unconstrained handwritten numerals
15. A probabilistic framework for combining multiple classifiers at abstract level
16. On combining classifiers
17. The self-organizing map
18. Optimal combination of pattern classifiers
19. Application of majority voting to pattern recognition: An analysis of its behavior and performance
20. A theory of classifier combination: The neural network approach
21. Multistage pattern recognition with reject option
22. An evaluation of multi-expert configurations for the recognition of handwritten numerals
23. Probabilistic neural networks
24. Cost-sensitive classification: Empirical evaluation of a hybrid genetic decision tree induction algorithm
25. Method of combining multiple classifiers and their application to handwritten numeral recognition