Search

Decision templates (DT) are a technique for classifier fusion for continuous-valued individual classifier outputs. The individual outputs considered here sum up to the same value (e.g., statistical classifiers, yielding some estimates of the posterior probabilities for the classes). First, the DT fusion algorithm is explained. Second, we show that two similarity measures ( S 1 and S 2 ) and two inclusion indices ( I 1 and I 2 ) between fuzzy sets (see Dubois and Prade, Fuzzy Sets and Systems: Theory and Applications, Academic Press, New York, 1980) produce the same DT classifier. The equivalence is proven by showing that for every object submitted for classification, all four measures induce the same ordering on the set of class labels (through DT fusion), thereby assigning the object to the same class.

An aggregation operator of quantitative opinions about the acceptance or rejection of a certain alternative is proposed. The main idea is to include a degree of consensus between the experts in computing the final value. We aim at strengthening the acceptance or rejection rate if the experts agree in their assessments. The proposed operator is directly applicable to the two-level classification paradigm where a pool of classifiers is used to infer the decision. The operator allows us to form a complex classification boundary in the space of experts' (classifiers') decisions expressed in terms of degrees of membership. The connective can easily be extended to define a classifier with a “refuse-to-decide” option.

A fuzzy MLP model, developed by one of the authors, is used for obtaining selective two-level partitioning of the feature space in order to improve its classification performance. The model can handle uncertainty and/or impreciseness in the input as well as the output. The input to the network is modelled in terms of linguistic pi-sets whose centres and radii along the feature axes in each partition are generated automatically from the distribution of the training data. The performance of the model at the end of the first stage is used as a criterion for guiding the selection of the appropriate partition to be subdivided at the second stage, in order to improve the effectiveness of the model. A comparative study of the performance of the two-level technique with other methods, viz., the conventional MLP, linear discriminant analysis and the k-nearest neighbours algorithms, is also provided to demonstrate its superiority.

This paper discusses a two-level pattern recognition paradigm for problems with complex classification configuration. As a basic unit at the second level of the scheme, a neuron-like element is proposed whose transition function depends on the degree of consensus between its inputs. The greater the consensus, the steeper the transition slope. For each object to be classified, this model provides an opportunity to embed the certainty, measured as consensus between first-level classifiers (“experts”), into the final decision value for or against a given class. A simulated annealing algorithm is used for training. An experimental illustration with real data from aviation medicine is presented. The problem of prognosis of cardiac disorders during centrifuge training is considered. The results compare favorably to those obtained through other classification techniques.

Pattern recognition with fuzzy sets is considered with regard to medical diagnostic problems. An alternative interpretation of membership grade is suggested which expresses the degree of ‘illness’ of a patient with respect to a certain disease. A formal statement of a two-level fuzzy classifier is presented. The main emphasis is put on additional criteria designed to evaluate a fuzzy diagnostic decision for an unknown object. Two groups of criteria are formed-decision-making connected, and domain-dependent. The decision-making group of criteria can be viewed as related to the ‘soft’ consensus measure in group decisions theory. Interconnections between criteria are discussed. The notions proposed are illustrated with real medical data from the fields of aviation medicine and neonatology.