Decision templates for multiple classifier fusion: an experimental comparison

By Ludmila I. Kuncheva, James C. Bezdek, Robert P. W. Duin. Pattern Recognition, 2001

1,083 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/5bc8e8631fda4f09c43d1dd68b1cb284d17a7c5c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistics and Probability

Citations in the corpus

Measures of Diversity in Classifier Ensembles and Their Relationship with the Ensemble Accuracy (2003, methodology): “%) between the diversity measures for the breast cancer data experiment Since the classiiers had continuous valued outputs, we applied other combination methods besides the majority vote (MAJ) (Kuncheva et al., 2001).”
A Theoretical Study on Six Classifier Fusion Strategies (2002, positive): “Simple fusion methods are the most obvious choice when constructing a multiple classifier system [4], [5], [11], [13], [14], i.e., the support for class ! i , d i ðxÞ, yielded by the team is d i ðxÞ ¼ Fðd 1;i ðxÞ; . . . ; d L;i ðxÞÞ; i ¼ 1; 2; ð1Þ where F is the chosen fusion method.”
Cost-sensitive decision tree ensembles for effective imbalanced classification (2014, positive): “While (majority) voting schemes are among the most popular fusion methods, often better results are obtained by approaches that consider the importance of decisions coming from particular committee members [28; 39].”
The combining classifier: to train or not to train? (2002, methodology): “An example of such a classifier used for com bining is the Decision Template proposed in [16].”
Fusing Multiple Features for Depth-Based Action Recognition (2015, background): “When there exist totally L classiﬁers, denoted by { D 1 , . . . , D L } , the representations for multiclassiﬁers can be given [Kuncheva et al. 2001] by (1) Decision i j D i , i ∈ [1 , L ], j ∈ [1 , c ]. we will present speciﬁc fusion methods for decision-level decision-level fusion as follows.”
Ensemble based systems in decision making (2006, methodology): “define the so-called decision profile matrix in [16], which allows us to present all of the following combination rules from a unified perspective.”
Learn$^{++}$ .NC: Combining Ensemble of Classifiers With Dynamically Weighted Consult-and-Vote for Efficient Incremental Learning of New Classes (2009, positive): “algebraic combinations of posterior probabilities [43], [51], Dempster–Shafer combination [52], decision templates [53], or meta decision trees [54].”
Classification with color and texture: jointly or separately? (2004, methodology): “Kuncheva et al. have carried out a comprehensive comparison of fusion methods for this kind of soft decisions [34].”
Relationships between combination methods and measures of diversity in combining classifiers (2002, methodology): “5 Decision Templates (DT ) The classifier outputs can be conveniently organised in a decision profile as the following matrix [22]”
Ensemble Learning for Time Series Prediction (2008, background): “In this study we rather focus on a different scheme that is combination of different classifiers [16], [26].”
Hybrid and ensemble-based soft computing techniques in bankruptcy prediction: a survey (2010, methodology): “The strategy used to aggregate predictors into an ensemble is one more issue greatly affecting the ensemble accuracy (Verikas and Lipnickas 2002; Kuncheva et al. 2001; Verikas et al. 1999; Liu 2005; Kuncheva 2002).”
Ensembles of Learning Machines (2002, methodology): “Different similarity measures can be used to evaluate the matching between the matrix of classifier outputs for an input x, that is the decision profiles referred to x, and the matrix templates (one for each class) found as the class means of the classifier outputs [81].”
Toward detecting emotions in spoken dialogs (2005, background): “2) because it achieves good performance in spite of its simplicity and less support by probabilistic interpretation [24], [25].”
A Survey of Decision Fusion and Feature Fusion Strategies for Pattern Classification (2010, methodology): “Most of decision fusion techniques discussed in this paper are taken from Kuncheva’s work [2,11] and classifier ranking has been obtained from Ho et al.”
Cost-sensitive boosting for classification of imbalanced data (2007, background): “Once a set of classifiers has been created, an effective way of combining their outputs must be found [54].”
Facial expression recognition using radial encoding of local Gabor features and classifier synthesis (2012, methodology): “Classical combination rules, such as the Borda count [39] and decision template [40], can be used to combine local classifiers and arrive at a global decision.”