Uncertainty Estimation Using Fuzzy Measures for Multiclass Classification

Abstract

Uncertainty arises in classification problems when the input pattern is not perfect or measurement error is unavoidable. In many applications, it would be beneficial to obtain an estimate of the uncertainty associated with a new observation and its membership within a particular class. Although statistical classification techniques base decision boundaries according to the probability distributions of the patterns belonging to each class, they are poor at supplying uncertainty information for new observations. Previous research has documented a multiarchitecture, monotonic function neural network model for the representation of uncertainty associated with a new observation for two-class classification. This paper proposes a modification to the monotonic function model to estimate the uncertainty associated with a new observation for multiclass classification. The model, therefore, overcomes a limitation of traditional classifiers that base decisions on sharp classification boundaries. As such, it is believed that this method will have advantages for applications such as biometric recognition in which the estimation of classification uncertainty is an important issue. This approach is based on the transformation of the input pattern vector relative to each classification class. Separate, monotonic, single-output neural networks are then used to represent the "degree-of-similarity" between each input pattern vector and each class. An algorithm for the implementation of this approach is proposed and tested with publicly available face-recognition data sets. The results indicate that the suggested approach provides similar classification performance to conventional principle component analysis (PCA) and linear discriminant analysis (LDA) techniques for multiclass pattern recognition problems as well as providing uncertainty information caused by misclassification.

Promises, Pitfalls, and Basic Guidelines for Applying Machine Learning Classifiers to Psychiatric Imaging Data, with Autism as an Example

“…This means that the labels are noisy, i.e., we cannot be certain that the label is correct in every case, and hence classification accuracy is limited by the accuracy of behavioral assessments. Employing classification approaches that account for the noisy labeling might deliver superior results (60). An alternative is to apply unsupervised methods that do not require any class labels [(24), Chapter 10].…”

Complement information entropy for uncertainty measure in fuzzy rough set and its applications

“…Uncertainty measure becomes increasingly important in computational intelligence, machine learning and artificial intelligence. Many different uncertainty representations can be used to measure information imprecision and ambiguity, such as probability uncertainty (Zadeh 1968;Eslami 2003, 2004;Halliwell and Shen 2009;Liu 2013), possibility uncertainty (Zadeh 1978;Cooman 1997;Nguyen and Bouchon-Meunier 2003;Coletti et al 2008;Yager 2011;Flage et al 2012), fuzzy uncertainty (De Luca and Termini 1972;Pal and Bezdek 1994;Klir and Smith 2001;Yager 2002;Bertoluzza et al 2004;Mesiar 2005;Graves and Nagarajah 2007) and rough uncertainty (Beaubouf et al 1998;Wierman 1999;Liang et al 2002Liang et al , 2006.…”

A study in facial regions saliency: a fuzzy measure approach

“…Other applications of fuzzy measure in pattern recognition were presented, for instance, in Pedrycz (1990), where the measure was found helpful in the process of features selection. Graves and Nagarajah (2007) presented the model of estimation of the uncertainty for a new observation for multiclass classifier. In Keller et al (1994) fuzzy measure was applied to fusion of handwritten character classifiers, and in (Yan and Keller 1991) the method of image segmentation was described.…”