Gradual Complex Numbers and Their Application for Performance Evaluation Classifiers
- 28 March 2017
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 26 (2) , 1058-1065
Abstract
Usually, the evaluation of the classifiers performance is not an easy task to be performed, mainly when we analyze different criteria (output parameters). In this evaluation process, we can use quantitative measures (accuracy, specificity, among others), however when the output values are very close and we have several criteria, the results are difficult to be interpreted by users. This paper aims to propose a new linguistic model to evaluate the performance of several classifiers. It is based on the notion of Gradual Complex Numbers (GCN), proposed in [19]. In this paper, we present the theoretical basis of GCNs for classifier evaluator and we assess the performance of the proposed model (GCN) through an empirical study. In addition, the performance of GCN is compared with that of Fuzzy Complex Numbers (FCN),[6], and it reveals gains.Keywords
This publication has 11 references indexed in Scilit:
- Gradual Complex Numbers2015
- Fuzzy complex numbers and their application for classifiers performance evaluationPattern Recognition, 2011
- Fuzzy Compositional ModelingIEEE Transactions on Fuzzy Systems, 2010
- A systematic analysis of performance measures for classification tasksInformation Processing & Management, 2009
- Exploring the boundary region of tolerance rough sets for feature selectionPattern Recognition, 2009
- New Approaches to Fuzzy-Rough Feature SelectionIEEE Transactions on Fuzzy Systems, 2008
- Gradual Numbers and Their Application to Fuzzy Interval AnalysisIEEE Transactions on Fuzzy Systems, 2008
- Fuzzy-rough nearest neighbor algorithms in classificationFuzzy Sets and Systems, 2007
- Instance-based learning algorithmsMachine Learning, 1991
- Methods and Applications of Interval Analysis1979