An extension of the type-1 and singleton fuzzy logic system trained by scaled conjugate gradient methods for multiclass classification problems

Abstract This paper proposes an extension of the type-1 and singleton fuzzy logic system for dealing with multiclass classification problems. The proposed extension enables a fuzzy classifier to generate more than one output, thereby avoiding the use of binary decomposition strategies when multiclass classification problems are considered. Additionally, with the goal of improving classifier performance, the scaled conjugate gradient training method was applied, as well as its modified version using the differential operator R · . The effectiveness of the proposed extension was evaluated using data from the UCI Machine Learning Repository based on well-established classification metrics. The numerical results reveal a significant reduction in computational complexity when using the proposed extension compared to the traditional decomposition strategy, as well as improved convergence speed when using the scaled conjugate gradient training method.

[1]  Cordelia Schmid,et al.  Good Practice in Large-Scale Learning for Image Classification , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Yu-Hong Dai,et al.  Conjugate Gradient Methods with Armijo-type Line Searches , 2002 .

[3]  Martin Fodslette Møller,et al.  A scaled conjugate gradient algorithm for fast supervised learning , 1993, Neural Networks.

[4]  Yoram Singer,et al.  Reducing Multiclass to Binary: A Unifying Approach for Margin Classifiers , 2000, J. Mach. Learn. Res..

[5]  Tom J. Moir,et al.  Comparison of multiclass SVM classification techniques in an audio surveillance application under mismatched conditions , 2014, 2014 19th International Conference on Digital Signal Processing.

[6]  Kishan G. Mehrotra,et al.  Efficient classification for multiclass problems using modular neural networks , 1995, IEEE Trans. Neural Networks.

[7]  Francisco Herrera,et al.  Enhancing Multiclass Classification in FARC-HD Fuzzy Classifier: On the Synergy Between $n$-Dimensional Overlap Functions and Decomposition Strategies , 2015, IEEE Transactions on Fuzzy Systems.

[8]  Francisco Herrera,et al.  Solving multi-class problems with linguistic fuzzy rule based classification systems based on pairwise learning and preference relations , 2010, Fuzzy Sets Syst..

[9]  S. Stehman.  Estimating the Kappa Coefficient and its Variance under Stratified Random Sampling , 1996 .

[10]  T. Steihaug.  The Conjugate Gradient Method and Trust Regions in Large Scale Optimization , 1983 .

[11]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[12]  Barak A. Pearlmutter.  Fast Exact Multiplication by the Hessian , 1994, Neural Computation.

[13]  D.T.H. Lai,et al.  The application of multiclass SVM to the detection of knee pathologies using kinetic data: a preliminary study , 2007, 2007 3rd International Conference on Intelligent Sensors, Sensor Networks and Information.

[14]  Stan Szpakowicz,et al.  Beyond Accuracy, F-Score and ROC: A Family of Discriminant Measures for Performance Evaluation , 2006, Australian Conference on Artificial Intelligence.

[15]  Moises V. Ribeiro,et al.  Type-1 and singleton fuzzy logic system trained by a fast scaled conjugate gradient methods for dealing with binary classification problems , 2019, Neurocomputing.

[16]  Ricardo Tanscheit,et al.  EANN 2014: a fuzzy logic system trained by conjugate gradient methods for fault classification in a switch machine , 2015, Neural Computing and Applications.