Rule-by-rule input significance analysis in fuzzy system modeling

2004-06-30
Uncu, O
Turksen, IB
Input or feature selection is one the most important steps of system modeling. Elimination of irrelevant variables can save time, money and can improve the precision of model that we are trying to discover. In Fuzzy System Modeling (FSM) approaches, input selection plays an important role too. The input selection algorithms that are under our investigation did not consider one crucial fact. An input variable may of may not be significant in a specific rule, not in overall system. In this paper, an input selection algorithm that takes this observation into account is proposed as an extension of the input selection algorithms found in the literature. The proposed algorithm is applied on a nonlinear function and successful results are achieved.

Suggestions

Comparison of two inference approaches in Gaussian graphical models
Purutçuoğlu Gazi, Vilda; Wit, Ernst (Walter de Gruyter GmbH, 2017-04-01)
Introduction: The Gaussian Graphical Model (GGM) is one of the well-known probabilistic models which is based on the conditional independency of nodes in the biological system. Here, we compare the estimates of the GGM parameters by the graphical lasso (glasso) method and the threshold gradient descent (TGD) algorithm.
Improvement in non-linearity of carlet-feng infinite class of boolean functions
Khan, Mansoor Ahmed; Özbudak, Ferruh (2012-12-01)
In this paper we present a Walsh spectrum based method derived from the genetic hill climbing algorithm to improve the non-linearity of functions belonging to Carlet-Feng infinite class of Boolean functions, without degrading other cryptographic properties they possess. We implement our modified algorithms to verify the results and also present a comparison of the resultant cryptographic properties with the original functions.
Two step feature selection: Approximate functional dependency approach using membership values
Uncu, O; Turksen, IB (2004-07-29)
Feature selection is one of the most important issues in fields such as system modelling and pattern recognition. In this study, a new feature selection algorithm that combines feature wrapper and feature filter approaches is proposed in order to identify the significant input variables in systems with continuous domains. The proposed method utilizes functional dependency concept and K-Nearest Neighbourhood method to implement the feature filter and feature wrapper, respectively. It is common to have outlie...
Supervisory control and formal methods for distributed systems
İnan, Kemal (1992-08-28)
A brief introductory exposure for logical discrete event system models is presented. Based on a specific version of this model tailored to supervisory control, some of the mainstream supervisory control problems are formulated in a unified framework. Formal methods used in software engineering has certain computational and structural similarities to supervisory control and unlike the latter, is closely connected to realistic and widespread practical applications. Formal specification, verification, impleme...
Texture classification and retrieval using random neural network model
Teke, Alper; Atalay, Mehmet Volkan; Department of Computer Engineering (2003)
Texture is one of the most important characteristics used in computer vision and image processing applications. In this thesis, a new texture classification and retrieval method is proposed for texture analysis applications. The technique makes use of the random neural network model and it is supervised. The main aim is to represent textures with parameters which are the random neural network weights and classify and retrieve textures using this texture definition. The network has neurons that correspond to...
Citation Formats
O. Uncu and I. Turksen, “Rule-by-rule input significance analysis in fuzzy system modeling,” 2004, p. 931, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/66157.