Integrated feature analysis and fuzzy rule-based system identification in a neuro-fuzzy paradigm

Chakrborty, D.; Pal, Nikhil R.

doi:10.1109/3477.931526

Cited by 73 publications

(59 citation statements)

References 30 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The feature selection phase in their method was integrated with the main learning task, and the MLP learned certain feature modulators along with the conventional weights and biases of a neural network. In [9], a neurofuzzy system was developed for simultaneous feature selection and system identification. The methodology developed in [9] was modified for a classifier in [10].…”

mentioning

confidence: 99%

“…In [9], a neurofuzzy system was developed for simultaneous feature selection and system identification. The methodology developed in [9] was modified for a classifier in [10].…”

mentioning

confidence: 99%

“…We term the feature selection methods described in [9], [10], and [39] and the method described in this paper as online methods. They are in spirit with the wrapper methods of feature selection.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Selecting Useful Groups of Features in a Connectionist Framework

Chakraborty

Pal

2008

IEEE Trans. Neural Netw.

Self Cite

View full text Add to dashboard Cite

Abstract-Suppose for a given classification or function approximation (FA) problem data are collected using sensors. From the output of the th sensor, features are extracted, thereby generating = =1 features, so for the task we have as input data along with their corresponding outputs or class labels . Here, we propose two connectionist schemes that can simultaneously select the useful sensors and learn the relation between and . One scheme is based on the radial basis function (RBF) network and the other uses the multilayered perceptron (MLP) network. Both schemes are shown to possess the universal approximation property. Simulations show that the methods can detect the bad/derogatory groups of features online and can eliminate the effect of these bad features while doing the FA or classification task.

show abstract

mentioning

confidence: 99%

“…In [9], a neurofuzzy system was developed for simultaneous feature selection and system identification. The methodology developed in [9] was modified for a classifier in [10].…”

mentioning

confidence: 99%

See 1 more Smart Citation

Selecting Useful Groups of Features in a Connectionist Framework

Chakraborty

Pal

2008

IEEE Trans. Neural Netw.

Self Cite

View full text Add to dashboard Cite

show abstract

“…ANFIS [32] is a well known neuro-fuzzy system consisting of a six-layer generalized network with supervised learning. Most of the current research on this area is derived from the original neuro-fuzzy concept, either in new flavors (i.e., by changing the network structure or the learning strategy) [33,34,35], or in adaptation of existing methods to face new hard problems. The main drawback of this approach is that the methods are intended to maximize accuracy, neglecting human interpretability.…”

Section: Bio-inspired Approaches: Neuro-fuzzy and Evolutionary-fuzzymentioning

confidence: 99%

Designing and Modeling Fuzzy Control Systems

Sharma¹

2011

IJCA

View full text Add to dashboard Cite

Fuzzy logic provides a formal framework for constructing systems exhibiting both good numeric performance (precision) and linguistic representation (interpretability). Fuzzy modeling-meaning the construction of fuzzy systems-is an arduous task, demanding the identification of many parameters. This paper analyses the fuzzy-modeling problem and different approaches to coping with it, focusing on evolutionary fuzzy modeling-the design of fuzzy inference systems using evolutionary algorithms. The purpose of this paper is twofold. We first provide an overview of the standard approach to constructing a fuzzy control system and then identify a wide variety of relevant system modeling techniques. The later part of the paper deals with discussing Fuzzy modeling problem -curse of dimensionality and techniques to solve the problem. The paper provides an introduction to the use of fuzzy sets and fuzzy logic for the approximation of functions and modeling of static and dynamic systems. The concept of a fuzzy system is first explained. Afterwards, the motivation and practical relevance of fuzzy modeling are highlighted.

show abstract

“…This is achieved by soliciting good debt, bad debt, and charge-off records from a credit card company database. An intelligent fuzzy-neural inference system (Chakraborty, 2001;Huang et. al., 2007) is utilized to construct a better prediction model.…”

Section: Introductionmentioning

confidence: 99%

Intelligent Detection of Bad Credit Card Accounts

Huang¹,

Sandnes²,

Chang³

et al. 2008

New Developments in Robotics Automation and Control

View full text Add to dashboard Cite

The effective management of credit risk is a critical component of risk management and essential to the long-term success of any banking organization. Credit-risk management practices vary considerably among organizations. Bad accounts affect the credit reputation of the cardholder and cause issuers to loose billions of dollars each year. However, bad debts problems are complex, full of uncertainty and can only be resolved through manual intervention. This study proposes an intelligent model for the early and accurate detection of bad accounts based on fuzzy logic (FL) and back propagation neural networks (BPN). Experimental results verify the effectiveness of the proposed strategy.

show abstract

Integrated feature analysis and fuzzy rule-based system identification in a neuro-fuzzy paradigm

Cited by 73 publications

References 30 publications

Selecting Useful Groups of Features in a Connectionist Framework

Selecting Useful Groups of Features in a Connectionist Framework

Designing and Modeling Fuzzy Control Systems

Intelligent Detection of Bad Credit Card Accounts

Contact Info

Product

Resources

About