Designing simulated annealing and subtractive clustering based fuzzy classifier

Torun, Yunis; Tohumoğlu, Gülay

doi:10.1016/j.asoc.2010.07.020

Cited by 32 publications

(11 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Where i ω are the weights. Compared with traditional mathematical modeling method, the ability of mathematical reasoning of T-S fuzz modeling is stronger [7,8].…”

Section: A the Description Of T-s Modelmentioning

confidence: 99%

“…Fuzzy rules can be detected from input and output datum of each subspace. Up to now, many methods have been proposed for this task including heuristics, clusteringbased method, neural networks, kernel-based method [8]. The method of clustering is the best way to identify object model structure.…”

Section: B Structure Identification Of T-s Fuzzy Modelingmentioning

confidence: 99%

“…In recent years, neural networks have been widely used for its strong ability of learning. According to the characteristics of the T-S fuzzy reasoning, it makes the mathematical model into a network structure, and creates an adaptive neural-fuzzy system [9,10].…”

Section: Parameter Estimation Of T-s Fuzzy Modelmentioning

confidence: 99%

See 2 more Smart Citations

Study on PIDNN control of circulating fluidized bed boiler based on T-S model

Liu¹,

Song²,

Song³

et al. 2013

JCP

View full text Add to dashboard Cite

Temperature and pressure are two main parameters of CFBB in the control system. Because of the CFBB possess the characteristics of time-varying, large lag and strong coupling, it is difficult to set up the arithmetical model and achieve better control effects. According to above difficulties, this paper adopts T-S fuzzy modeling method to description the input-output relationship for the control system based on collected data of system. On this basis, it adopts the PIDNN controller algorithm which has very strong adaptability and the whole system simulation is carried out by using MATLAB. The results of simulation experiment show that the designed model is effective and the control system achieves satisfied control effect.

show abstract

“…Where i ω are the weights. Compared with traditional mathematical modeling method, the ability of mathematical reasoning of T-S fuzz modeling is stronger [7,8].…”

Section: A the Description Of T-s Modelmentioning

confidence: 99%

Section: B Structure Identification Of T-s Fuzzy Modelingmentioning

confidence: 99%

See 1 more Smart Citation

Study on PIDNN control of circulating fluidized bed boiler based on T-S model

Liu¹,

Song²,

Song³

et al. 2013

JCP

View full text Add to dashboard Cite

show abstract

“…Consequents and outputs are shown in Figure 3a. (9) where u i is the normalized degree of fulfilment of the antecedent clause of rule shown in Equation (6) [13,18]. The normalized degree of fulfilment can be expressed by Equation (10).…”

Section: Takagi-sugeno's Modelmentioning

confidence: 99%

Computing Air Demand Using the Takagi–Sugeno Model for Dam Outlets

Zounemat‐Kermani

Scholz

2013

Water

View full text Add to dashboard Cite

An adaptive neuro-fuzzy inference system (ANFIS) was developed using the subtractive clustering technique to study the air demand in low-level outlet works. The ANFIS model was employed to calculate vent air discharge in different gate openings for an embankment dam. A hybrid learning algorithm obtained from combining back-propagation and least square estimate was adopted to identify linear and non-linear parameters in the ANFIS model. Empirical relationships based on the experimental information obtained from physical models were applied to 108 experimental data points to obtain more reliable evaluations. The feed-forward Levenberg-Marquardt neural network (LMNN) and multiple linear regression (MLR) models were also built using the same data to compare model performances with each other. The results indicated that the fuzzy rule-based model performed better than the LMNN and MLR models, in terms of the simulation performance criteria established, as the root mean square error, the Nash-Sutcliffe efficiency, the correlation coefficient and the Bias.

show abstract

“…The difference between filters and wrappers is whether the classifier is constructed during feature selection. The structure of the classifier is most often formed with the use of clustering methods designed to identify the data structure and build information granules that may be related to linguistic terms [5,8,9]. Parameters of fuzzy rules can be optimized using conventional approaches based on calculation of derivatives or of metaheuristics methods [9][10][11][12][13][14].…”

mentioning

confidence: 99%

Gravitational Search For Designing A Fuzzy Rule-Based Classifiers For Handwritten Signature Verification

Bardamova

Konev

Hodashinsky

et al. 2019

JCOMSS

View full text Add to dashboard Cite

Handwritten signatures are used in authentication systems as a universal biometric identifier. Signature authenticity verification requires building and training a classifier. This paper describes a new approach to the verification of handwritten signatures by dynamic characteristics with a fuzzy rule-based classifier. It is suggested to use the metaheuristic Gravitational Search Algorithm for the selection of the relevant features and tuning fuzzy rule parameters. The efficiency of the approach was tested with an original dataset; the type II errors in finding the signature authenticity did not exceed 0.5% for the worst model and 0.08% for the best model.

show abstract

Designing simulated annealing and subtractive clustering based fuzzy classifier

Cited by 32 publications

References 44 publications

Study on PIDNN control of circulating fluidized bed boiler based on T-S model

Study on PIDNN control of circulating fluidized bed boiler based on T-S model

Computing Air Demand Using the Takagi–Sugeno Model for Dam Outlets

Gravitational Search For Designing A Fuzzy Rule-Based Classifiers For Handwritten Signature Verification

Contact Info

Product

Resources

About