A new computationally efficient mamdani interval type-2 fuzzy modelling framework

Wang, Shen; Mahfouf, Mahdi

doi:10.1109/fuzz-ieee.2012.6251288

Cited by 4 publications

(2 citation statements)

References 27 publications

(23 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results of the proposed DPGMM (TSK1 -T1 TSK model, TSK2 -T2 TSK model, Mam1 -T1 Mamdani model and Mam2 -T2 Mamdani model) approaches are compared with four algorithms obtained from the literature i.e. Artificial Neural Networks (ANN), type-1 fuzzy model (T1FM) [19], Mamdani Interval Type-2 Fuzzy Model (MIT2FM) [36], Linear Regression (LR) and Interval Type-2 Fuzzy Modelling (IT2FM) [18].…”

Section: Resultsmentioning

confidence: 99%

A Dirichlet Process Based Type-1 and Type-2 Fuzzy Modeling for Systematic Confidence Bands Prediction

Obajemu

Mahfouf

2019

IEEE Trans. Fuzzy Syst.

View full text Add to dashboard Cite

This paper presents a new methodology for fuzzy logic systems modelling based on the Dirichlet Process Gaussian Mixture Models (DPGMM). The proposed method simultaneously allows for the systematic elicitation of confidence bands as well as the automatic determination of model complexity.The work is new since existing fuzzy model elicitation techniques use ad-hoc methods for confidence band estimations which do not meet the stringent requirements of today's challenging environments where data is sparse, incomplete, and characterised by noise as well as uncertainties. The proposed approach involves an integration of fuzzy and Bayesian topologies and allows for the generation of confidence bands based on both the random and linguistic uncertainties embedded in the data.Additionally, the proposed method provides a 'right-first time approach' to fuzzy modelling as it does not require an iterative model complexity determination. In order to see how the proposed framework performs across a variety of challenging data modelling problems, the proposed approach was tested on a non-linear synthetic dataset as well as two real multi-dimensional datasets generated by the authors from materials science and bladder cancer studies. Results show that the proposed approach consistently provides better generalisation performances than other well-known soft computing modelling frameworks -in some cases, improvements of up to 20% in modelling accuracy were achieved. The proposed method also provides the capability to handle uncertainties via the generation of systematic confidence intervals for informing on model reliability. These results are significant since the generic methodologies developed in the paper should help material scientists as well as clinicians, for example, assess the risks involved in making informed decisions based on model predictions.

show abstract

Section: Resultsmentioning

confidence: 99%

A Dirichlet Process Based Type-1 and Type-2 Fuzzy Modeling for Systematic Confidence Bands Prediction

Obajemu

Mahfouf

2019

IEEE Trans. Fuzzy Syst.

View full text Add to dashboard Cite

show abstract

“…4) in the FLS instead of the general T2 FLS. The Karnik-Mendel algorithms and its variants [22]- [24] provide a fast iterative mechanism for type reduction. This work makes use of the IT2 approach since it represents a trade-off between exploiting the degree of freedom and the reasonable computational speed especially for high dimensional modelling problems.…”

Section: A Fuzzy Systems Modellingmentioning

confidence: 99%

A New Fuzzy Modeling Framework for Integrated Risk Prognosis and Therapy of Bladder Cancer Patients

Obajemu

Mahfouf

Catto

2018

IEEE Trans. Fuzzy Syst.

Self Cite

View full text Add to dashboard Cite

This paper presents a new fuzzy modelling approach for analysing censored survival data and finding risk groups of patients diagnosed with bladder cancer. The proposed framework involves a new procedure for integrating the frameworks of interval type-2 fuzzy logic and Cox modelling intrinsically. The output of this synergistic framework is a score/prognostics index which is indicative of the patient's level of mortality risk. A threshold value is selected whereby patients with risk scores that are greater than this threshold are classed as high risk patients and vice versa.Unlike in the case of black-box type modelling approaches, the paper shows that interpretability and transparency are maintained using the proposed fuzzy modelling framework.Two data sets are used to test the modelling accuracy of the elicited models. The first is an artificial data set which has similar characteristics as in a typical survival data. The second relates to real-life bladder cancer data from which one requires a model that identifies the low risk and high risk patients and then recommends risk management decisions based on, predicted risk level, patient history and characteristics, disease pathology and event times. The performance of the proposed framework is compared with the traditional Cox model, logistic regression as well as a non-linear survival data modelling technique based on neural networks. This is the first time an attempt has been made to exploit the transparency advantages of fuzzy models and the principled statistical framework of the Cox model in order to identify risk groups and recommend risk management decisions from complex survival data sets. In both the artificial data and real data, the proposed modelling framework, although minimalistic, shows better generalisation performances than the previously reported models against which the results were compared.O. Obajemu and M. Mahfouf are with the

show abstract

On defining complex uncertainty data points by type-2 fuzzy number: two specials cases

Zakaria¹,

Wahab²

2013

ijma

View full text Add to dashboard Cite

In this paper, we will discuss about the defining complex uncertainty data points based on the definition of type-2 fuzzy number (T2FN) concepts. This defining process of complex uncertainty data points have two cases that are the complex uncertainty data points which defined when the complex uncertainty happened at their membership function values, and the complex uncertainty data points are defined when the complex uncertainty happened at their footprint. After the complex uncertainty data points had been defined which known as type-2 fuzzy data points (T2FDPs) for both cases, we applied the fuzzification (alpha-cut operation), type-reduction and defuzzification processes to show the data forms processes from T2FDPs to crisp T2FDPs solution which in singular data forms. These steps for obtaining the crisp T2FDPs solution are being modeled through non-uniform rational B-spline (NURBS) curve function as the addition for more understanding.

show abstract

A new computationally efficient mamdani interval type-2 fuzzy modelling framework

Cited by 4 publications

References 27 publications

A Dirichlet Process Based Type-1 and Type-2 Fuzzy Modeling for Systematic Confidence Bands Prediction

A Dirichlet Process Based Type-1 and Type-2 Fuzzy Modeling for Systematic Confidence Bands Prediction

A New Fuzzy Modeling Framework for Integrated Risk Prognosis and Therapy of Bladder Cancer Patients

On defining complex uncertainty data points by type-2 fuzzy number: two specials cases

Contact Info

Product

Resources

About