Uneven Input Space Division and Balance of Generality and Conciseness of Submodels for Hierarchical Fuzzy Modeling

2000 ◽  
Vol 4 (2) ◽  
pp. 152-157
Author(s):  
Kanta Tachibana ◽  
◽  
Takeshi Furuhashi ◽  
Keyword(s):  
Fuzzy Neural Network ◽  
Fuzzy Model ◽  
Fuzzy Modeling ◽  
Performance Indices ◽  
Promising Technique ◽  
Input Space ◽  
Fuzzy Models ◽  
Multiple Input ◽  
Fuzzy Neural ◽  
Hierarchical Fuzzy Model

Hierarchical fuzzy modeling is a promising technique to describe input-output relationships of nonlinear systems with multiple input. This paper presents a new method of dividing input spaces for hierarchical fuzzy modeling using the Fuzzy Neural Network (FNN) and Genetic Algorithm (GA). Uneven division of input space for each submodel in the hierarchical fuzzy model can be achieved with the proposed method. The obtained hierarchical fuzzy models are likely more concise and more precise than those identified with conventional methods. Studies on effects of the weights on performance indices of generality and conciseness of the fuzzy model are also shown in this paper.

Application of T-S Fuzzy Neural Network in the Assessment of River Ecosystem Health

2013 ◽  
Vol 726-731 ◽  
pp. 958-962 ◽  
Author(s):  
Zhen Chun Hao ◽  
Xiao Li Liu ◽  
Qin Ju
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Fuzzy System ◽  
Ecosystem Health ◽  
Fuzzy Neural Network ◽  
Evaluation Model ◽  
Fuzzy Model ◽  
River Ecosystem ◽  
Fuzzy Neural

Healthy river ecosystem has been acknowledged as the object of river management, which is crucial for the sustainable development of cities. Simple and practical evaluation methods with great precision are necessary for the evaluation of river ecosystem health. Fuzzy system has been widely used in evaluation and decision making for its simple reasoning and the adoption of experts knowledge. However, much artificial intervention decreases the precision. Neural network has a strong ability of self-leaning while it is not good at expressing rule-based knowledge. The T-S fuzzy neural network model combines the advantages of fuzzy system and neural network. In this paper, the T-S fuzzy neural network model was used to establish a river ecosystem health evaluation model. Results show that the combination of T-S fuzzy model and neural network eliminates the influences of subjective factors and improve the final precisions efficiently.

scholarly journals Optimization of parameters of neuro-fuzzy model

2020 ◽  
Vol 17 (3) ◽  
pp. 1206
Author(s):  
Lyalya Bakievna Khuzyatova ◽  
Lenar Ajratovich Galiullin
Keyword(s):  
Neural Network ◽  
Decision Support ◽  
Decision Support Systems ◽  
Fuzzy Neural Network ◽  
Support Systems ◽  
Fuzzy Model ◽  
Knowledge Bases ◽  
Fuzzy Neural Networks ◽  
Neural Network Models ◽  
Fuzzy Neural

<p>The questions and problems of the formation of knowledge bases of intelligent man-machine decision support systems are considered. The neuron-fuzzy model used in the work is described. The need for increasing the efficiency of the neuron-fuzzy model in the formation of knowledge bases is being updated. The task is to develop methods and algorithms for presetting and optimizing the parameters of a fuzzy neural network. To solve difficult formalized tasks, it is necessary to develop decision support systems - expert systems based on a knowledge base. ES developers are constantly faced with the problems of “extraction” and formalization of knowledge, as well as the search for new ways to obtain it. To do this, use the extraction, acquisition and formation of knowledge. Currently, the formation of knowledge bases is relevant for the creation of hybrid technologies - fuzzy neural networks that combine the advantages of neural network models and fuzzy systems. The analysis of the efficiency of the fuzzy neural network carried out in the work showed that the quality of training of the NN largely depends on the choice of the number of fuzzy granules for input drugs. In addition, to use fuzzy information formalized by the mathematical apparatus of fuzzy logic, procedures are required for selecting optimal forms and presetting the parameters of the corresponding membership functions (MF).</p>

A Proposal of Visualization Method for Interpretable Fuzzy Model on Fusion Axes

2006 ◽  
Vol 10 (1) ◽  
pp. 121-131 ◽  
Author(s):  
Kosuke Yamamoto ◽  
◽  
Tomohiro Yoshikawa ◽  
Takeshi Furuhashi
Keyword(s):  
Fuzzy Model ◽  
Visualization Method ◽  
Statistical Features ◽  
Artificial Data ◽  
Linear Combinations ◽  
Useful Knowledge ◽  
Fuzzy Models ◽  
Multiple Input ◽  
Input Variables ◽  
Interpretable Models

Interpretability of fuzzy models has become one of the major topics in the field of fuzzy modeling. Visualization that makes input-output relationships interpretable is effective in extracting useful knowledge from unknown data. This paper presents visualization method that considers the visibility of fuzzy models. This method identifies clusters that have different statistical features, and projects the data to the “fusion axes”, which are linear combinations of the multiple input variables, considering the distribution of each cluster in the projected space. This paper applies the proposed method to artificial data and also to collected data from the mobile robot, and shows that the proposed method can extract useful knowledge from the obtained visible and interpretable models.

scholarly journals Optimization of parameters of neuro-fuzzy model

2020 ◽  
Vol 19 (1) ◽  
pp. 229
Author(s):  
Lyalya Bakievna Khuzyatova ◽  
Lenar Ajratovich Galiullin
Keyword(s):  
Neural Network ◽  
Fuzzy Neural Network ◽  
Fuzzy Model ◽  
Network Models ◽  
Knowledge Bases ◽  
Fuzzy Neural Networks ◽  
Neural Network Models ◽  
Neuro Fuzzy ◽  
Fuzzy Neural

<p>The need for increasing the efficiency of the neuron-fuzzy model in the formation of knowledge bases is being updated. The task is to develop methods and algorithms for presetting and optimizing the parameters of a fuzzy neural network. To solve difficult formalized tasks, it is necessary to develop decision support systems - expert systems based on a knowledge base. ES developers are constantly faced with the problems of “extraction” and formalization of knowledge, as well as the search for new ways to obtain it. To do this, use the extraction, acquisition and formation of knowledge. Currently, the formation of knowledge bases is relevant for the creation of hybrid technologies - fuzzy neural networks that combine the advantages of neural network models and fuzzy systems. The analysis of the efficiency of the fuzzy neural network carried out in the work showed that the quality of training of the NN largely depends on the choice of the number of fuzzy granules for input drugs. In addition, to use fuzzy information formalized by the mathematical apparatus of fuzzy logic, procedures are required for selecting optimal forms and presetting the parameters of the corresponding membership functions (MF).</p>

A Robust Operator Functional State Fuzzy Modeling Approach Based on EEG Data

2014 ◽  
Vol 556-562 ◽  
pp. 4065-4068
Author(s):  
Shao Zeng Yang ◽  
Jian Hua Zhang
Keyword(s):  
Membership Function ◽  
Functional State ◽  
Fuzzy Model ◽  
Fuzzy Modeling ◽  
Crossover Point ◽  
New Approach ◽  
Fuzzy Models ◽  
Eeg Data ◽  
Operator Functional State ◽  
Machine Systems

Operator functional state (OFS) is defined as the time-variable ability that an operator completes his/her assigned tasks. To evaluate the OFS in safety-critical human-machine systems, it is modeled by using the Wang-Mendel-based fuzzy system paradigm in this paper. The fuzzy model is constructed to correlate three EEG features (as model inputs) to the human-machine system performance (as model output). To derive a fuzzy model for real-time OFS assessment, the Gaussian membership function membership crossover point membership gradeδis found to be an essential parameter that controls the robustness of data-driven fuzzy models. The fuzzy models with differentδare applied to the OFS fuzzy modeling. The results have demonstrated that an appropriate value ofδcan be selected to derive robust fuzzy models. Compare with the results obtained by fuzzy models based on symmetric Gaussian membership functions, the new approach based on asymmetric Gaussian membership function leads to considerably improved robustness performance.

Sign in / Sign up

Export Citation Format

Share Document