International Journal of Fuzzy Systems and Advanced Applications
E-ISSN: 2313-0512
Volume 1, 2014
Notice: As of 2014 and for the forthcoming years, the publication frequency/periodicity of NAUN Journals is adapted to the 'continuously updated' model. What this means is that instead of being separated into issues, new papers will be added on a continuous basis, allowing a more regular flow and shorter publication times. The papers will appear in reverse order, therefore the most recent one will be on top.
Submit a paper | Submission terms | Paper format
Volume 1, 2014
Title of the Paper: On Creation of Expert Knowledge Base in Information Systems of Decision Making Support
Authors: Lyudmila V. Borisova, Inna N. Nurutdinova, Valery P. Dimitrov
Pages: 88-93
Abstract: We have considered designation and structure of the knowledge acquisition block of the expert system for technical and technological service of complex machines. The main aspects of fuzzy expert knowledge representation designated for setting parameters of the machines technological adjustment have been studied. The block of expert knowledge acquisition and representation is one of the main parts in decision making problems under uncertainty. This paper suggests the technique of fuzzy knowledge base generation based on various criteria of consistency including those, that take into account different hierarchy of expert knowledge. This technique makes it possible to determine an optimal term-set for a linguistic variable, which is required to construct a general membership function and describe input and output parameters of the system. The method was applied to the subject domain of the combine harvesting of grain.
Title of the Paper: OWA–type Fuzzy Aggregations in a Decision Making Regarding the Selection of Investments
Authors: Gia Sirbiladze, Gvantsa Tsulaia, Otar Badagadze
Pages: 83-87
Abstract: The Ordered Weighted Averaging (OWA) operatorwas introduced by R.R. Yager (Yager, 1988) to provide a method foraggregating inputs that lie between the Max and Min operators. Inthis article a new generalization of the OWA aggregation operator -AsFPOWA is presented in the environment of possibility uncertainty.For the illustration of the applicability of the new aggregationoperator - AsFPOWA an example of the fuzzy decision makingregarding optimal selection of investment is considered. Severalvariants of the new aggregation operator are used for the comparingof decision making results.
Title of the Paper: Fuzzy Hybrid Decision Model for FMS Evaluation and Selection Based on GRA-TOPSIS Method
Authors: Shanliang Yang, Xiao Xu, Mei Yang, Ge Li
Pages: 74-82
Abstract: The aim of this paper is to present a hybrid group decisionmodel for evaluating flexible manufacturing systems(FMSs), inwhich the information about attribute weights is completely unknown,and the attribute values take the form of triangular fuzzy numbers. Inthis proposed methodology, the voting method is adopted to calculatethe attribute weights by aggregating the decision-makers’ attitudesand preferences on weights of each attribute. Then grey relationalanalysis(GRA) is combined with the concepts of TOPSIS to evaluateand select the best FMS from a set of alternatives. An illustrativeexample is given to demonstrate the practicality and feasibility ofthe proposed group decision model. The comparative study resultsshowed that this model is an effective means for tackling FMSevaluation problems under fuzzy environment. Finally, a sensitivityanalysis is performed to show the robustness of the model.
Title of the Paper: Fuzzy Modeling for Contaminated Soil Parameters
Authors: T. S. Umesha, S. V. Dinesh, M. A. Jayaram
Pages: 66-73
Abstract: Soil waste interaction can affect almost all the properties of soil. The unintended modification of soil properties due to interaction with pollutants can lead to alteration in physico-chemical properties such as pH and specific surface area of soil which in turn reduces the unconfined compressive strength of soil. The determination of soil properties due to acid contamination is highly ambiguous due to the complex behavior of soils. The fuzzy set theory provides a powerful tool for modeling uncertainty associated with vagueness and imprecision. The MATLAB fuzzy toolbox was used for the design of the fuzzy model. The experimental data is modeled in four distinct steps. In the first three steps, one antecedent and one consequent model is developed. In the fourth step, two antecedents and one consequent model is developed. The important parameters such as acid concentration, pH, specific surface area and unconfined compressive strength were considered. The available results from experimental work were compared with the outcome of fuzzy system model. It is observed that the results of the developed Fuzzy Inference System are comparable to the experimental results and the fuzzy model is applicable.
Title of the Paper: A Tool for Implementation of a Domain Model Based on Fuzzy Relationships
Authors: Ali Aajli, Karim Afdel
Pages: 61-65
Abstract: The domain model is one of the important components used by adaptive learning systems to automatically generate customized courses for the learners. In this paper our contribution is to propose a new tool for implementation of a domain model based on fuzzy relationships among concepts. This tool allows the experts and teachers to find the best parameters in order to adapt the learners’ differences.
Title of the Paper: MIMO System with GA DFE-ANFIS Framework
Authors: Kandarpa Kumar Sarma, Nikos Mastorakis
Pages: 55-60
Abstract: Modeling multi input multiple output (MIMO) wireless channel continues to be a challenging area of research due to the stochastic nature observed in the path gains and the medium being infested with uncertainty. Traditional methods of modeling the MIMO channels have already been established to be reliable tools yet certain issues still remain in the forefront. This primarily is attributed to the fact that at some stage a prediction aspect plays a significant part where soft computing tools can play a significant part. Soft-computational approaches have been accepted as additional options as these tools learn from the environment, retain it and use the knowledge acquired for subsequent processing. The constraints observed with computational complexity of such systems are lowered by combining them with other statistical and evolutionary aids. Here, we propose such a framework designed using fuzzy systems and a variation of Recurrent Neural Network (RNN). Fuzzy systems have proven to be effective for modeling uncertainty while RNN is a derivative of Artificial Neural Network (ANN) that adopts multiple multiple feedback loops to track time-dependent variations in input patterns. Further, decision directed equalizer (DFE) based estimates of the channels are utilized for training the composite hybrid block formed around an adaptive neuro-fuzzy inference system (ANFIS). The ANFIS is constituted by fuzzified RNN (FRNN) blocks configured to model MIMO channel characteristics and optimized by a Self Organizing Map (SOM). During the fuzzification stage, a genetic algorithm (GA) block selects the most suitable set of parameters (center, slop and spread) of the Bell-membership function (MF) which contributes to the precision of the system. The proposed architecture demonstrates lower processing speed and improved precision during recovery of transmitted data through severely faded MIMO channels compared to other fuzzy based methods.
Title of the Paper: Multiple-Use Water Resources Management by Using Fuzzy Multi-Objective Heuristic Optimization Methods: An Overview
Authors: André A. Keller
Pages: 36-54
Abstract: Environmental management and planning problems cover important real life areas. These problems may include the scarcity of groundwater resources, the optimality of a multi-reservoir system, the management of forest resources, the air quality monitoring networks, the municipal solid waste policies. Management and planning targets by authorities consist in allocations at appropriate places and times, protection from disasters, maintenance of quality (e.g., water quality, water pollution control, nitrate concentration diminishing), sustainable development of the groundwater resources. The formalization of such optimization problems includes multiple objectives and constraints. The multiple objectives consist in maximizing/minimizing of various aspects of environmental management (e.g., maximizing irrigation releases, maximizing the hydropower production, maximizing net returns, minimizing costs, minimizing the investment in water development, minimizing groundwater quality deterioration.) [1]. Physical, biological, economic and environmental constraints are notably the constraint of surface water balance, water supply constraints, water quality constraints, economic constraints (e.g., demand, resource costs), reservoir storage constraints. The eco-environmental objectives are often conflicting (e.g., the optimum use of water resources under conflicting demands). The use of multi-objective optimization allows a simultaneous treatment of all the objectives and constraints. The solutions take the form of non-dominated Pareto solutions, which enable the decision makers to study the tradeoffs between the objectives (e.g., between profitability and risk). Most of the environmental domains are faced to uncertainties due to variabilities (e.g., climate, rainfalls, hydrologic variability, environmental policy, markets), imprecisions and lack of data, vagueness of judgments by decision makers. These uncertainties lead to extending the analysis to fuzzy environments. This presentation introduces to the multiple-use water resources management by using heuristic optimization methods in a fuzzy environment where the decision makers have vague objectives. Most of the case studies are on river basins and dams in China.
Title of the Paper: Five-Level Fuzzy Logic Direct Torque Control of Double Star Synchronous Machine
Authors: Elakhdar Benyoussef, Abdelkader Meroufel, Said Barkat
Pages: 29-35
Abstract: This paper deals with the direct torque control of the salient-pole double star synchronous machine drive fed by two five-level diode-clamped inverters. This approach combines the well-known advantages of the multilevel inverter with those of a direct torque control. The proposed approach consist to replace the hysteresis controllers by one fuzzy controller and the output vector of the fuzzy controller is led to a multilevel switching table to decide which reference vector should be applied to control the two three-level inverters. Simulation results show some improvement regarding in the reduction of torque and flux ripples.
Title of the Paper: Motion Model Transitions in GPS-IMU Sensor Fusion for User Tracking in Augmented Reality
Authors: Erkan Bostanci
Pages: 21-28
Abstract: Finding the position of the user is an important processing step for augmented reality (AR) applications. This paper investigates the use of different motion models in order to choose the most suitable one, and eventually reduce the Kalman filter errors in sensor fusion for such applications where the accuracy of user tracking is crucial. A Deterministic Finite Automaton (DFA) was employed using the innovation parameters of the filter. Results show that the approach presented here reduces the filter error compared to a static model and prevents filter divergence. The approach was tested on a simple AR game in order to justify the accuracy and performance of the algorithm.
Title of the Paper: Fuzzy Sliding Design of Chopper Controller in Wind Turbine
Authors: Ahmed Tahour, Abdel Ghani Aissaoui, Mohamed Abid, Najib Essounbouli, Frédéric Nollet
Pages: 15-20
Abstract: In this paper, a fuzzy logic controller (FLC) is designed, based on the similarity between the FLC and the sliding mode control (SMC), for a class of nonlinear system to tackle the nonlinear control problems with modelling uncertainties, plant parameters variations and external disturbances. The purpose is therefore to make the voltage and the current control resist to speed variations, because the variation of speed degrades the performance of the voltage pruducted to the networks. The use of the nonlinear sliding mode method provides very satisfactory performance for chopper control of synchronous generator, and the chattering effect is also elim¬inated by fuzzy function. Simulation study was done to prove the validation of the strategy and the method of control used in power control. Conclusions are summarized in the last section.
Title of the Paper: Using GUI of Matlab and Fuzzy Principles for Evaluating of Some Process Quality
Authors: S. Hrehova, J. Mizakova
Pages: 7-14
Abstract: Quality is becoming a key factor in customer choice among several products. Knowledge of the achieved level of quality of the production process is becoming an important element in attracting and retaining marketing. It is therefore desirable to give this information to managers in an acceptable form, to have enough relevant information in obtaining of orders for your business. The paper deals with design of graphical user interface to evaluate the achieved quality of the production process using tools of Matlab. In conjunction with the principles of fuzzy logic, which can be converted numerical value into verbal expressing are expanding their area of application. There are evaluated data which are gained through process and which are written to a file. They are subsequently evaluated using fuzzy toolbox of Matlab system. The rules designed for individual decision-making processes reflect the experience of experts in the field. These tools allow easy application of fuzzy rules by Fuzzy Toolbox and the connection with Simulink and its tools allow display the results.
Title of the Paper: Causal Modeling of the Higher Education Determinants Regarding the Labour Market Absorption of Graduates: A Fuzzy Cognitive Maps Approach
Authors: Marilena-Aura Din, Georgiana-Camelia Cretan
Pages: 1-6
Abstract: The paper aims at developing a framework methodology based on Fuzzy Cognitive Maps (FCM) for causal modeling of the higher education determinants regarding the labor market absorption of the Romanian universities graduates, shorthand notation here as HEtoJob problem. As the FCM is a cognition intelligent tool useful to model and analyze complex dynamical systems in those situations where other methods do not cover them, the results of the conducted research reveal the propagation of causality within the relationship between the concepts of such complex socio-economic system including higher education and labor market. Furthermore, the Fuzzy Cognitive Map methodology highlights the higher education determinants and their order of importance able to help policy makers to know on which priority should intervene by appropriate educational policies. Finally, the scenario simulations allow higher education decision-makers to analyze and understand relational structures as a facile visual tool in order to fit higher education policies to a better labor market absorption of graduates. Through network analysis of the FCM we determined that the concept ”higher education-job match”, denoted here as HE-job match, exerts the greatest force in the model and hence impacts the dynamism and complexity of the system. Moreover, such an approach proposed in this paper can underpin substantiate higher education policies built on the principle of bottom up, based on the perception of the participants in the higher education process and ensure their implementation with a high degree of trust from them.