International Journal of Fuzzy Systems and Advanced Applications


ISSN: 2313-0512
Volume 4, 2017

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.

Main Page

Submit a paper | Submission terms | Paper format

 


Volume 4, 2017


Title of the Paper: A Comparative Study of PID-PSO and Fuzzy-PID Controller Design for Time Delay System

 

Authors: Youcef Zennir, Mohand Said Larabi

Pages: 55-60

Abstract: This paper present comparative between classical and advanced control technique with classical PID controller, Fuzzy controller, Fuzzy-PID controller, PID-PSO controller applied to control on real system (Experiment setup of a flow control). In order to ensure all performances required by several complex industrial process. Detailed descriptions of the process with different mathematical models (with time delay) are exposed. The principal of different technique has been described before simulation section. Finally several simulations have proved the efficiency of the PID-PSO control in term of stability, robustness and precision


Title of the Paper: Harmonic Resonance Reduction Using Hybrid Active Filter with Fuzzy Logic Controller in Industrial Power Systems

 

Authors: Murikipudi Pavan Kumar, A. Manjula

Pages: 49-54

Abstract: This paper proposes a hybrid active filter for damping harmonic resonance and reducing harmonic distortion in industrial power systems. The change in load and variation in parameters causes harmonic distortions which are reduced to a considerable level by operating hybrid filter as variable harmonic conductance in accordance with voltage total harmonic distortion. The hybrid filter consists of an active filter and a seventh tuned passive filter connected in series. Therefore the dc voltage and kVA rating are reduced noticeably in comparison with the pure shunt active filter. The simulation study for the proposed method is carried out in Matlab/Simulink software which validates the efficiency. This paper also considers the filtering performances on line resistance, line impedance, capacitive filters and voltage unbalance.


Title of the Paper: Applying Fuzzy Clustering algorithm in Genetic Data Set

 

Authors: Ozer Ozdemir, Asli Kaya

Pages: 45-48

Abstract: Clustering is an important analysis in discovering groups of genes that have similar expression patterns in microarray data analysis. However, the hard clustering method, which correctly assigns each gene to a cluster, is not well appropriate for these data sets. In this work, it is going to be worked with fuzzy clustering algorithm to overcome hard clustering limitations. Fuzzy clustering algorithms allow each gene to belong to all clusters with a certain membership rating by removing the constraint of assigning to a single cluster. It is aimed to perform simpler analyzes by studying fuzzy clustering algorithms, a method of soft techniques developed to meet the need for developing alternative statistical methods in cases where classical clustering analysis is insufficient to analyze data.


Title of the Paper: Optimum Power Allocation for Multi-Relay Amplify-and-Forward Cooperative Networks Using Fuzzy Logic

 

Authors: Ghasem Saeidi

Pages: 38-44

Abstract: One of the modern and most operational techniques to overcome disappearing in wireless environment is cooperative communication. As most mobile units are provided for limited power, control, the improvement of the power distribution for cooperative networks is of high significance. Power allocation approaches in these types of systems can be applied for saving conveying power and improving the lifetime. In this paper, the approaches for limited power distribution whose quantities are specified by the restraint in single-relay amplify and forward cooperative network are planned to diminish the symbol error rate applying Lagrange approach and fuzzy logic. Linguistic value of membership purposes of fuzzy approach applying Particle Swarm Optimization algorithm is attained. The results of simulation revealed that the symbol error rate presentation of both approaches is indistinguishable. As the computational intricacy of the power allocation with Lagrange scheme particularly in multi-relay nets is high, hypothetical examination and the closed-form have not been found yet so fuzzy, logic is a suitable technique for power distribution in multi-relay amplify and forward cooperative networks.


Title of the Paper: Fuzzy Logic Schemes of Schools Grouping

 

Authors: Ivan Borshukov, Olga Georgieva

Pages: 32-37

Abstract: The paper presents and analyses different fuzzy rule-base schemes for a model that finds groups of schools according to the scores presented by their students. The model reflects the existing uncertainty in the data by applying information fusion concept. The expert knowledge and statistical analysis are useful for definition of the model structure, whereas fuzzy values account for the imprecision in the data. By the discussed schemes having the current scores of a certain school we are able to predict its learning deficit.


Title of the Paper: A Fuzzy Inference System as a Risk Analysis Tool to Prioritize Risks in Medication Dispensing Process

 

Authors: Salini Mettu, Rene V. Mayorga, Wei Peng

Pages: 23-31

Abstract: In this paper, a Fuzzy Inference System (FIS) is developed as a risk analysis tool to prioritize risks involved in drug dispensing process at pharmacies. The tool uses Bow-tie analysis and Fuzzy concepts to analyze and prioritize a risk by computing its score. The risks, risk factors, and impacts are identified based on reported events and expert's knowledge. Bow-tie analysis is used to determine the factors that cause the occurrence of a risk and the impacts of a risk. Fuzzy estimates for the risk factors and impacts are obtained from an expert. The developed Mamdani FIS is used to compute the risk score. The developed FIS risk analysis tool is applied to assess the risks in a drug dispensing process in a pharmacy. For comparison, Failure Mode Effects Analysis (FMEA) is also applied on the drug dispensing process and the results are shown to be similar. Proper mitigation plans are suggested to control the risk events based on their risk score, thus improving patient safety by reducing the number of risk events i.e., medication errors.


Title of the Paper: Determining Number of Cluster in Fuzzy Clustering

 

Authors: Ozer Ozdemir, Asli Kaya

Pages: 19-22

Abstract: Clustering analysis is one of the multivariate statistical techniques that help to divide data groups of which are not exactly known to subgroups according to similarities and explore different correlation and structures in large data sets. In particular, fuzzy clustering analysis has recently been researched and used in various fields. Determining the number of cluster is an important task in fuzzy cluster analysis. In this study, notions relating to cluster validity were introduced and cluster validity indices in literature were reviewed. These indices were used in common genetic data set with fuzzy c-means algorithms and changeable fuzzifier parameter. The result was simply analyzed.


Title of the Paper: Facial Emotion Recognition Using Nonparametric Weighted Feature Extraction and Fuzzy Classifier

 

Authors: Maryam Imani, Gholam Ali Montazer

Pages: 14-18

Abstract: The most facial emotion recognition methods use the geometrical features of face such as eye opening and mouth opening, which extraction of them is a hard and complicated task. But, in this paper, we propose to use the discriminant features simply extracted by nonparametric weighted feature extraction (NWFE). Moreover, to model the inherent uncertainties contained in the emotional features, we use the fuzzy measure in the classifier. To this end, a nearest neighbor classifier with fuzzy Euclidean distance is used to recognize emotions of face images. The experimental results on JAFFE database show the superiority of the proposed method compared to some other emotion recognition methods.


Title of the Paper: Managing the Uncertainty for Student Understanding of the Infinity

 

Authors: Michael Gr. Voskoglou

Pages: 8-13

Abstract: The concept of infinity plays a fundamental role for the adequate learning of many mathematical topics, like the limits of sequences and functions, the differential and integral calculus, etc. However, from the instructor’s point of view, and not only, the student understanding of the infinity is characterized by a degree of uncertainty. Therefore fuzzy logic, due to its property of assigning multiple values to the ambiguous cases, could help for a more effective study of the student difficulties to deal with the infinity. In this paper the fuzzy system possibilistic/probabilistic uncertainty is utilized as an assessment tool in an experimental study on the effects that the instruction to the basic philosophical / epistemological aspects about the infinity could have for the improvement of student abilities to deal successfully with it in their mathematical courses.


Title of the Paper: Use of TFNs and TpFNs for Evaluating the Effectiveness of CBR Systems

 

Authors: Michael Gr. Voskoglou

Pages: 1-7

Abstract: The fuzzy numbers play an important role in fuzzy mathematics analogous to the role played by the ordinary numbers in crisp mathematics. In the present paper we utilize a combination of the Centre of Gravity defuzzification technique and of triangular (TFNs) / trapezoidal (TpFNs) fuzzy numbers as tools for evaluating the effectiveness of Case-Based Reasoning (CBR) systems. The CBR approach for problem solving and learning (usually with the help of computers) has got a lot of attention over the last few years, because as an intelligent-systems method enables information managers to increase efficiency and reduce cost by substantially automating processes like diagnosis, scheduling and design.