Accepted papers
- Fuzzy Score Relevance Valorization
Chkiwa Mounira,Jedidi Anis and Faiez Gargouri,Sfax University, TunisiaABSTRACT
In this short paper we present two methods to valorise score relevance of some documents basing on their characteristics in order to enhance the ranking quality. Our framework is an information retrieval system dedicated for children. The valorisation methods aim to increase or decrease the relevance score of some documents by an additional value which can be positive or negative. The added value is proportional to the number of multimedia objects included in a document and the number of personal information items used. Both of valorization methods use fuzzy rules to identify the valorization value. - Linguistic Reasoning For Personnel Selection Problem
Ali Reza Afshari1,Rosnah Mohd Yusuff 2,1Islamic Azad University,Iran,2Universitiy Putra Malaysia,MalaysiaABSTRACT
The main objective of this paper is to develop a model based on linguistic variables for evaluating based on new group fuzzy linguistic modeling for determining criteria importance and candidate ratings. This includes also fuzzy aggregating and ranking the candidates based on new linguistic.. - Use Of Fuzzy Logic For Segmenting Of Brain Images By Multi-Agent System
Soraya Nasser and Rachida Mekki,USTO Oran University,AlgeriaABSTRACT
The segmentation of medical images is a new technology, rich and varied, but in which many existing methods are difficult to apply to real problems. In this work, we present a segmentation system for brain MRI images that is based on two approaches method "growth area" and "FCM" algorithm for each of these approaches, we will explain and illustrate their usefulness. The proposed system aims to improve the segmentation of brain images to classify the three components of the human brain matter in a clearer way in a multi-agent environment. - Coiflet-Based Fuzzy-Classifier For Defect Detection In Industrial LNG/LPG Tanks
Uvais Qidwai and Mohamed Shakir,Qatar University,QatarABSTRACT
This paper describes a classification method for raw sensor data using a Fuzzy Inference System to detect the defects in large LNG tanks. The data is obtained from a Magnetic Flux Leakage (MFL) sensing system which is usually used in the industry to located defects in metallic surfaces, such as tank floors. A robotic inspection system has been developed in conjunction with the presented work which performs the same inspection tasks at much lower temperatures than human operators would thus reducing the shutdown time significantly which is typically of the order of 15-20 million Dollars per day. The main challenge was to come up with an algorithm that can map the human heuristics used by the MFL inspectors in field to locate the defects into an automated system and yet keep the algorithm simple enough to be deployed in near real-time applications. Unlike the human operation of the MFL equipment, the proposed technique is not very sensitive to the sensor distance from the test surface and the calibration requirements are also very minimal which are usually a big impediment in speedy inspections of the floor by human operator. The use of wavelet decomposition with Coiflet waves has been utilized here for deconvolving the essential features of the signal before calculating the classification features. This wavelet was selected to its canny resemblance with the actual MFL signals that makes these wavelets very natural basis function for decomposition. - Fuzzy Logic Based Multiplexer Design & Simulation
Furqan Fazili,Islamic University of Science & Technology,IndiaABSTRACT
In this paper we try to design and implement the logic of a Fuzzy Multiplexer (fMUX) system. A design of Fuzzy Multiplexer is presented and its generalization to classical logic has been shown with simulations. In fuzzy modelling, a fuzzy multiplexer fMUX acts as a fuzzy switch to select one of the fuzzy inputs. Selection of the inputs is determined by the value of candidate inputs termed as “Select Inputs”. These fMUX’s could be used as generic building modules in fuzzy systems. All simulations were done using MultiSim 11.0 . - A Survey Of Feature Selection And Feature Extraction Techniques In Machine Learning
Samina Khalid1,Shamila Nasreen2,1Bahria University,2University of Engineering & Technology Taxila,PakistanABSTRACT
Dimensionality reduction as a preprocessing step to machine learning is effective in removing irrelevant and redundant data, increasing learning accuracy, and improving result comprehensibility. However, the recent increase of dimensionality of data poses a severe challenge to many existing feature selection and feature extraction methods with respect to efficiency and effectiveness. In the field of machine learning and pattern recognition, dimensionality reduction is important area, where many approaches have been proposed. In this paper, some widely used feature selection and feature extraction techniques have analyzed with the purpose of how effectively these techniques can be used to achieve high performance of learning algorithms that ultimately improves predictive accuracy of classifier. An endeavor to analyze dimensionality reduction techniques briefly with the purpose to investigate strengths and weaknesses of some widely used dimensionality reduction methods is presented. - Development Of Fuzzy Logic Inference Scheme For Hartley Oscillator Design
S. R. Ghatage1, V. C. Mahajan2,N. S. Sonar3, R. R. Mudholkar4,1G. K. G. College,2Vivekanand College,3Ibra College of Technology,Oman,4Shivaji University,IndiaABSTRACT
Fuzzy logic emerged as a tool to deal with uncertain, imprecise, or qualitative decision making problems. The complex design issues in oscillator make the fuzzy logic based CAD framework is an appropriate choice. The present paper deals with the development of fuzzy logic inference scheme for Hartley oscillator. The Adaptive Neuro Fuzzy Inference Scheme (ANFIS) methodology is used for Hartley oscillator design. The result shows satisfactory performance compares to convention design methodology with minimum error. - A New Machine Translation Decoder Based On Artificial Immune System
Manel Ammar and Salma Jamoussi,Sfax University, TunisiaABSTRACT
It was observed that for non-stationary and quasi-stationary signals, wavelet transform has been found to be an effective tool for the time-frequency analysis. Recent years have seen wavelet transform being used for feature extration in speech recognition applications. Here a new filter structure using admissible wavelet packet analysis is proposed. These filters have the benefit of having frequency bands spacing similar to the auditory gammatone filter whose central frequencies are equally distributed along the ERB scale. A new sets of features have been derived using wavelet packet transform's multi-resolution capabilities, which perform better than conventional features like GFCC and MFCC for unvoiced phoneme recognition problems. - The Information Energy Change Through Arithmetic Operations
Kheffache djedjiga1,Pomorski Denis2,1USTHB,2LAGIS, University of Lille,AlgeriaABSTRACT
This paper is about information energy and its change through the arithmetic operations as addition and subtraction. The case of trapezoidal fuzzy numbers of same type is studied. - Embed System For Robotic Arm With 3degree Of Freedom Controller Using Computational Vision On Real-Time
Luiz Cortinhas1, Patrick Monteiro1, Amir Zahlan1, Gabriel Vianna1 and Marcio Moscoso2,1Instituto de Ensinos Superiores da Amazonia,2Instituto Federal do Pará, BelémABSTRACT
This Paper deals with robotic arm embed controller system, with distributed system based on protocol communication between one server supporting multiple points and mobile applications trough sockets .The proposed system utilizes hand with glove gesture in three-dimensional recognition using fuzzy implementation to set x,y,z coordinates. This approach present all implementation over: two raspberry PI arm based computer running client program, x64 PC running server program, and one robot arm controlled by ATmega328p based board. - Velocity Prediction Model Of Servo Motor System Using Adaptive Fuzzy Petri Nets Reasoning System
Raed I. Hamed,University of Anbar, IraqABSTRACT
A graphical fuzzy model that uses rules base system to effectively process the uncertainties variables is built. Modules that represent distinct types of fuzzy rules are created and defined. An AFPN module for velocity estimation ve is constructed according to the structure, relations, rules, certainty factors and weights of the adaptive fuzzy model for servo motor system. The servo motor system is analysed, and definitions are prepared for the AFPN model and the input data. An AFPN model is created and trained with input data on weight w(pi) . Input places are represented the membership function values the initial values of the input places are entered (position error velocity error we), and the output value of ( p2) represented the velocity estimation ve. The system can perform fuzzy reasoning automatically to evaluate the degree of truth a (pi)of the proposition. The presented study demonstrates that the proposed model is able to achieve the purpose of reasoning, and computing of the velocity estimation value. An AFPN structure has been used rather than FPNs formalism to improve the efficiency of fuzzy reasoning. The effectiveness of the proposed method is verified by both model simulations and experimental results.