Search for: fuzzy-modeling
Total 51 records
Article Intelligent Automation and Control Trends, Principles, and Applications - International Symposium on Intelligent Automation and Control, ISIAC - Sixth Biannual World Automation Congress, WAC 2004, Seville, 28 June 2004 through 1 July 2004 ; 2004 , Pages 43-48 ; 1889335223 (ISBN) ; Halavati, R ; Shouraki, S. B ; Lucas, C ; Sharif University of Technology
Zamin, is an Artificial Life ecosystem, suitable for cognitive studies such as evaluation of different thinking and acting methods. Up to now, simple models for decision making, generalization and abstraction, environment perception and pleasure computation is developed and tested in Zamin. In this paper, we have promoted the two layered decision-making system of Zamin creatures, the Aryos, to a three layered emotional decision making mechanism, compared the learning and coping with predators capabilities of the new creatures with the old ones and shown that they can defeat the previous, emotion-less creatures
Article Proceedings of the Fifteenth IASTED Internatinal Conference on Modeling and Simulation, Marina Del Rey, CA, 1 March 2004 through 3 March 2004 ; 2004 , Pages 272-277 ; 10218181 (ISSN) ; Haratizadeh, S ; Bagheri Shouraki, S ; Sharif University of Technology
Zamin, which is a high level artificial life environment have been successfully used as a test bed for a number of cognitive and AI studies. Here we have tried to test the evolution of a pleasure computing mechanism in Zamin's artificial creatures and have extended their mental capabilities to cover uncertainty in action selection mechanism. The results show some improvements in both genetic evolution process and learning capabilities. More specifically, we have evolved an internal pleasure system in Zamin creatures for the first time, quite unsupervised. In addition creatures could learn much more efficient behavioral patterns than what they could before
Article Computing and Informatics ; Volume 30, Issue 5 , 2011 , Pages 913-941 ; 13359150 (ISSN) ; Lakdashti, A ; Sharif University of Technology
To reduce the semantic gap in the content based image retrieval (CBIR) systems we propose a fuzzy rule base approach. By submitting a query to the proposed system, it first extracts its low-level features and then checks its rule base for determining the proper weight vector for its distance measure. It then uses this weight vector to determine what images are more similar to the query image. For the training purpose, an algorithm is provided by which the system adjusts its fuzzy rules' parameters by gathering the trainers' opinions on which and how much the image pairs are relevant. For further improving the performance of the system, a feature space dimensionality reduction method is also...
M.Sc. Thesis Sharif University of Technology ; Bagheri Shouraki, Saeed ; Haj Sadeghi, Khosrow
Neuron models are the elementary units, which determine the performance of an Artificial Spiking Neural Network (ASNN) as they are known to be a particular class of machine learning methods. The ASNNs that are inspired by the features of biological neurons and organizational structure of biological nervous system as the third generation of Artificial Neural Networks (ANN). This thesis concentrates on study of biologically plausible neuron; based on Fuzzy approach and tries to develop fuzzy state of Leaky Integrate and Fire (LIF) model, in order to resemble closely the neuron-electrical dynamics for ASNN in most efficient way. In this study, the Fuzzy methods including TAKAGI-SUGENO-KANG...
Article 2006 World Automation Congress, WAC'06, Budapest, 24 June 2006 through 26 June 2006 ; 2006 ; 1889335339 (ISBN); 9781889335339 (ISBN) ; Shouraki, S. B ; Razaghpour, M ; Tajik, H ; Cholakian, A ; Sharif University of Technology
IEEE Computer Society 2006
This paper presents a novel approach to isolated word speech recognition using fuzzy modeling which is specifically designed to ignore noise. The task is based on conversion of speech spectrogram into a linguistic fuzzy description and comparison of this representation with fuzzy linguistic descriptions of words. The method is tested on single speaker and multiple speaker tests and the results are compared with a widely used speech recognition approach, showing much higher noise resistance. Copyright - World Automation Congress (WAC) 2006
Fuzzy modeling techniques and artificial neural networks to estimate annual energy output of a wind turbine, Article Renewable Energy ; Volume 35, Issue 9 , September , 2010 , Pages 2008-2014 ; 09601481 (ISSN) ; Ranjbar, A. M ; Sharif University of Technology
The purpose of this article is to develop a new method to estimate annual energy output for a given wind turbine in any region which should be easy to use and has satisfactory accuracy. To do this, hourly wind speeds of 25 different stations in Netherlands, output power curve of S47 wind turbine and fuzzy modeling techniques and artificial neural networks were used and a model is developed to estimate annual energy output for S47 wind turbine in different regions. Since this model has three inputs (average wind speed, standard deviation of wind speed, and air density of that region), this model is easy to use. The accuracy of this method is compared with the accuracy of conventional methods...
Development of an Intelligent System to Predict and Control Blood Glucose Level in Type 1 Diabetic Patients, M.Sc. Thesis Sharif University of Technology ; Bozorgmehri, Ramin
All living entities requires energy to continue their lives. In human beings this energy is provide through consumption of food, at first the consumed food gets converted to glucose and the produced glucose enters the blood and then goes to the body cells in which it is used to produce the required energy. The essential hormone which makes it possible to use Glucose for energy production is INSULIN. In the patients suffering from Type 1 Diabetes, lack of Insulin production makes it impossible for the cells to use Glucose for the production of their required energy. In these patients due to the fact that the blood Glucose is not used by the cells, the Blood Glucose Level (BGL) increases,...
M.Sc. Thesis Sharif University of Technology ; Bagheri Shouraki, Saeed
The first physical realization of the missing fourth fundamental element of electrical circuits, namely memristor, in 2008 by HP labs triggered an immense amount of research on the capabilities of this element in implementing artificial neurons and artificial brain. In this project we will propose several reinforcement learning-based algorithms that are implemented on a specific memristor-based structure, the memristor crossbar structure. Hence we provide a learning paradigm that resembles the human learning paradigm not only because of the the algorithmic core, which is based on learning from sparse and delayed rewards and penalties, but also because of the hardware over which the...
Article International Journal of Pattern Recognition and Artificial Intelligence ; Volume 21, Issue 3 , 2007 , Pages 491-513 ; 02180014 (ISSN) ; Bagheri Shouraki, S ; Sharif University of Technology
Persian is a fully cursive handwriting in which each character may take different forms in different parts of the word, characters overlap and there is a wide range of possible styles. These complexities make automatic recognition of Persian a very hard task. This paper presents a novel approach on recognition of such writings systems which is based on the description of input stream by a sequence of fuzzy linguistic terms; representation of character patterns with the same descriptive language; and comparison of inputs with character patterns using a novel elastic pattern matching approach. As there is no general benchmark for recognition of Persian handwriting, the approach has been tested...
Article Wec 05: Fourth World Enformatika Conference, Istanbul, 24 June 2005 through 26 June 2005 ; Volume 6 , 2005 , Pages 237-240 ; 9759845857 (ISBN) ; Bagheri Shouraki, S ; Harati Zadeh, S ; Lucas, C ; Ardil C ; Sharif University of Technology
Artificial Life can be used as an agent training approach in large state spaces. This paper presents an artificial life method to increase the training speed of some speech recognizer agents which where previously trained by genetic algorithms. Using this approach, vertical training (genetic mutations and selection) is combined with horizontal training (individual learning through reinforcement learning) and results in a much faster evolution than simple genetic algorithm. The approach is tested and a comparison with GA cases on a standard speech data base is presented. COPYRIGHT © ENFORMATIKA
M.Sc. Thesis Sharif University of Technology ; Ranjbar, Ali Mohammad
One of the most important problems in using wind energy is the estimation of wind energy potential of a region with acceptable accuracy. To use wind energy and convert it to electrical energy it is necessary to study the economical aspects of wind farm installation, and to choose an appropriate wind turbine to be installed in a region. To do such a study and to choose approperiate wind turbine, annual energy output of different wind turbines should be estimated in that region. The porpuse of this thesis is to develop new methods to estimate annual energy production of a wind turbine by using some of the parameters of wind speed pattern of a region such as wind speed average, wind speed...
M.Sc. Thesis Sharif University of Technology ; Pishvaie, Mahmoud Reza
In industries there are many nonlinear processes which cannot be easily controlled with classical methods. Model predictive control is a useful method for nonlinear processes which not only has high efficiency, but also extension of this control to interferential multi variable case, with constraint on the controlled and manipulated variables and other problematic dynamic specifications such as slow dynamics and inverse response is very simple. Industrial polymerization processes are regarded as significant nonlinear processes. Optimization and control of polymerization reactors have considerable importance in process applicability and in economics. The molecular structure of polymer such as...
Comparison Of Various Models Proposed for Blood Glucose Level Prediction in Patients with Type 1 Diabetes to Obtain Optimal Insulin Injection Scenario, M.Sc. Thesis Sharif University of Technology ; B. Boozarjomehry, Ramein
Diabetes is one of the most epidemic metabolic disease which needs to be controlled through medications. The main objective of this study is to model and control diabetes type1 with exercise. It is important to choose an appropriate yet simple model based on which the design of the controller is accomplished (Bergman model is the one which is appropriate for this purpose). On the other hand, a comprehensive model which is used as the virtual patient has been chosen to assess the performance of the controller designed based on simple mode. The chosen comprehensive model is Cinar’s model. A good control of diabetes was achieved when the glucose blood (GB) of the two models almost had the same...
M.Sc. Thesis Sharif University of Technology ; Bagheri Shouraki, Saeed ; Beigy, Hamid
Developing algorithms in engineering and decision making systems based on psychological and biological mechanisms is a promising area of research. The challenging part of any psychological or biological system development is its learning necessity to adapt itself to random incidents, inherent in the environment. Goals, as defined in engineering problems, are the performance functions that continuously evaluate the responses of environment. They have a duty of directing the learning system to the desirable state. If the environment is corrupted by a variety of disturbances that cannot be predicted from the outset, adapting the parameter of learning agent is inevitable. In this work, we...
M.Sc. Thesis Sharif University of Technology ; Shafahi, Yousof ; Tabatabaei, Nader
Fatigue is one of the most common failure modes that reduce the structural integrity of asphalt pavements. Dynamic tests are used as fatigue performance indicators for asphalt mixture. However, these tests are expensive and require special equipment and set up. At this research, the main goal is to develop a fuzzy model which is more efficient than the existing regression model for prediction of the fatigue life. A database from the available data from various research was compiled. For each model, a comparison between Fuzzy and regression output by actual outputs was done and it was seen that the fuzzy modeling can predict fatigue life very closely. Finally, the required software for this...
Development of An Intelligent System For Thyroid Disease Diagnosis , Modeling And Simulation of Thyroid Hormone In Human Body, M.Sc. Thesis Sharif University of Technology ; Bozorgmehri, Ramin
The abstract is the most important section of the thesis because many readers limit most of their reading to abstracts, saving in-depth reading for specific theses. It should give the reader a "preview" of what's to come. The abstract should emphasize new and important aspects of the study or observations. The purpose of the abstract is to allow researchers to decide whether or not to read the whole thesis. The abstract is what researchers read first to decide if the thesis is important, interesting, and it allows them to assess the relevance of a thesis to their own research, without having to read the entire thesis. Thus, it is crucial that the abstract both summarize succinctly the key...
M.Sc. Thesis Sharif University of Technology ; Fotouhi Firouzabad, Morteza
In this Thesis, we investigate the Modeling of Oscillator Neural Networks. Let Oscillators are coupled to each other Weakly. agood way to use Phase Model to describe each Oscillator. Then provide specific Examples to see the nesseceryConditions forExsistence and Stability of Synchrony and desyncrony
Article 2006 ASME International Mechanical Engineering Congress and Exposition, IMECE2006, Chicago, IL, 5 November 2006 through 10 November 2006 ; 2006 ; 10716947 (ISSN); 0791837904 (ISBN); 9780791837900 (ISBN) ; Layeghi, N ; Salarieh, H ; Alasty, A ; Sharif University of Technology
American Society of Mechanical Engineers (ASME) 2006
A simple and systematic approach is developed for modeling and adaptive control of an unknown (or uncertain) chaotic system of the form x(n) = f(X) + g(X)u, using only input-output data obtained from the underlying dynamic system. Two different fuzzy identification methods, i.e. least-squares and gradient descent, are used for identifying the unknown functions f (X) and g (X). Based on the fuzzy modeling, an adaptive controller is devised, which works through sliding mode method. The presented procedure is illustrated by using the chaotic system-modified Duffing's equation as an example, on which simulation results demonstrate the effectiveness of the proposed adaptive algorithm. Copyright ©...
Article 8th US National Conference on Earthquake Engineering 2006, San Francisco, CA, 18 April 2006 through 22 April 2006 ; Volume 13 , 2006 , Pages 8001-8008 ; 9781615670444 (ISBN) ; Khalili, A ; Sadati, N ; Sharif University of Technology
Lateral spreading generated by earthquake induced liquefaction, is a major cause for significant damage to the engineered structures, during earthquakes. Knowing the amount of displacement which is likely to occur due to the lateral spreading, will lead to better construction policies, and will reduce unexpected damages. A Neuro-Fuzzy model based on subtractive clustering is developed to predict the amount of lateral spreading expected to occur due to an earthquake. A large database containing the case histories of observed lateral spreading during seven major earthquakes of the past is used for training and evaluating the models. The results of this study show that Neuro-Fuzzy method serves...
Article Electric Power Systems Research ; Volume 81, Issue 8 , 2011 , Pages 1696-1708 ; 03787796 (ISSN) ; Vakilian, M ; Sharif University of Technology
Wind power is a promising source of electric power generation since it has tremendous environmental and social benefits. The generation scheduling (GS) problem encounters several uncertainties in terms of the system's parameters such as load, reserve and available wind power generation. The modeling of those uncertainties is an important issue in power system scheduling. A fuzzy based modeling approach can be used to develop the generation schedule under an uncertain environment. In this paper, the type-2 fuzzy membership function (MF) is implemented to model the linguistic uncertainty of type-1 MF of available wind power generation which stems from opinions of different experts. The...