By Topic

Soft Computing Applications, 2009. SOFA '09. 3rd International Workshop on

Date July 29 2009-Aug. 1 2009

Filter Results

Displaying Results 1 - 25 of 53
  • Author's index

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (278 KB)  
    Freely Available from IEEE
  • Committees

    Page(s): 9 - 10
    Save to Project icon | Request Permissions | PDF file iconPDF (608 KB)  
    Freely Available from IEEE
  • [Copyright notice]

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (47 KB)  
    Freely Available from IEEE
  • Table of contents

    Page(s): 3 - 5
    Save to Project icon | Request Permissions | PDF file iconPDF (501 KB)  
    Freely Available from IEEE
  • [Title page]

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (243 KB)  
    Freely Available from IEEE
  • Welcome message

    Page(s): 7 - 8
    Save to Project icon | Request Permissions | PDF file iconPDF (259 KB)  
    Freely Available from IEEE
  • New control algorithm and defuzzification

    Page(s): 15 - 20
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (148 KB) |  | HTML iconHTML  

    Fuzzy defuzzification is one of the most important part of the fuzzy control. Several approaches exist. Mamdani uses the a-cuts and builds the union of the membership function. The resulted function is the starting point of the defuzzification process. In this article we define more natural way to get the membership function by using fuzzy arithmetics. The defuzzification is the optimum value of the resulted membership function. The main idea is that the membership function a soft inequality which we call distending function and we handled the left and right hand side of the inequalities.. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fuzzy communication and cooperation of mobile robots

    Page(s): 25 - 26
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (69 KB) |  | HTML iconHTML  

    Summary form only given. Intelligent cooperation of agents/entities in autonomous robotics is a new and very exiting research field. If one plans/implements a cooperating robot system with intelligent behavior, not all scenarios appearing in the "life of robots" can be programmed in advance and thus effective, fast and compact communication is one of the most important cornerstones of the high-end cooperating system. Communication itself is very expensive so, generally speaking, it is much more advisable to build up as big as possible contextual knowledge bases and codebooks in distant on-board robot controller computers in order to shorten the communication process if it essentially reduces the amount of information that must be transmitted from one to another, than to concentrate all contextual knowledge in one of them and then to export its respective parts whenever they are needed in the other(s). It seems to be very important in the cooperation and communication of intelligent robots or physical agents that the information exchange among them is as effective and compressed as possible. We propose a context dependent reconstructive or fuzzy communication system where the codebooks are built up by fuzzy signatures. Fuzzy signatures structure data into vectors of fuzzy values, each of which can be a further vector, have been introduced in order to handle complex structured data. This will widen the application of fuzzy theory to many areas where objects are complex and sometimes interdependent features are to be classified and thus similarities/dissimilarities are evaluated. Often, human experts can and must make decisions based on comparisons of cases with different numbers of data components, even with some missing components. Fuzzy signatures have been created with this objective in mind. This tree structure is a generalization of fuzzy sets and vector valued fuzzy sets in a way modeling the human approach to complex problems. However, when dealing with a very - large data set, it is possible that they hide hierarchical structures that appear in the subvariable structures. Apart from the application of fuzzy signatures, another modeling structure of intention guessing is designed for the further intentional inference of cooperative robot communication. By the combination of these two theoretical issues, a codebook for intelligent robot decision making has been developed, as well as its implementation in some real scenarios of autonomous mobile robot cooperation has been examined. Research towards extending this fuzzy communication method to more complex robot cooperation is going on currently. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Application of paraconsistent annotated logic program EVALPSN to intelligent control/safety verification

    Page(s): 21 - 22
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (101 KB)  

    I have already proposed a paraconsistent annotated logic program called Extended Vector Annotated Logic Program with Strong Negation (EVALPSN), which can deal with conflict resolving and defensible deontic reasoning. These EVALPSN reasoning functions have been applied to various intelligent control and safety verification systems such as pipeline valve control, traffic signal control, railway interlocking safety verification, etc. I introduce these applications of EVALPSN with some simulation systems. Moreover, I have developed EVALPSN to deal with before-after relations between processes (time intervals) The developed EVALPSN has been named bf (before-after)EVALPSN. It has been shown that bf-EVALPSN can be applied to real-time process order control with a simple example of pipeline control. In this lecture, it will also be introduced how to apply bf-EVALPSN to intelligent real-time process order control and safety verification with examples and simulation results. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A research based approach to predictive simulation in disaster management

    Page(s): 23 - 24
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (484 KB) |  | HTML iconHTML  

    The presentation will describe an innovative collaborative research effort between a university, industry and government agency to research and develop a series if simulation based decision aids. This simulation decision aid, tool, known as SimSeries is designed to be a reliable and research based tool to support decision making and risk mitigation for multiple types of natural and manmade disasters. The first phase of the project objective focus on three areas: (1) Establishment of a theoretically sound framework for a modeling data sources and constructing a series of simulation systems using a hierarchical approach (2) Using this theoretical basis to develop a suite of robust, dynamic simulation tools to support mitigation, training, preparation, and response, and (3) Convert the system into exportable programs that have the ability to interface with existing exercise simulation products. A strong theoretical foundation is critical in the development of SimSeries as this will impact the confidence, accuracy, repeatability and scientific merit associated with the system as well as future models that are constructed using the principles outlined in the methodology. SimSeries will be used to support states, municipalities, private companies, and federal agencies in disaster mitigation and training. The second phase of our project will focus on ensuring that the simulations provide the needed information to support preparedness and mitigation strategies. Agent based simulation approach will be used to do optimization for evacuation routes, first aid, agency network coordination, distribution of lifeline utilities and shelters. Creating an environment to simulate near-real time disaster events will be the third phase of our project. The discrete event simulation, predictive models, agent-based modeling, mitigation plans and GIS will be integrated to form the final platform. The presentation provides an overview of the initial phases of the research. The preliminary pl- atforms that have been developed offer a user friendly system that is robust, flexible and provides valuable information to support decision making. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The 60 years old “Information theory” and the fuzzy concept of information

    Page(s): 13 - 14
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (58 KB) |  | HTML iconHTML  

    60 years ago the American mathematician and electrical engineer Claude Elwood Shannon (1916-2001) published "A Mathematical Theory of Communication" and nobody could survey this theory's enormous consequences for science and technology. Shannon's article appeared in two parts in the July and October 1948 editions of the Bell System Technical Journal. However, it is very probable that this article wouldn't have become famous without the help of the American mathematician and Science administrator Warren Weaver (1894-1978), whose popular text "The Mathematics of communication" re-interpreted Shannon's work for broader scientific audiences. Weaver's "preface" and Shannon's article were published together in the book The Mathematical Theory of Communication (1949) that represents the beginning of the then so-called "Information theory". View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Neurodynamic optimization with its application for model predictive control

    Page(s): 11 - 12
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (49 KB)  

    Summary form only given. Optimization problems arise in a wide variety of scientific and engineering applications. It is computationally challenging when optimization procedures have to be performed in real time to optimize the performance of dynamical systems. For such applications, classical optimization techniques may not be competent due to the problem dimensionality and stringent requirement on computational time. One very promising approach to dynamic optimization is to apply artificial neural networks. Because of the inherent nature of parallel and distributed information processing in neural networks, the convergence rate of the solution process is not decreasing as the size of the problem increases. Neural networks can be implemented physically in designated hardware such as ASICs where optimization is carried out in a truly parallel and distributed manner. This feature is particularly desirable for dynamic optimization in decentralized decision-making situations arising frequently in control and robotics. In this talk, the author presents the historic review and the state of the art of neurodynamic optimization models and selected applications in robotics and control. Specifically, starting from the motivation of neurodynamic optimization, we will review various recurrent neural network models for optimization. Theoretical results about the stability and optimality of the neurodynamic optimization models will be given along with illustrative examples and simulation results. It will be shown that many problems in control systems, such model predictive control, can be readily solved by using the neurodynamic optimization models. Specifically, linear and nonlinear model predictive control based on neurodynamic optimization will be delineated. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Probabilistic model for a distributed feature selection method

    Page(s): 27 - 32
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (233 KB) |  | HTML iconHTML  

    When building topic based document classifiers, feature selection is a key step: features not holding any information about the topic of a document introduce only unnecessary noise during the classification. In a distributed environment, when the nodes are interacting, the locally retrieved features and the their attributes must be shared to have at every node a more accurate estimation of the global classifier. When expanding the knowledge of the local classifiers, to reduce costs, the network traffic should be kept to a minimum. We propose a probabilistic model for a keyword selection method which makes a more thorough analysis possible and can be used as a baseline when sharing information in a distributed environment. It can be used for incrementally building up the distributed classifiers ensuring minimal network traffic. This model can be refined later on by sending more content-related information to achieve higher performance. This probabilistic model together with experimental results are presented in this paper. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The physical sensor for pressure measurement

    Page(s): 33 - 36
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (152 KB) |  | HTML iconHTML  

    In this paper we will present utilization the magnetic fluid in pressure measurement. Pressure measurements are based on fluidic and magnetic proprieties on magnetic fluids, which allow obtaining values or limited of pressure of gas in a container. The device experimental presented is based on magnetic fluid positioned inside of a coil by the help of a membrane of elastic material. The device experimental consists of a cylindrical vertical nonmagnetic vessel surrounded by a coil filled in the bottom part with the magnetic fluid. In the top part of the vessel, over the magnetic fluid and between two plates of an electric condenser is placed water. This coil is a component of an electrical oscillating circuit, which contains an electric condenser too. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Preliminary issues on brain - machine contextual communication structure development

    Page(s): 37 - 42
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (555 KB) |  | HTML iconHTML  

    The increasing sophistication of computer programs and communication systems requires the development of more efficient and interactive human-computer interfaces. One solution to this problem could be the brain-machine interfaces. The aim of this paper is to explore the possibilities of using context dependent interpretations of EEG signals, in addition to signal processing techniques. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Wear simulation through cellular automata method

    Page(s): 43 - 48
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (347 KB) |  | HTML iconHTML  

    Cellular automata (CA) are used to simulate a various number of complex processes, based on simple rules applied to a large population of cells. Wear of turbine blades is also a very complex process which is analyzed in most cases using empirical data. The model described in this paper uses cellular automata obeying a set of rules and using values of initial state parameters which were computed by FEA flow analysis (fluid pressure and velocity). The model is then adjusted using experimental data. The obtained results, corresponds to former studies and observations. Further developments can be made by alternatively applying FEA analysis and CA simulation in order to increase model accuracy. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic image classification from Cherenkov telescopes using Bayesian ensemble of neural networks

    Page(s): 49 - 54
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (388 KB) |  | HTML iconHTML  

    The problem of identifying cosmic gamma ray events out of charged cosmic ray background in Cherenkov telescopes is one of the key problems in very high energy gamma ray astronomy. Separation between gamma-like and hadron-like events is performed by a Bayesian ensemble of neural networks and Markov chain Monte Carlo methods for model parameters optimization. The results are discussed in terms of the energy of the primaries and a complete study is made by using various data representation methods with different levels of feature reduction. Our classifier clearly outperforms the results obtained using standard feedforward neural networks, and its performance is comparable with random forests, which is actually used in data analysis of the MAGIC Cherenkov telescope. Regarding the energy of the primaries, it achieves very promising results in terms of classification accuracy with low energy events, the most difficult and unexplored energy range which will be a major issue in future explorations. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Some aspects about 3D objects recognition and distance approximation

    Page(s): 55 - 60
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (530 KB) |  | HTML iconHTML  

    The present work approaches some important issues from image processing such as object recognition and distance estimations of different objects from the environment. As we know image processing deals with endowing computers with visual functions. Until now the capabilities of similar systems were limited to object recognition and to avoid obstacles. We have tried to combine those two capabilities into one system. In this application fuzzy techniques for controlling the luminosity of the image and some new filtering methods were addressed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An integrated monitoring system for the human robot collaborative workspace

    Page(s): 61 - 66
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (436 KB) |  | HTML iconHTML  

    Safety is a major concern in many complex robotized systems especially when the task implies collaboration between human and robot with the workspace sharing. In this research a theoretical representation of the integrated safety monitoring system is introduced. The monitoring system is modeled as a separated unit which decision making mechanism is based on the safety expert system (SES) data analysis and the danger index approach, and which operation relies on the safety related algorithms associated with four human-robot interaction levels. A new scale of the injury severity and likelihood for a HRI domain is proposed and the concept is integrated into the safety modes control algorithm. The case study analysis is modeled by means of the united modeling (UML) and the Visual C# Edition software(s). View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Histogram intersection based image retrieval technique using relevance feedback

    Page(s): 67 - 70
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (262 KB) |  | HTML iconHTML  

    This article provides a color-based image retrieval technique for RGB image databases. Our proposed CBIR system uses the query by example approach and a relevance feedback mechanism. Feature extraction process is performed by computing a global color histogram for each image. Feature vectors are compared using the histogram intersection difference metric, and a relevance feedback mechanism is used in the retrieval process. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • New attempts in sound diarization

    Page(s): 71 - 76
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (202 KB) |  | HTML iconHTML  

    The paper discusses a new hybrid method in sound diarization (the process of segmenting an audio file into chunks that represent unique sources and clustering the obtained segments into groups that represent the same item). The most recent results are focusing mainly on the identification of voices during the telephonic recordings. In the hybrid method proposed here, a clustering is applied first, using an agglomerative approach regarding the construction of speaker models. Subsequently, when consistent amounts of data are gathered, special models are built using speaker factors. This idea gives good performance over the classical approach as the low-level clustering Bayesian Information Criterion scheme has poor performance on complex models, where speaker factors have very good precision. Speaker diarization improves speaker verification for multi-speaker audio (summed channel telephone data, single microphone interview data), is very important for speech recognition, and improves readability of an automatic transcription by structuring the audio stream into speaker turns and in some cases by providing the identity of the speakers. Sound diarization offers information which can be of interest for the multimedia documents indexing, in human-computer interaction, robotics, security systems, etc. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive gain sliding mode control in uncertain MIMO systems

    Page(s): 77 - 82
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (232 KB) |  | HTML iconHTML  

    This paper addresses robust adaptive sliding mode control for MIMO nonlinear systems in the presence of uncertainties and external disturbances. To achieve stability and performance, we propose a sliding mode control scheme with the design of a gain, whose gain is not constant and need to be adaptively updated. Unlike some existing methods for sliding mode control, no knowledge on the bound of uncertainty and disturbance is required to be known and only the fixed points and the dimensions of uncertain nonlinear systems are required to be known for control purpose. The effectiveness of the proposed controller design methodology is demonstrated by simulations. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Extension of a control structure with PSAIC

    Page(s): 83 - 86
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (266 KB) |  | HTML iconHTML  

    The interpolative control structures, in fuzzy or other variants, don't achieve very good performances when the controlled plant contains dead times. In an interpolative adaptive controller is presented, named PSAIC, which for certain types of plants offers good performances regarding variations of the plant's parameters, and particulary for some small variations of the dead time. This paper enhances this structure so that it can have good performances even for great variations of the dead time. The proposed solution consists in using linear correction blocks on the upstream and downsteam of the controlled plant. Through a PD operation very good performances are obtained. This solution is suitable for an adaptive type implementation. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Thermal consumptions: Control and monitoring

    Page(s): 87 - 92
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1180 KB) |  | HTML iconHTML  

    The presented application is the real implementation of a monitoring system at one of the clients of a company. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Case based reasoning approach for transaction outcomes prediction on currency markets

    Page(s): 93 - 98
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (290 KB) |  | HTML iconHTML  

    This paper presents a case based reasoning approach for making profit in the foreign exchange (forex) market with controlled risk using k nearest neighbour (kNN) and improving on the results with neural networks (NNs) and a combination of both. Although many professionals have proven that exchange rates can be forecast using neural networks for example, poor trading strategies and unpredictable market fluctuation can inevitably still result in substantial loss. As a result, the method proposed in this paper will focus on predicting the outcome of potential trades with fixed stop loss (ST) and take profit (TP) positions, in terms of a win or loss. With the help of the Monte Carlo method, randomly generated trades together with different traditional technical indicators are fed into the models, resulting in a win or lose output. This is clearly a case based reasoning approach, in terms of searching similar past trade setups for selecting successful trades. There are several advantages over classical forecasting associated with such an approach, and the technique presented in this paper brings a novel perspective to problem of exchange trades predictability. The strategies implemented have not been empirically investigated with such wide a range of time granularities as is done in this paper, in any to the authors known academic literature. The profitability of this approach is back-tested at the end of this paper and highly encouraging results are reported. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.