By Topic

Computational Intelligence and Intelligent Informatics, 2007. ISCIII '07. International Symposium on

Date 28-30 March 2007

Filter Results

Displaying Results 1 - 25 of 57
  • Controllability of Quantum Bits from the von Neumann Architecture to Quantum Computing

    Publication Year: 2007 , Page(s): 9 - 12
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (225 KB) |  | HTML iconHTML  

    In this paper we consider the (state) reachability and controllability problems of special two-level quantum systems, the so-called quantum bits via externally applied electro-magnetic field. The system is described by special a bilinear right-invariant model whose state varies on the Lie group of 2 x 2 special unitary matrices. We show that if two or more independent controls are used, then every state can be achieved in arbitrary time using finite energy. The mathematical construction is motivated by the demand of manipulating (or logically operating on) the state of quantum bits, and the results provide some insight into the feasibility of realizing given operations in quantum computers. The paper has a special actuality: both computer science and quantum mechanics are closely related to the famous Hungarian mathematician John von Neumann, and this year there is the 50 th Anniversary of his early and sorrowful death. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Context Dependent Reconstructive Communication

    Publication Year: 2007 , Page(s): 13 - 19
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1906 KB) |  | HTML iconHTML  

    Fuzzy communication contains vague or imprecise components and it might lack of abundant information. If two entities (man or machine) are communicating by a fuzzy channel, it is necessary that both ends possess the same codebook. The codebook might partly consist of common knowledge but it usually requires a context dependent part that is either learned by the communicating entity or defined by expert knowledge. Possibly it is continuously adapting to the input information. If such a codebook is not available or it contains too imprecise information, the information to be transmitted might be too much distorted and might lead to misunderstanding, misinterpretation and serious damage. If however the quality of the available codebook is satisfactory, the communication will be efficient i. e., the original contents of the message can be reconstructed. At the same time it is cost effective, as fuzzy communication is compressed as compared to traditional "abundant communication". View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dense optical Flow Computation for 2D and 3D images via multigrid on a parallel machine

    Publication Year: 2007 , Page(s): 21
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (98 KB)  

    Summary form only given. Optical flow computation is known to be a fundamental step in many applications in image processing, pattern recognition, data compression, and biomedical technology. The goal is to compute an approximation to the projection of the 3D motion field onto the imaging surface. I consider in this talk the problem of real-time computation of dense optical flow for 2D and 3D images by the classical Horn-Schunck model. The basic assumption of this model is that the intensity variations are weak and only due to a movement in the image plan. This constant brightness assumption leads to an ill-posed problem that can only be solved by imposing an additional constraint requiring the flow field to be smooth by means of a standard regularization approach. The Horn-Schuck model is traditionally solved via a coupled point wise relaxation. The performance is generally poor when the image sequence data are strongly textured. I will review and discuss the multigrid components for a fast and robust computation. The parallel implementation of the proposed scheme using domain partitioning shows that the algorithm scales well up to 32 processors on a cluster of AMD Opteron CPUs which consists of four-way nodes connected by an Infiniband network. I will conclude by presenting some experimental results showing the good performance of the proposed algorithm on some classical 2D test images and also for computing 3D motion from cardiac C-arm CT images. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computational Intelligence Based Intelligence Control for Stepping Motors and a Mobile Robot is "Mascot Robot" Project

    Publication Year: 2007 , Page(s): 23
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (575 KB) |  | HTML iconHTML  

    Intelligent control for 5 phase stepping motors is presented based on computational intelligence technology. It enables to divide each revolution/rotation into 5 million equiangular positions by keeping normal speed, torque, low vibration, small heat loss, and low electric power consumption. The products are now being released in the real market. The outline of the algorithm is mentioned with several experimental results by using DVD demonstration. The stepping motors are used in a part of the on going "Mascot Robot" project included in "Development Project for a Common Basis of Next-Generation Robots" sponsored by NEDO (New Energy and industrial technology Development Organization, Japan), i.e., the nano drive controlled stepping motors are used to develop a mobile part. Its design-concept is also introduced by using DVD video images. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Information Enhancement Method for Image Retrieval and Object Recognition

    Publication Year: 2007 , Page(s): 25 - 29
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2470 KB) |  | HTML iconHTML  

    Recently, the importance of information enhancement methods in digital image processing has increased significantly. A large amount of research has been focused on information retrieval and image understanding. Typical examples are searching for similar objects/images in large databases and understanding the objects in images. The main point of these tasks is to extract the most characteristic features of the objects in the images, like edges, corners, characteristic textures, etc. Another very important aspect can be the separation of the "significant" and "unimportant" parts of these features, i.e. the enhancement of those features which carry primary information and to filter out the part which represents information of minor importance. By this, the complexity of the searching and/or interpreting algorithms can be decreased while the performance increased. This paper describes a new edge processing method which is able to extract the "primary", i.e. those edges which can advantageously be used in sketch based image retrieval algorithms. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Arabic Speech Recognition System Based on CMUSphinx

    Publication Year: 2007 , Page(s): 31 - 35
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2624 KB) |  | HTML iconHTML  

    In this paper we present the creation of an Arabic version of Automated Speech Recognition System (ASR). This system is based on the open source Sphinx-4, from the Carnegie Mellon University. Which is a speech recognition system based on discrete hidden Markov models (HMMs). We investigate the changes that must be made to the model to adapt Arabic voice recognition. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Estimation of Motion Parameters Using 2-D Lines without Correspondences Based on Virtual Electric Potential Model

    Publication Year: 2007 , Page(s): 37 - 43
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3158 KB) |  | HTML iconHTML  

    This paper addresses the estimation problem of the motion parameters using 2D lines without correspondences. The method is based on two main ideas. The first one consists to model the image as grid of the virtual electric potential and to exploit the corners detected by an improved version of Harris and Stephens detector. Characteristic of gradient vectors at the corners detected is used in order to draw the strait lines. The second one uses the invariance property of the correlation matrix eigenstructure decomposition. The correlation matrix is formulated from the directing vectors of the straight lines. To determine the correspondence between the lines and to remove the outliers we use an affinity function based on a heuristic criterion. The performances of the method are degraded considerably in presence of noise. For this reason, a preprocessing stage is suitable. It consists to estimate the noise correlation matrix by evaluating iteratively the noise subspace in order to improve the signal noise ratio (SNR). The robustness of the method to the noise and the outliers is remarkable in synthetic or real images. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Gray-level Corner Detection by Virtual Electric Field Model

    Publication Year: 2007 , Page(s): 45 - 49
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (801 KB) |  | HTML iconHTML  

    Corner detection and feature extraction are widely used in image processing and computer vision applications. In this paper, we propose a new gray-level corner detection based on virtual electric field model having different configurations, which demonstrate the best detection. The basic idea is to model the image as a grid of virtual electric charges of a plane surface in electrostatic balance. The algorithm is achieved in two main steps. The first one uses an adaptive method for computing directional gradients which permits to build an edge detection operator of 3times3 pixels. The second one introduces this operator for determining image derivatives in order to detect the corners. The smoothed squared images derivatives are given by using a Gaussian function. Then, the response function proposed by Harris and Stephens is computed for each pixel, using auto-correlation matrix. The local maxima search is performed as a final step of the method. Simulation results on synthetic and real images show the performances of the proposed method compared to that presented by an improved version of Harris detector. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Feature Selection on Supervised Classification Using Wilks Lambda Statistic

    Publication Year: 2007 , Page(s): 51 - 55
    Cited by:  Papers (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (203 KB) |  | HTML iconHTML  

    Variable and feature selection have become the focus of much research in areas of application for which datasets with tens or hundreds of thousands of variables are available. This paper addresses the feature selection problem for supervised classification. We operate this feature selection step by step, which leads to search for a criterion to quantify the most relevant variable and its contribution compared to the others already selected. In this article we present a feature selection method based on the Wilk's lambda criterion which is a statistical one used in discriminant analysis. Our objective is to evaluate the performances of this method when used in another application different from its classical one i.e. the discriminant analysis. This criterion is compared to other very known algorithms in the field of the feature selection on various real data sets. The obtained results with the criterion of Wilk's lambda are satisfactory and even better in some cases. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Combining Information Extratction for Text Mining by Using Morphological Patterns and Knowledge Discovery Using Inductive Logic Programming

    Publication Year: 2007 , Page(s): 57 - 62
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3311 KB) |  | HTML iconHTML  

    This paper introduces concepts and a rule-based model for information extraction (IE) strategy using unsupervised algorithm and inductive learning in a top-down fashion. We have used the natural language processing techniques for identifying the morphological patterns (features) and for constructing patterns based on which the necessary information is extracted. The extracted information is then used to discover knowledge in the form of if-then rules. We have considered the technical abstracts of two different domains, by relating the information extracted from the abstract part with the information provided in the conclusion part. The information gain is found as the result of knowledge discovery and we have found our system producing an accuracy of 90%. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Some Observations on Stability of the Switching Adaptive Rule Bases of the Fuzzy Self-Adapted Interpolative Controllers

    Publication Year: 2007 , Page(s): 63 - 66
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (281 KB) |  | HTML iconHTML  

    The fuzzy self adapted interpolative controllers are able to identify on-line and to control a wide range of unknown plants. These controllers are developed by combining fuzzy-inter-polative modules (implemented by look-up tables). In order to cope with contradictory strategies demanded by time variable plants, several adaptive correctors, corresponding to different operating regimes can be fusioned or switched. Switching adaptive rule bases can cause the same stability problems as switching simple controllers. A stability benchmark study is provided in this issue, the instability generating factors are revealed, and the use of the switching error is recommended. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Switching Adaptive Correctors for Fuzzy Fusion Self-Adapted Interpolative Controllers

    Publication Year: 2007 , Page(s): 67 - 72
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4502 KB) |  | HTML iconHTML  

    The fuzzy self adapted interpolative controllers are able to identify on-line and to control a wide range of unknown plants. These controllers are developed by combining fuzzy-inter-polative modules (implemented by look-up tables). In order to cope with contradictory strategies demanded by time variable plants, several adaptive correctors, corresponding to different operating regimes can be fusioned. The paper is investigating the replacement of the fuzzy fusion by the switching of the adaptive correctors. The fusion and the switching are compared. Two adaptive correctors are involved, for systems with and without dead times. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fuzzy Neighborhood Based Approach for Practical Delivery Problem

    Publication Year: 2007 , Page(s): 73 - 78
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3980 KB) |  | HTML iconHTML  

    A solving method is proposed for the practical delivery problem by truck. In order to make easier the weight setting for each of the evaluation criteria presented in the evaluation function, an integrated evaluation criterion is proposed based on fuzzy neighborhood degree concept. Furthermore, with the objective to obtain a high-quality solution in short computational time, (i) a simulated annealing based method for finding a (sub-)optimal route for each vehicle; and (ii) an evolutionary computation based method for finding a (sub-)optimal schedule for a group of vehicles are proposed. The proposed method is implemented in C++ language on a personal computer, and is evaluated on real-world data from a food company in Saitama prefecture, Japan. Compared to a scheduling expert, the proposed method has resulted in 18% lower delivery cost, with 80%-90% shorter computational time. The proposed methods is able to also be applied to other delivery problem such as home delivery services and mail delivery problems. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Toward an Integration of the Fuzzy Logic and MCDA to GIS: Application to the Project of the Localization of a Site for the Implantation of Chemical Products Factory

    Publication Year: 2007 , Page(s): 79 - 83
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (311 KB) |  | HTML iconHTML  

    The implementation of a new urban infrastructure causes more and more conflicts mainly because of the correlation of actors coming often from opposed different domains, such as the political, the social, the economic, and the spatial one. To help the decision makers in the territory management, several actors have shown the adequacy of the association of the geographical information systems (GIS) and the multicriterion decision aid (MCDA) methods. This association not only permits to manage the spatial reference information but also to apply new analysis methods permitting to have the most pertinent and most profitable information. However, most problems of MCDA take into account not only the traditional quantitative criteria, but also the qualitative and imprecise criteria, which make their use difficult for the decision and analysis. We propose in this paper, a hybrid model of MCDA for the localization of a site for the implantation of a chemical products factory. This model enables us to combine the use of the multi-representation geographical information systems (MRGIS) and the MCDA methods, such as AHP (analytic hierarchy process). Then, to facilitate the interpretation of the qualitative data in our model, we propose an approach of data modelling based on the fuzzy set theory, which makes it possible to interpret the qualitative values by precise values rather than by classical intervals. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On Aggregation of Fuzzy Preference Structures

    Publication Year: 2007 , Page(s): 85 - 88
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (152 KB) |  | HTML iconHTML  

    We investigate the problem of aggregation of fuzzy preference structures in multicriteria decision making. Starting from monocriterion weak preferences, there are two ways to define global strict preference, indifference and incomparability. We prove that, under very mild conditions, the only aggregation for which those two ways result in the same global preference structure is dictatorial. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the Use of Fuzzy Logic for Inherently Parallel Computations

    Publication Year: 2007 , Page(s): 89 - 92
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4366 KB) |  | HTML iconHTML  

    The possibility of using fuzzy logic for performing parallel computation is introduced. An analogy is drawn between non-deterministic models of computing and fuzzy computing. In practice this can be implemented using strings of fuzzy bits, which can represent a "superposition" of several crisp bit strings. Thus, using fuzzy logic and analog fuzzy hardware, inherently single instruction multiple data parallel computing can be achieved. The possibility of speeding up computations using oracle machines using the proposed concept is examined. As a proof of concept, the rapid solution to Deutsch's problem is presented. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fuzzy Logic Based Gradient Descent Method with Application to a PI-type Fuzzy Controller Tuning: New Results

    Publication Year: 2007 , Page(s): 93 - 97
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4459 KB) |  | HTML iconHTML  

    An improved self-tuning mechanism of fuzzy control by gradient descent method is presented. The membership function parameters are tuned by minimizing some criterion defined on the control output using the steepest gradient descent algorithm. The factor which controls how much the fuzzy controller parameters are altered is adjusted continuously using a set of fuzzy rules. This varying factor is determined with respect to the values of the objective function and its change. An application to the control output optimization of a Pi-type fuzzy controller shows the superiority of the proposed self-tuning mechanism over a previously published approach in terms of both precision and convergence rate. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computational Relaxed TP Model Transformation by Restriction of the Computation to Subspaces of the Dynamic Model

    Publication Year: 2007 , Page(s): 99 - 104
    Cited by:  Papers (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (362 KB) |  | HTML iconHTML  

    The Tensor-Product (TP) model transformation Is a recently proposed numerical method capable of transforming linear parameter varying state-space models to the Higher Order Singular Value Decomposition (HOSVD) based canonical form of polytopic models. It is also capable of generating various types of convex TP models as well for linear matrix inequality based control design. The crucial point of the TP model transformation is that its computational load exponentially explodes with the dimensionality of the parameter vector of the state-space model. In this paper we propose a modified TP model transformation that computes the HOSVD-based canonical form by dimensionality reduced sub-spaces of the parameter vector that leads to the considerable reduction of the computation. A numerical example is also given to show how the modified TP model transformation can readily be executed in cases when the original TP model transformation fails. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modeling and Simulation in Scicos: A Case Study

    Publication Year: 2007 , Page(s): 105 - 110
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3746 KB) |  | HTML iconHTML  

    In this paper, we explore some modeling capabilities of Scicos. Our aim is to generate chaos from a simple hybrid dynamical system. We give the chaotic dynamics of the current-programmed boost converter in open-loop circuit as a case study. By considering two bifurcation parameters the current reference and the voltage input, we observe that the obtained Scicos simulations show that the boost converter is prone to subharmonic behavior and chaos. We also present the corresponding bifurcation diagrams. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Numerical Reconstruction of the HOSVD Based Canonical Form of Polytopic Dynamic Models

    Publication Year: 2007 , Page(s): 111 - 116
    Cited by:  Papers (10)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (299 KB) |  | HTML iconHTML  

    The main objective of the paper is to introduce how the concept of tensor HOSVD (higher order singular value decomposition) can be carried over to the TP (tensor product) dynamic models. We term this decomposition as HOSVD based canonical form of TP model or polytopic model form. The key idea and the basic concept of this decomposition was proposed recently with the TP model transformation based control design methodology. The novelty of this paper is to present the mathematical background of this concept. The paper shows convergency theorems how the TP model transformation is capable of reconstructing this HOSVD based canonical form numerically. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Prediction of the Acoustic Pressure Backscattered by a Steel Tube Using Neural Networks Approach

    Publication Year: 2007 , Page(s): 117 - 119
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1210 KB) |  | HTML iconHTML  

    A new approach is used to predict the pressure backscattered by a tube using the artificial neural networks (ANNs) techniques. The studied tube consists of steel. During the development of the network, several configurations are evaluated for various radius ratio b/a (a: outer radius, b: inner radius of tube). The multilayer perceptron (MLP) is used in the current study. The optimal model selected is a network with one hidden layer. This model is able to predict the pressure backscattered with a mean relative error (MRE) of about a 1.6%. The comparison of the obtained and the experimental results indicate that the ANN method is suitable to be used to predict this one. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive Beamformer-Rake Receiver for Space-Time Coded DS-CDMA Systems

    Publication Year: 2007 , Page(s): 121 - 124
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (832 KB) |  | HTML iconHTML  

    An adaptive beamformer-Rake receiver is proposed for code division multiple access (CDMA) space-time block coded (STBC) systems in frequency selective fading channels (FSFC). The system is based on a blind code filtering adaptive beamformer at the base station and the Alamouti's transmit diversity at the mobile users. The system performance is evaluated by simulation in terms of bit error rates (BER) and beampatterns. It is shown that, in severe FSFC, the proposed hybrid system significantly outperforms MIMO systems without beamforming. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Output Feedback Nonlinear GPC Using High Gain Observer

    Publication Year: 2007 , Page(s): 125 - 129
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2315 KB) |  | HTML iconHTML  

    In this paper, Nonlinear Generalized Predictive Control (NGPC), proposed by Chen [4] in continuous time, is reformulated into a quadratic optimization problem in order to take into account constraints, and this approach is applied to a particular class of nonlinear systems. The states which are assumed available will be estimated in this work by a high gain observer (HGO). The closed loop dynamics, under combination of predictive controller and observer synthesis, is shown transparent to the designers, and merely manipulated in the sense that output feedback controller explicitly depend on choice of only two parameters (prediction time and high gain parameter). For a nonlinear example of considered class, we show satisfactory performances and robustness in presence of disturbance. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis of the Discontinuous PWM Strategies Applied to the VSI

    Publication Year: 2007 , Page(s): 131 - 136
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1224 KB) |  | HTML iconHTML  

    Fully digital AC drives with pulse width modulator inverters are becoming an industrial standard. For PWM inverters the most commonly used is the conventional sine PWM (SPWM). An attempt to improve this carrier based strategy is presented by means of the introduction of discontinuous techniques; such as the dead band PWM (DBPWM) and the modified SPWM (MSPWM). Their characteristics and qualities are evaluated by some performance criteria such as, modulation index concerning the inverter output voltage fundamental, the distortion factor of the load current, torque harmonics, and the influence of the switching frequency upon losses in the converter. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Speed Sliding Control of PMSM Drives

    Publication Year: 2007 , Page(s): 137 - 141
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2220 KB) |  | HTML iconHTML  

    The current controlled voltage source inverter fed PMSM has received wide spread interest in high performance vector control and motion control applications. Hysteresis controllers are intrinsically robust to system parameters, exhibit very high dynamics and are suitable for simple implementation. The main drawback of the hysteresis controller is a limited control on switching frequency. Very high switching frequency may be resulted from the use of three independent controllers. In this paper, both the fixed band and the sinusoidal band current controllers are presented and their performances evaluated. In addition, a mixed mode controller of a sinusoidal band added to a fixed band is proposed. For comparison purposes, the harmonics spectra of the phase currents are obtained using the fast Fourier transformer (FFT). This paper presents also a detailed analysis and simulation of speed sliding mode control (SMC). The effectiveness is demonstrated for different operating conditions. View full abstract»

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