Showing papers in "International Journal of Applied Mathematics and Computer Science in 2008"
TL;DR: Fractional Positive Continuous-Time Linear Systems and Their Reachability A new class of fractional linear continuous-time linear systems described by state equations is introduced and the solution to the state equation is derived using the Laplace transform.
Abstract: A new class of fractional linear continuous-time linear systems described by state equations is introduced. The solution to the state equations is derived using the Laplace transform. Necessary and sufficient conditions are established for the internal and external positivity of fractional systems. Sufficient conditions are given for the reachability of fractional positive systems.
221 citations
TL;DR: A practical modification of the Hough transform is proposed that improves the detection of low-contrast circular objects and is applied to localize cell nuclei of cytological smears visualized using a phase contrast microscope.
Abstract: A practical modification of the Hough transform is proposed that improves the detection of low-contrast circular objects. The original circular Hough transform and its numerous modifications are discussed and compared in order to improve both the efficiency and computational complexity of the algorithm. Medical images are selected to verify the algorithm. In particular, the algorithm is applied to localize cell nuclei of cytological smears visualized using a phase contrast microscope.
135 citations
TL;DR: In this paper, a fast two-step algorithm is proposed for fault detection and isolation based on robust principal component analysis (PCA) which is applied to remove the effect of outliers on the PCA model.
Abstract: Principal component analysis (PCA) is a powerful fault detection and isolation method. However, the classical PCA, which is based on the estimation of the sample mean and covariance matrix of the data, is very sensitive to outliers in the training data set. Usually robust principal component analysis is applied to remove the effect of outliers on the PCA model. In this paper, a fast two-step algorithm is proposed. First, the objective was to find an accurate estimate of the covariance matrix of the data so that a PCA model might be developed that could then be used for fault detection and isolation. A very simple estimate derived from a one-step weighted variance-covariance estimate is used (Ruiz-Gazen, 1996). This is a "local" matrix of variance which tends to emphasize the contribution of close observations in comparison with distant observations (outliers). Second, structured residuals are used for multiple fault detection and isolation. These structured residuals are based on the reconstruction principle, and the existence condition of such residuals is used to determine the detectable faults and the isolable faults. The proposed scheme avoids the combinatorial explosion of faulty scenarios related to multiple faults to be considered. Then, this procedure for outliers detection and isolation is successfully applied to an example with multiple faults.
102 citations
TL;DR: A framework for automatic malignancy grading of fine needle aspiration biopsy tissue using Support Vector Machines (SVM) is presented and it is shown that SVMs performed best out of four tested classifiers.
Abstract: According to the World Health Organization (WHO), breast cancer (BC) is one of the most deadly cancers diagnosed among middle-aged women. Precise diagnosis and prognosis are crucial to reduce the high death rate. In this paper we present a framework for automatic malignancy grading of fine needle aspiration biopsy tissue. The malignancy grade is one of the most important factors taken into consideration during the prediction of cancer behavior after the treatment. Our framework is based on a classification using Support Vector Machines (SVM). The SVMs presented here are able to assign a malignancy grade based on preextracted features with the accuracy up to 94.24%. We also show that SVMs performed best out of four tested classifiers.
95 citations
TL;DR: The proposed hybrid automatic approach for the extraction of retinal image vessels consists in the application of mathematical morphology and a fuzzy clustering algorithm followed by a purification procedure.
Abstract: The extraction of blood vessels from retinal images is an important and challenging task in medical analysis and diagnosis. This paper presents a novel hybrid automatic approach for the extraction of retinal image vessels. The method consists in the application of mathematical morphology and a fuzzy clustering algorithm followed by a purification procedure. In mathematical morphology, the retinal image is smoothed and strengthened so that the blood vessels are enhanced and the background information is suppressed. The fuzzy clustering algorithm is then employed to the previous enhanced image for segmentation. After the fuzzy segmentation, a purification procedure is used to reduce the weak edges and noise, and the final results of the blood vessels are consequently achieved. The performance of the proposed method is compared with some existing segmentation methods and hand-labeled segmentations. The approach has been tested on a series of retinal images, and experimental results show that our technique is promising and effective.
93 citations
TL;DR: For both of these fundamental structural properties, new concepts inherent to fractional-order systems are established and new analytical methods for checking these properties are developed.
Abstract: In this paper we extend some basic results on the controllability and observability of linear discrete-time fractional-order systems. For both of these fundamental structural properties we establish some new concepts inherent to fractional-order systems and we develop new analytical methods for checking these properties. Numerical examples are presented to illustrate the theoretical results.
92 citations
TL;DR: A new approach to enhance the performance of an active fault tolerant control system based on a modified recovery/trajectory control system in which a reconfigurable reference input is considered when performance degradation occurs in the system due to faults in actuator dynamics.
Abstract: The prospective work reported in this paper explores a new approach to enhance the performance of an active fault tolerant control system. The proposed technique is based on a modified recovery/trajectory control system in which a reconfigurable reference input is considered when performance degradation occurs in the system due to faults in actuator dynamics. An added value of this work is to reduce the energy spent to achieve the desired closed-loop performance. This work is justified by the need of maintaining a reliable system in a dynamical way in order to achieve a mission by an autonomous system, e.g., a launcher, a satellite, a submarine, etc. The effectiveness is illustrated using a three-tank system for slowly varying reference inputs corrupted by actuators faults.
88 citations
TL;DR: The paper presents various methods for quantitative description of material structures based on image analysis and it is shown that the methods applied are useful for the assessment of service degradation of materials.
Abstract: The paper presents various methods for quantitative description of material structures. The main focus is on direct methods of description based on image analysis. In particular, techniques for the estimation of the size, shape and spatial distribution of structural elements observed by different microscopic techniques are described. The application of these methods for the characterization of the structures of engineering materials is demonstrated on a stainless steel used in petrochemical installations. It is shown that the methods applied are useful for the assessment of service degradation of materials.
86 citations
TL;DR: Two different neural network based schemes for fault diagnosis based on the nonlinear behaviour of the system being diagnosed as well as the robustness of a fault diagnosis scheme with respect to modelling uncertainty are described.
Abstract: Challenging design problems arise regularly in modern fault diagnosis systems. Unfortunately, classical analytical techniques often cannot provide acceptable solutions to such difficult tasks. This explains why soft computing techniques such as neural networks become more and more popular in industrial applications of fault diagnosis. Taking into account the two crucial aspects, i.e., the nonlinear behaviour of the system being diagnosed as well as the robustness of a fault diagnosis scheme with respect to modelling uncertainty, two different neural network based schemes are described and carefully discussed. The final part of the paper presents an illustrative example regarding the modelling and fault diagnosis of a DC motor, which shows the performance of the proposed strategy.
66 citations
TL;DR: The classical cumulative sum (CUSUM) test will be modified with respect to the AFD approach applied, and it will be shown how it is possible to apply both the gain and the phase change of the output signal in CUSUM tests.
Abstract: The focus of this paper is on stochastic change detection applied in connection with active fault diagnosis (AFD). An auxiliary input signal is applied in AFD. This signal injection in the system will in general allow us to obtain a fast change detection/isolation by considering the output or an error output from the system. The classical cumulative sum (CUSUM) test will be modified with respect to the AFD approach applied. The CUSUM method will be altered such that it will be able to detect a change in the signature from the auxiliary input signal in an (error) output signal. It will be shown how it is possible to apply both the gain and the phase change of the output signal in CUSUM tests. The method is demonstrated using an example.
61 citations
TL;DR: This paper investigates how the particular parameters of the learning algorithm affect the process of learning, and considers the issue of speeding up the adaptation process, while maintaining the stability of the optimal solution.
Abstract: In this paper we perform an analysis of the learning process with the ReSuMe method and spiking neural networks (Ponulak, 2005; Ponulak, 2006b). We investigate how the particular parameters of the learning algorithm affect the process of learning. We consider the issue of speeding up the adaptation process, while maintaining the stability of the optimal solution. This is an important issue in many real-life tasks where the neural networks are applied and where the fast learning convergence is highly desirable.
TL;DR: Three cytological image segmentation methods are described that include the watershed algorithm, active contouring and a cellular automata GrowCut method for fine Needle Biopsy Cytological Images.
Abstract: This paper describes three cytological image segmentation methods. The analysis includes the watershed algorithm, active contouring and a cellular automata GrowCut method. One can also find here a description of image pre-processing, Hough transform based pre-segmentation and an automatic nuclei localization mechanism used in our approach. Preliminary experimental results collected on a benchmark database present the quality of the methods in the analyzed issue. The discussion of common errors and possible future problems summarizes the work and points out regions that need further research.
TL;DR: The performed computer simulations show that the neural network reconstruction algorithm designed to work in this way outperforms conventional methods in the obtained image quality.
Abstract: A new neural network approach to image reconstruction from projections considering the parallel geometry of the scanner is presented. To solve this key problem in computed tomography, a special recurrent neural network is proposed. The reconstruction process is performed during the minimization of the energy function in this network. The performed computer simulations show that the neural network reconstruction algorithm designed to work in this way outperforms conventional methods in the obtained image quality.
TL;DR: A new approach to sensor placement based on diagnosability criteria, based on the study of structural matrices, is presented, where all the diagnosable, discriminable and detectable constraint sets are specified.
Abstract: This paper presents a new approach to sensor placement based on diagnosability criteria. It is based on the study of structural matrices. Properties of structural matrices regarding detectability, discriminability and diagnosability are established in order to be used by sensor placement methods. The proposed approach manages any number of constraints modelled by linear or nonlinear equations and it does not require the design of analytical redundancy relations. Assuming that a constraint models a component and that the cost of the measurement of each variable is defined, a method determining sensor placements satisfying diagnosability specifications, where all the diagnosable, discriminable and detectable constraint sets are specified, is proposed. An application example dealing with a dynamical linear system is presented.
TL;DR: Numerical analysis shows that interleukin-2 alone can cause the tumor cell population to regress, and theoretical analysis gives an expression for the discrete time delay and the length of the time delay to preserve stability.
Abstract: Immunotherapy with Interleukin-2: A Study Based on Mathematical ModelingThe role of interleukin-2 IL-2 in tumor dynamics is illustrated through mathematical modeling, using delay differential equations with a discrete time delay a modified version of the Kirshner-Panetta model. Theoretical analysis gives an expression for the discrete time delay and the length of the time delay to preserve stability. Numerical analysis shows that interleukin-2 alone can cause the tumor cell population to regress.
TL;DR: Several possible interpretations of the diagnostic matrix with rule-based systems are provided and analyzed and an approach to the diagnosis of multiple faults based on inconsistency analysis is outlined, and a refinement procedure using a qualitative model of dependencies among system variables is sketched out.
Abstract: The diagnosis of multiple faults is significantly more difficult than singular fault diagnosis. However, in realistic industrial systems the possibility of simultaneous occurrence of multiple faults must be taken into account. This paper investigates some of the limitations of the diagnostic model based on the simple binary diagnostic matrix in the case of multiple faults. Several possible interpretations of the diagnostic matrix with rule-based systems are provided and analyzed. A proposal of an extension of the basic, single-level model based on diagnostic matrices to a two-level one, founded on causal analysis and incorporating an OR and an AND matrix is put forward. An approach to the diagnosis of multiple faults based on inconsistency analysis is outlined, and a refinement procedure using a qualitative model of dependencies among system variables is sketched out.
TL;DR: The state of the art in Fault Detection and Isolation for NCSs has received increasing attention in recent years is reviewed, and a new theory for systems that operate in a distributed and asynchronous environment is developed.
Abstract: Networked Control Systems (NCSs) deal with feedback control systems with loops closed via data communication networks. Control over a network has many advantages compared with traditionally controlled systems, such as a lower implementation cost, reduced wiring, simpler installation and maintenance and higher reliability. Nevertheless, the network-induced delay, packet dropout, asynchronous behavior and other specificities of networks will degrade the performance of closed-loop systems. In this context, it is necessary to develop a new theory for systems that operate in a distributed and asynchronous environment. Research on Fault Detection and Isolation (FDI) for NCSs has received increasing attention in recent years. This paper reviews the state of the art in this topic.
TL;DR: A relaxed problem is discussed in which the sensor locations are given a priori and the aim is to determine the associated weights, which quantify the contributions of individual gauged sites, and a gradient projection algorithm is proposed to perform the search for the optimal solution.
Abstract: The problem of fault detection in distributed parameter systems (DPSs) is formulated as that of maximizing the power of a parametric hypothesis test which checks whether or not system parameters have nominal values. A computational scheme is provided for the design of a network of observation locations in a spatial domain that are supposed to be used while detecting changes in the underlying parameters of a distributed parameter system. The setting considered relates to a situation where from among a finite set of potential sensor locations only a subset can be selected because of the cost constraints. As a suitable performance measure, the Ds-optimality criterion defined on the Fisher information matrix for the estimated parameters is applied. Then, the solution of a resulting combinatorial problem is determined based on the branch-and-bound method. As its essential part, a relaxed problem is discussed in which the sensor locations are given a priori and the aim is to determine the associated weights, which quantify the contributions of individual gauged sites. The concavity and differentiability properties of the criterion are established and a gradient projection algorithm is proposed to perform the search for the optimal solution. The delineated approach is illustrated by a numerical example on a sensor network design for a two-dimensional convective diffusion process.
TL;DR: In this paper, instability of first order PFC is addressed, and solutions to handle higher order and difficult systems are proposed.
Abstract: Predictive Functional Control (PFC), belonging to the family of predictive control techniques, has been demonstrated as a powerful algorithm for controlling process plants. The input/output PFC formulation has been a particularly attractive paradigm for industrial processes, with a combination of simplicity and effectiveness. Though its use of a lag plus delay ARX/ARMAX model is justified in many applications, there exists a range of process types which may present difficulties, leading to chattering and/or instability. In this paper, instability of first order PFC is addressed, and solutions to handle higher order and difficult systems are proposed. The input/output PFC formulation is extended to cover the cases of internal models with zero and/or higher order pole dynamics in an ARX/ARMAX form, via a parallel and cascaded model decomposition. Finally, a generic form of PFC, based on elementary outputs, is proposed to handle a wider range of higher order oscillatory and non-minimum phase systems. The range of solutions presented are supported by appropriate examples.
TL;DR: The fact that the knowledge of the inverse of a Jordan transition matrix enables us to directly verify the controllability by Chen's theorem enabled us to obtain more general conditions for different types of controllable for infinite dimensional systems than the conditions existing in the literature so far.
Abstract: The objective of the article is to obtain general conditions for several types of controllability at once for an abstract differential equation of arbitrary order, instead of conditions for a fixed order equation. This innovative approach was possible owing to analyzing the n-th order linear system in the Frobenius form which generates a Jordan transition matrix of the Vandermonde form. We extensively used the fact that the knowledge of the inverse of a Jordan transition matrix enables us to directly verify the controllability by Chen's theorem. We used the explicit analytical form of the inverse Vandermonde matrix. This enabled us to obtain more general conditions for different types of controllability for infinite dimensional systems than the conditions existing in the literature so far. The methods introduced can be easily adapted to the analysis of other dynamic properties of the systems considered.
TL;DR: Three approaches to the detection of defects in continuous production processes, which are based on local methods of processing image sequences, are discussed, one of them is based on the estimation of fractal dimensions of image cross-sections, which provides different information on defects.
Abstract: Our aim is to discuss three approaches to the detection of defects in continuous production processes, which are based on local methods of processing image sequences. These approaches are motivated by and applicable to images of hot metals or other surfaces, which are uniform at a macroscopic level, when defects are not present. The first of them is based on the estimation of fractal dimensions of image cross-sections. The second and third approaches are compositions of known techniques, which are selected and tuned to our goal. We discuss their advantages and disadvantages, since they provide different information on defects. The results of their testing on 12 industrial images are also summarized.
TL;DR: The paper discusses particular features of the pipelined architecture and presents selected techniques of implementing early image processing procedures in hardware, which can realize many simple, still time-consuming operations in a parallel or a pipelining manner.
Abstract: Image processing in industrial vision systems requires both real-time speed and robustness. Modern computers, which fulfill the first demand, are sensitive to hard industrial environment conditions and require considerable amounts of energy. Programmable logic chips are available, which can realize many simple, still time-consuming operations in a parallel or a pipelined manner. The paper discusses particular features of the pipelined architecture and presents selected techniques of implementing early image processing procedures in hardware.
TL;DR: This paper concentrates on linear systems and the potential for the use of optimization methods and switching strategies to achieve effective control and introduces some of these issues from the point of view of the research group at Sheffield University.
Abstract: The area if Iterative Learning Control (ILC) has great potential for applications to systems with a naturally repetitive action where the transfer of data from repetition (trial or iteration) can lead to substantial improvements in tracking performance. There are several serious issues arising from the "2D" structure of ILC and a number of new problems requiring new ways of thinking and design. This paper introduces some of these issues from the point of view of the research group at Sheffield University and concentrates on linear systems and the potential for the use of optimization methods and switching strategies to achieve effective control.
TL;DR: This study investigates the properties of multiple matchings with respect to isolability and suggests to explore the topologies of multiple use-modes for the process and to employ active techniques for fault isolation to enhance structural isolability of faults.
Abstract: A water for injection system supplies chilled sterile water as a solvent for pharmaceutical products. There are ultimate requirements for the quality of the sterile water, and the consequence of a fault in temperature or in flow control within the process may cause a loss of one or more batches of the production. Early diagnosis of faults is hence of considerable interest for this process. This study investigates the properties of multiple matchings with respect to isolability, and it suggests to explore the topologies of multiple use-modes for the process and to employ active techniques for fault isolation to enhance structural isolability of faults. The suggested methods are validated on a high-fidelity simulation of the process.
TL;DR: It is shown that vertically weighted filters can be realized by a structure of three interconnected radial basis function (RBF) networks and the performance of the algorithm is assessed by studying industrial images.
Abstract: A class of nonparametric smoothing kernel methods for image processing and filtering that possess edge-preserving properties is examined. The proposed approach is a nonlinearly modified version of the classical nonparametric regression estimates utilizing the concept of vertical weighting. The method unifies a number of known nonlinear image filtering and denoising algorithms such as bilateral and steering kernel filters. It is shown that vertically weighted filters can be realized by a structure of three interconnected radial basis function (RBF) networks. We also assess the performance of the algorithm by studying industrial images.
TL;DR: This work surveys the so-called behavioral approach to systems and control theory, which was founded by J. C. Willems and his school and puts the focus on the set of trajectories of a dynamical system rather than on a specific set of equations modelling the underlying phenomenon.
Abstract: Behavioral Systems Theory: A SurveyWe survey the so-called behavioral approach to systems and control theory, which was founded by J. C. Willems and his school. The central idea of behavioral systems theory is to put the focus on the set of trajectories of a dynamical system rather than on a specific set of equations modelling the underlying phenomenon. Moreover, all signal components are treated on an equal footing at first, and their partition into inputs and outputs is derived from the system law, in a way that admits several valid cause-effect interpretations, in general.
TL;DR: This paper defines requirements which have to be taken into account in the background and address sequence selection process and a set of backgrounds which satisfied those requirements guarantee to achieve a very high fault coverage for multi-background memory testing.
Abstract: It is widely known that pattern sensitive faults are the most difficult faults to detect during the RAM testing process. One of the techniques which can be used for effective detection of this kind of faults is the multi-background test technique. According to this technique, multiple-run memory test execution is done. In this case, to achieve a high fault coverage, the structure of the consecutive memory backgrounds and the address sequence are very important. This paper defines requirements which have to be taken into account in the background and address sequence selection process. A set of backgrounds which satisfied those requirements guarantee us to achieve a very high fault coverage for multi-background memory testing.
TL;DR: New technical challenges that arise from networking dynamical systems, including challenges arising in prominent areas such as congestion control, sensor networks, as well as vehicle networks and swarms are described.
Abstract: This paper describes new technical challenges that arise from networking dynamical systems. In particular, the paper takes a look at the underlying phenomena and the resulting modeling problems that arise in such systems. Special emphasis is placed on the problem of synchronization, since this problem has not received as much attention in the literature as the phenomena of packet drop, delays, etc. The paper then discusses challenges arising in prominent areas such as congestion control, sensor networks, as well as vehicle networks and swarms.
TL;DR: This paper proposes an approach to dimensionality reduction as a first stage of training RBF nets and uses random projections as the first (additional) layer to reduce the dimensionality of input data.
Abstract: The dimensionality and the amount of data that need to be processed when intensive data streams are observed grow rapidly together with the development of sensors arrays, CCD and CMOS cameras and other devices. The aim of this paper is to propose an approach to dimensionality reduction as a first stage of training RBF nets. As a vehicle for presenting the ideas, the problem of estimating multivariate probability densities is chosen. The linear projection method is briefly surveyed. Using random projections as the first (additional) layer, we are able to reduce the dimensionality of input data. Bounds on the accuracy of RBF nets equipped with a random projection layer in comparison to RBF nets without dimensionality reduction are established. Finally, the results of simulations concerning multidimensional density estimation are briefly reported.
TL;DR: The paper presents a method of the extraction of the information about faults from the symptom observation matrix by means of singular value decomposition (SVD), in the form of generalized fault symptoms, and an application of grey system theory (GST) to symptom prognosis is presented.
Abstract: With the tools of modern metrology we can measure almost all variables in the phenomenon field of a working machine, and many of the measured quantities can be symptoms of machine conditions. On this basis, we can form a symptom observation matrix (SOM) intended for condition monitoring and wear trend (fault) identification. On the other hand, we know that contemporary complex machines may have many modes of failure, called faults. The paper presents a method of the extraction of the information about faults from the symptom observation matrix by means of singular value decomposition (SVD), in the form of generalized fault symptoms. As the readings of the symptoms can be unstable, the moving average of the SOM is applied with success. An attempt to assess the diagnostic contribution of a primary symptom is made, and also an approach to assess the symptom limit value and to connect the SVD methodology with neural nets is considered. Finally, a condition forecasting problem is discussed and an application of grey system theory (GST) to symptom prognosis is presented. These possibilities are illustrated by processing data taken directly from the machine vibration condition monitoring area.