Optimal linear filter design for systems with correlation in the measurement matrices and noises: recursive algorithm and applications

This paper addresses the optimal least-squares linear estimation problem for a class of discrete-time stochastic systems with random parameter matrices and correlated additive noises. The system presents the following main features: (1) one-step correlated and cross-correlated random parameter matrices in the observation equation are assumed; (2) the process and measurement noises are one-step autocorrelated and two-step cross-correlated. Using an innovation approach and these correlation assumptions, a recursive algorithm with a simple computational procedure is derived for the optimal linear filter. As a significant application of the proposed results, the optimal recursive filtering problem in multi-sensor systems with missing measurements and random delays can be addressed. Numerical simulation examples are used to demonstrate the feasibility of the proposed filtering algorithm, which is also compared with other filters that have been proposed.     

Multi-objective uniform design as a SVM model selection tool for face recognition

The primary difficulty of support vector machine (SVM) model selection is heavy computational cost, thus it is difficult for current model selection methods to be applied in face recognition. Model selection via uniform design can effectively alleviate the computational cost, but its drawback is that it adopts a single objective criterion which can not always guarantee the generalization capacity. The sensitivity and specificity as multi-objective criteria have been proved of better performance and can provide a means for obtaining more realistic models. This paper first proposes a multi-objective uniform design (MOUD) search method as a SVM model selection tool, and then applies this optimized SVM classifier to face recognition. Because of replacing single objective criterion with multi-objective criteria and adopting uniform design to seek experimental points that uniformly scatter on whole experimental domain, MOUD can reduce the computational cost and improve the classification ability simultaneously. The experiments are executed on UCI benchmark, and on Yale and CAS-PEAL-R1 face databases. The experimental results show that the proposed method outperforms other model search methods significantly, especially for face recognition.     

FLC design for bounded separable functions with linear input-outputrelations as a special case

A systematic procedure is presented for designing a knowledge base which exactly implements a specified bounded separable function in fuzzy logic. The design of a fuzzy logic control (FLC) for local linear control is a special case of the result. Examples, including controller design for a nonlinear process control application, are presented     

Performance of a diagnostic system (Iliad) as a tool for quality assurance.

Quality assurance improves health care through detection of quality problems and feedback to the care giver. Current review procedures employed by the Peer Review Organizations (PROs), however, appear to underdetect quality problems, particularly those arising from diagnostic errors. We studied the use of an expert diagnostic system, Iliad, to detect quality problems arising from diagnostic errors. One hundred cases were selected from among those Medicare cases reviewed by the Utah PRO (UPRO) and which contained diagnoses recognized by Iliad. Iliad flagged 28 cases out of the 100 as containing diagnostic errors, and a gold standard physician review confirmed quality problems in 17 cases (60.7%). The UPRO review found 28 cases with quality problems, mostly treatment and documentation errors. The quality problems detected by Iliad appeared to be more serious than those detected by the UPRO review. Among the six cases with quality problems detected by both the UPRO and the Iliad review, there was none for which the same quality problem was detected by the two procedures. The two review procedures were therefore complementary.     

Input design as a tool to improve the convergence of PEM

The Prediction Error Method (PEM) is related to an optimization problem built on input/output data collected from the system to be identified. It is often hard to find the global solution of this optimization problem because the corresponding objective function presents local minima and/or the search space is constrained to a nonconvex set. The shape of the cost function, and hence the difficulty in solving the optimization problem, depends directly on the experimental conditions, more specifically on the spectrum of the input/output data collected from the system. Therefore, it seems plausible to improve the convergence to the global minimum by properly choosing the spectrum of the input; in this paper, we address this problem. We present a condition for convergence to the global minimum of the cost function and propose its inclusion in the input design. We present the application of the proposed approach to case studies where the algorithms tend to get trapped in nonglobal minima.     

An energy model for the optimal design of linear continuum structures

An analytical model is presented for the optimal design of linearly elastic continuum structures. To facilitate the expression of the combined analysis and design problem in general form, a basis is introduced covering a general set of energy invariants. Both internal (strain) energy and the expression of generalized cost are represented conveniently in terms of this basis, and as a result the optimality conditions for the design problem have a particularly simple form. Present developments comprise a reinterpretation and an extension of existing models where the design variable is the material modulus tensor, and where cost is represented in a general form. The conventional potential energy statement for linear continuum elastostatics is restated in the form of an isoperimetric problem, as a preliminary step. This interpretation of the mechanics is then incorporated in a max-min formulation applicable for the general design of linear continuum structures. To exemplify its application, the model is interpreted as it would apply for certain materials with particular geometric structure, e.g. crystalline forms. Also problems treated earlier where optimal material properties are predicted for the case where unit cost is proportional to the trace of the modulus tensor are identified as examples within the generalized formulation. The application of a recently developed technique to predict optimal black-white structures, i.e. designs having sharp topological features, is considered in the setting of the present generalized model.     

Establishment of thermodynamic equilibrium in a cosmological model with arbitrary acceleration

We build a strict mathematical model of thermodynamic equilibrium establishment in an originally non-equilibrium cosmological ultrarelativistic plasma for an arbitrarily accelerated Universe under the assumption that scaling of elementary particle interactions is restored at energies above the unitary limit. It has been shown that in the case of a positive acceleration of the Universe, a thermodynamic equilibrium can never be completely restored.     

Using PRISM model checker as a validation tool for an analytical model of IEEE 802.15.4 networks

Commonly, simulation by using an existing network simulation tool or a simulator developed from scratch is employed for validation of analytical network performance models. An analytical model of star-shaped wireless sensor networks has been proposed in the literature in which, upon receiving a query from the coordinator, each sensor node sends one data frame to it by executing the IEEE 802.15.4 unslotted carrier-sense multiple access with collision avoidance algorithm. The model consists of expressions for calculation of the probability of successful receipt of the data at a certain time and the like. The authors of the model have written a special simulation program in order to validate the expressions. Our aim was to employ probabilistic model checker PRISM instead. PRISM only requires the user to formally specify the network as a kind of state machine and the queries about the probabilities sought in the form of logical formulas. It finds the probabilities automatically and can present them on graphs. We show how to specify the networks formally in such a way that all the expressions from the analytical model can be validated with PRISM. For those networks containing a few nodes, the validation can be carried out by normal model checking, which, in contrast to the simulation, always checks all the possible network behaviors, whereas statistical model checking can be used for the larger networks.     

Simultaneous design of robust gain-scheduled static output-feedback controller and scaling matrices for linear parameter varying systems with inexact scheduling parameters

This article presents a design method of the robust gain-scheduled static output-feedback controller exploiting inexact measured scheduling parameters for multi-affine linear parameter-varying systems with structured uncertainty blocks. Performance scaling matrices are introduced in the design process to reduce conservatism. By introducing auxiliary variables and properly utilizing projection lemma, a parameter-dependent linear matrix inequality with a single line search parameter is derived to synthesize the static output-feedback controller gains and scaling matrices simultaneously. Based on vertices of the convex polytope covering the admissible region of scheduling parameters and inexact ones, the given parameter-dependent synthesis condition is further expressed as a set of linear matrix inequalities at the vertices of the polytope to guarantee the robustness against inaccurate scheduling parameters. Several examples show the effectiveness of the proposed algorithm.     

Minimax design for a class of linear quadratic problems with parameter uncertainty

It is found for a class of linear-quadratic problems that the parameter strategy for the unknown time-varying bounded parameters are found to be independent of the present state. Since the parameter strategy is only a function of time, the feedback gains of the linear-quadratic problem are still easily calculatable functions of time.     

An algorithm for estimating the parameters in multiple linear regression model with linear constraints

This paper develops an algorithm for estimating the parameters when the parameters are restricted by linear constraints in a general multiple regression model. The algorithm solves discrete approximation in the Φ error where Φ is a convex and symmetric function. These discrete approximations arise in fitting by polynomials, linear regression and goal programming. Discrete approximation problems in the L₁ norm is a special case. The approaches to the solution of these approximation problems have a long history. The algorithm utilizes certain properties of the problem to significantly reduce the number of iterations to find the approximated solution.     

Addendum to: An energy model for the optimal design of linear continuum structures

The original paper of the above title presents an analytical model for problems in the optimal design of linearly elastic continuum structures, where the material modulus tensor has the role of design variable. Both internal (strain) energy and the expression of generalized cost are represented conveniently there, in a form where the modulus tensor is transformed into vector coordinates. The general design of linear continuum structures is stated as a max-min problem. Optimality conditions for the transformed design problem have particularly simple form.¶Both local properties, represented by the relative values of components of the modulus tensor, and the global distribution of structural resource (material) are variable in the design.With some modification to the original formulation, these separate aspects of design can be represented explicitly in the model. This modified form, which directly facilitates study of the role of local properties in the prediction of optimal design, and which ultimately serves as the basis for schemes to perform computational solution, is described and substantiated here.     

Numerical simulation of thermodynamic equilibrium establishment in a cosmological model with arbitrary acceleration

We present the results of a numerical simulation of the previously constructed strict mathematical model of thermodynamic equilibrium establishment in an originally nonequilibrium cosmological ultrarelativistic plasma in a universe with any acceleration, under the assumption of scaling restoration for elementary particle interactions at energies above a unitary limit. The limiting parametres are found for a residual nonequilibrium distribution of nonequilibrium relic ultra-high energy particles.     

Kinetic modelling as a tool for the design of a vascular bioartificial pancreas: feedback between modelling and experimental validation

A bioartificial pancreas is a system which contains isolated islets of Langerhans protected against immune rejection by an artificial membrane, permeable to glucose and insulin, but not to lymphocytes and immunoglobulins. However, it is necessary to design a device which performs as a closed-loop insulin delivery system, more specifically which rapidly responds to a change in the recipient's blood glucose concentration by an appropriate change in insulin release. We have designed a system intended to be connected as an arteriovenous shunt of the recipient; islets are placed between two flat ultrafiltration membranes, and blood circulates successively above the upper, and below the lower, membrane, in reverse direction. A complete kinetic model of glucose transfer from blood to the islet compartment, of insulin generation by the islets displaying a biphasic insulin pattern, and of insulin transfer into the bloodstream was described, and parameters were calculated on the basis of experimental data obtained when islets of Langerhans were perfused in vitro with a synthetic buffer. The resulting calculations indicated that both diffusional and convective transfers were involved in glucose and insulin mass transfer across the membrane, the contribution of diffusion being the most important. The geometry of the system was therefore modified in order to decrease the resistance to flow inside the blood channel. This should increase, at a given hydrostatic pressure, the blood flow rate, and thereby improve the diffusional transfer of insulin. This should also decrease the thrombogenicity of the device.(ABSTRACT TRUNCATED AT 250 WORDS)     

Control design for a class of linear 0-controllable discrete systems with constraints

Formation of a feedback control for the class of 0-controllable linear stationary systems with constraints is studied.Translated from Avtomatika i Telemekhanika, No. 1, 2005, pp. 49–58.Original Russian Text Copyright © 2005 by Sirotin.This work was supported by the Russian Foundation for Basic Research, project no. 03-01-00050 and Russian Ministry of Education, project no. T02-14.0-681.This paper was recommended for publication by B.T. Polyak, a member of the Editorial Board     

Limitations of the computer as a tool for the fine artist

This paper proposes that the commercial nature of currently available graphic computer systems inclines their use by fine artists toward limited applications. The repeated and fictive nature of commercial imagery is described. A brief phenomenology of the graphic computer is offered, and on-going awareness of the form and social context of the machine is recommended.     

Relational database as a tool in industrial design. Experience from a human factors engineering analysis of a module for manned space-flight

A human factors engineering analysis was carried out to verify that the CUPOLA—a module developed by the European Space Agency for the International Space Station—complies with an extensive set of human factors requirements. Analysis was carried out in three steps: task analysis, computer simulation of tasks and empirical test of tasks in a physical mock up. In advance to each step the method of assessment and type of information to be obtained were determined in detail and the way of documentation was established as input forms to a relational database. Advantages and drawbacks of this early formalisation as seen by project members are discussed in the present paper.

Relevance to industry

The method of early formalisation by a relational database used throughout the project showed to be a suitable tool in this human factors analysis of a working place under design. Early formalisation of the results and documentation served as a quality system supporting a homogeneous high standard of data collection and documentation. In industry, the use of relational databases underlying Product Data Management systems increases. This makes it relevant to try and link human factors work to these methods of documentation in order to promote the integration of human factors work at an early stage of product and production development.     

Some uses of the microcomputer as a simulation tool in the design and development of electronic visual display devices

During the development of displays employing solid-state devices, the need arises for a technique to assist in the preliminary evaluation of proposed applications of this fast-moving technology. Some examples are given of alphameric and graphic displays which may be simulated using a microcomputer.