This contribution describes an active-set algorithm for the optimization of regression support vector machines (SVMs). Its intended use is mainly system identification. Currently, SVMs are computed solving a QP proble...
详细信息
This contribution describes an active-set algorithm for the optimization of regression support vector machines (SVMs). Its intended use is mainly system identification. Currently, SVMs are computed solving a QP problem by working-set algorithms like the SMO method. Although showing good results in general, they may perform weakly in some situations, particularly when solving regression problems. In these cases, active-set techniques (which are robust general-purpose QP solvers) have been shown to be a reasonable alternative. The paper considers how to adapt them to SVM regession with fixed or variable bias term and applies them to the identification of a condensing boiler.
There has been much interest recently in the analysis of optomechanical systems incorporating dielectric nano- or microspheres inside a cavity field. We analyze here the situation when one of the mirrors of the cavity...
详细信息
There has been much interest recently in the analysis of optomechanical systems incorporating dielectric nano- or microspheres inside a cavity field. We analyze here the situation when one of the mirrors of the cavity itself is also allowed to move. We reveal that the interplay between the two oscillators yields a cross-coupling that results in, e.g., appreciable cooling and squeezing of the motion of the sphere, despite its nominal quadratic coupling. We also discuss a simple modification that would allow this cross-coupling to be removed at will, thereby yielding a purely quadratic coupling for the sphere.
The ranking of MBA programmes by newspapers and magazines is common and usually controversial. This paper discusses the use of the most popular method of making these rankings via a multicriteria model which uses the ...
详细信息
The ranking of MBA programmes by newspapers and magazines is common and usually controversial. This paper discusses the use of the most popular method of making these rankings via a multicriteria model which uses the weighted sum of a number of performance measures to give an overall score on which selection or ranking may be based. The weights are a quantitative model of the preferences of those making the evaluation. Many methods are available to obtain weights from preference statements so that for any set of preferences a number of different weight sets can be found depending on the method used. Cognitive limits lead to inconsistency in preference judgements so that weights may be subject both to uncertainty and to bias. It is proposed that choosing weights to minimize discrimination between alternatives (not weights) guards against unjustified discrimination between alternatives. Applying the method to data collected by the Financial Times shows the effect of varying the level of discrimination between weights and also the effect of using a reduced data set made necessary by the partial publication of information. Journal of the Operational Research Society (2010) 61, 632-639. doi: 10.1057/jors.2008.193 Published online 18 March 2009
When an iterative method is applied to solve the linear equation system in interior point methods (IPMs), the attention is usually placed on accelerating their convergence by designing appropriate preconditioners, but...
详细信息
When an iterative method is applied to solve the linear equation system in interior point methods (IPMs), the attention is usually placed on accelerating their convergence by designing appropriate preconditioners, but the linear solver is applied as a black box with a standard termination criterion which asks for a sufficient reduction of the residual in the linear system. Such an approach often leads to an unnecessary ``oversolving"" of linear equations. In this paper, an IPM that relies on an inner termination criterion not based on the residual of the linear system is introduced and analyzed. Moreover, new indicators for the early termination of the inner iterations are derived from a deep understanding of IPM needs. The new technique has been adapted to the conjugate gradient (CG) and to the minimum residual method (MINRES) applied in the IPM context. The new criterion has been tested on a set of quadratic optimization problems including compressed sensing, image processing, and instances with partial differential equation constraints, and it has been compared to standard residual tests with variable tolerance. Evidence gathered from these computational experiments shows that the new technique delivers significant improvements in terms of inner (linear) iterations and those translate into significant savings of the IPM solution time.
The tendency towards carbon dioxide reduction greatly stimulates the popularity of electric vehicles against conventional vehicles. However, electric vehicle chargers represent a huge electric burden, which affects th...
详细信息
The tendency towards carbon dioxide reduction greatly stimulates the popularity of electric vehicles against conventional vehicles. However, electric vehicle chargers represent a huge electric burden, which affects the performance and stability of the grid. Various optimization methodologies have been proposed in literature to enhance the performance of the distribution grids. However, existing techniques handle the raised issues from individual perspectives and/or with limited scopes. Therefore, this paper aims to develop a distributed controller-based coordination scheme in both medium and low voltage networks to handle the electric vehicles' charging impact on the power grid. The scope of this work covers improving the network voltage profile, reducing the total active and reactive power, reducing the load fluctuations and total charging cost, while taking into consideration the random arrivals/departures of electric vehicles and the vehicle owners' preferred charging time zones with vehicle-to-grid technology. Simulations are carried out to prove the success of the proposed method in improving the performance of IEEE 31-bus 23 kV system with several 415 V residential feeders. Additionally, the proposed method is validated using Controller Hardware-in-the-Loop. The results show that the proposed method can significantly reduce the issues that appear in the electric power grid during charging with minor changes in the existing grid. The results prove the successful implementation of different types of charging, namely, ultra-fast, fast, moderate, normal and vehicle-to-grid charging with minimum charging cost to enhance the owner's satisfaction level.
A framework for constructing robust classification models is proposed in the paper. An assumption about importance of one of the classes in comparison with other classes is incorporated into the models. It often takes...
详细信息
A framework for constructing robust classification models is proposed in the paper. An assumption about importance of one of the classes in comparison with other classes is incorporated into the models. It often takes place in the real application, for example, in reliability, in medical diagnostic, etc. A main idea underlying the models is to consider a set of probability distributions on training examples produced by the imprecise probability models such as linear-vacuous mixture and constant odd-ratio contaminated models. Extreme points of the sets of probability distributions are a main tool for constructing the robust classifiers. It is shown that algorithms for computing optimal classification parameters are reduced to a finite number of weighted support vector machines with weights determined by the extreme points. Experimental results with synthetic and real data illustrate the proposed models.
The recurrent network of Xia et al. was proposed for solving quadratic programming problems and was recently adapted to support vector machine (SVM) learning by Tan et al. We show that this formulation contains some u...
详细信息
The recurrent network of Xia et al. was proposed for solving quadratic programming problems and was recently adapted to support vector machine (SVM) learning by Tan et al. We show that this formulation contains some unnecessary circuit which, furthermore, can fail to provide the correct value of one of the SVM parameters and suggest how to avoid these drawbacks.
In this paper an algorithm is presented for deriving the explicit robust model based optimal control law. The system is represented by linear, discrete-time, time-invariant model with constraints on control and state ...
详细信息
In this paper an algorithm is presented for deriving the explicit robust model based optimal control law. The system is represented by linear, discrete-time, time-invariant model with constraints on control and state variables and a quadratic objective function. Using the fundamentals of flexibility analysis the algorithm proposed in this paper derives the robust optimal control law off-line as a function of the state of the process, thus eliminating the repetitive solution of on-line optimisation problems. Hence, the on-line implementation is reduced to a sequence of simple function evaluations. The key advantageous features of the algorithm are demonstrated via an illustrative example.
We introduce a modification to the standard spherical harmonic closure used with linear kinetic equations of particle transport. While the standard closure is known to produce negative particle concentrations, the mod...
详细信息
We introduce a modification to the standard spherical harmonic closure used with linear kinetic equations of particle transport. While the standard closure is known to produce negative particle concentrations, the modification corrects this defect by requiring that the ansatz used to close the equations itself be a nonnegative function. We impose this requirement via explicit constraints in a quadratic optimization problem.
In this paper we introduce a Sequential Convex programming (SCP) algorithm for the motion generation with the centroidal dynamics of legged robots using a sequential bounds tightening of McCormick envelopes strategy t...
详细信息
In this paper we introduce a Sequential Convex programming (SCP) algorithm for the motion generation with the centroidal dynamics of legged robots using a sequential bounds tightening of McCormick envelopes strategy to cope with the nonconvexity of the problem (related to bilinear terms). Therefore, the proposed SCP algorithm is initialized with relaxed McCormick envelopes and then their bounds are sequentially tightened around the current estimate of the solution enforcing this way convergence to a feasible point. The SCP algorithm solves a quadratic program at each iteration by an interior point method. Additionally, the proposed SCP algorithm is alternated with an inverse kinematics algorithm to achieve the whole body motion generation. Finally, extensive numerical experiments show the effectiveness of the proposed algorithm in generating highly agile motions such as trotting, bounding, stotting and running for humanoid and quadruped robots.(c) 2023 Elsevier B.V. All rights reserved.
暂无评论