Weighted principal component extraction with genetic algorithms

Pattern recognition techniques have been widely used in a variety of scientific disciplines including computer vision, artificial intelligence, biology, and so forth. Although many methods present satisfactory performances, they still have several weak points, thus leaving a lot of space for further improvements. In this paper, we propose two performance-driven subspace learning methods by extending the principal component analysis (PCA) and the kernel PCA (KPCA). Both methods adopt a common structure where genetic algorithms are employed to pursue optimal subspaces. Because the proposed feature extractors aim at achieving high classification accuracy, enhanced generalization ability can be expected. Extensive experiments are designed to evaluate the effectiveness of the proposed algorithms in real-world problems including object recognition and a number of machine learning tasks. Comparative studies with other state-of-the-art techniques show that the methods in this paper are capable of enhancing generalization ability for pattern recognition systems.     

具有随机丢包的网络化多自主体系统的一致性

研究具有随机丢包的网络化多自主体系统的均方一致性问题,其中不同自主体间的通信通道具有相同的丢包情况并且均服从马尔可夫(Markov)分布。首先,利用系统变换和迭代方法,得到了系统达到均方一致的一个初等充要条件。然后,利用矩阵理论和图论知识,如果拓扑图含有有向生成树,则可以将系统的均方一致性转化成一个线性Markov跳变系统的均方稳定性,并且可以建立线性矩阵不等式形式的均方可镇定准则。最后,通过相应的仿真实例说明了所得结论的可行性。     

基于强跟踪滤波器训练的前向神经网络及其在系统辨识中的应用研究*

给出基于强跟踪滤波器训练前向神经网络的新方法。由于强制残差序列保持相互正交,强跟踪滤波器相对扩展Kalman滤波的收敛速度更快,同时精度更高。最后通过系统辨识仿真实例验证该方法的有效性。     

非线性滤波在射线图像降噪增强中的应用

射线数字成像是当前射线检测与诊断技术发展的方向，图像降噪增强是提高射线成像检测灵敏度和分辨力的关键。重点探讨以排序滤波为代表的非线性滤波图像降噪增强方法，对射线图像的处理表明，线性滤波在降噪的同时会引起较大的边级模糊，而排序滤波不仅降低噪声且能保持图像细节，提高图像质量效果明显。     

Static output feedback control via PDE boundary and ODE measurements in linear cascaded ODE–beam systems

This paper addresses the problem of feedback control design for a class of linear cascaded ordinary differential equation (ODE)–partial differential equation (PDE) systems via a boundary interconnection, where the ODE system is linear time-invariant and the PDE system is described by an Euler–Bernoulli beam (EBB) equation with variable coefficients. The objective of this paper is to design a static output feedback (SOF) controller via EBB boundary and ODE measurements such that the resulting closed-loop cascaded system is exponentially stable. The Lyapunov’s direct method is employed to derive the stabilization condition for the cascaded ODE–beam system, which is provided in terms of a set of bilinear matrix inequalities (BMIs). Furthermore, in order to compute the gain matrices of SOF controllers, a two-step procedure is presented to solve the BMI feasibility problem via the existing linear matrix inequality (LMI) optimization techniques. Finally, the numerical simulation is given to illustrate the effectiveness of the proposed design method.     

Decentralized observers with consensus filters for distributed discrete-time linear systems

This paper presents a decentralized observer with a consensus filter for the state observation of discrete-time linear distributed systems. Each agent in the distributed system has an observer with a model of the plant that utilizes the set of locally available measurements, which may not make the full plant state detectable. This lack of detectability is overcome by utilizing a consensus filter that blends the state estimate of each agent with its neighbors’ estimates. It is proven that the state estimates of the proposed observer exponentially converge to the actual plant states under arbitrarily changing, but connected, communication and pseudo-connected sensing graph topologies. Except these connectivity properties, full knowledge of the sensing and communication graphs is not needed at the design time. As a byproduct, we obtained a result on the location of eigenvalues, i.e., the spectrum, of the Laplacian for a family of graphs with self-loops.     

Variance analysis of identified linear MISO models having spatially correlated inputs,with application to parallel Hammerstein models

This contribution concerns variance analysis of linear multi-input single-output models when the inputs are temporally white but where different inputs may be correlated. An expression is provided for the variance of a linearly parametrized estimate of the frequency response function from one block, i.e. from one input to the output. In particular, this expression reveals that the variance increases in one block when the number of estimated parameters in another block is increased, but levels off when the number of parameters in the other block reaches the number of parameters in the block in question. It also quantifies exactly how correlation between inputs affects the resulting accuracy and a graphical representation is provided for this purpose. The results are applicable to parallel MISO Hammerstein models when the nonlinearities are known and generalize an existing variance expression for this type of model.     

A unified method for optimal arbitrary pole placement

We consider the classic problem of pole placement by state feedback. We offer an eigenstructure assignment algorithm to obtain a novel parametric form for the pole-placing feedback matrix that can deliver any set of desired closed-loop eigenvalues, with any desired multiplicities. This parametric formula is then exploited to introduce an unconstrained nonlinear optimisation algorithm to obtain a feedback matrix that delivers the desired pole placement with optimal robustness and minimum gain. Lastly we compare the performance of our method against several others from the recent literature.     

Dynamics in input and output coefficients for land use studies: a case study for nitrogen in crop rotations

Increasingly, model-based approaches play a role in the design and development of new land use systems. Simulation modeling may play a role in the generation of land use systems for land units, and optimization modeling (e.g. linear programming – LP) may be used in the upscaling to farm and region. In the quantification of new land use systems for land units, often equilibrium conditions with respect to soil resources are assumed, following a so-called target-oriented approach. This facilitates ex ante computation of inputs and emissions of nutrients and allows their use in static optimization models based on LP. The condition of equilibrium in soil resources is often not met, nor is it the ultimate aim. Hence, the dynamics in new systems are insufficiently dealt with. This paper presents an approach for the design of land use systems (crop rotations) and their quantification in terms of input and output coefficients, using particular yields and dynamics in soil resources as targets. Interactions between N input and output of succeeding crops are explicitly taken into account. A simple N-balance model is used describing major processes affecting soil N-dynamics. For the Koutiala region in Mali five crop rotations are evaluated that differ in target crop yield, crop choice, crop residue management and external N source. Modeled crop rotations aiming at high yields, in combination with incorporation of crop residues and legumes, result in depletion of soil N stock. Only in crop rotations aiming at high yields and with incorporation of crop residues combined with a supply of large quantities of animal manure, soil N depletion can be prevented. Four approaches are presented of how to use the dynamic input–output coefficients of these systems in land use studies using LP: (i) use of average coefficients, (ii) use of discounted coefficients, (iii) use of pessimistic estimates of coefficients in an optimization of the land use allocation followed by a recalculation of the objective values for the optimized land use with optimistic coefficients, and (iv) a combined use of systems characteristics, i.e. cumulative N-inputs of land use systems over the time horizon and the magnitude of the soil N pool at the end of the time horizon, which can be used as filters for land use systems. Though none of the approaches completely captures the dynamics in input–output coefficients, they enable a well-founded consideration of the consequences of dynamics in, for instance, soil N stocks in static optimization approaches for farm and regional studies.     

Use of cascade reduction potential for selective precipitation of Au,Cu, and Pb in hydrochloric acid solution

Optimization of reduction potential for electroseparation was studied for the recovery of gold, copper, and lead from acidic solution. A linear sweep voltammetric method enabled us to determine characteristic reduction potentials for each metal and the kinetics of the metal deposition indicated by current-voltage curves. In order to precipitate the metal species sequentially, reduction potentials were examined for the individual and mixed solutions of Au(III), Cu(II), and Pb(II). The three metals were reasonably well isolated from the mixed solutions such as Cu(II)/ Pb(II) and Au(III)/Cu(II)/Pb(II) in the order of the corresponding reduction potentials, in particular, the mass transfer controlled reduction potentials, obtained from linear sweep voltammetry (LSV) measurement.