Search

Abstract: In this paper, a one-layer recurrent projection neural network is proposed for solving pseudoconvex optimization problems with general convex constraints. The proposed network in this paper deals with the constraints into two parts, which brings the network simpler structure and better properties. By the Tikhonov-like regularization method, the proposed network need not estimate the exact penalty parameter in advance. Moreover, comparing with some existing neural networks, the proposed network can solve more general constrained pseudoconvex optimization problems. When the solution of the proposed network is bounded, it converges to the optimal solution set of considered optimization problem, which may be nonsmooth and nonconvex. Meantime, some sufficient conditions are presented to guarantee the boundedness of the solution of the proposed network. Numerical examples with simulation results are given to illustrate the effectiveness and good characteristics of the proposed network for solving constrained pseudoconvex optimization. [Copyright &y& Elsevier]

Abstract: In this paper, we focus on the stability problem for a class of stochastic delayed recurrent neural networks. Different from the traditional stability criteria, we introduce and study a new stability criterion: the mean-square exponential input-to-state stability. To the best of our knowledge, this new stability criterion has never been discussed in the field of stochastic recurrent neural networks. The main objective of the paper is to fill the gap. With the help of the Lyapunov–Krasovskii functional, stochastic analysis theory and Itô's formula, we prove that the addressed system is mean-square exponentially input-to-state stable. Moreover, two numerical examples and their simulations are presented to verify the theoretical results well. [Copyright &y& Elsevier]

In this paper, a class of impulsive inertial neural networks with time-varying delays is considered. By choosing proper variable transformation, the original inertial neural networks can be rewritten as first-order differential equations. Based on Lyapunov functions method and inequality techniques, some sufficient conditions are derived to guarantee global exponential convergence of the discussed inertial neural networks with impulsive effects. Meanwhile, the framework of the exponential convergence ball in the state space with a pre-specified convergence rate is also given. Here, the existence and uniqueness of the equilibrium points need not to be considered. Finally, some numerical examples with simulation are presented to show the effectiveness of the obtained results. [ABSTRACT FROM AUTHOR]

Most existing dimensionality reduction algorithms have two disadvantages: their computational cost is high and they cannot estimate the intrinsic dimension of the original dataset by themselves. To deal with these problems, in this paper we propose a fast linear dimensionality reduction method named Orthogonal Component Analysis (OCA). While avoiding solving eigenproblem and matrix inverse problem, OCA successfully achieves high-speed orthogonal component extraction. By proposing an adaptive threshold scheme, OCA is able to estimate the dimension of the feature space automatically. Meanwhile, the algorithm is guaranteed to be numerical stable. In the experiments, OCA is compared with several typical dimensionality reduction algorithms. The experimental results demonstrate that as a universal algorithm, OCA is efficient and effective. [ABSTRACT FROM AUTHOR]

This paper studies a class of complex-valued neural networks with time-varying delays. By using the conjugate system of the complex-valued neural networks and Brouwer׳s fixed point theorem, sufficient conditions to guarantee the existence and uniqueness of an equilibrium are obtained. Some criteria on globally exponential stability of the equilibrium of the complex-valued neural networks are also established by using a delay differential inequality. These results are easy to apply to the study of the complex-valued neural networks whether their activation functions are explicitly expressed by separating their real and imaginary parts or not. Two examples with numerical simulations are given to highlight the effectiveness of the obtained results. [ABSTRACT FROM AUTHOR]

In this paper, the distributed node-to-node consensus problem is addressed for a class of linear multi-agent systems with time-varying pinning links by using relative state feedback. The coordination goal in the present work is to make the states of each follower track those of its corresponding leader asymptotically where only a small fraction of followers can sense the states of their corresponding leaders through some switched communication channels. By using tools from M -matrix theory and stability analysis of switched systems theory, it is theoretically shown that such a node-to-node consensus in the closed-loop multi-agent systems can be guaranteed if each follower can be directly or indirectly influenced by at least one leader over some uniformly bounded time intervals, with the inner coupling matrix as well as the coupling strength being appropriately designed. Distributed node-to-node consensus for multi-agent systems with general Lipschitz-type nonlinear dynamics is also investigated. Numerical simulations are finally performed to verify the effectiveness of the theoretical results. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we focus on investigating group consensus of dynamical multi-agent networks via pinning scheme. The topology of the network is a general digraph, which needs neither being symmetric nor containing a spanning directed tree, and some criteria are proposed to guarantee the realization of group consensus instead of relying on other conservative assumptions presented by majority of the relevant research works, such as in-degree balance. In addition, it is interesting to find that the nodes with zero in-degree should be pinned first based on the property of M-matrix. Furthermore, an adaptive pinning control approach is developed to obtain the appropriate control gains. Finally, the effectiveness and correctness of our theoretical findings are verified by some numerical simulations. [Copyright &y& Elsevier]

Abstract: The paper analyzes wave-type partial differential equations that describe the transmission of neural signals and proposes filtering for estimating the spatiotemporal variations of voltage in the neurons' membrane. It is shown that in specific neuron models the spatiotemporal variations of the membrane's voltage follow partial differential equations (PDEs) of the wave type while in other models such variations are associated with the propagation of solitary waves in the membrane. To compute the dynamics of the membrane PDE model without knowledge of initial conditions and through the processing of noisy measurements, a new filtering method, under the name Derivative-free nonlinear Kalman Filtering, is proposed. The PDE of the membrane is decomposed into a set of nonlinear ordinary differential equations with respect to time. Next, each one of the local models associated with the ordinary differential equations is transformed into a model of the linear canonical (Brunovsky) form through a change of coordinates (diffeomorphism) which is based on differential flatness theory. This transformation provides an extended model of the nonlinear dynamics of the membrane for which state estimation is possible by applying the standard Kalman Filter recursion. The proposed filtering method is tested through numerical simulation tests. [Copyright &y& Elsevier]

Abstract: In this paper, the problem of Hopf bifurcation control for a complex network model with time delays is considered by using a new hybrid control strategy, in which state feedback and parameter perturbation are used. To control the Hopf bifurcation, a hybrid control strategy is proposed and the onset of an inherent bifurcation is delayed (advanced) when such a bifurcation is undesired (desired). Furthermore, the dynamic behaviors of the controlled system can also be changed by choosing appropriate control parameters. Numerical simulation results confirm that the new control strategy is efficient in controlling Hopf bifurcation. [Copyright &y& Elsevier]

Abstract: This paper investigates the problem of designing H ∞ filter for gene regulatory networks (GRNs) with time-varying delays and Markovian jumping parameters. Since in real gene networks the current jump mode is not easily accessible, the filter parameters are considered to be independent from the current system mode. By using mode-dependent Lyapunov–Krasovski functionals, appropriate conditions for the stochastic stability and disturbance attenuation of mixed GRN/filter system is derived. Mode independent filter gains are then obtained from some sufficient conditions in the form of linear matrix inequalities which are easy to solve by numerical methods. In the end, a numerical example and the relevant simulations are presented to evaluate the results. [Copyright &y& Elsevier]

Abstract: Feature statistics normalization in the cepstral domain is one of the most performing approaches for robust automaticspeech and speaker recognition in noisy acoustic scenarios: feature coefficients are normalized by using suitable linear or nonlinear transformations in order to match the noisy speech statistics to the clean speech one. Histogram equalization (HEQ) belongs to such a category of algorithms and has proved to be effective on purpose and therefore taken here as reference. In this paper the presence of multi-channel acoustic channels is used to enhance the statistics modeling capabilities of the HEQ algorithm, by exploiting the availability of multiple noisy speech occurrences, with the aim of maximizing the effectiveness of the cepstra normalization process. Computer simulations based on the Aurora 2 database in speech and speaker recognition scenarios have shown that a significant recognition improvement with respect to the single-channel counterpart and other multi-channel techniques can be achieved confirming the effectiveness of the idea. The proposed algorithmic configuration has also been combined with the kernel estimation technique in order to further improve the speech recognition performances. [Copyright &y& Elsevier]

Abstract: Several interesting problems in neuroscience are of multiscale type, i.e. possess different temporal and spatial scales that cannot be disregarded. Such characteristics impose severe burden to numerical simulations since the need to resolve small scale features pushes the computational costs to unreasonable levels. Classical numerical methods that do not resolve the small scales suffer from spurious oscillations and lack of precision. This paper presents an innovative numerical method of multiscale type that ameliorates these maladies. As an example we consider the case of a cable equation modeling heterogeneous dendrites. Our method is not only easy to parallelize, but it is also nodally exact, i.e., it matches the values of the exact solution at every node of the discretization mesh, for a class of problems. To show the validity of our scheme under different physiological regimes, we describe how the model behaves whenever the dendrites are thin or long, or the longitudinal conductance is small. We also consider the case of a large number of synapses and of large or low membrane conductance. [Copyright &y& Elsevier]

Abstract: The target of no-reference (NR) image quality assessment (IQA) is to establish a computational model to predict the visual quality of an image. The existing prominent method is based on natural scene statistics (NSS). It uses the joint and marginal distributions of wavelet coefficients for IQA. However, this method is only applicable to JPEG2000 compressed images. Since the wavelet transform fails to capture the directional information of images, an improved NSS model is established by contourlets. In this paper, the contourlet transform is utilized to NSS of images, and then the relationship of contourlet coefficients is represented by the joint distribution. The statistics of contourlet coefficients are applicable to indicate variation of image quality. In addition, an image-dependent threshold is adopted to reduce the effect of content to the statistical model. Finally, image quality can be evaluated by combining the extracted features in each subband nonlinearly. Our algorithm is trained and tested on the LIVE database II. Experimental results demonstrate that the proposed algorithm is superior to the conventional NSS model and can be applied to different distortions. [Copyright &y& Elsevier]

Abstract: The paper presents a new sufficient condition for the existence, uniqueness and global robust exponential stability of the equilibrium point for interval neural networks with time-varying delays. Theoretical analysis indicates that the obtained result improves and generalizes some previous results derived in the literatures. It is also shown by a numerical example that a recently reported result is invalid because the proof of it is not always right. Finally, a numerical example and the corresponding simulation are given to show the effectiveness of the obtained result. [Copyright &y& Elsevier]

Abstract: In the problem of one-class classification one of the classes, called the target class, has to be distinguished from all other possible objects. These are considered as non-targets. The need for solving such a task arises in many practical applications, e.g. in machine fault detection, face recognition, authorship verification, fraud recognition or person identification based on biometric data. This paper proposes a new one-class classifier, the minimum spanning tree class descriptor (MST_CD). This classifier builds on the structure of the minimum spanning tree constructed on the target training set only. The classification of test objects relies on their distances to the closest edge of that tree, hence the proposed method is an example of a distance-based one-class classifier. Our experiments show that the MST_CD performs especially well in case of small sample size problems and in high-dimensional spaces. [Copyright &y& Elsevier]