New LMT-based delay-dependent criterion for global asymptotic stability of cellular neural networks

The problem of global asymptotic stability analysis is studied for a class of cellular neural networks with time-varying delay. By defining a Lyapunov–Krasovskii functional, a new delay-dependent stability condition is derived in terms of linear matrix inequalities. The obtained criterion is less conservative than some previous literature because free-weighting matrix method and the Jensen integral inequality are considered. Three illustrative examples are given to demonstrate the effectiveness of the proposed results.     

Robust synchronization in an array of fuzzy delayed cellular neural networks with stochastically hybrid coupling

In this paper, the robust synchronization control problem of an array of fuzzy cellular neural networks with uncertain stochastically coupling is investigated, which involves constant coupling, discrete time-varying delay coupling and distributed time-varying delay coupling. By using adaptive feedback control scheme and exploiting some stochastic analysis techniques, several sufficient conditions are developed to ensure the synchronization of stochastically hybrid coupled fuzzy neural networks with all admissible uncertainties in mean square. Finally, a numerical example illustrated by scale-free complex networks is provided to show the effectiveness and the applicability of the proposed method.     

Nonlinear system identification using optimized dynamic neural network

In this paper, both off-line architecture optimization and on-line adaptation have been developed for a dynamic neural network (DNN) in nonlinear system identification. In the off-line architecture optimization, a new effective encoding scheme—Direct Matrix Mapping Encoding (DMME) method is proposed to represent the structure of neural network by establishing connection matrices. A series of GA operations are applied to the connection matrices to find the optimal number of neurons on each hidden layer and interconnection between two neighboring layers of DNN. The hybrid training is adopted to evolve the architecture, and to tune the weights and input delays of DNN by combining GA with the modified adaptation laws. The modified adaptation laws are subsequently used to tune the input time delays, weights and linear parameters in the optimized DNN-based model in on-line nonlinear system identification. The effectiveness of the architecture optimization and adaptation is extensively tested by means of two nonlinear system identification examples.     

Synchronization analysis of coupled connected neural networks with mixed time delays

In this paper, the global exponential synchronization of coupled connected neural networks with both discrete and distributed delays is investigated under mild condition, assuming neither the differentiability and strict monotonicity for the activation functions nor the diagonal for the inner coupling matrices. By employing a new Lyapunov–Krasovskii functional, applying the theory of Kronecker product of matrices and the linear matrix inequality (LMI) technique, several delay-dependent sufficient conditions in LMI form are obtained for global exponential synchronization of such systems. Moreover, the decay rate is estimated. The proposed LMI approach has the advantage of considering the difference of neuronal excitatory and inhibitory efforts, which is also computationally efficient as it can be solved numerically using efficient Matlab LMI toolbox, and no tuning of parameters is required. In addition, the proposed results generalize and improve the earlier publications. An example with simulation is given to show the effectiveness of the obtained results.     

Properties of variations in the periods of ring neural oscillators with noise

Effects of additive noise on a series of the periods of oscillations in unidirectionally coupled ring neural networks of ring oscillator type are studied. Kinematical models of the traveling waves of an inconsistency, i.e. the successive same signs in the states of adjacent neurons in the network, are derived. A series of the half periods in the network of N neuron is then expressed by the sum of N sequences of the N-first order autoregressive process, the process with the spectrum of exponential type and the first-order autoregressive process. Noise and the interaction of the inconsistency cause characteristic positive correlations in a series of the half periods of the oscillations. Further, an experiment on an analog circuit of the ring neural oscillator was done and it is shown that correlations in the obtained periods of the oscillations agree with the derived three expressions.     

Convergence of non-autonomous discrete-time Hopfield model with delays

This paper is concerned with boundedness, convergence of solution of a class of non-autonomous discrete-time delayed Hopfield neural network model. Using the inequality technique, we obtain some sufficient conditions ensuring the boundedness of solutions of the discrete-time delayed Hopfield models in time-varying situation. Then, by exploring intrinsic features between non-autonomous system and its asymptotic equations, several novel sufficient conditions are established to ensure that all solutions of the networks converge to the solution of its asymptotic equations. Especially, for case of asymptotic autonomous system or asymptotic periodic system, we obtain some sufficient conditions ensuring all solutions of original system convergent to equilibrium or periodic solution of asymptotic system, respectively. An example is provided for demonstrating the effectiveness of the global stability conditions presented. Our results are not only presented in terms of system parameters and can be easily verified but also are less restrictive than previously known criteria.     

Computational intelligence tools for next generation quality of service management

In this paper we explore the interest of computational intelligence tools in the management of heterogeneous communication networks, specifically to predict congestion, failures and other anomalies in the network that may eventually lead to degradation of the quality of offered services. We show two different applications based on neural and neuro-fuzzy systems for quality of service (QoS) management in next generation networks for voice and video service over heterogeneous Internet protocol (V2oIP) services. The two examples explained in this paper attempt to predict the communication network resources for new incoming calls, and visualizing the QoS of a communication network by means of self-organizing maps.     

Global asymptotic stability of delayed neural networks with discontinuous neuron activations

This paper investigates a class of delayed neural networks whose neuron activations are modeled by discontinuous functions. By utilizing the Leray–Schauder fixed point theorem of multivalued version, the properties of M-matrix and generalized Lyapunov approach, we present some sufficient conditions to ensure the existence and global asymptotic stability of the state equilibrium point. Furthermore, the global convergence of the output solutions are also discussed. The assumptive conditions imposed on activation functions are allowed to be unbounded and nonmonotonic, which are less restrictive than previews works on the discontinuous or continuous neural networks. Hence, we improve and extend some existing results of other researchers. Finally, one numerical example is given to illustrate the effectiveness of the criteria proposed in this paper.     

Application of the OBD method for optimization of neural state variable estimators of the two-mass drive system

This paper presents neural estimators of the mechanical state variables of the electrical drive system with elastic joints. The non-measurable state variables, as the torsional torque and the load machine speed are estimated using multilayer feed-forward neural networks. The main stages of the design methodology of these neural estimators are presented. The optimal brain damage method is implemented for the structure optimization of each neural network. Then signals estimated by neural estimators are tested in the electrical drive control structure with additional feedbacks from the estimated shaft torque and the difference between the motor and the load speeds. The simulation results show good accuracy of both presented neural estimators for the wide range of changes of the reference speed and the load torque. The simulation results are then verified by laboratory experiments.