Application of local polynomial estimation in suppressing strong chaotic noise

In this paper, we propose a new method that combines chaotic series phase space reconstruction and local polynomial estimation to solve the problem of suppressing strong chaotic noise. First, chaotic noise time series are reconstructed to obtain multivariate time series according to Takens delay embedding theorem. Then the chaotic noise is estimated accurately using local polynomial estimation method. After chaotic noise is separated from observation signal, we can get the estimation of the useful signal. This local polynomial estimation method can combine the advantages of local and global law. Finally, it makes the estimation more exactly and we can calculate the formula of mean square error theoretically. The simulation results show that the method is effective for the suppression of strong chaotic noise when the signal to interference ratio is low.

Least mean square error difference minimum criterion for adaptive chaotic noise canceller

The least mean square error difference （LMS-ED） minimum criterion for an adaptive chaotic noise canceller is proposed in this paper. Different from traditional least mean square error minimum criterion in which the error is uncorrelated with the input vector, the proposed LMS-ED minimum criterion tries to minimize the correlation between the error difference and input vector difference. The novel adaptive LMS-ED algorithm is then derived to update the weights of adaptive noise canceller. A comparison between cancelling performances of adaptive least mean square （LMS）, normalized LMS （NLMS） and proposed LMS-ED algorithms is simulated by using three kinds of chaotic noises. The simulation results clearly show that the proposed algorithm outperforms the LMS and NLMS algorithms in achieving small values of steady-state excess mean square error. Moreover, the computational complexity of the proposed LMS-ED algorithm is the same as that of the standard LMS algorithms.

CHAOTIC ANNEALING NEURAL NETWORK FOR GLOBAL OPTIMIZATION OF CONSTRAINED NONLINEAR PROGRAMMING

Chaotic neural networks have global searching ability.But their applications are generally confined to combinatorial optimization to date.By introducing chaotic noise annealing process into conventional Hopfield network,this paper proposes a new chaotic annealing neural network (CANN) for global optimization of continuous constrained non linear programming.It is easy to implement,conceptually simple,and generally applicable.Numerical experiments on severe test functions manifest that CANN is efficient and reliable to search for global optimum and outperforms the existing genetic algorithm GAMAS for the same purpose.

A new procedure for exploring chaotic attractors in nonlinear dynamical systems under random excitations

Due to uncertain push-pull action across boundaries between different attractive domains by random excitations, attractors of a dynamical system will drift in the phase space, which readily leads to colliding and mixing with each other, so it is very difficult to identify irregular signals evolving from arbitrary initial states. Here, periodic attractors from the simple cell mapping method are further iterated by a specific Poincare map in order to observe more elaborate structures and drifts as well as possible dynamical bifurcations. The panorama of a chaotic attractor can also be displayed to a great extent by this newly developed procedure. From the positions and the variations of attractors in the phase space, the action mechanism of bounded noise excitation is studied in detail. Several numerical examples are employed to illustrate the present procedure. It is seen that the dynamical identification and the bifurcation analysis can be effectively performed by this procedure.