Han Chongzhao

Selection of Embedding Dimension and Delay Time in Phase Space Reconstruction

A new algorithm is proposed for computing the embedding dimension and delay time in phase space reconstruction. It makes use of the zero of the nonbias multiple autocorrelation function of the chaotic time series to determine the time delay, which efficiently depresses the computing error caused by tracing arbitrarily the slop variation of average displacement (AD) in AD algorithm. Thereafter, by means of the iterative algorithm of multiple autocorrelation and Γ test, the near-optimum parameters of embedding dimension and delay time are estimated. This algorithm is provided with a sound theoretic basis, and its computing complexity is relatively lower and not strongly dependent on the data length. The simulated experimental results indicate that the relative error of the correlation dimension of standard chaotic time series is decreased from 4.4% when using conventional algorithm to 1.06% when using this algorithm. The accuracy of invariants in phase space reconstruction is greatly improved.

Adaptive control and identification of chaotic systems

A novel adaptive control and identification on-line method is proposed for a class of chaotic system with uncertain parameters. We prove that, using the presented method, a controller and identifier is developed which can remove chaos in nonlinear systems and make the system asymptotically stabilizing to an arbitrarily desired smooth orbit. And at the same time, estimates to uncertain parameters converge to their true values. The advantage of our method over the existing result is that the controller and identifier is directly constructed by analytic formula without knowing unknown bounds about uncertain parameters in advance. A computer simulation example is given to validate the proposed approach.

Global adaptive synchronization of chaotic systems with uncertain parameters

We propose a novel adaptive synchronization method for a class of nonlinear chaotic systems with uncertain parameters. Using the chaos control method, we derive a synchronizer, which can make the states of the driven system globally track the states of the drive system asymptotically. The advantage of our method is that our problem setting is more general than those that already exist and the synchronizer is simply constructed by an analytic formula, without knowledge in advance of the unknown bounds of the uncertain parameters. A computer simulation example is given to validate the proposed approach.

A Self-Stabilizing Neural Algorithm for Total Least Squares Filtering

A neural approach for solving the total least square (TLS) problem is presented in the paper. It is based on a linear neuron with a self-stabilizing neural algorithm, capable of resolving the TLS problem present in the parameter estimation of an adaptive FIR filters for system identification, where noisy errors affect not only the observation vector but also the data matrix. The learning rule is analyzed mathematically and the condition to guarantee the stability of algorithm is educed. The computer simulations are given to illustrate that the neural approach is self-stabilizing and considerably outperforms the existing TLS methods when a larger learning factor is used or the signal-noise-rate is lower.

Tracking of maneuvering target in glint noise environment

This paper presents a tracking algorithm for maneuvering target in the presence of glint noise. In radar target tracking system. because of the random wandering of the target position. the measurement noise is clearly non-Gaussian distribution, called as glinf noise, which have a considerable influence on convenfional linear estimates. In this paper, the glint noise is modeled via the mirfure of Gaussian distribufion and Laplace distribution, and tackled wifh WO model sets. The tracking algorithm for maneuvering target is derived detailedly when the model sets is interacting in the presence of glint noise. The Monte Carlo simulafion results express its better performance in comparison wifh the IMM algorithm.

Adaptive synchronization of Rossler and Chen chaotic systems

A novel adaptive synchronization method is proposed for two identical Rossler and Chen systems with uncertain parameters. Based on Lyapunov stability theory, we derive an adaptive controller without the knowledge of the system parameters, which can make the states of two identical Rossler and Chen systems globally asymptotically synchronized. Especially, when some unknown uncertain parameters are positive, we can make the controller more simple and, besides, the controller is independent of those positive uncertain parameters. All results are proved using a well-known Lyapunov stability theorem. Numerical simulations are given to validate the proposed synchronization approach.

Nonlinear system identification with genetic algorithms

Based on the genetic algorithm and Volterra series model, a new identification method of nonlinear systems is proposed. The method is adapted to the difference magnitude of parametric of model. An adaptation algorithm is developed in order to get a wider search range and achieve more accurate solutions synchronously. With unique mutation and selection, an effective genetic algorithm is achieved for solving the identification of nonlinear systems. The simulation and experimental results indicate that the new method achieved high accuracy, robustness and adaptability.

Inter-Class Distance Based Kernel Parameter Evaluating Method for RBF-SVM

Selecting the optimal parameters of the Support Vector Machines (SVM) is very important in practice. This paper detailedly analyzes the effects given by the Radial Basis Function (RBF) kernel parameter on the feature space, and proposes a novel kernel parameter evaluating method, which is based on the Inter-Class Mean Distance (ICMD). Theoretical and experimental analysis is made on the proposed method. The proposed method makes it possible to select the kernel parameter and the penalty parameter by two stages, which significantly decreases the time cost of the parameters selection. Experiments are made to compare the “two stage” method with the grid search method, results show that the former can select the optimal parameters with greatly shortened time cost.

Fusion for CT image and MR image based on nonsubsampled transformation

The paper propose a new algorithm based on NSCT in fusion for CT image and MR image. The low-frequents subbands and high-frequents subbands are get after NSCT. Gray value weighting is adopted in low-frequency image, and maximum module rule are adopted in high-frequents subbands. Experimental results compare with other method, and a set of quantitative evaluation criteria is given. Experimental results show that anatomical information can be obtained effectively , and both the edge and texture features can be reserved successfully.

Interpolation particle filter for tracking with out-of-sequence measurements

In multisensor tracking system, the center processor receives the out-of-sequence measurements (OOSMs) because of communication time delays. An improved particle filter for filtering out-of-sequence measurements with arbitrary lag was proposed. The interpolation filter is used to generate the proposal distribution for particle filter. The proposal distributions integrate the most current observation, thus greatly improving the filter performance. The detailed implementation steps of OOSM processing scheme based on OOSM-interpolation particle filter (OOSM-IPF) is deduced. The performance estimates of the OOSM-IPF obtained for ground moving target indicator (GMTI) is compared with similar performance estimates obtained from the OOSM extend Kalman filter (OOSM-EKF). Simulation results show that the tracking performance of OOSM-IPF is much improved than other schemes.