Tianshuang Qiu

Automatic Image Segmentation Based on a Simplified Pulse Coupled Neural Network

Recent researches indicate that pulse coupled neural network (PCNN) can be effectively utilized in image segmentation. However, the near optimal parameter set should always be predetermined to achieve desired segmentation result for different images, which impedes its application for segmentation of various images. So far as that is concerned, there is no method of adaptive parameter determination for automatic real-time image segmentation. To solve the problem, this paper brings forward a new automatic segmentation method based on a simplified PCNN with the parameters determined by images’ spatial and grey characteristics adaptively. The proposed algorithm is applied to different images and the experimental results demonstrate its validity.

Performance of RBF neural networks for array processing in impulsive noise environment

This paper addresses the array processing problems (mainly focuses on direction of arrival estimation and beamforming) of mobile communication system using linear antenna arrays in high impulsive noise environment. One possible way to simulate the impulsive noise is to introduce alpha-stable distribution as the noise model. In order to reduce the computational complexity, the problems of DOA and beamforming are approached as a nonlinear mapping which can be modeled using a suitable radial-basis function neural network (RBFNN) trained with input-output pairs. This paper discusses the application of a three-layer RBFNN to perform the DOA estimation and beamforming in presence of impulsive noise. The performance of the network is compared to that of the algorithms based fractional lower-order statistics. Simulations show that the RBFNN is appropriate to approach the DOA estimation and beamforming. At the same time, the RBFNN substantially reduces the computation complexity.

Joint estimation of time difference of arrival and frequency difference of arrival for cyclostationary signals under impulsive noise

The problem of jointly estimating time difference of arrival (TDOA) and frequency difference of arrival (FDOA) or Doppler has a variety of practical applications. The conventional cyclic ambiguity function and the fractional lower-order ambiguity function suffer performance degradation in the presence of non-Gaussian α-stable impulsive noise and corruptive interference. To overcome these drawbacks, a new robust signal-selective algorithm for cyclostationary signals based on the fractional lower-order cyclostationarity is proposed. The new method makes use of cyclostationarity features and fractional lower-order statistics, and is highly tolerant to interference and robust to both Gaussian noise and non-Gaussian α-stable impulsive noise. The robustness and effectiveness of the proposed method in the presence of impulsive noise and interference are demonstrated by comparing it with the cyclostationarity-based and fractional lower-order statistics (FLOS)-based methods.

Nonlinear regression A*OMP for compressive sensing signal reconstruction

Abstract A number of tree search based methods have recently been utilized for compressive sensing signal reconstruction. Among these methods, a heuristic algorithm named A* orthogonal matching pursuit (A*OMP) follows best-first search principle and employs dynamic cost model which makes sparse reconstruction exceptionally excellent. Since the algorithm performance of A*OMP relies heavily on preset parameters in the cost model and the estimation of these preset parameters requires a large number of experiments, there is room for improvement in A*OMP. In this paper, an improved algorithm referred to as Nonlinear Regression A*OMP (NR-A*OMP) is proposed which is built on the residue trend to avoid the estimation procedure. This method is inspired by the fact that the residue is correlated closely to the measurement matrix. The residue trend reflects the characteristics of nonlinear regression with the increasing of sparsity K. In addition, restricted isometry property (RIP) based general conditions are introduced to ensure the effectiveness and practicality of the algorithm. Numerical simulations demonstrate the superiority of NR-A*OMP in both reconstruction rate and normalized mean squared error. Results indicate that the performance of NR-A*OMP can become nearly equal to or even better than that of A*OMP with perfect preset parameters.

A New Blind Source Separation Method Based on Fractional Lower Order Statistics and Neural Network

Lower order alpha stable distribution processes can model the impulsive random signals and noises well in physical observation. Conventional blind source separation is based on second order statistics (SOS). In this paper, we propose neural network structures related to multilayer feedforward networks for performing blind source separation based on the fractional lower order statistics (FLOS). The simulation results and analysis show that the proposed networks and algorithms are robust.

Neural Congestion Control Algorithm in ATM Networks with Multiple Node

In ATM networks, congestion control is a distributed algorithm to share network resources among competing users.It is important in situation where the availability of resources and the set of competing users vary over time unpredictably, round trip delay is uncertain and constraints on queue, rate and bandwidth are saturated, which results in wasted bandwidth and performance degradation. A neural congestion control algorithm is proposed by real-time scheduling between the self-tuning neural controller and the modified EFCI algorithm, which makes the closed-loop systems more stable and robust with respect to uncertainties and more fairness in resources allocation. Simulation results demonstrated the effectiveness of the proposed controller.

Robust direction of arrival (DOA) estimation using RBF neural network in impulsive noise environment

The DOA problem in impulsive noise environment is approached as a mapping which can be modeled using a radial-basis function neural network (RBFNN). To improve the robustness, the input pairs are preprocessed by Fractional Low-Order Statistics (FLOS) technique. The performance of this network is compared to that of the FLOM-MUSIC for both uncorrelated and correlated source. Numerical results show the good performance of the RBFNN-based DOA estimation.

A neural network blind separation method based on special frequency bins

It is a usual approach to separate the convolutive mixtures blindly in frequency domain. Many blind separation algorithms proposed for instantaneous mixtures were employed to separate signals in each frequency bin. These approaches must consider all frequencies, and correct the permutation/ amplitude of output signals, resulting in a huge computation. In this paper we propose a neural network blind separation approach with a few special frequency bins, which have line spectra or some foreknowing characteristics. The approach can separate convolutive signals effectively with a reduced computation, suitable for the application on real time. The validity and performance of the proposed approach is demonstrated by computer simulation with speech and ship radiating underwater acoustic signals. The comparison between the proposed method and all frequency bins algorithms is performed on their calculation complexity and separation effect.

A TVAR Parametric Model Applying for Detecting Anti-electric-Corona Discharge

It is well known that the time-varying parametric model based on wavelet neural network has excellent performance on modeling a signal. The spark discharge signal is a typical nonstationary one. The spark discharge has two types in a static dust catcher. one is normal discharge, another is anti-electric-corona discharge. A few simulations indicate that the performance of the TVAR model on modeling a discharge signal is fineness, especially, on distinguishing between normal discharge and anti-electric-corona discharge.

A Method for Fast Estimation of Evoked Potentials Based on Independent Component Analysis

Independent component analysis (ICA) is a new powerful tool for blind source separation. This paper proposes a new algorithm that combines two existent algorithms, the improved infomax algorithm and the fastICA algorithm. Utilizing the initial weights obtained by the improved infomax algorithm, we can not only reduce the length of data which fastICA algorithm needs, but also enhance the convergence stability of fastICA algorithm. The effectiveness of the algorithm is verified by computer simulations.