Kai Tat Ng

Linear neural network based blind equalization

Abstract This letter considers the problem of blind equalization in digital communications by using linear neural network. Unlike most adaptive blind equalization methods which are based on matrix decomposition or the Hankel property of matrix, we give a stochastic approximate learning algorithm for the neural network according to the property of the correlation matrices of the transmitted symbols. The network outputs provide an estimation of the source symbols, while the weight matrix of network estimates the inverse of the channel matrix. Simulation results demonstrate the performance and validity of the proposed approach for blind equalization.

An adaptive demodulator for the chaotic modulation communication system with RBF neural network

Chaotic modulation is an important spread spectrum (SS) technique amongst chaotic communications. The logistic chaotic signal acts as the modulation signal in this paper. An adaptive demodulator based on the radial basis function (RBF) neural network is proposed. The demodulator makes use of the good approximant capacity of RBF network for a nonlinear dynamical system. Using the proposed adaptive learning algorithm, the source message can be recovered from the received SS signal. The recovering procedure is on line and adaptive. The simulated examples are included to demonstrate the new method. For the purpose of comparison, the extended-Kalman-filter-based (EKF) demodulator was also analysed. The results indicate that the mean square error (MSE) of the recovered source signal by the proposed demodulator Is significantly reduced, especially for the SS signal with a higher signal-to noise ratio (SNR).

Linear prediction based multipath channel identification algorithm

In digital communication systems, the pulse-shaping filter in the transmitter and the anti-aliasing filter in the receiver are often known. In this brief, this a priori knowledge is exploited to simplify the channel identification problem. The multipath identification problem is formulated as a homogeneous linear equation, in which a matrix is formed from the optimal linear predictor. Instead of solving directly the underlying linear equation, the estimate is obtained by finding the minor eigenvector of a matrix. The presented analysis shows that the performance of the proposed approach degrades significantly when the order is over estimated. An effective approach is then proposed to remove the redundant components in the estimated multipath channel vector. The obtained results show that the proposed approach is able to enhance the performance of the linear programming approach significantly when the order is over estimated.

Chaotic network synchronization with application to communications

Chaotic signals are widely exploited for the spread spectrum communication technique. Synchronization of a chaotic communication system between a single point and multiple points is recognized as an essential issue. In this paper, a chaotic network synchronization scheme is proposed to tackle the problem of multi-access synchronization. The proposed synchronization scheme enables the realization of a fast synchronization of multiple chaotic systems. In this paper, the proposed system is validated by application to direct-sequence (DS) spread spectrum communication (SSC) with code division multiple access (CDMA). Promising results were obtained on the applications of speech, characters and image communications. The obtained results indicate that the proposed SSC is effective and reliable even under the situations of a noisy channel, and multi-path interference. Copyright

Improvement of borrowing channel assignment for patterned traffic load by online cellular probabilistic self-organizing map

This paper describes an improvement of borrowing channel assignment (BCA) for patterned traffic load by using the short-term traffic prediction ability of cellular probabilistic self-organizing map (CPSOM). The fast growing cellular mobile systems demand more efficient and faster channel allocation techniques today. In case of patterned traffic load, the traditional BCA methods are not efficient to further enhance the performance because heavy-traffic cells cannot borrow channels from their neighboring cells with light or medium traffic that may have unused nominal channels. The performance can be increased if the short-term traffic load can be predicted. The predicted results can then be used for channel re-assignment. Therefore, the unused nominal channels of the light-or-medium-traffic cells can be transferred to the heavy-traffic cells that need more nominal channels. In this paper, CPSOM is used online for traffic prediction. In this sense, the proposed CPSOM-based BCA method is able to enhance the performance for patterned traffic load compared with the traditional BCA methods. Simulation results corroborate that the proposed method enables the system to work with better performance for patterned traffic load than the traditional BCA methods.

Blind adaptive identification of FIR channel in chaotic communication systems

In this paper we study the problem of blind channel identification in chaotic communications. An adaptive algorithm is proposed, which exploits the boundness property of chaotic signals. Compared with the EKF-based approach, the proposed algorithm achieves a great complexity gain but at the expense of a slight accuracy degradation. However, our approach enjoys the important advantage that it does not require the a priori information such as nonlinearity of chaotic dynamics and the variances of measurement noise and the coefficient model noise. In addition, our approach is applicable to the ARMA system.

ADAPTIVE IDENTIFICATION ALGORITHMS FOR AR SYSTEM DRIVEN BY CHAOTIC SEQUENCE

In this article the identification of AR system driven by chaotic sequences is addressed. This problem emerges in chaotic communication system, in which chaos-modulated signal passes through a channel described as an AR system. Two adaptive algorithms are presented to tackle this problem. Compared with the existing algorithms such as MPSV and MNPE, the proposed algorithms have very low computational complexities and can be used to track the system parameters in a slowly time-variant environment. The obtained simulation results illustrate that the proposed scheme can offer a better estimation accuracy than the conventional typical method in the high SNR case.

Using Cellular Probabilistic Self-Organizing Map in Borrowing Channel Assignment for Patterned Traffic Load

The fast growing cellular mobile systems demand more efficient and faster channel allocation techniques. Borrowing channel assignment (BCA) is a compromising technique between fixed channel allocation (FCA) and dynamic channel allocation (DCA). However, in the case of patterned traffic load, BCA is not efficient to further enhance the performance because some heavy-traffic cells are unable to borrow channels from neighboring cells that do not have unused nominal channels. The performance of the whole system can be raised if the short-term traffic load can be predicted and the nominal channels can be re-assigned for all cells. This paper describes an improved BCA scheme using traffic load prediction. The prediction is obtained by using the short-term forecasting ability of cellular probabilistic self-organizing map (CPSOM). This paper shows that the proposed CPSOM-based BCA method is able to enhance the performance of patterned traffic load compared with the traditional BCA methods. Simulation results corroborate that the proposed method delivers significantly better performance than BCA for patterned traffic load situations, and is virtually as good as BCA in the other situations analyzed.

Shape From Shading by Using Neural Based Colour Reflectance Model

In this Letter, a new methodology for Colour Shape From Shading problem is proposed. The problem of colour SFS refers to the well-known fact that most real objects usually contain mixtures of diffuse and specular colour reflections. In this paper, these limitations are addressed and a new colour neural based model is proposed. The proposed approach focuses on developing a generalized neural based colour reflectance model. Experimental results on synthetic coloured objects and a real coloured object were performed to demonstrate the performance of the proposed methodology.