Sun Yunshan

Variable Step-size CMA Blind Equalization based on Non-linear Function of Error Signal

Variable step-size was introduced in the constant module blind equalization algorithm (CMA). A nonlinear function of remainder error was taken as a step-size control factor to control the change of step-size. This article proposed a kind of new constant module variable step-size blind equalization algorithm, and analyzed the selection principle of parameters. Theory and simulation indicate that, compared with the traditional constant module blind equalization algorithm, new algorithm has the quicker convergence rate and smaller stable remainder error.

Notice of Retraction Application research of vehicle routing problem based on an improved ant colony algorithm

An improved and colony algorithm was proposed. Genetic algorithm was utilized to optimize the parameters of ant colony algorithm. The improved algorithm was used to solve the optimization routing of the basic vehicle routing problem. The algorithm possesses some characteristics such as strong total researching ability. The experimental results show that the improved ant colony algorithm possesses better optimization quantity and effect than the traditional ant colony algorithm.

A QAM Blind Equalization Algorithm based on Fuzzy Neural Network

As a key technology of digital broadcast and TV, blind equalization overcomes inter-symbol interference to improve the effect of receiving signals. A new QAM blind equalization algorithm based on fuzzy neural network classifier is proposed. Channel estimation and fuzzy neural network classifier are combined to carry out equalization. The primary signal is attained by de-convolution. Judgment range of fuzzy neural network is adjusted dynamically by competition study algorithm, and then blind equalization is realized. Simulation shows that the new algorithm improves convergence speed and reduces residual error and BER (Bit Error Ratio).

A Novel Neural Network Blind Multi-user Detection Algorithm

Blind multi-user detection (BMUD) is a key technology in CDMA to improve communication quality. This paper introduced FNN (feed-forward neural network) to BMUD algorithm. It combined FNN with CMA algorithm, constructed a cost function, optimized FNN weights and parameters by LMS and then realized BMUD. Compared with traditional CMA blind multi-user algorithm, simulation results indicate new algorithm improves the performances in bit-error ratio, following ability and soon.

Blind Equalization Algorithm based on Fuzzy Neural Network in QAM System

A new blind equalization algorithm based on fuzzy neural network classifier was proposed. It was applied in the QAM System. Channel estimation and fuzzy neural network classifier are combined to carry out blind equalization. The primary signal was attained by de-convolution. Judgment range of fuzzy neural network was adjusted dynamically by competition study algorithm, and then blind equalization was realized. Simulations illuminate that the new algorithm improves convergence speed and reduces residual error and BER (Bit Error Ratio).

An Adaptive Multi-user Detection Algorithm Based on Forward Neural Network

Neural network has some characteristics like self-study, adaptation, better fault tolerance, which make it widely used in dealing with un-linear dynamic problem. An improved multi-user detection algorithm based on three-layer forward neural network was proposed, the transfer function was adopted, and the iteration equation was deduced. The computer simulations show that the proposed algorithm has faster convergence rate and smaller bit error rate.

Research on ACA Optimization in the Logistics Distribution System

Ant colony algorithm is a new simulation-biological evolution algorithm. ACA Applications in the logistics distribution system were analyzed. During the process of constructing the logistics distribution system, logistics center location was optimized by ACA, which guarantees highly effective logistics supply. Logistics route optimization offers the optimization route of goods transportation. And it is the precondition for obtaining the best economic efficiency. Logistics distribution vehicles optimization dispatch makes vehicles dispatch accord with the largest supply capacity of logistics center, simultaneously satisfies the largest request of the customer service.

Variable Step Size Blind Multi-user Detection Algorithm based on Fuzzy Control

A variable step size blind multi-user detection algorithm based on fuzzy control was proposed. It overcame the shortcoming of slow convergence rate in the fixed step algorithm. Step size of new algorithm could dynamically be adjusted by error and erroneous change, and it improves algorithm performance. The validity of new algorithm has been verified by computer simulation.

Variable step size blind equalization algorithm based on minimum error probability

A variable step size blind equalization algorithm based on minimum error probability (MEP) was proposed. The cost function based on minimum error probability was founded. And the iterative equations of the variable step size blind equalization algorithm were deduced by the steepest gradient. Simulations demonstrate that the novel proposed algorithm possessed faster convergence and smaller steady MSE than MEP algorithm.