Search

In this paper, a new scheme based on chaotic neural network for stock index prediction is proposed. The data from a Chinese stock market, Shenzhen stock market, are applied as a case study. The chaotic neural network is used to learn the non-linear stochastic and chaotic patterns in the stock system and forecast a new index with former indexes. The validity of the scheme is analyzed theoretically, and the simulation results show that it has a good performance. [ABSTRACT FROM AUTHOR]

In this paper, a new structure for moving targets detection and characteristics extraction in ground clutter is proposed. This structure combines Radial Basis Function (RBF) neural network, Burg algorithm, and notch filter. After dynamical reconstruction, the RBF network is used to predict the ground clutter. Spectral characteristics of the ground clutter are estimated using the Burg algorithm. We apply notch filter to cancel the interference caused by the ground clutter. Moreover, a hardware platform based on FPGA is also realized for this paper to demonstrate this proposed structure and sufficient details of the hardware platform are discussed. The results of simulation and hardware implementation show that the presented structure has a good performance in processing target signals mixed with the ground clutter. [ABSTRACT FROM AUTHOR]

A new hyper-chaos communication system based on cellular neural network (CNN) is proposed in this paper. Hyper-chaos is generated with fifteen-cell CNN, then it's transferred to a digital sequence. The chaotic sequence is better than gold sequence when they are utilized in direct sequence spread spectrum system. Compared with the traditional gold sequence system, there is 3dB improvement in CNN chaotic sequence system when the channel is multi-path channel. Because of the complex dynamic behavior of hyper-chaos, security signal could be transferred through wireless channel. The structure of hardware CNN spread spectrum system is also shown, and the security of CNN communication is analyzed at last. [ABSTRACT FROM AUTHOR]

In this paper, a kind of relation between CNN (cellular neural network) and GIM (Gibbs image model) is noted. Based on this relation, a new approach for CNN's template design is proposed, this approach is valid to many questions that could be processed with GIM, such as segmentation, edge detection and restoration. We also discuss the learning algorithm and hardware annealing jointed with the new approach. Simulations of some examples are shown in order to validate effectiveness of new approach. [ABSTRACT FROM AUTHOR]