In the trend prediction to the state development of the large-scale rotary sets, the most important problem is how to enhance the accuracy of prediction. The combined predicting model based on neural networks can real...
详细信息
ISBN:
(纸本)980656068X
In the trend prediction to the state development of the large-scale rotary sets, the most important problem is how to enhance the accuracy of prediction. The combined predicting model based on neural networks can realize a comprehensive utilization to the effective information offered by several prediction methods and receive an optimum prediction result. But in the traditional combined predicting model, the weight coefficients are calculated complicatedly. And the current combined predicting model based on neural networks lacks enough emphases to the advantages of different prediction methods. Therefore, a new combined predicting model based on variable-weight neural networks is presented in this paper. And the weight coefficients of all methods in the new combined predicting model are also determined. By using the new model, a satisfying predictive effect is received in the application of the large-scale rotary sets.
Reinforcement learning is a powerful method for solving sequential decision making problems. But it is difficult to apply to practical problems such as multi-agent systems with continuous state space problems. In this...
详细信息
Reinforcement learning is a powerful method for solving sequential decision making problems. But it is difficult to apply to practical problems such as multi-agent systems with continuous state space problems. In this paper we present a cooperative strategy learning method to solve the problem. It combines WoLF-PHC algorithms with function approximation of RL techniques. By this method an agent could learn cooperative behavior in the multi-agent environment with continuous state space. Using a subtask of RoboCup soccer,Keepaway, we demonstrate the effective of this learning method and the experiment results show that the algorithm converges.
Luneburg lens has the character of converging the incoming plane wave in the position of the spherical diametrical focus. It can change the width of the beam and increase the gain of the whole antenna system. Generall...
详细信息
ISBN:
(纸本)1424401224
Luneburg lens has the character of converging the incoming plane wave in the position of the spherical diametrical focus. It can change the width of the beam and increase the gain of the whole antenna system. Generally, the Luneburg lens antenna consists of a Luneburg lens and a feed source with certain gain such as wave guide port or horn antenna. Luneburg lens which this paper researches makes up of layered dielectric spherical shells. Normally, the production of this kind of lens is complicated which makes the cost of the antenna very high. Consequently, the concept of single medium spherical lens was proposed. This paper focuses on the research of a kind of simple-structured single medium spherical lens. The radiation characteristics of both lens are simulated and compared, especially their focus characteristic, using the rectangular wave guide in X wave band as the feed source
In this paper, an efficient method based on nonlinear adaptive filtering is proposed to detect the small IR target of low SNR under the complex background. The morphologic filter can be constructed firstly based on th...
A novel high-speed photopolarimeter is presented in this paper, which is composed by the optical system, electronics system and PC. This instrument uses a metallic grating that can produce both reflective diffraction ...
To meet the requirement for precision location of optical feature in the vision coordinates measurement system based on optical features imaging, the Gauss distribution multi-fitting location algorithm based on biline...
In order to achieve micro-wound, intelligence and high efficiency for fracture setting, intelligent setting system for fracture is proposed in accordance with biomechanics and fracture therapy theory. In the comprehen...
Ending effect is produced in the decomposition process of empirical mode decomposition (EMD) based Hilbert-Huang transformation. It leads to distortion near the two end points of the signal processed. Several methods ...
详细信息
Ending effect is produced in the decomposition process of empirical mode decomposition (EMD) based Hilbert-Huang transformation. It leads to distortion near the two end points of the signal processed. Several methods of restraint aimed at ending effect are proposed. Comparison has been made among the global average statistic method, the parallel line extending method, the polynomial curvefitting method, the mirror extending method and the neural networks extending method. As a result of simulation and experiment, it is shown that ending effect can be effectively restrained.
暂无评论