作者：
Jan BeranDepartment Of Control
Measurement and Instrumentation Faculty Of Electrical Engineering and Communication Brno University Of Technology
Industrial communication is experiencing pennanent penetration of IT solutions into industrial automation. However IT technologies are efficient in the office floor, they miss significant amount of features and parame...
详细信息
Industrial communication is experiencing pennanent penetration of IT solutions into industrial automation. However IT technologies are efficient in the office floor, they miss significant amount of features and parameters for being suitable for direct implementation into industry. This article introduces and emerging project Virtual Automation Network (VAN) whose main objective is to eliminate these shortages and develop a transparent scalable industrial communication solution targeted to embedded devices
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.
Based on the study of patterns used in many fast algorithms for the block-matching motion estimation (BMME), a new search pattern, SSP (Simplified Square Pattern), is introduced in this paper. In most cases, SSP has t...
详细信息
Based on the study of patterns used in many fast algorithms for the block-matching motion estimation (BMME), a new search pattern, SSP (Simplified Square Pattern), is introduced in this paper. In most cases, SSP has the same performance as SP (Square Pattern). By combing SSP with SDSP (Small Diamond Search Pattern), a fast BMA (BMME Algorithm), DSS (Diamond-Square Search), is also proposed in this paper. In order to avoid the MBD (Minimum Block Distortion) point being trapped into the local minimum area, DSS adopts SSP or SP adaptively according to the distance between the MBD and SMBD point. Experimental results show that DSS reduces the computational complexity of the BMME remarkably while incurring little, if any, loss in quality.
The recent explosive growth of multimedia information in many applications requires advanced techniques for multimedia information retrieval (MIR). Audio is one of Important media in multimedia and contains abundant i...
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...
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...
暂无评论