Applied Mechanics and Materials Vols. 536-537

Abstract: Train operation regulation is the key technology to ensure the orderly operation of trains, its value has been fully realized under the background of rapid construction and high traffic density in urban rail transit. This paper did a deep analysis on different strategies and methods for urban rail transit train operation regulation and the applications of these strategies and methods in different conditions. Furthermore, an automatic train operation regulation mathematical model was established. Then developed a software system in Visual C++ and used it to analysis and test the model by data of a real metro line, the result showed that both the model and the system were available.

Abstract: This paper proposes a novel and efficient method for channel equalization of MIMO- OFDM system. The method utilizes extreme learning machine (ELM), a class of supervised learning algorithms, to achieve fast training and low bit error rates. The numerical simulation results show that the proposed methods significantly outperform traditional feed-forward neural networks based MIMO-OFDM system equalizers in terms of bit error rate performance.

Abstract: According to the characteristics and existing problem of the stationary and moving traffic flow information collection technology, this paper proposes the traffic information detection’s new ideas and methods based on satellite images, this paper systematically analysis and summarized the traffic flow information collection technology for the vehicle queues, single vehicle targets and moving vehicles at home and abroad based on satellite remote sensing image, and points out the research emphasis in future.

Abstract: Path planning is a key factor in intelligent transportation vehicle navigation system, compared to a variety of advantages and disadvantages of the path planning optimization algorithm. According obstacle distribution characteristics similar characteristics to the grid circuit resistor, proposed a Circuit Map path planning algorithm. The city's roads each segment was mapped to the circuit network, and the resistance of the resistor were mapped to with the Weighted sum of road length and width, and traffic density. This can be achieved by solving the circuit that intelligent transportation systems path planning and navigation services.

Abstract: A BP neural network model was employed to forecast the railway freight turnover. First, this paper analyses the data of railway freight turnover in China from 1998 to 2012, build a three layers BP neural network, then by training and learning, a well-trained network can be used for simulating and forecasting. Finally, predict by the Grey GM(1,1) model and well-trained BP neural network respectively, and compares the errors of two prediction model, the results show that predicting the railway freight turnover by BP neural network has higher precision.

Abstract: In order to guarantee the special vehicle capacity, quality of service protocol in computer network is referred, travel characteristics of special vehicle is analyzed. Put forward the special vehicle operation control scheme based on agent, analyzes the functions of each agent and collaborative way. Finally on the basis of this design the special vehicle priority security algorithm.

Abstract: An improved genetic algorithm for route optimization in DGT is proposed in this paper. In which, method of initial population, cross and mutation are improved to make it more suitable for DGT. It uses a dynamic operator to realize the adaptive adjustment of the parameters. The experimental results show that the improved algorithm overcomes the shortcomings of local optimum and "premature convergence" and improves the search efficiency and adaptability. The proposed algorithm can effectively solve the path optimization problem in DGT in time.

Abstract: The samples marked bottlenecks and imbalanced protocol flows restrict the development of the network traffic classification technology, to solve this problem a semi-supervised machine learning traffic identification method is presented. Employ K-means algorithm to partition a training datasets that consists of a few labeled flows combined with abundant unlabeled flows.Then, identify the unlabeled samples using the labeled samples in the cluster based on k Nearest Neighbor algorithm. The theoretical analysis and experimental results show that the algorithm can improve the recognition rate of minority flows in the case of the imbalanced protocol flows.

Abstract: In this paper, a portable integrated ship monitoring command system is designed to meet the needs of automatic maritime security working, remote monitoring and commanding ship, while adapting the harsh working environment. The propose ship monitoring command system has merits of ease of installation, highly-integrated features, easy-to-use, and so on. Application of Beidou Navigation Satellite System's high precision positioning and SMS(Short Messaging Service) communication technology in integrated ship monitoring command system can well solve the problem of ship navigation and positioning, remote monitoring and commanding. In our system, ECDIS( Electronic Chart Display and Information System) is chosen as the display platform, HF(High frequency), VHF(Very high frequency) and Beidou is chosen as the communicational measure, Beidou and GPS is chosen as the positioning measure. With the help of the above measures, the static and dynamic data of ship, real-time voice and text are transported to realize the function of ship positioning, ship navigation, remote monitoring and commanding.

Abstract: In this paper we formulated and analyzed a eco-epidemiological model with disease in the predator, analysis of the existing conditions of equilibrium point, the sufficient condition of the local asymptotical stability of the equilibrium was studied with the method of latent root, the global asymptotical stability of two of the boundary equilibriums and the local asymptotical stability of the positive equilibrium is proved by using the Lyapunov function.