Advanced Materials Research Vols. 671-674

Abstract: In this paper, genetic neural network is applied to forecast the short-term traffic flow and traffic guidance. Because of the factors of time correlation and spatial correlation, we construct the short-term traffic flow forecasting model using back-propagation neural network that has the function of arbitrary nonlinear function approximation. In order to find proper initial values of the neural network weights and threshold quickly, a combination of neural network prediction method is presented. This method utilizes genetic algorithm to choose the initial weights and threshold, and uses L-M algorithm to train sample, which can enhance the global convergence rate. Trained network is used for short-term traffic flow prediction with mean square error as the forecast performance evaluation. The results show that the performance of genetic neural network is better than a separate BP neural network for short-term traffic flow prediction.

Abstract: A partitioned approach to real time lane detection is proposed based on the ARM core microprocessor S3C6410. With the help of the dedicated camera interface in S3C6410, the original image can be converted to RGB format and got window-cut in hardware, leaving the target region of interest (ROI). The pixels in ROI are partitioned into two parts to deal with some hostile weather conditions when lane markings in far field are hard to be distinguished from the homogenous road surface. Hough transform is applied into the top part to utilize lane continuum, and the pixel in bottom part is detected in some fixed search bars to reduce computation complexity. Experiments show that the detection algorithm possesses real time performanceand good robustness at different weather conditions.

Abstract: In order to measure the urban traffic occupying natural resources and energy and influencing to the ecological environment, the paper, for the first time, has applied the ecological footprint (EF) theory to the transportation and founded a perfect model of traffic EF. Taking Wuhan city for example, the paper has also calculated the EF and ecological efficiency (EE) of passenger traffic system, and then found out the vehicle with optimal EE. By making comparison with the EE and ecological pressure (EP) of passenger traffic in Xi’an, Beijing and Shenyang, it was found that the EE of passenger traffic in Wuhan was much lower, and it was encountering great EP. Therefore, it was significant to optimize the structure of passenger traffic and enhance the proportion of green transportation.

Abstract: To make commodity play its spatial function and achieve the optimal allocation of resources effectively, it analyzes the influence factors of co spatial value added for commodity to transport. It begins with the relationship between different region's disposable income, economic level and commodity prices to search for computation spatial value added for commodity to transport. Then it analyzes calculation method of spatial value added for commodity to transport and establishing the space added value-price model to reflect commodity space added value. Last it raises commodity space value-added effective method. It gives full use of goods value and promotes commodity reasonable space layout.

Abstract: The convenience and comfort of public transportation system become more and more insufficient because of its backward management and less technicalization and standardization. According to the gradual introduce of BRT in China, the paper takes the example of RenShouShan-west station BRT in Lanzhou in order to get the operation effect in the traffic jam release as the BRT in operation. According to the uncertainty and fuzziness of residents travel way selection, Dynamic Bayesian Networks (DBN) is used to evaluate the operation effect based on its operation characters and the present situation. The aim of which is to discuss the status and role of BRT in the whole city traffic system.

Abstract: Collisions involving trucks have long been a major safety concern for the collision severity. This paper describes the rationale and construction of a hierarchical model that can be used to assess severity of truck collisions in a freeway network. The outcome of models and associated data analysis revealed that presence of ramp and freeway segment length were important factors affecting truck safety performance. Furthermore, weather condition was found to be a significant factor in the severity of truck collisions. Using these models, practitioners can identify freeway sites where truck crashes are more likely to occur and then take measure to mitigate the severity.

Abstract: Visual cognition system is an important research content of intelligent vehicle control system. This paper researched traffic lights recognition, lane line identification and traffic sign recognition which consist of vehicle intelligent multi-visual cognition system. The intelligent vehicle navigation system based on multi-visual cognition information fusion was also built and some algorithms had been tested on the real unmanned vehicle which led a good result.

Abstract: To remit the increasingly serious traffic problems in recent years, planning plaza reasonably and keeping coordination with integrated transport hub is imperative. Firstly, this paper puts stations’ optional methods forward. Secondly, it provides the latest evaluation index and reduces some redundant indexes by applying rough set theories, which improves the efficiency of scheme selection. Again, make dynamic index into static by the dynamic multiple valued background principle, and by introducing decision makers’ index sensitive function to correct index weight, it makes the multi-attribute decision making process reflect the dynamic changes of the decision makers’ preference indexes, and make up for the existing traffic plaza operation the shortage of the evaluation system. Finally, it establishes a model by the application of extension theory for solving the optimal scheme, which provides a new way of thinking and methods for our traffic station layout plan.

Abstract: For the city’s road conditions, a nonlinear regression prediction model based on BP Neural Network was built. The simulation shows it has good adaptability and strong nonlinear mapping ability. Using the wavelet basis function as hidden layer nodes transfer function, a BP-Neural- Network-topology-based Wavelet Neural Network model was proposed. The model can overcome the defects of the BP Neural Network model that easy to fall into local minimum and cannot perform global search. The feasibility of the model was proved using measured data from yingbin avenue in jiangmen city.

Abstract: Air traffic is increasing worldwide at a steady annual rate, and airport congestion is already a major issue for air traffic controllers. The traditional method of traffic flow prediction is difficult to adapt to complex air traffic conditions. Due to its self-learning, self-organizing, self-adaptive and anti-jamming capability, the neural network can predict more effectively the air traffic flow than the traditional methods can. A good method for training is an important problem in the prediction of air traffic flow with neural network. This paper will try to find a new model to solve the traffic flow prediction problem by back propagation neural network.