A deep learning-based binocular perception system

An obstacle perception system for intelligent vehicle is proposed.The proposed system combines the stereo version technique and the deep learning network model,and is applied to obstacle perception tasks in complex environment.In this paper,we provide a complete system design project,which includes the hardware parameters,software framework,algorithm principle,and optimization method.In addition,special experiments are designed to demonstrate that the performance of the proposed system meets the requirements of actual application.The experiment results show that the proposed system is valid to both standard obstacles and non-standard obstacles,and suitable for different weather and lighting conditions in complex environment.It announces that the proposed system is flexible and robust to the intelligent vehicle.     

PREDICTIVE STUDY ON THE ECONOMIC VALUE OF RADIO SPECTRUM IN CHINA

Increasing popularity of spectrum-based services brings the striking contradictions between the limited spectrum resource and its increasing demands.This paper puts forward an approach to forecast the future spectrum demand and its economic value,so as to offer a scientific basis for spectrum regulators to resolve this contradiction effectively and make a long-term spectrum-use plan.Specifically,this paper analyzes the driving factors of spectrum demand firstly,based on which a forecasting model is constructed to predict the spectrum demand and its deficit/surplus in the next few years.Then,a forecasting model to measure the economic value of spectrum is proposed based on marginal opportunity cost theory,and the indifference curve is introduced to show the economic value generated by additional spectrum.Additionally,an empirical study is conducted to forecast the spectrum demand and its economic value for China in the next 10 years according to the proposed method.The results of this study show that spectrum deficit is a trend in future and releasing additional spectrum will bring China huge economic benefits.     

Forecasting China’s Foreign Trade Volume with a Kernel-Based Hybrid Econometric-Ai Ensemble Learning Approach

Due to the complexity of economic system and the interactive effects between all kinds of economic variables and foreign trade, it is not easy to predict foreign trade volume. However, the difficulty in predicting foreign trade volume is usually attributed to the limitation of many conventional forecasting models. To improve the prediction performance, the study proposes a novel kernel-based ensemble learning approach hybridizing econometric models and artificial intelligence （AI） models to predict China＇s foreign trade volume. In the proposed approach, an important econometric model, the co-integration-based error correction vector auto-regression （EC-VAR） model is first used to capture the impacts of all kinds of economic variables on Chinese foreign trade from a multivariate linear analysis perspective. Then an artificial neural network （ANN） based EC-VAR model is used to capture the nonlinear effects of economic variables on foreign trade from the nonlinear viewpoint. Subsequently, for incorporating the effects of irregular events on foreign trade, the text mining and expert＇s judgmental adjustments are also integrated into the nonlinear ANN-based EC-VAR model. Finally, all kinds of economic variables, the outputs of linear and nonlinear EC-VAR models and judgmental adjustment model are used as input variables of a typical kernel-based support vector regression （SVR） for ensemble prediction purpose. For illustration, the proposed kernel-based ensemble learning methodology hybridizing econometric techniques and AI methods is applied to China＇s foreign trade volume prediction problem. Experimental results reveal that the hybrid econometric-AI ensemble learning approach can significantly improve the prediction performance over other linear and nonlinear models listed in this study.     

Parametric equation solving and quantifier elimination in finite fields with the characteristic set method

For a parametric algebraic system in finite fields,this paper presents a method for computing the cover and the refined cover based on the characteristic set method.From the cover,the author knows for what parametric values the system has solutions and at the same time presents the solutions in the form of proper chains.By the refined cover,the author gives a complete classification of the number of solutions for this system,that is,the author divides the parameter space into several disjoint components,and on every component the system has a fix number of solutions.Moreover,the author develops a method of quantifier elimination for first order formulas in finite fields.     

A Model-Based, Aspiration-Led Decision Support System NY-IEDSS

An Al-aided simulation system embedded in a model-based, aspiration-led decision support system NY-IEDSS is reported. The NY-IEDSS is designed for mid-term development strategic study of the Nanyang Region in Henan, China, and is getting beyond its prototype stage under the decision maker's (the end user) orientation. The integration of simulation model system, decision analysis and expert system for decision support in the system implementation was reviewed. The intent of the paper is to provide insight as to how system capability and acceptability can be enhanced by this integration. Moreover, emphasis is placed on problem orientation in applying the method.     

A Model-Based, Aspiration-Led Decision Support System NY-IEDSS

An AI-aided simulation system embedded in a model-based, aspiration-led decision support system NY-IEDSS is reported. The NY-IEDSS is designed for mid-term development strategic study of the Nanyang Region in Henan, China, and is getting beyond its prototype stage under the decision maker's (the end user) orientation. The integration of simulation model system, decision analysis and expert system for decision support in the system implementation was reviewed. The intent of the paper is to provide insight as to how system capability and acceptability can be enhanced by this integration. Moreover, emphasis is placed on problem orientation in applying the method.     

Quantifying the Indirect Benefits of Transport Infrastructures and Value Capture Ways in Transportation

1. INTRODUCTIONA metropolis is a dynandc system thected by many elements. In this dynamic system, transportation and landuse are two key elernents to which mally social and econoIIilc problerus in metropolis are related. These twoelemeots are the cause and effect of Problerns faced by some metropolises in China, such as trdri congestion,excessive agglomeration of economic activities. One effective way to solve u-rban probIems in China is to studythe reIationship between transportatiOn …     

Using Fundamental Economic Structures to Estimate Chinese Regional Input-Output Tables

The estimation of regional input-output tables is well discussed in the literature and a large variety of methods exist. In this paper we will use the concept of fundamental economic structure （FES） to estimate the matrix of intermediate deliveries for some ＂missing＂ region（s）. Furthermore, the estimates will be compared with the estimates obtained from ＂traditional＂ estimating techniques, including regionalization on the basis of the national table, and borrowing coefficients from similar regions. The results show FES is very helpful for compiling regional tables of China.     

PERSPECTIVES ON URBAN WATER INFRASTRUCTURE IN CHINA FOR THE 21^ST C0ENTURY： SDMUWEIC MODEL

Based on system dynamics approach, SDMUWEIC model is developed in order to evaluatefuture dynamics of urban water infrastructure development in China. Firstly, this paper presents thebasic structure and characteristics of the model, focusing on water infrastructure‘s dynamicrelationships with population increase, economic development, water resources shortage and waterconservation practices. Secondly, model veracity and robustness tests based on behavior reproductionand uncertainty analyses are illustrated. Thirdly, based on the model, future pattems of China‘s urbanwater infrastructure investment requirements are simulated, and effectiveness of two different policyscenarios are evaluated. Finally, conclusion,; and policy implications are drawn, allowing insights intoChina‘s sustainable water infrastructure policies and managements.     

Study on China＇s Economic Vulnerability to Energy Import Using Decomposition Method

Vulnerability means the degree to which that a system is susceptible to suffer damage. This paper focuses on the economic vulnerability to risk of energy import by employing ratio of net energy import to GDP as indicator, and decomposes the vulnerability change into effects of energy import, structure and intensity in order to find out key factors that influence economic security to energy import. Decomposition analysis on China indicates that effect of rising energy import takes more than 90 percent of total vulnerability change during the last 10 years, along with insignificant effect of structural change and intensity decline. International analysis on cross- section data of net energy importers also presents the positive relationship between external energy dependence and economic vulnerability. However, results of America show that long-term effect of energy intensity is much larger than China from 1954 to 2007, which is 70.8% of its total vulnerability change. Experience from developed countries confirms the necessary and validity of improving energy efficiency on depressing economic vulnerability to energy import, which provides lessons for the energy development of China.