Green Connected Automated Transportation and Safety

Table of Contents

1. An Improved Comprehensive Evaluation Method of Road Passenger Transportation Safety

   Guoliang Dong, Fujia Liu, Haiying Xia, Chaozhou Chen

   Abstract

   Carrying out safety assessment before the departure of road passenger transport vehicles can find hidden dangers and prevent accidents. This article discusses the determination of the safety evaluation index of the transportation process, and the construction and improvement of the evaluation method. After analyzing the participating factors in the accident, the relevant factors affecting the safety of the transportation process are obtained. The main influencing factors were analyzed and combined with the principal component analysis method to analyze and filter the importance of the influencing factors to determine the safety evaluation index. Based on the comprehensive evaluation method, the road passenger transportation process safety evaluation method is constructed. Aiming at the problem of the inconsistency between the evaluation results of the traditional evaluation method and the actual input in the actual application, the reasons for the problems were analyzed and an improved comprehensive evaluation method was proposed. The improved evaluation method was applied to verify an accident instance, and the results showed that the improved evaluation method solved the problem of the deviation between output and input in the traditional evaluation method, and could objectively reflect the impact of various factors on the safety of the transportation process.

2. Vehicle Detection at Night Based on the Feature of Taillight and License Plate

   Guosheng Ma, Mante Cai, Guanliang Chen, Zhixiao Li

   Abstract

   This paper proposes a algorithm of vehicle feature extraction and detection based on video data for night time. The color characteristics of taillights can be roughly divided into two parts no matter how far or near they are: inner ring-highlights area partial to pink and outer ring-high saturation Red areas. Through a large number of sampling statistics, this method obtains the accurate threshold range of each layer based on HSV color space. Thus, the suspected area of the inner and outer ring of tail lights can be segmented accurately and filtered preliminarily according to the shape characteristics of the tail lamp. In order to improve the detection rate and image recognition quality, the paper carry out AOI region segmentation and median filtering. After getting the suspected area of license plate, the tail light and license plate are combined to determine the rear of the vehicle. Secondly, all the connected regions of the tail lamp suspected area are paired and the confidence level of the pair is established. The confidence level is evaluated according to the characteristics of the tail lamp pair such as the horizontal height, the distance width and the symmetry centered on the license plate. According to the confidence level, whether it is qualified to pair with the license plate is determined Finally, according to the characteristics of taillight pairs, the mismatched relationship pairs are eliminated and the vehicles are identified. The experimental results show that the method can accurately detect the vehicle tail light features to identify the vehicle, and the false detection rate is low.

3. Spatial Integration Based on Big Data—A Case Study on the Integration of Nanjing and Ma’anshan

   Xiaofeng Lou, Hong Zhang

   Abstract

   By carrying out a case study on the integrated urban development of the cities of Nanjing and Ma’anshan in China, we developed a method to analyze the integration characteristics and assess the integration of adjacent areas based on multi-dimensional analysis of big data on population and industry. We investigated the spatial distributions, connections, and the integration of urban elements such as population, industry, and transportation. We evaluated the degree of integration of the two cities based on multiple attributes. The findings will guide the integration planning of key areas for the next phase of urban development and provide new ideas for research on integrated development.

4. A Method of Household Car Ownership Prediction Using Ordered Probit Model

   Guangzheng Yao, Yanyan Chen, Kaijun Cui, Donghui Xu, Jiarui Liu

   Abstract

   Predicting the demand for cars accurately is of great significance to urban planning and parking facilities planning. This paper uses the data from the Beijing 2010 Resident Travel Survey and takes the family income level, family demographic characteristics, the geographical environment of the family and the personal attributes of the head of the household as parameters. Random forest method is used to rank the importance of explanatory variables and carry out variable reorganization. Use the ordered probability model (Ordered Probit) to establish the relationship between explanatory variables and the number of vehicles owned by the household. The model found that the three parameters of the number of family driver’s licenses, the level of family income, and the number of people have the greatest impact on the family’s decision to own a car, and the income group mean transformation has a better fitting effect.

5. Long Short-Term Memory Neural Network for Traffic Speed Prediction of Urban Expressways Using Floating Car Data

   Deqi Chen, Xuedong Yan, Shurong Li, Xiaobing Liu, Liwei Wang

   Abstract

   Recently, accurate and rapid prediction of traffic speed has become a research hotspot in the current applied traffic field. Based on deep learning models, especially Long Short-Term Memory neural network (LSTM), real-time traffic speed prediction of the urban expressway has been a new challenge. Since it takes a long time to extract traffic parameter by map matching method, we present a novel grid model to rapidly derive a series of traffic parameters from the floating car data (FCD). To improve the prediction accuracy, we consider the spatial–temporal characteristics of traffic speed (i.e. upstream and downstream speed, historical average speed, etc.). To verify the validity of the model of the proposed model, we employ 40-day FCD to train and test the model. Our final result, compared with other machine learning methods, the LSTM model has advantages of accuracy and stability, which could facilitate the prediction of the traffic speed and the traffic operation performance.

6. Design and Implementation of Automobile Test Monitoring Management System Based on PDA Terminal

   Hong Jia, Hao Li, Hai-ying Xia

   Abstract

   In order to ensure the traceability of the test and detection work of road transport standard vehicles, and supervise and manage the test quality of automobile inspection institutions, this paper designs a monitoring and management system for automobile test and detection based on PDA terminal, and realizes the functions of PC terminal and PDA terminal by using C++ language and Java JDK1.8 language. Using PDA terminal, through real-time recording the operation data of the test sample vehicle or remote synchronous video recording, the original data of the test and detection of the standard vehicle are saved to the inspection quality supervision and management system, so as to ensure the traceability of the test and detection work of the standard vehicle type test organization, and on this basis, the test work quality of the standard vehicle type inspection organization is supervised and managed.

7. A Three-layer Optimal Distribution Problem for Electric Vehicle Charging Stations

   Di Chen, Xinyu Yu, Linghan Li, Yuyang Zhou

   Abstract

   Following the boost in technology in recent years, electric vehicles have flourished at an amazing rate and have become viable replacements for gasoline vehicles. Accordingly, an urgent need for optimal land use planning (LUP) for charging stations (CSs) has emerged. With the purpose of satisfying this demand, this study aims to solve the charging station distribution problem by determining the suitable number of chargers in a station, optimizing the distribution of CSs, and generating growth plans in lines with countries’ regulations. First, queuing theory was used to determine the optimal number of chargers in a station; the effectiveness was measured by adopting China as an example. Second, in order to optimize the area distribution of CSs, graph theory was used to determine the shortest path using Floyd algorithm (FA); the aptness of the distribution of CSs was examined in parts of South Korea. Finally, analytic hierarchy process (AHP) was used to test the growth plan of the CS network in the U. S., South Korea, China, and Cote d’Ivoire, considering population density distributions, wealth distributions, and geographical conditions.

8. Analysis of Mixed Vehicle Traffic Flow at Signalized Intersections Based on the Mixed Traffic Agent Model of Autonomous-Manual Driving Connected Vehicles

   You Ren, Shan Jiang, Guan Yan, Hongmei Shan, Huiying Lin, Zhilong Zhang, Liangzhe Wang, Xuesheng Zheng, Jiaqi Song

   Abstract

   Signalized intersection is an important node of urban traffic network, but also the most likely place in the urban traffic network to generate congestion, complex traffic conditions; and relatively high traffic flow will cause the reduction of urban traffic network operating efficiency, or even cause the paralysis of the urban traffic network. With the participation of pedestrians, the situation at the intersection will be more complex and diverse. In recent years, with the rapid development of automobile and related technology, manual driving connected vehicle (MDCV) and autonomous driving intelligent connected vehicles (ADICV) are gradually entering people’s daily life. And ADICVs have coordinated and unified driving behaviors. In short, ADICVs have similar driving habits and can accelerate and decelerate at a systematic synchronization pace, which can help alleviate road traffic congestion and improve transportation network operation efficiency. Therefore, this paper uses the combination of ant algorithm and cellular automata to establish a pedestrian model, and constructs a traffic simulation model for the mixed traffic flow of the autonomous-manually driving vehicle agent at the intersection with/without pedestrian interference. Based on the assumption that the ADICVs have the coordinated driving behaviors, the paper analyzes the influence of green time ratio, mixed traffic ratio and average delay time on the traffic flow of MDCVs and ADICVs. Through the statistical analysis of the average velocity, traffic flow and other parameters, the mechanism and conclusion of the mixed traffic flow of MDCVs and ADICVs are obtained.

9. Driving Velocity Tracking Error Analysis of Different Broadcast Methods Under Green Light Optimal Speed Advisory System

   Shanshan Guo, Tao Zhang, Yongsheng Liu

   Abstract

   Green light optimal speed advisory (GLOSA) system provides the speed recommendations to drivers so that they can pass through successive intersections at the appropriate instants, aiming at saving time costs while maximizing energy efficiency. However, there is rare literature mentioning the impact of drivers’ behaviors by different broadcast modes under GLOSA system. Combined with the direct “speed value” voice broadcast method, this paper compares the driving behavior differences under the effects of dashboard display of three different visual stimuli on driving behavior. The driving data of the driver when performing the optimal speed is collected from the real world, and the speed tracking error in the driving behavior is counted. Furthermore, the advantages and disadvantages regarding the three broadcast methods and voice broadcast method are illustrated with detailed analysis. The value and time recommendations of the “speed value” of the best speed consultation system are given at last. Thereby minimizes the error of the driver when performing the optimal driving speed.

10. Mechanical Modeling and Analysis Based on Fine Drill

    Kuikui Feng, Haodong Zhang, Qian Cheng, Wuhong Wang

    Abstract

    The main purpose of this paper is to study the change law of the contact condition between the fine drilling tool and the workpiece surface during cutting. Firstly, the structure of the drill tip of the fine drilling tool is analyzed, and the contact force of the drill tip is effectively decomposed. Then, on the basis of considering the cutting edge radius, the cutting mechanics model of each part of the drill tip was established according to the theory of slip line field. Finally, drilling experiments under different cutting conditions were carried out to solve the contact coefficient between the tool and the workpiece surface. The research shows that the high feed leads to greater ploughing effect in cutting, resulting in sharp change of contact force, which provides a research direction for tool tip design.

11. Backmatter