2017 No. 4

column
  Previous Issue | Next Issue 
Display Method:
Overview
Trends and Prospects of Marine Navigation and Safety of Sea Transportation from TansNav 2017 Conference
WANG Kai, WANG tengfei, WU Bing, YAN Xinping
2017, 35(4): 1-11. doi: 10.3963/j.issn.1674-4861.2017.04.001
Abstract(423) PDF(4)
Abstract:
Safe, intelligent, and efficient navigation have been pursuing by various fields of the shipping industry.The 12th International Conference on Marine Navigation and Safety of Sea Transportation (TansNav 2017) manages to promote the developments of ship navigation safety, intelligence, and energy efficiency optimization.Keynote speeches and technical papers are statistically categorized and analyzed from the perspective of ship navigation optimization, the hot topics including ship collision avoidance, ship domain, human reliability, intelligent ship, and energy efficiency optimization are summarized, and their applications in the field of ship navigation optimization are introduced.The challenges of ship navigation optimization in terms of navigation safety, intelligence, and energy efficiency optimization are illustrated.Finally, the main trends of future ship navigation optimization are given, including the design of safety management and decision-making system, development of navigation brain system, studies on intelligent energy efficiency management and fleet energy efficiency optimization based on big data, etc.
American Truck Traffic Safety Theory and Practice Technology: A Survey of the State-of-art
YANG Wenchen, LI Li, TIAN Bijiang, HU Chengyu
2017, 35(4): 12-19,35. doi: 10.3963/j.issn.1674-4861.2017.04.002
Abstract(419) PDF(1)
Abstract:
Steady increase of the worldwide economy results in a rapid growth of truck transport.However, there is high risk of truck transport under various influences of road conditions, vehicle performances, and risky driving behaviors, for which cause death and great loss in property.A comprehensive review of the state-of-art theory for truck traffic safety in United States is conduct with purpose to improve safety management of trucks.Frameworks and main practical achievements of previous studies are reviewed and analyzed from three aspects: truck accident theories, proactive safety prevention technologies, and simulation modeling methods on traffic safety.Then model systems, equipment research and development, hot issues, information systems, and analyzing techniques of truck safety on highways are summarized.Finally, the key issues and trends on theoretical studies, equipment developments, and management of truck safety are analyzed for future studies.The review results demonstrated that detailed and reliable data is the foundation of theoretical studies of truck transport safety.The ideas of proactive safety have been gradually accepted in developing and managing practice of truck operation systems.Various types of simulation techniques can extend the scope and depth of future studies on truck safety.
Transportation Safety
A Method on Macroscopic Traffic Safety Evaluation Based on Weighting Triangular Fuzzy Number Algorithm
LIANG Xinyu, GUO Tong, MENG Xianghai
2017, 35(4): 20-28,35. doi: 10.3963/j.issn.1674-4861.2017.04.003
Abstract(435) PDF(2)
Abstract:
In order to improve a method on fuzzy comprehensive evaluation of road traffic safety in China.The focus is paid to determining the weight by a pairwise comparison matrix in fuzzy analytic hierarchy (FAHP) process.A weighting method based on triangular fuzzy numbers (TFN) is proposed.First, 9 indices of accident rate are determined based on an absolute index of traffic accidents and related factors, including people, vehicles, roads, etc.Second, a triangular fuzzy number is expressed as an interval concept.Unlike the traditional FAHP that used 1-9 integers and their reciprocal for weights determination, the upper and lower limits of the probability interval, and the maximum possible value of the whole range are set.Thereby the possibility of different parameters in the whole range is obtained.The effective information in the process of fuzzy evaluation is better reserved, so that evaluation results are more reasonable and accurate.Based on membership function, a judgment matrix and final fuzzy comprehensive evaluation method is developed.Taking the statistical data of 31 provinces, autonomous regions, and municipalities in China as a case study, the proposed method is applied to analyzing the macroscopic situations of traffic safety.According to the results, the proportion of areas with poor safety has been reduced from 87% to 6.5% during the past 10 years from 2005 to 2014, which reflects a great improvement of traffic safety in China.
An Analysis on Influences of Spacing of Emergency Parking Harbors on Driving Behaviors
CUI Xianglong, CHEN Yuren, XING Xiaoliang, LI Can
2017, 35(4): 29-35. doi: 10.3963/j.issn.1674-4861.2017.04.004
Abstract(349) PDF(3)
Abstract:
Spacing of emergency parking harbors on highways influences driving behaviors and safety of drivers.Few studies have focused on the correlation between driving behaviors and spacing of harbors.Experiments are conducted using a large 8-DOF driving simulation platform to study the correlation between the spacing of harbors and the speed and lateral offset of vehicles.This study records driving behaviors of 15 drivers when the spacing of emergency parkingharbors is 250-1 500 m (the interval is 250 m).Results of ANOVA conduct that the p-value is much smaller than 0.05 (p=5.3e-06 < 0.05;p=1.7e-13 < 0.05) when analyzing lateral offset and speed, which shows that there is a significant correlation between the spacing of harbors and the speed and lateral offset of vehicles.When emergency parking harbor areas are set in the spacing of 750 m, the driving behaviors are more coordinated (the lateral offset is 0.675 m, and the speed is 96.99 km/h).When the spacing increases to 1 000 m, it barely influences driving behaviors.However, in the experiments, the geometric alignment is simply straight.As the combination of the geometric alignments and the traffic flow are not considered, further study is needed in this area.
Graded Warning Methods of Dangerous Degree of Typical Traffic Violations on Highways
LIU Zhiyong, LI Ruimin, LIU Yingqi
2017, 35(4): 36-43. doi: 10.3963/j.issn.1674-4861.2017.04.005
Abstract(404) PDF(0)
Abstract:
Safety and efficiency of highways are impacted by frequent occurrences of dangerous driving behaviors and traffic violations.Based on related data of traffic safety on highways, a graded warning method is developed to evaluate dangerous degree of traffic violations.First, the relationships between traffic accidents and influence factors, including inclement weather, geometric alignments, and types of traffic violation behaviors, are investigated quantitatively.Second, considering weather conditions, traffic conditions, road geometric alignments and traffic violations, a method combining analytic hierarchy process (AHP) with fuzzy comprehensive evaluation is proposed to develop a graded warning model of traffic violations.A case study is further used to validate the proposed method.Results show that the model is effective and can provide supports for initiative traffic warning and management on highways.
Transportation Information Engineering and Control
A Method for Detection of Ship Traffic in Inland Waterways Based on Virtual Loop
MU Mengchao, HU Zhaozheng, LI Yicheng
2017, 35(4): 44-51. doi: 10.3963/j.issn.1674-4861.2017.04.006
Abstract(307) PDF(1)
Abstract:
Real time detection of ship traffic flow in inland waterways is of great significance to maritime transportation management.In order to detect ship traffic flow in a real-time mode, a detection system based on virtual loop is presented in this paper.The virtual loop is a closed area within a video image, which can detect moving targets according to the change of the image in the regions.Firstly, a binary image is obtained by RGB three-channel background difference method, in which three segmentation thresholds are obtained by Otsu method.Secondly, the ships that traverse the virtual loops are detected and recorded by two paralleled virtual loops.Besides, the length and width of the ships can also be detected.Finally, the detected ships are further classified by BP neural network.The videos collected from Wuhan Yangtze River Bridge and Second Wuhan Yangtze River Bridge at different time periods are selected as a case study.The results of the case study show that the success rate of detecting the ships reaches 97.1%, the missing rate is 2.9%, and the false alarm rate is 0%.The accuracy of classification is 98.6%.In addition, the proposed method also reveals that the average time of processing one frame is 7 ms, which indicates a good performance in term of timeliness.
A Simulation Study of Departure Time Selection in Dual-modal with Impacts of Vehicle Restriction Policies Based on Reinforcement Learning
WU Xuexin, LING Shuai, LI Geng
2017, 35(4): 52-62. doi: 10.3963/j.issn.1674-4861.2017.04.007
Abstract(386) PDF(2)
Abstract:
Combining multi-agent technology with a reinforcement learning model, a computer simulation model of travel modes and choice of departure time of commuters in peak hours is established.In a simulation, travel choice behaviors of commuters are studied with the consideration of impacts of vehicle restriction policies, and the formation of commuting equilibrium in peak periods is also reproduced.Based on simulation results, the effects of different measures for improving public transportations are analyzed.The results show that the number of commuters by bus increases by 18% after the implementation of restriction policies, which eases congestions in peak periods to a certain extent.Meanwhile, the probabilities that commuters travel by bus in unrestricted days become smaller, which means the effects of adopting restriction policies exclusively are fairly limited.Under the influences of restriction policies, if departure frequencies of public transport increase, the number of commuters travel by bus increases by 17.5%, and drivers′ waiting time in congestions decreases by 85%, which can effectively improve the traffic situations.Compared with that, reducing ticket price of public transport is less effective.The multi-agent approach applied in this study shows the richness in individual behaviors which can be realized intuitively and conveniently.It also has advantages in describing interactions between individuals and traffic systems, which provides an effective way to explore formation and evolution of complicated traffic phenomena.
A Study on Location of License Plate and Feature Recognition of Vehicles
DONG Hao, CAO Congyong, YANG Ying
2017, 35(4): 63-68. doi: 10.3963/j.issn.1674-4861.2017.04.008
Abstract(411) PDF(3)
Abstract:
Location of license plate and recognition of vehicles are main issues in intelligent traffic management.Through image preprocessing and morphology, the locations of license plates are roughly recognized, which then be filtered to obtain the accurate locations.A recognition process for characters on the plates is completed by utilizing a neural network.Transfer Learning is used for recognition of vehicles, and a deep feature vector is developed by using an AlexNet Convolutional neural network.Morphology can be used to process poor quality of grey background and guarantee accuracy of recognition.Compared with a direct classification of image features, the classification accuracy of the deep feature vectors constructed by Transfer Learning is 85.13%, which increases by 38%.It verifies the effectiveness of Transfer Learning and image attributes that characterized by deep features based on the KNN algorithm.However, it takes time when re-extracting features and training samples for new data sets.This method is found to have the equal accuracy of classification when it is compared with Transfer Learning and AlexNet framework, which proves the robustness of Transfer Learning.
A Study on Threshold of Exclusive Pedestrian Phase for Typical Signalized Intersections
WANG Xueyuan, SHAO Chunfu, HUANG Shichen
2017, 35(4): 69-75. doi: 10.3963/j.issn.1674-4861.2017.04.009
Abstract(450) PDF(1)
Abstract:
Pedestrian-vehicle mixed in urban intersections is common and has negative effects on efficiency and safety of intersections.A cost model of intersection operations with or without exclusive phase signal for pedestrians is developed using delay cost and conflict cost as evaluation indices.Signal delay, conflict delay, and detour delay are all considered to calculate delay cost of pedestrians and non-motor vehicles.As for the conflict cost, based on traffic conflict theory, time headway is used to judge whether motor vehicles have conflicts with pedestrians or non-motor vehicles.Conflict possibility can be determined by arrival distribution of vehicles and pedestrians.The Sidaokou intersection in Beijing is chosen as a case study.Based on the collected data and genetic algorithm, the threshold of pedestrian flow is 750-900 ped/h for setting exclusive phase for pedestrians.With the increase of traffic flow, the requirement of pedestrian flow is descending at first, and then ascending at last.This study can provide a theoretical support for signal setting of urban intersections, and improve safety and convenience for pedestrians and non-motor vehicles.
An Identification Method of Fake Plate Vehicles Using Two Type Traffic Data Collecting from Traffic Base Stations
YU Ying, WANG Jing, NING Dan, GUO Jianhua
2017, 35(4): 76-83. doi: 10.3963/j.issn.1674-4861.2017.04.010
Abstract(318) PDF(2)
Abstract:
False plates vehicles have negative impacts on social security and transportation management.Therefore, it is necessary to explore a fast and effective approach to identify the false plate vehicles.This paper develops an identification approach based on radio frequency identification (RFID) data and images from traffic base stations.At one base station, a vehicle''s plate number should be coincident in RFID system and image recognition system.Based on this fact, suspected fake plate vehicles can be detected in each station.Combines data from multiple base stations, the recognition rates effectively increased.Actual data collected from six base stations on arterial roads of Nanjing is used as a case study.Compared with only two base stations, the number of fake plate vehicles detected by five base stations is reduced by 210, which indicates that increasing number of stations can decrease the false positive rate of fake plate vehicles.The accuracy of verifying the suspected vehicles based on this method is 94.5%.Large coverage, timelessness limitation, and rapid response are the advantages of this method compared with traditional methods, and it can provide strong supports for traffic police departments to investigate and control fake plate vehicles.
Transportation Planning and Management
A Study on Prediction of Waiting Time of Ships Crossing Three Gorges Locks based on M/M/C Queuing Models
ZHONG Ming, LI Chenhui, LIU Shaobo
2017, 35(4): 84-91. doi: 10.3963/j.issn.1674-4861.2017.04.011
Abstract(323) PDF(0)
Abstract:
In order to study the issue of serious delay of ships during the process of crossing Three Gorges Locks, downstream traffic flow consisting of different types of ships arriving at anchorages and passing Locks in 2013 is collected and analyzed.Frequency distribution of different waiting durations of ships are also summarized and presented.Queuing theory is used to conceptualize the anchorages of Three Gorges Dam as a queuing system with random arrival rate and multiple servers, M/M/C queuing model is used to best represent the system and used to model average waiting time and average queuing length, etc.of the system.The observed arrival rate of ships and service rate of anchorages in 2013 are used as inputs of the model, average delay time estimated from the model is compared with the actual data, and the absolute percent error (APE) is found to be 7.3%, which suggests that the accuracy of the model is acceptable.Then sensitivity analysis of the model is carried out by specifying different arrival rates and service rates.Study results show that decreasing arrival rate by 15% (e.g.the goods from 15% of all of the ships arrived will be transfer to road transportation) would change the status of the anchorages from overloading to operating within the capacity.On the other hand, if increasing arrival rate by 15%, then the system will be unstable and fully congested.However, if, at the same time, the service rate of the anchorages increases by 30%, the system will return to its stable status and the parking demand of arriving vessels can be accommodated.
A Performance Evaluation of Practice Examination for Inland First-grade Captains based on Fuzzy Cognitive Maps
WANG Mengyu, GUO Guoping, WU Bing
2017, 35(4): 92-99,126. doi: 10.3963/j.issn.1674-4861.2017.04.012
Abstract(266) PDF(0)
Abstract:
In order to conduct the performance evaluation of practice examination for inland first-grade captains, this paper proposes a model of fuzzy cognitive maps based performance evaluation method (FCMES).After identifying the 25 influencing factors by using questionnaires, the evaluation grades are first defined.Then, the qualitative expert judgments are transformed to triangular fuzzy numbers, through which the fuzzy matrixes are obtained.Moreover, adjacent matrix is obtained after integrating fuzzy matrixes using fuzzy rule based reasoning and defuzzification methods.Second, the importance of influencing factors are analyzed to select the key factors by using three parameters, which are input, output, and centrality.Finally, Matlab simulation is used to verify the proposed FMCES model, the result indicates that there are four significant factors for practice examination of inland first-grade captains, specifically, they are evaluation of performance, professional quality of evaluator, efficiency of simulator, and rationality of examination process.
A Prediction Model of Fuel Consumption for Inland River Ships Based on Random Forest Regression
MOU Xiaohui, YUAN Yupeng, YAN Xinping, ZHAO Guangpu
2017, 35(4): 100-105. doi: 10.3963/j.issn.1674-4861.2017.04.013
Abstract(552) PDF(10)
Abstract:
An accurate model to predict fuel consumption of ships is the basis for optimizing ship navigation.Taking a cruise ship in the Yangtze River as a case study, a large volume of data on ship operations is collected by an information acquisition system.Based on theoretical analysis, the main factors that influence fuel consumption of the ship are identified, which are wind speed, wind direction, water depth, water velocity, and ship speed.A method of setting parameters of random forest model is improved and a way to measure the significance of variables is proposed.Sample data is obtained by systematic samples after de-noise process.The data is then randomly divided into training samples and testing samples by a ratio of 0.7 to 0.3.A prediction model of fuel consumption is developed by using random forest (RF) algorithm to address the training samples.Compared with the measured data, the errors are within 6.8%, which is better than the model established by utilizing BP neural network or support vector machine (SVM) with same samples.Order of the importance of each variable is: ship speed > water velocity > water depth > wind speed > wind direction.Finally, the quantitative relationship between a single factor and fuel consumption is analyzed by using partial correlation analysis.
A Study on Behavior Mechanism of Travel Mode Choice Based on a Perspective of Social Interaction
PAN Chi, GUO Zhida
2017, 35(4): 106-111,126. doi: 10.3963/j.issn.1674-4861.2017.04.014
Abstract(264) PDF(0)
Abstract:
Most of the previous travel behavior models implicitly stipulated a biased assumption that individual decision-making is independent from others′ behaviors.Thus, these models cannot accurately reflect macro traffic situations when analyzing traffic behaviors with obvious social interaction effects.In this study,''travel mode choice behavior''is regarded as a collective behavior, and equilibrium shift states of travel choice behaviors are analyzed with a consideration of social interaction effects.Accordingly, a threshold model of travel mode choice behavior is developed.Taking parking fee as an indicating variable of policy interventions, it quantitatively estimates the threshold of eliminating inferiority equilibrium (i.e.unrestrained travel of private cars).The results show that when parking fee increases to over RMB 15 yuan per trip, the collective behavior will reach the equilibrium shift threshold, which can promote the proportion of travels using public transport from 19.3% to 72.3%.
Optimizing Passenger Traffic Structure Based on a Fuzzy Interpretive Structural Model
WANG Jian, CAO Yang
2017, 35(4): 112-118. doi: 10.3963/j.issn.1674-4861.2017.04.015
Abstract(290) PDF(0)
Abstract:
Optimization of the structure of passenger transportation is considered as one of effective ways for sustainable development of urban transport systems.It plays an important role in improving efficiency of urban transport systems for passengers.A fuzzy interpretive structural model is developed based on characteristics of influencing factors, and divides them into four levels which including direct influencing perceptional layer, indirect influencing cognitive factor layer, transitional connection factor layer, and fundamental factor layer.Meanwhile, inter-layer and intra-layer influencing factors are connected by the directional arc.The modeling results show that urban scale of the passenger traffic structure is the fundamental factor;capital investment is the transitional connection factor;and road layout, infrastructure, and characteristics of passengers are the indirect influencing cognitive factors.The urban transport systems in Harbin are taken as a case study.The results of this study determines key factors for optimizing structure of passenger transportation, and puts forward suggestions on optimization of urban transport systems for passengers from the aspects of traffic policy, land use, and travel modes.
A Benefit Evaluation Method of Traffic Big Data Platform
PENG Qingyan
2017, 35(4): 119-126. doi: 10.3963/j.issn.1674-4861.2017.04.016
Abstract(238) PDF(0)
Abstract:
Owing to the versatile traffic big data platforms, a benefit evaluation method based on "trip mode share ratio" is developed.The method is different from traditional ITS evaluation methods which are generally based on the economic benefits of vehicle owners.Cost Savings include fares of vehicle transportation, time cost of passengers, and environmental cost (e.g.CO2 emission).Considering different income level of passengers, a comprehensive formula is proposed to calculate the time cost of different travel modes and purposes.Values of parameters are determined through a traffic big data platform.Moreover, a benefit evaluation formula of cost savings resulted from traffic mode transfers is proposed by "with and without comparison method".Take the traffic big data platform of Wuhan City as a case study, a cost-benefit analysis is carried out in terms of the influence area and selection of parameters.The method is proved to be a useful way of quantitative benefit evaluation for traffic big data platforms, and provides a guideline for future similar projects.

Copyright Editorial Office of Transport Information and Safety鄂ICP备05003336号-2

Address：No. 1178，Heping Avenue, Wuchang, Wuhan, CHINA (430063)

Tel：027-86580355 Email：jtjsj@vip.163.com

Supported by: Beijing Renhe Information Technology Co. Ltd