2017 No. 5

column
  Previous Issue | Next Issue 
Display Method:
2017, 35(5)
Abstract(201) PDF(0)
Abstract:
A Review on Driving Behavior under Adverse Weather Conditions
ZHAO Xiaohua, REN Guichao, CHEN Cheng, RONG Jian
2017, 35(5): 70-75,98. doi: 10.3963/j.issn.1674-4861.2017.05.009
Abstract(725) PDF(7)
Abstract:
Adverse weather has great influences on operation and safety of urban traffic.In fact,the change of driving behavior under adverse weather conditions is the primary cause of traffic congestion and accidents.A review of driving behaviors in adverse weathers is of positive significances for studying traffic congestion and accidents under adverse weather conditions.Studies abroad and in China are both reviewed in this paper.Basing on three common adverse weather conditions (rain,snow,and fog),the environmental change and its impacts on driving behavior are analyzed.Additionally,orientations of future studies are discussed.According to related studies,the results show that drivers choose different speeds and headways in different levels of rain,snow,or fog;the reaction time of drivers and vehicle delay are all different from which in good weather conditions.
A Model of Travel Speed Calculation for Freeway Road Segments with ETC Transaction Data
WENG Jiancheng, WANG Yuan, YUAN Rongliang, MA Siyong
2017, 35(5): 76-82. doi: 10.3963/j.issn.1674-4861.2017.05.010
Abstract(277) PDF(1)
Abstract:
Aiming to enhance the level of monitoring of expressway status,a procedure of data preprocessing is presented,and structure of ETC transaction data within a calculation period is analyzed to establish a dual-level calculation model of travel speed under different levels of sample sizes.In order to improve credibility of velocity extraction under conditions of small samples,the ETC data of different enter-leave toll plazas pairs is used to extracting the travel speed of a road section.A velocity correction method is proposed bases on the speed reduction factor a and speed reliable weight θ coming from OD investigation.The model is verified by a special designed field experiments.The results show that the mean absolute error is 4.5 km/h,and the average relative error is about 6.5%.The mean square errors are 2.38 km/h and 3.39 km/h in peak and non-peak periods,respectively.It shows that stability of the model in peak periods is better than which in non-peak periods.However,the results cannot entirety reflect driving states.In future,other data can be applied to increase the accuracy and reliability of traffic running status on freeways.
A Study on Information Demand and Publishing Framework of Accidental Events for Mobile Terminal
QIAO Jing, SUN Lishan, WANG Wei, RONG Jian, LIU Xiaoming
2017, 35(5): 83-90,98. doi: 10.3963/j.issn.1674-4861.2017.05.011
Abstract(297) PDF(0)
Abstract:
At present,characteristics of urban transport are gradually changing from regular to sporadic.The demand for early warning of accidents is also increasing.For accidental events in public transport,a SP survey is used to analyze the characteristics from three parts:degree of influence,frequency of occurrence,and behavior of residents.A system-clustering algorithm is used to classify accidental events into three levels:point,local,and global.A list of information requests under different accidental events is established based on analyses of different types,locations,and time of information demand.A framework and an APP of accidental events are developed to obtain the best access to information demands with analyzing characteristics of release and collection at different service terminals in Mobile Internet environment.Results show that the satisfaction rate of mobile terminals is up to 85 %.It can be conducive to deal with the conflicts between the uncertainty of characteristics of urban transport and the reliability and timeliness of travel information,then improve efficiency of urban transport.
An Effective Evaluation of Yellow Flashing Warning Light of Intersection Based on an Efficiency Coefficient Method
FAN Zhaodong, CHEN Dong, ZHAO Xiaohua
2017, 35(5): 91-98. doi: 10.3963/j.issn.1674-4861.2017.05.012
Abstract(262) PDF(0)
Abstract:
In order to solve issues of quantitative assessment of the effectiveness of yellow flashing warning lights,improve comprehensive operation level of intersections,and reduce occurrence of traffic accidents,an evaluation method based on driving simulation technology is developed to evaluate yellow flashing warning lights in three different types of intersections.The effectiveness of them is comprehensively evaluated by combining microscopic driving behavior data with an efficiency coefficient method based on entropy weight.Based on actual scenes in T-intersections,cross-intersections and abnormal intersections of a partial roadway on G101 national highway,two kinds of virtual scenarios are developed,which are named as the national standard group and the special group.Eight evaluation indicators are selected from three aspects.The results show that the total effectiveness of the same type of intersections can be significantly improved after set up a yellow flashing warning light.The level of safety,comfort,and predictability at the intersections are improved.An efficacy coefficient method can scientifically and reasonably achieve the mutual contrast between alternative programs which has strong practicability,and provides a theoretical basis for setting the yellow flashing warning light.
An Evaluation Method of Road Operation Condition Based on Two-Stage K-means Clustering
ZHANG Linlin, LI Xuewei, LI Zhenlong, WANG Guan
2017, 35(5): 99-105. doi: 10.3963/j.issn.1674-4861.2017.05.013
Abstract(291) PDF(0)
Abstract:
In order to effectively evaluate road operation condition,an evaluation method based on Two-Stage Kmeans clustering (TSKC) is developed by analyzing variation of vehicle operating state.First,aiming at the arbitrariness in the choice of K-means cluster number and the randomness of selection of cluster center,a K-means clustering method based on traversal is proposed.The cluster number and initial centers are determined by class attractiveness,and used as the initial condition of the second stage K-means clustering to explore the traffic pattern.The pattern attractiveness,the road evaluation indices,and the distribution equilibrium are proposed as indices to evaluate road operation condition.Beichen East Road of Chaoyang district in Beijing is taken as a case study.The results show that the proposed method is more detailed,comprehensive,and intuitive than the traditional evaluation method when describing the evolution of vehicle state and the distribution of traffic patterns.The results also indicate the great practicability of the method.
Methods to Plan Travel Routes of Cycling Under Different Travel Demands
HE Fan, BIAN Yang, MA Junlai
2017, 35(5): 106-114. doi: 10.3963/j.issn.1674-4861.2017.05.014
Abstract(280) PDF(0)
Abstract:
Currently,studies on route planning of cycling commonly contain issues as lack of considering different demands or low accuracy of solutions,which cannot satisfy the growing demands of cycling.A method to plan travel routes is developed to provide more selections of cycling routes according to various demands.Regarding trips for commuting,business,and entertainment as main purposes,through literature research,field investigation,and factor analysis,main travel demands including travel time,travel safety,and travel environment are confirmed.Then their relative influencing factors are analyzed.Data of bicycle lanes of Xicheng District in Beijing is used to process numerical calibration and algorithm description.Methods to plan travel routes under influences of a single demand or complex demands are studied respectively.Different paths are recommended according to specific travel needs.The impacts of crossing streets improve recommended precision under travel time requirements.The differences between a single demand and complex demands can provide more options for cycling.
A Method of Multi Granularity Intercity Passenger Demand Forecasting for Operation Management
QI Hao, WENG Jiancheng, LIN Pengfei, LIU Wentao, XU Shuo
2017, 35(5): 115-122. doi: 10.3963/j.issn.1674-4861.2017.05.015
Abstract(223) PDF(0)
Abstract:
Passenger volume is a basic indicator of the demand for inter-provincial passenger transport,which reflects levels of operation and management in this industry.A forecasting model with multi-granularity for passengers' volume in one year or on holidays is developed to promote level of management,travel efficiency of passengers,and capacity of emergency response.A prediction model of passengers' volume using BP neural network based on correlation analysis of influencing factors and annual passengers' volume is developed.Considering special influencing characteristics of passengers' volume on holidays,a forecasting model combines an exponential smoothing model and a seasonal model is proposed.The total and daily volume of inter-provincial passenger transport during holidays is predicted.Taking actual transport data in Beijing as a case study,the accuracy of the prediction model is verified.The results show that the average relative error of the prediction model of annual passenger volume is 0.15%,and the average relative error of the prediction model of daily passenger volume during the Spring Festival is 6.70%.These indicating that the prediction models can reflect the variation trend of passenger volume in different periods,and has good stability.
A Study on a System of Dynamic Driving Safety Education Based on Simulator+
Zhao Xiaohua, XU Wenxiang, YAO Ying
2017, 35(5): 123-130. doi: 10.3963/j.issn.1674-4861.2017.05.016
Abstract(231) PDF(0)
Abstract:
Traffic accidents have seriously affected people's lives and caused huge social and economic losses in development.An immersive experience education system (DSIES) based on simulator experimental platforms is developed as a new tool for driving training which can help to reduce human error by correcting risky driving behaviors.On the basis of the Theory of Planned Behavior (TPB),a "perception-training-immerse" (PTI) driving simulator-based training model is proposed.Four representative illegal driving behaviors are selected as experimental subjects,42 drivers are randomly divided into two groups for traditional education method and new education method.Descriptive statistics,variance analysis,and gray correlation analysis method are used to verify the results of different educational methods.The results show that the new education system has more effects than traditional education in both short-term and long-term education;however the effects of training decrease with time.Actually,DSIES can effectively improve driving ability,and help drivers to forecast risks and reduce traffic accidents.
Overview
Trends and Prospects of Polar Navigation Research from 24th POAC International Conference
ZHANG Chi, ZHANG Di, MENG Shang, ZHANG Mingyang
2017, 35(5): 1-10. doi: 10.3963/j.issn.1674-4861.2017.05.001
Abstract(422) PDF(2)
Abstract:
In recent years,navigation in Polar areas has become a hot topic around the world.The 24th International Conference on Port and Ocean Engineering under Arctic Conditions (POAC 2017) manages to create a platform of communicating and learning for experts and scholars in this area.A review of safety of port and ocean engineering in Arctic area is developed by introducing and analyzing keynote speeches and technical papers from POAC 2017.Frontier studies in this field including remote sensing of sea ice,Arctic sea ice load analysis,researches on Polar Codes and risk assessment of Arctic navigation are summarized.For the hot topics of navigation in Polar area and safety security,future trends on this field from POAC 2017 have been elucidated.Focuses for future studies are put forward to seize the opportunities for the development of polar ship navigation.
Transportation Safety
A Real-time Accident Risk Model on Freeways Based on Monitoring Data
FU Cunyong, WANG Junhua
2017, 35(5): 11-17,36. doi: 10.3963/j.issn.1674-4861.2017.05.002
Abstract(380) PDF(2)
Abstract:
In recent years,the incidence of highway accidents on freeways remains high.In the meantime,loop detectors are commonly equipped on freeways.Thus,it is necessary to dig the data of loop detectors in order to predict realtime risk of traffic accidents on freeways.Based on data of actual accidents and collected from detectors on four freeways called I5,I10,I405 and I15 in California,where the most accident numbers occurred in the year 2012,extracting data group of accidents and non-accidents based on an idea of case-control study.Study coverage of detector data is selected.Meanwhile,ADASYN algorithm is used to solve the problem of unbalanced data sets.Based on random forest,three basic traffic flow data within 10-40 min before accidents collected from four upstream detectors and two downstream detectors is used to compute locations of accidents.A real-time accident risk model on freeways is developed with the accuracy rate of accident prediction is 88.02 %.The top ten important variables are selected as important inducements of accidents.Then,the values of the important inducements are adjusted.The modified test set is applied to the random forest model for classification forecasting afterwards.The result shows that the numbers of accidents are reduced by 41.82%.Therefore,it can be found that the important inducements of accidents can be applied to the early warning of traffic accidents,thus reducing the incidence of them.
An Investigation and Analysis on Influences of Traffic Violation Monitoring on Psychology and Behaviors of Professional and Non-Professional Drivers
LUO Shulan, PAN Fuquan, WANG Jian, QI Rongjie, ZHANG Lixia, BING Qichun
2017, 35(5): 18-27,44. doi: 10.3963/j.issn.1674-4861.2017.05.003
Abstract(349) PDF(0)
Abstract:
In order to find out the different influence of traffic violation monitoring on psychology and behaviors of both professional and non-professional drivers,a questionnaire survey is applied to acquire data of 321 drivers on 11 subjects,including driving psychology and behaviors at intersections with and without traffic violation monitoring,drivers' attitude towards monitoring,etc.Then the chi square analysis and paired sample t test is used to analyze the data.The results show that psychology differences between non-professional and professional drivers go through intersections with or without traffic violation monitoring are exist.The impacts of traffic violation monitoring on non-professional drivers is greater than that of professional drivers.At the intersections without traffic violation monitoring,non-professional drivers are more prone to risk driving than professional drivers.For non-professional drivers,it has significant difference in driving behaviors between the intersections with and without traffic violation monitoring.For professional drivers,the difference is not that significant.Whether they are non-professional or professional,most drivers support the installation of traffic violations monitoring.
Transportation Information Engineering and Control
A Detection Method for Vehicles in Nighttime by Virtual-loop Sensors Based on Kinect Depth Data
ZHANG Rufeng, HU Zhaozheng, MU Mengchao
2017, 35(5): 28-36. doi: 10.3963/j.issn.1674-4861.2017.05.004
Abstract(378) PDF(1)
Abstract:
Detection methods for vehicles based on video cameras have problems of low accuracy,poor robustness,and difficult to identify types of vehicles in nighttime situations.A method using virtual-loop sensors based on Kinect depth data is proposed for detecting vehicles in nighttime.Firstly,depth image from Kinect is pre-processed to derive the target Motion Depth Map (MDM) and the Hole Depth Map (HDM).Secondly,virtual-loop sensors are set on MDM and HDM respectively,and generate integral images to compute the one-dimensional motion signals.The motion signals from corresponding MDM and HDM are fused to formulate the description of vehicle motions,from which vehicles are detected and counted.Then geometric features of vehicles are extracted,and types of vehicles are recognized by using SVM.The results show that the proposed method can accurately detect and count vehicles in nighttime situations with recognition rates 99.75 % and 99.25 % for one-lane and two-lane scenarios respectively.Its classify accuracy is 99.80 % in terms of dis tinguish light and heavy vehicles.The average time of processing one image is only 7 ms.
A Multi-aspect Method for Vehicle Dynamic Detection Based On Deep Learning
LI Hao, ZHANG Yunsheng, LIAN Jie, LI Zeping
2017, 35(5): 37-44. doi: 10.3963/j.issn.1674-4861.2017.05.005
Abstract(307) PDF(0)
Abstract:
In order to address the problems of dynamic target detection rate is low due to excessive interference of background areas and fast moving speed of detected targets in complex scenes,this article proposes a multi-aspect method for vehicle dynamic detection based on deep learning.The traditional deep learning algorithm is improved by using convolutional neural network with a multiplayer perceptron (MLP-CNN).The kernel of this improved method is first to apply the fast candidate region extraction algorithm to find the regions where vehicles may exist,then to utilize a deep convolutional neural network (CNN) to extract features of candidate region,and to use an enhanced convolutional layer with multilayer perceptron (MLP) to further abstract optimal features for each layer.The Support vector machine (SVM) is finally used to classify CNN features of backgrounds.The results show that the proposed method can deal with part occlusion or fast motion objects.With a recognition accuracy of 87.9% and elapsed time of 225 ms,it is more efficient than other traditional methods.
Coordinated Control Between Expressway Ramp and Exclusive Bus Lane Based on a Breakdown Probability Model
XIE Dongqi, FEI Wenpeng, SUN Jianping, SONG Guohua
2017, 35(5): 45-54. doi: 10.3963/j.issn.1674-4861.2017.05.006
Abstract(337) PDF(0)
Abstract:
Traffic delay is often considered as an important indicator for evaluating coordination control schemes of expressways.However,due to Breakdown phenomenon,sudden changes of vehicle speed can happen,which lead to great uncertainties in great uncertainties based on the delay.Therefore,in order to solve this problem,Breakdown probability is introduced as an evaluation indicator,and it is combined with the delay indicator to form a comprehensive evaluation indicator.In this paper,four control schemes are designed based on ramp control and bus lane settings.Based on the improved Breakdown probability model and INTEGRATION simulation software,the proposed four control schemes are evaluated using,Breakdown probability indicator,delay indicator,and the comprehensive evaluation indicator.The results show that the indicator of Breakdown probability is inconsistent with evaluation results of delay indicator,which means this indicator is reasonable to evaluate the coordination schemes during formation processes of congestions.However,the indicator of Breakdown probability is consistent with the results of comprehensive indicators.In addition,the indicator of Breakdown probability can be used to quantitatively evaluate impacts of coordination methods of Breakdown probability.The ramp metering can reduce the Breakdown probability by 7 % while the installation of exclusive bus lanes increases the probability by 12 %.The comprehensive evaluation indicator can balance the differences between the results of Breakdown probability indicator and traffic delay indicator,which can get a comprehensive evaluation of control schemes.
Transportation Planning and Management
A Traffic Density Estimation and Congestion Identification of Urban Freeways Based on Kalman Filter
ZHANG Chiyuan, CHEN Yangzhou, GUO Yuqi
2017, 35(5): 55-61,82. doi: 10.3963/j.issn.1674-4861.2017.05.007
Abstract(344) PDF(0)
Abstract:
For the situation where only a part of traffic detectors are available to obtain traffic information in urban freeway networks,a Kalman filter based ona macroscopic traffic flow model is studied in order to accurately estimate traffic density,and moreover,to quickly identify traffic congestion of all road sections.A macroscopic traffic flow model of urban freeway networks is developed by combining Dynamic Graph Hybrid Automata (DGHA) with Cell Transmission Model (CTM),and a Piecewise Affine Linear System (PWALS) model is deduced.Traffic density is estimated in the switched Kalman filter designed by this model,and congestion of urban freeway networks can be identified by comparing the road density estimation with the critical congestion density.The experiment takes Jingtong freeway in Beijing as a case study,and the Mean Absolute Error (MAE) which is generated by estimated value and actual value is 0.625 988.The resuits indicate the effectiveness of the proposed method.
A Prediction Approach of Short-term Passenger Flow of Rail Transit Considering Dynamic Volatility
DUAN Jinxiao, DING Chuan, LU Yingrong, MA Xiaolei
2017, 35(5): 62-69. doi: 10.3963/j.issn.1674-4861.2017.05.008
Abstract(395) PDF(1)
Abstract:
Previous methods on forecasting passenger flow of rail transit lacks consideration of dynamic volatility,and cannot predict the range of short-term passenger flow.Taking typical rail transit stations in Beijing as a case study,an ARIMA-GARCH model is established to simulate the prediction interval (PI),and fit the stochastic volatility of shortterm passenger flow.The effect of "sharp peak and heavy tail" is analyzed by using t distribution.The asymmetry volatility effects are addressed by using T-GARCH and E-GARCH models.Results show that the integrated ARIMA-GARCH models can significantly reduce the mean prediction interval length (MPIL) in forecasting passenger flow by more than 20%,and improve the prediction interval coverage probability (PICP) by about 1%.It is also found that volatility of passenger flow in weekdays is larger than weekends,while no evident volatility exists during non-peak hours.Note that,an ARIMA-GARCH model will not significantly reduce mean absolute prediction error (MAPE).However,the hybrid models can accurately forecast the range of passenger flow of rail transit under the premise of ensuring single-point forecasting.

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