Top Read

Published in last 1 year |

In last 2 years |

In last 3 years |

All

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

Method for Identifying Dangerous Driving Behaviors in Heavy-duty Trucks Based on Multi-modal Data WUJianqing, ZHANG Ziyi, WANG Yubo, ZHANGYu, TIANYuan Journal of Transportation Systems Engineering and Information Technology    2024, 24 (2): 63-75.   DOI: 10.16097/j.cnki.1009-6744.2024.02.007 Abstract （697）      PDF （3402KB）（372）       This paper proposes a multi-modal method to identify dangerous driving behaviors of heavy-duty trucks, which integrates driving operation data, eye-tracking data and electrocardiogram (ECG) data in the analysis. A naturalistic driving experiment is designed to collect driving data using three types of devices: vehicle inertial navigation systems, eye-tracking decoders, and physiological data recorders. A multi-modal driving dataset is established through data synchronizing and data cleaning processes. The dangerous driving behaviors are divided into two categories: dangerous manipulation behaviors and fatigue driving behaviors. By extracting data features, nine dangerous driving behavior indicators are defined to represent five types of dangerous driving behaviors, including speeding, unstable speed, rapid speed changing, rapid lane changing, and fatigue driving. For dangerous manipulation behaviors, characteristic thresholds are determined through literature review, indicator calculation, and interquartile range method. For fatigue driving behaviors, fatigue driving levels are identified through factor analysis and K-means clustering methods. A random forest (RF) classification model is then developed to identify dangerous driving behavior. When compared to traditional methods, including back propagation neural network (BPNN), K-nearest neighbors (KNN), support vector machine (SVM), the proposed model surpassed others in terms of accuracy and fitting performance. The model achieved a classification accuracy of over 90% for all types of dangerous driving behaviors. The results prove that the proposed methods are effective in identifying dangerous driving behaviors and it provides a theoretical basis for multimodal warning systems of dangerous driving behaviors.

Select

Vehicle Trajectory Prediction Based on Mixed Teaching Force Long Short-term Memory FANG Hua-zhen, LIU Li, XIAO Xiao-feng, GU Qing, MENG Yu Journal of Transportation Systems Engineering and Information Technology    2023, 23 (4): 80-87.   DOI: 10.16097/j.cnki.1009-6744.2023.04.009 Abstract （669）      PDF （2292KB）（372）       To improve the long-term trajectory prediction of the intelligent connected vehicle to the surrounding vehicles, this paper proposes an interaction-aware network framework based on mixed teacher forcing Long Short�Term Memory (LSTM) encoder-decoder. First, a trajectory prediction dataset is established through feature selection and trajectory sequence labeling. Then, the LSTM encoder-decoder model is developed. The encoder encodes the historical trajectory of the target vehicle, the information of surrounding vehicles, and the road environment into the context vector. The decoder adopts the mixed teaching mode to decode the context vector dynamically into the future trajectory. At last, the model is verified on the real road datasets NGSIM US101 and I-80 and compared with the traditional models. The experimental results show that the proposed model performs better than the traditional methods in long-term prediction. The 5 seconds final displacement error is 2.7 meters. The accuracy of the model after sparse sampling has been significantly improved compared with other methods, the 5 seconds final displacement error is 1.3 meters.

Select

Analysis of Residents' Travel Mode Choice in Medium-sized City Based on Machine Learning LI Wenquan, DENGAnxin, ZHENGYan, YIN Zijuan, WANG Baifan Journal of Transportation Systems Engineering and Information Technology    2024, 24 (2): 13-23.   DOI: 10.16097/j.cnki.1009-6744.2024.02.002 Abstract （616）      PDF （3143KB）（567）       This paper aims to investigate the characteristics of travel behaviors and the influencing factors on travel mode choice in a medium-sized city. Utilizing travel data from a medium-sized city in China, a random forest model embedded with a particle swarm optimization algorithm adding a variation procedure (PSO-RF) was proposed for travel mode choice prediction, due to the distinctions in prediction accuracy and modeling rationality of discrete choice model and machine learning model, as well as the characteristics and efficiency of hyperparameter optimization algorithms. The predictive accuracy, predictive mode proportion's absolute deviation, and expected simulation error were used to statistically compare the predictive performance among PSO-RF, machine learning models, and the multinomial Logit model. The SHAP (SHapley additive exPlanation) model was employed to thoroughly analyze the nonlinear relationships among individual socio-economic attributes, travel attributes, mode attributes, and residents' travel mode choices. The results indicate that PSO-RF has the highest average overall prediction accuracy (0.856), and the lowest average predictive mode proportion's absolute deviation (0.062) and average expected simulation error (0.306). Statistically significant differences in models' predictions are observed. Distance has the most prominent impact on the choice of different travel modes. The modes of walking and private cars show higher sensitivity to distance, with probability changes exceeding 35% at different distances. Individuals under 30 years old exhibit greater variations in the probability of choosing different travel modes compared to other age groups. Gender, car ownership, and bus IC card ownership notably affect the probability of choosing a bus and a private car.

Select

Impact of Charging and Incentive Strategies on Commuting Mode Choice WANGDianhai, LIYiwen, CAI Zhengyi Journal of Transportation Systems Engineering and Information Technology    2024, 24 (2): 1-12.   DOI: 10.16097/j.cnki.1009-6744.2024.02.001 Abstract （592）      PDF （2668KB）（554）    PDF(English version) （436KB）（4）    This paper investigates the regulatory impact of two traffic demand management strategies, tolls and rewards, on travel mode choices, using the main urban area of Hangzhou as a case study. The stated preference (SP) and revealed preference (RP) surveys were performed to understand the intention of private car commuters' mode choice under parking charge and travel reward scenarios. The disaggregate theory was used to establish Nested Logit (NL) models for commuting mode selection under separate and joint implementation of parking fees and travel rewards. The results indicate that both parking fees and travel incentives can reduce private car travel demand and promote public transportation. Only when the parking price reaches a certain level can private car trips be effectively reduced, and appropriate incentives can actively encourage travelers to switch to other modes of travel. If charging and incentive strategies are implemented simultaneously, it will manifest a joint effect of charging as the main approach and incentive as a supplement. In all three scenarios, income is a significant factor influencing travel mode choices. The higher the income, the more likely the continuation of private car usage. In the scenario with only a parking fee, the elasticity of parking fees increases with the rate; there are limited elasticity when the rate is low. The elasticity of travel rewards initially raises and then drops with the increase in the reward amount; Small rewards also show elasticity.

Select

Empirical Study on Carbon Dioxide Emissions and Atmospheric Environment Impact of Urban Public Passenger Transportation CHEN Dan, YU Hui, TANG Cheng, CHEN Zhi-xiong, TANG Miao Journal of Transportation Systems Engineering and Information Technology    2023, 23 (4): 1-10.   DOI: 10.16097/j.cnki.1009-6744.2023.04.001 Abstract （560）      PDF （1881KB）（430）       This paper proposes a novel medium-and long-term prediction method for carbon dioxide emissions and their atmospheric environmental impact on public passenger transportation, which can facilitate the improvement of transportation structure and the high-quality development of green low-carbon transportation. To handle the issue of unclear method and incomplete data accumulation of carbon emissions and their atmospheric environmental impact in China's public passenger transportation, a micro calculation model for carbon dioxide emissions from public passenger transportation is proposed in this paper. Then a new medium-and long-term prediction method for carbon dioxide emissions is presented based on a dynamic linear model, which can accurately capture the development trend of transportation demand and micro characteristics of transportation behavior. On this basis, a linear climate response model-based carbon dioxide emissions prediction method is proposed to forecast the medium-and long-term atmospheric environmental impact of the carbon emissions from China's public passenger transportation. Several major public passenger transportation modes, including urban rail transit, traditional & new energy cruise taxis, traditional & new energy buses, high-speed rail, and civil aviation, are studied to verify the effectiveness of the proposed method. The results show that carbon emissions from China's public passenger transportation will keep rising in the next 10 years, with the largest amount of carbon emissions from civil aviation accounting for 71.72%. Besides, the impact of the carbon emissions from public passenger transport on the atmospheric environment will increase rapidly as well, where civil aviation has the largest impact accounting for 69.26% , and urban rail transit has the smallest impact accounting for 1.35%.

Select

Calculation for Carbon Emission Reduction Effect of Urban Rail Transit Based on Carbon Recovery Period Theory YANG Yang, WANG Xue-chun, YUAN Zhen-zhou, CHEN Jin-jie, NA Yan-ling Journal of Transportation Systems Engineering and Information Technology    2023, 23 (5): 1-11.   DOI: 10.16097/j.cnki.1009-6744.2023.05.001 Abstract （514）      PDF （2003KB）（581）    PDF(English version) （1142KB）（33）    Reasonable quantification of the carbon emission reduction effect of urban rail transit has theoretical and practical significance to calculate the external cost of urban rail transit, enrich the theoretical system of carbon trading in the field of transportation, and even formulate subsidy policies for urban rail transit. This paper considered the passengers' travel behavior difference after the construction of urban rail transit, and established the carbon emission model of urban rail transit datum line and project activity from the perspective of life cycle. Furthermore, a theoretical model of carbon recovery period was established as a quantitative indicator of carbon emission reduction effect of urban rail transit. Carbon recovery period refers to the duration of carbon emission recovery toward the construction period through carbon emission reduction during the operation period, which is the time when the cumulative carbon footprint changes from positive to negative for the first time. Then, the urban rail transit data collection was completed in the datum line, project construction and activity period, and the model is calibrated. The Shijiazhuang Subway Line 3 was taken as a case study, the carbon emissions of its datum line, the project construction period and the project activity period were analyzed, and the carbon recovery period was calculated under the two models of future development. The results show that the carbon recovery period is respectively 27 years, 22 years and 29 years under normal, rapid, and slow growth scenarios. Under the scenario of normal development of energy structure and energy efficiency level, rapid development and slow development, the carbon recovery period is respectively 25 years, 24 years and 29 years. The conclusions indicate that large-scale passenger volume and efficient passenger transportation intensity are important elements for the positive impact of carbon emission reduction in urban rail transit. The systematic changes brought about by the adjustment of energy structure and the energy efficiency improvement can have a great positive impact on the carbon emission reduction of urban rail transit.

Select

Prediction of Transportation Industry Carbon Peak in China LI Ninghai, CHEN Shuo, LIANG Xiao, TIAN Peining Journal of Transportation Systems Engineering and Information Technology    2024, 24 (1): 2-13.   DOI: 10.16097/j.cnki.1009-6744.2024.01.001 Abstract （513）      PDF （2327KB）（609）    PDF(English version) （684KB）（2）    Transportation industry faces a series of challenges under the strategy of "carbon peak" due to the high carbon emissions. This paper analyzes the current situation of the carbon emissions in passenger and freight transportation in China. Based on the statistical data and relevant research results, this study simulates the carbon emissions of the transportation industry including private cars. The carbon emission factors of each transportation mode are calculated. The trend of passenger and freight turnover in 2019 to 2040 is predicted based on the experience of some developed countries. Taking 2040 as the target year, the scenarios of future transportation structure and carbon emission factors were designed, and the time and value of carbon peak for transportation in China are estimated. The results show that the transportation carbon emission, including private cars, is 1.11 billion tons in 2020. It is predicted that the passenger transportation demand will be 8.2 to 8.7 trillion person-kilometers, and the freight transportation demand will be 27.3 to 28.7 trillion tonnage kilometers in 2040. It is verified that it would be difficult to achieve the carbon peak before 2040 only through improving the transportation structure, and it is also significantly important to promote the upgrading of clean transportation technology. The scenario analysis shows that the transportation industry is expected to achieve the carbon peak in 2031 to 2034 by encouraging the transformation of transportation structure such as "road to rail" and "road to water", and promoting the cleanliness of roadway transportation.

Select

Prediction Model for Residents Travelling OD in Urban Areas Based on Mobile Phone Signaling Data HU Bao-yu, LIU Xue Journal of Transportation Systems Engineering and Information Technology    2023, 23 (6): 296-306.   DOI: 10.16097/j.cnki.1009-6744.2023.06.029 Abstract （511）      PDF （3125KB）（405）    PDF(English version) （1242KB）（27）    To reveal the travel pattern and OD generation principle of urban area residents, the destination selection mechanism of urban area residents is explored based on mobile phone signaling data. The position opportunity selection (POS) model was developed by considering the population and the number of POI. The mobile phone signaling travel data of Harbin residents, obtained from the Unicom Smart Footprint Platform, is used to validate the model. The analysis is conducted at both the traffic cell and traffic mid-zone levels, focusing on Harbin's second, third, and fourth ring roads. The results show that the POS model predictions were generally consistent with the actual data patterns in the traffic attraction capacity and travel distance distributions. At both the traffic cells and mid-zones scales, the model achieves a prediction accuracy of 67% ~72% and 75% ~83% , respectively. These results indicate an improvement of 13%~18% and 9%~20% over the opportunity priority selection model and a superiority of 57%~60% and 55%~60% over the radiation model, respectively. The advantage of the proposed model lies in its simplicity and lack of parameters. The input data are easily obtainable, and the model offers high prediction accuracy. The findings provide a theoretical reference for urban traffic planning.

Select

Signalized Intersection Eco-driving Strategy Based on Deep Reinforcement Learning LI Chuanyao, ZHANG Fan, WANG Tao, HUANG Dexin, TANG Tieqiao Journal of Transportation Systems Engineering and Information Technology    2024, 24 (1): 81-92.   DOI: 10.16097/j.cnki.1009-6744.2024.01.008 Abstract （510）      PDF （2473KB）（478）    PDF(English version) （2399KB）（2）    Eco-driving in a connected and autonomous driving environment has great potential to improve traffic efficiency, energy saving, and emission reduction. This paper proposes a prosocial eco-driving strategy based on the deep reinforcement learning algorithm that optimizes the longitudinal manipulation and lateral decision-making of the connected and automated vehicle (CAV). The state space is divided into the local variables related to dynamic vehicle characteristics and the global variables associated with signalized intersection to ensure adequate interaction between the CAV and the roadway environment. The designed reward function integrates the vehicle driving requirements, synergy with signals and global energy saving incentives. In addition, this study developed a typical urban road intersection scenario to train the model. The results show that the proposed strategy can achieve eco-driving of the CAV in collaboration with the signal and output lateral control to ensure the vehicle travels to the target lane. In addition, simulations in a dynamic traffic environment reveal that the proposed method can improve the capacity at the intersection by about 17.90% and reduce the traffic system's fuel consumption and pollutant emissions by approximately 8.76% through the control of multiple CAVs to guide the human-driven vehicles.

Select

Variable Speed Limit Control Based on Improved Dueling Double Deep Q Network Under Mixed Traffic Environment HAN Lei, ZHANG Lun, GUO Wei-an Journal of Transportation Systems Engineering and Information Technology    2023, 23 (3): 110-122.   DOI: 10.16097/j.cnki.1009-6744.2023.03.013 Abstract （494）      PDF （7199KB）（250）       Existing variable speed limit (VSL) control strategies suffer from poor flexibility, slow response time, and a heavy reliance on the compliance rate and traffic flow prediction models. Additionally, it is difficult to achieve effective control by relying solely on variable message signs (VMS) to post speed limits to drivers in the mixed traffic environment where connected and automated vehicles (CAVs) and human-driven vehicles (HDVs) coexist. To this end, this paper proposes a VSL control strategy based on the improved dueling double deep Q network (IPD3QN) under the mixed traffic flow environment, i.e., IPD3QN-VSL. This strategy integrates the ability of deep reinforcement learning to automatically adapt to complex environments without establishing traffic flow prediction models, and the advantages of controllability of CAVs. Firstly, the prioritized experience replay mechanism is introduced into the dueling double deep Q network (D3QN) framework of deep reinforcement learning to enhance the convergence speed and parameter update efficiency of the network. Meanwhile, a novel adaptive ��-greedy algorithm is proposed to solve the problem of balance between exploration and utilization in D3QN’s learning process. The proposed VSL control strategy aims to minimize the total time spent (TTS) of vehicles on the freeway section. Real-time traffic data and speed limits within the previous control cycle are used as inputs to the IPD3QN algorithm. Then, a reward function is constructed to guide the algorithm to generate the dynamic speed limit value executed in the VSL control area. Finally, the effectiveness of the IPD3QN-VSL control strategy is verified under different conditions and compared to no control, feedback control, and D3QN-VSL control in terms of control performance. Analysis results indicate that the proposed strategy can achieve remarkable control performance at a 30% penetration rate and effectively improve bottleneck traffic efficiency and reduce the spatiotemporal range of traffic congestion in both stable and fluctuating demand scenarios. Compared to the suboptimal D3QN-VSL control, the proposed strategy can achieve improvements of 14.46% and 10.36% on TTS in stable and fluctuating traffic demand scenarios, respectively.

Select

Urban Transportation Management from Perspective of General Spatial Equilibrium: Review and Trend XU Shu-xian, LIU Tian-liang, WANG Ting, XIAN Kai, HUANG Hai-jun, MA Shou-feng Journal of Transportation Systems Engineering and Information Technology    2023, 23 (3): 6-19.   DOI: 10.16097/j.cnki.1009-6744.2023.03.002 Abstract （491）      PDF （8507KB）（379）    PDF(English version) （660KB）（65）    Urban transportation is the foundation of urban social and economic activities. Coordinated development of urban transportation and land use is of great practical significance to reduce traffic congestion, optimize the urban spatial structure, and realize sustainable urban development from the root of problems. With the development of urban society and the advancement of urbanization, as well as the low-carbon, green, and intelligent development trend of the transportation system, traditional urban transportation strategies purely focusing on supply or demand management cannot meet the needs of rapid urban development and the aspirations of the people to live a better life. Urban transportation management needs to focus on comprehensive governance of employment, housing, and transportation and dynamic equilibrium of supply and demand, to realize the coordinated and integrated development with urban spatial layout and land use. Based on the general spatial equilibrium theory, the literature on urban travel behavior analysis, travel demand management, transportation infrastructure supply, and supply-demand coupling strategies are systematically reviewed in this paper. Besides, the theoretical models, methods, and research problems in this area are also reviewed. It is found that the existing models cannot describe the dynamic process of urban development and the reality of China, and the related studies still focused on the traditional transportation management research problems. In the context of urban renewal, new territorial space planning systems, new transportation technologies and travel patterns, and big data, it is suggested that there is great potential for urban transportation management research from the perspective of general spatial equilibrium. It needs urgently a breakthrough in the corresponding theories and methods. Further research directions are proposed: the first is to analyze the influencing factors of residents' utility in the process of urban development, and put forward household utility decision-making theories and models under the integrated transportation and urban development; the second is to do activity/travel behavior analysis and management based on the data-driven and theory-driven methods; the third is to explore the impact of new technologies and modes of the transportation system on urban spatial structure and traffic characteristics, and study urban transport management issues for the era of digitization and intelligence; and the fourth is to explore theories and methods of urban space reshaping guided by transportation under urban renewal.

Select

A Rescheduling Optimization Method for Metro Trains Under Cross-line Operation ZHANG Xi-ran, CHEN Shao-kuan, ZHAO Xing-dong, WANG Zhuo Journal of Transportation Systems Engineering and Information Technology    2023, 23 (4): 164-174.   DOI: 10.16097/j.cnki.1009-6744.2023.04.017 Abstract （485）      PDF （2358KB）（297）    PDF(English version) （1827KB）（32）    The cross-line operation makes emergency train timetable rescheduling complex. In order to handle a reduction of passing capacity in a line section, train timetables of metro lines are rescheduled by integrating five strategies including short-turning, service cancellation/insertion, and cross-line cancellation/restoration. A train timetable rescheduling optimization model is proposed to minimize the delay of trains and the traveling time of passengers, in which operational safety, occupation of sidings, circulation of rolling stocks, and dynamic passenger flow are considered. A solution algorithm incorporating the non-dominated sorting genetic algorithm Ⅱ and timetable recalculation algorithm under cross-line operation is addressed to solve the proposed model, and the effectiveness of the proposed model and algorithm are verified by a case study. The results from the case study show that: compared with rescheduled timetables in which the original cross-line operation scheme is completely maintained or changed to an independent operation, the proposed method is able to effectively reduce the passenger traveling time by 3.86% and reduce the train delay by 21.07%. The stability of train rescheduling will be increased if the buffer time of cross-line operation is long, and the average passenger transfer waiting time and train delay are further reduced by 4.06% and 3.77% respectively.

Select

Multimodal Transportation Route Optimization for Long and Bulky Cargo Considering Carbon Emissions WANGJuan, CHENGYuli, YANGYuhan, ZHANGYinggui Journal of Transportation Systems Engineering and Information Technology    2024, 24 (4): 1-11.   DOI: 10.16097/j.cnki.1009-6744.2024.04.001 Abstract （478）      PDF （1887KB）（504）       Long and bulky cargo has the characteristics of large outline, overweight and high cost and cannot be disassembled during the transportation process. Multimodal transportation is becoming the first choice of long and bulky cargo transportation, the core of which is route decision problem. In this paper, an energy consumption factor is introduced, and calculation formulas of carbon emissions during the transportation and reconstruction and reloading process at the node for long and bulky cargo multimodal transportation are all proposed. Then, taking into consideration the following factors, i.e., loading outline, gauge, bridge bearing capacity and reloading capacity at the nodes, and road reconstruction, a multimodal transportation route optimization model for long and bulky cargo with carbon emissions is proposed with the objective of minimizing multimodal transportation cost and carbon emissions. In addition, an adaptive genetic algorithm with an elite retention strategy is designed for the multimodal route decision for long and bulky cargo considering carbon emissions. Numerical results show that, compared with the traditional genetic algorithm and the adaptive genetic algorithm, the objective value of the proposed method is 20% higher and its cost and carbon emissions are 12% and 22% lower, respectively. The route plan by the proposed method can consider transportation cost and carbon emissions simultaneously, which can provide support to solve the multimodal route decision problem for long and bulky cargo and also reduce the cost and increase the efficiency in logistics and achieve the "dual-carbon" target.

Select

Intra-driver Heterogeneity Prediction and Modeling Based on Naturalistic Driving Experiment ZHANG Duo, RAO Hong-yu, LIU Jia-qi, WANG Jun-hua, SUN Jian Journal of Transportation Systems Engineering and Information Technology    2023, 23 (5): 33-44.   DOI: 10.16097/j.cnki.1009-6744.2023.05.004 Abstract （451）      PDF （2856KB）（459）       To provide reliable support for car-following behavior in traffic flow modeling research and advanced driving assistance systems, this study proposes a method for predicting and modeling the intrinsic heterogeneity of driver following behavior based on the Transformer deep learning model and considers individual driver's behavior changes in the car-following process. This study is based on a large-scale naturalistic driving experiment, which involved over 200000 kilometers of naturalistic driving records. First, the baseline models are developed using longterm behavioral observations of 41 drivers, and 3194 intra-driver heterogeneity events are identified and extracted according to the baseline model. Further, a deep learning predictor based on the Transformer multi-head self-attention mechanism is designed to accurately predict intra-driver heterogeneity events of drivers. The results show that the predictor performs better than the long short-term memory network in predicting the three-class time points of carfollowing intra-driver heterogeneity, with an F1 score of 87.13%. Based on prediction results, dynamic car-following parameter switching can reduce the driving behavior modeling error by 21.08%. The research results help to understand the behavioral response mechanism of drivers, and further improve the accuracy of traffic flow simulation and the design of personalized control strategies.

Select

Natural Peak Characteristics and Peak Forecast of Carbon Emissions in Transportation Industry YANGDong, LIYanhong, TIAN Chunlin Journal of Transportation Systems Engineering and Information Technology    2024, 24 (2): 34-44.   DOI: 10.16097/j.cnki.1009-6744.2024.02.004 Abstract （439）      PDF （3274KB）（284）       The peak of carbon emissions in the transportation industry is a natural long-term evolutionary process. In order to study the process of carbon peaking in China's transportation industry, this paper adopts the international analogy method, selects typical foreign countries, and compares the time of the peaks of the overall national carbon emissions, transportation industry carbon emissions, and converted turnover. The natural peak characteristics of transportation industry carbon emission are analyzed and the time of the natural peaks of carbon emissions in China's transportation industry is predicted according to transportation demand forecast. Then, the STIRPAT (Stochastic Impacts by Regression on Population, Affluence, and Technology) prediction model is constructed by introducing the core influencing factors such as carbon emissions per unit of converted turnover and the ratio of railroad to road freight transportation. Finally, through analogical analysis and model prediction, the time and volume of peak carbon emissions of China's transportation sector are obtained. The results of the international analogy show that there is no clear causal relationship between the peak carbon emissions of the transportation industry and the national peak carbon emissions, but it is closely related to the peak converted turnover, and the converted turnover reaches the peak or is close to the peak when the carbon emissions of the transportation industry reach the peak. It is predicted that China's converted turnover will reach a plateau period of 26 trillion ton-kilometers in about 2048. From the perspective of the international analogy, the time of the natural peak of China's carbon emissions from transportation is roughly roughly between 2040 and 2043. The STIRPAT model shows that the carbon emissions of China's transportation industry will increase by 1.201%, 0.259%, 0.454%, and-0.389%, respectively, for every 1% increase in urbanization rate, per capita GDP, carbon emissions per unit converted turnover, and railway- road freight ratio. Based on the combination prediction of international analogy and STIRPAT model, China's transportation industry will achieve peak carbon emissions in 2038-2040, with about 1.3 billion tons.

Select

Analysis and Improvement Strategy on Freeway Traffic Capacity in Foggy Weather QIN Yan-yan, XIAO Teng-fei, HE Zheng-bing Journal of Transportation Systems Engineering and Information Technology    2023, 23 (3): 39-47.   DOI: 10.16097/j.cnki.1009-6744.2023.03.005 Abstract （432）      PDF （4175KB）（289）       This paper studies the freeway traffic capacity in foggy weather. An improvement strategy for freeway traffic capacity in foggy weather is proposed based on vehicle-to-vehicle (V2V) communications. Firstly, a Gipps model calibrated in foggy weather was selected to describe the car-following behavior, and its spacing-speed function was derived to construct the analysis method of freeway capacity. Secondly, the influence of traffic capacity was analyzed from the perspectives of different foggy scenes and speed limit conditions. Under the influence mechanism by foggy weather, we conducted sensitivity analyses on driver reaction time T n, the maximum brake deceleration b n of the following vehicle, and the estimated maximum brake deceleration b n-1 of the front vehicle by the follower. Finally, considering the influence of the driver reaction time and the braking deceleration on traffic capacity, a car-following control strategy for improving freeway capacity was proposed based on foggy V2V conditions. The results show that speed limit values of 80 km · h -1 and 100 km · h -1 will lead to the maximum traffic capacity under light fog (visibility of 150 meters) and heavy fog (visibility of 60 meters) conditions, respectively. Both conditions of light fog and heavy fog have the minimum traffic capacity when 60 km · h -1 is selected as the speed limit value. Compared with the speed limit of 40 km · h -1, the maximum traffic capacities corresponding to the speed limit of 80 km · h -1 in light fog and 100 km · h -1 in heavy fog increase by 21.83% and 9.68%, respectively. Additionally, the minimum traffic capacities corresponding to the speed limit of 60 km · h - 1 are reduced by 15.88% and 4.61% under light fog and heavy fog conditions, respectively. Traffic capacity improves with the decrease of the driver reaction time and it is positive for capacity improvement when b n-1> b n. The proposed control strategy can effectively improve the freeway capacity in foggy weather, and the control strategy has a significant effect on the improvement of traffic capacity with a confidence level of 95%. The average improvement percentage is 44.22% under different foggy scenes and speed limit conditions.

Select

Nested Logit Model of Elderly Travel Mode Choice Based on Boundedly Rationality ZHANG Bing, TAO Wen-kang, LIU Jian-rong, XUE Yun-qiang, DENG Ming-jun Journal of Transportation Systems Engineering and Information Technology    2023, 23 (6): 74-82.   DOI: 10.16097/j.cnki.1009-6744.2023.06.008 Abstract （426）      PDF （1656KB）（235）       To study the travel mode choice behavior of the elderly group and improve the travel mode convenience and accessibility for the elderly people, this paper proposes a travel mode choice model that meets the needs of the elderly group. Based on the traditional Logit model, the nested Logit model is used to improve the assumption of maximum traveler utility in the model. Taking the elderly travel group as the research object, the model is hypothesized based on the bounded rational satisfactory decision criterion, and the indifference threshold is introduced to establish the bounded rational nested Logit model that represents the elderly travel group. Then, taking the travel mode choice strategy data of the elderly group in Nanchang city as an example, the double-nested continuous average algorithm is used to solve and analyze the model. The results show that: (1) The elderly traveler group does not always choose the transportation mode with the lowest travel cost, and its mode choice behavior is affected by their degree of rationality and travel preferences. (2) The no-difference thresholds between nests of different travel modes interact with each other and gradually stabilize the mode choice probability between nests as the no- difference threshold increases; (3) The mode choice behavior of elderly travelers is affected by their rationality and preference, and when the travel cost differential is in one of the undifferentiated intervals of whether older people are able to make limited rational judgments, the probability of choosing public transportation changes with the propensity coefficient and stabilizes gradually as the propensity coefficient increases.

Select

Substituted Relationship Between Ride-hailing and Public Transit and Emission Reduction Potential LV Ying, HE Lu-lu, SUN Hui-jun, XU Guang-tong Journal of Transportation Systems Engineering and Information Technology    2023, 23 (4): 11-23.   DOI: 10.16097/j.cnki.1009-6744.2023.04.002 Abstract （417）      PDF （3983KB）（260）       As a popular travel mode, ride-hailing has changed people's travel choices to some extent, which makes some passengers who used to take public transit turn to ride-hailing. The resulting substituted relationship between ride�hailing and public transit will have a certain impact on urban transport carbon emissions, and it is necessary to conduct in-depth research. Based on the comparison of utility functions, this paper uses the ride-hailing order data in Chengdu to infer whether the ride-hailing service has the chance to be replaced by public transit. From the OD (Origin Destination) level, this paper analyzes the characteristics of replaceable and irreplaceable trips by public transit and the emission reduction potential of the urban public transit system. The results show that 54.16% of all ride-hailing orders have a potential substituted relationship with public transit. Travel time and travel cost are the main factors that affect passengers' choices. When the public transit travel plan only includes subway travel or subway travel distance accounts for a relatively high proportion, it is more likely to show that there is a potential substituted relationship between ride�hailing and public transit. If public transit has the opportunity to replace some ride-hailing trips, it will lead to a reduction of about 45.59% in carbon emissions. The periods and areas with the greatest emission reduction potential are between 10:00 and 17:00, as well as areas near urban centers and subway lines. This study can provide decision support for relevant government departments to improve the service level and utilization efficiency of public transit by implementing effective means, and thus reduce the carbon emissions of the urban transport system.

Select

Traffic Demand Prediction Method Based on Deep Learning for Dynamic Traffic Assignment LI Yan, WANG Taizhou, XU Jinhua, CHEN Jianghui, WANG Fan Journal of Transportation Systems Engineering and Information Technology    2024, 24 (1): 115-123.   DOI: 10.16097/j.cnki.1009-6744.2024.01.011 Abstract （417）      PDF （2045KB）（305）       This paper proposes a deep learning traffic demand prediction method to meet the requirements of high accuracy and time sensitivity in dynamic traffic assignment. The time interval of traffic demand data is determined based on the requirements of dynamic traffic assignment. A prediction method using long short-term memory neural network is established for better performance in complex traffic demand. Combining the periodicity, randomness and nonlinearity of traffic demand in dynamic traffic assignment, this study uses a time series decomposition method to decompose the traffic demand data and to reduce the interference of data noise. The trend component and residual component are used as the input of the deep learning prediction method. Meanwhile, the periodic component is predicted using the cycles. The key parameters of the prediction method, such as the number of hidden layer units, learning rate and training iterations, are optimized by using the cuckoo search algorithm, which is characterized by strong random optimization ability and high optimization efficiency. The proposed method is verified using the checkpoint data in Chang'an District of Xi'an, China. In each of the four consecutive periods of peak and off peak, the results of proposed method are compared with the auto regressive moving average model, the long short-term memory model, and the support vector regression model. The results indicate a reduction of the average absolute error of 10.55% to 19.80%, a reduction of the root mean square error of 11.20% to 17.99%, and the coefficient of determination increased by 8.62% to12.48% . Compared with the models optimized by genetic algorithm and particle swarm optimization, the proposed model reduced the average absolute error by 7.36% to 13.81% and reduced the root mean square error by 4.23% to 10.67%. The coefficient of determination increased by 3.50% to 7.01%. The proposed model has the shortest running time. Compared with the traditional methods, the proposed prediction method has higher prediction accuracy in the traffic demand prediction for dynamic traffic assignment.

Select

Route and Speed Optimization for Green Intermodal Transportation Considering Emission Control Area WU Peng, LI Ze, JI Hai-tao Journal of Transportation Systems Engineering and Information Technology    2023, 23 (3): 20-29.   DOI: 10.16097/j.cnki.1009-6744.2023.03.003 Abstract （414）      PDF （5114KB）（458）       This study solves a new green high-seas multimodal transportation route and speed optimization problem considering emission control areas. This study first formulates a multi-objective mixed integer nonlinear programming model under different carbon emission policies and transforms the nonlinear model into an equivalent mixed-integer linear programming model according to the problem characteristics. To effectively solve the models, an improved adaptive genetic algorithm (IAGA) incorporating the characteristics of the problem is proposed, in which a customized multi-layer coding and decoding mechanism and an adaptive genetic evolution operator are proposed. Finally, a case study from the high-sea multimodal transportation system in China is conducted to demonstrate the viability of the proposed model and algorithm and a sensitivity analysis is also done for various time frames and low-sulfur fuel costs. The numerical experimental results show that: 1) Compared with a traditional genetic algorithm and the commercial solver Lingo, the improved adaptive genetic algorithm results in more satisfactory solutions and reduces total multimodal transportation costs by 5.2% and 3.7% . 2) Under the mandatory carbon emissions policy, changes in emission allowances typically do not affect the choice of the route made by an operator, but only affect whether the operator conducts transportation activities. Under the carbon tax policy, the overall cost of intermodal transportation is not significantly affected by the carbon tax price increase. Under the carbon trading policy, multimodal transport options with different emission allowances may be consistent. And 3) the shipping cost can lead to a direct proportion to the price of low- sulfur fuel, and adopting different ship speeds inside and outside the emission control areas can bring clear economic advantages.