Users Login
Column
MORE+
01 A Cooperative Map Matching Algorithm Applied in Intelligent and Connected Vehicle Positioning
02 Indoor Sign-based Visual Localization Method
03 Intelligent Vehicles Localization Based on Semantic Map Representation from 3D Point Clouds
04 Companion Relationship Discovering Algorithm for Passengers in the Cruise Based on UWB Positioning
05 An Overview of Traffic Management in "Automatic+Manual" Driving Environment
06 An Image Generation Method for Automated Driving Based on Improved GAN
07 An Analysis of Injury Severities in School Bus Accidents Based on Random Parameter Logit Models
Display Method:
, Available online
Abstract:
, Available online
Abstract:
, Available online
Abstract:
, Available online
Abstract:
Display Method:
2024, 42(6): 1-13.
doi: 10.3963/j.jssn.1674-4861.2024.06.001
Abstract:
In order to systematically analyze and comprehensively summarize the current state of research and development trends of highway tunnel traffic safety, relevant English languageliterature published between 2000 and 2022 in this field is retrieved from the Web of Science Core Collection database. Using VOSviewer software, the literature is visually presented and analyzed to create a knowledge map of major research themes and hotspots in highway tunnel traffic safety. The research status, challenges, and development trends in this field are summarized. The results indicate that the annual publication volume of research literature on traffic safety in highway tunnels shows an overall upward trend. In terms of contributions, China leads among countries, Tongji University among institutions, and "Tunnelling and Underground Space Technology" among journals. Current research hotspots in highway tunnel traffic safety focus on topics such as the analysis ofaccident characteristics in highway tunnels, driving environment and driving performance in highway tunnels, highway tunnel lighting and its impact on driving safety, and traffic facilities in highway tunnels and their relving in highway tunnels, levation to driving safety. However, there are limitations in the evaluation methods and technical standards for highway tunnel traffic safety. The consideration of factors in the evaluation system is one-sided and inconsistent, the accuracy and validity of data sources and mathematical models still need to be improved, and the application effects of intelligent transportation technologies on highway tunnel traffic safety need further investigation. Future research in this field should prioritize the development of methods and evaluation models to enhance the driving environment in highway tunnels, considering different levels of demand. It should also focus on macro-level situation analysis and micro-level individual analysis of driving in highway tunnels, leveraging multi-source, heterogeneous, and big data. Additionally, research should study driving risk perception models and control strategies for highway tunnels, utilizing machine learning and intelligent connected vehicle technologies.
In order to systematically analyze and comprehensively summarize the current state of research and development trends of highway tunnel traffic safety, relevant English languageliterature published between 2000 and 2022 in this field is retrieved from the Web of Science Core Collection database. Using VOSviewer software, the literature is visually presented and analyzed to create a knowledge map of major research themes and hotspots in highway tunnel traffic safety. The research status, challenges, and development trends in this field are summarized. The results indicate that the annual publication volume of research literature on traffic safety in highway tunnels shows an overall upward trend. In terms of contributions, China leads among countries, Tongji University among institutions, and "Tunnelling and Underground Space Technology" among journals. Current research hotspots in highway tunnel traffic safety focus on topics such as the analysis ofaccident characteristics in highway tunnels, driving environment and driving performance in highway tunnels, highway tunnel lighting and its impact on driving safety, and traffic facilities in highway tunnels and their relving in highway tunnels, levation to driving safety. However, there are limitations in the evaluation methods and technical standards for highway tunnel traffic safety. The consideration of factors in the evaluation system is one-sided and inconsistent, the accuracy and validity of data sources and mathematical models still need to be improved, and the application effects of intelligent transportation technologies on highway tunnel traffic safety need further investigation. Future research in this field should prioritize the development of methods and evaluation models to enhance the driving environment in highway tunnels, considering different levels of demand. It should also focus on macro-level situation analysis and micro-level individual analysis of driving in highway tunnels, leveraging multi-source, heterogeneous, and big data. Additionally, research should study driving risk perception models and control strategies for highway tunnels, utilizing machine learning and intelligent connected vehicle technologies.
2024, 42(6): 14-22.
doi: 10.3963/j.jssn.1674-4861.2024.06.002
Abstract:
With the continuous expansion of the global economy and the sustained improvement of the industrial level, the demand for energy and chemical products is constantly increasing in various countries, and such chemical products are mostly classified as dangerous goods. Due to its advantages of low transportation cost, large capacity, safety, environmental friendliness, and wide transport range, waterway transportation has become the primary mode for the transport of dangerous goods. In recent years, to enhance the safety and efficiency of waterway transportation of dangerous goods, domestic scholars have conducted a large amount of research. To systematically review the current research status and future development trends in this field in China, this paper retrieved 368 relevant docu-ments published in Chinese core journals from 2015 to 2024. Through statistical analysis of the annual publication volume, journal distribution, research institutions, and key scholars of the retrieved literature, and using VOSviewer software for keyword clustering and evolutionary trend analysis, this paper summarizes the research hotspots into four main aspects: design of dangerous goods ships, management of dangerous goods transportation, transportation risk assessment, and emergency response. Current research has made certain progress in the innovation of ship design, intelligent management of transportation, precise risk assessment, and efficient emergency response, but it still faces challenges such as low intelligence in design and safety management, insufficient comprehensiveness in risk assessment, and lack of targeted emergency response equipment. Future research should focus on the application of artificial intelligence technology in the design and operational safety monitoring of hazardous material ships, as well as promoting the integration of green and low-carbon technologies in ship energy efficiency optimization and power sub-situation, to enhance the safety and sustainability of waterway transportation of dangerous goods.
With the continuous expansion of the global economy and the sustained improvement of the industrial level, the demand for energy and chemical products is constantly increasing in various countries, and such chemical products are mostly classified as dangerous goods. Due to its advantages of low transportation cost, large capacity, safety, environmental friendliness, and wide transport range, waterway transportation has become the primary mode for the transport of dangerous goods. In recent years, to enhance the safety and efficiency of waterway transportation of dangerous goods, domestic scholars have conducted a large amount of research. To systematically review the current research status and future development trends in this field in China, this paper retrieved 368 relevant docu-ments published in Chinese core journals from 2015 to 2024. Through statistical analysis of the annual publication volume, journal distribution, research institutions, and key scholars of the retrieved literature, and using VOSviewer software for keyword clustering and evolutionary trend analysis, this paper summarizes the research hotspots into four main aspects: design of dangerous goods ships, management of dangerous goods transportation, transportation risk assessment, and emergency response. Current research has made certain progress in the innovation of ship design, intelligent management of transportation, precise risk assessment, and efficient emergency response, but it still faces challenges such as low intelligence in design and safety management, insufficient comprehensiveness in risk assessment, and lack of targeted emergency response equipment. Future research should focus on the application of artificial intelligence technology in the design and operational safety monitoring of hazardous material ships, as well as promoting the integration of green and low-carbon technologies in ship energy efficiency optimization and power sub-situation, to enhance the safety and sustainability of waterway transportation of dangerous goods.
2024, 42(6): 23-30.
doi: 10.3963/j.jssn.1674-4861.2024.06.003
Abstract:
A method for recognizing risky driving behaviors using vehicle trajectory data is established to improve safety and prevent traffic accident in urban expressway merging areas. The characteristic thresholds of four types of risky driving behaviors are firstly determined using a risk assessment approach and the interquartile range method. Subsequently, drivers'risk scores (G) are calculated using the established spectrum of risky driving behaviors, enabling the classification of drivers as safe or risky. To balance the datasets, the driving risk samples are augmented by data equalization (DE) algorithms (ROS, ADASYN, and SMOTE). Combining ensemble learning (EL) algorithms (XGBoost, LGBM and AdaBoost) to build various DE-EL models for risky driving behaviors recognition. The Spearman correlation coefficient is used to optimize the input feature parameters, which include five categories: vehicle speed, acceleration and deceleration, lateral operation, position characteristics and time occupation ratio. The optimal recognition model is is determined based on precision rate, recall rate, F1 -score and AUC value. The results show that the level of driver risk is most strongly correlated with driver lateral operation and less so with vehicle speed in merging areas. The unbalanced trajectory dataset makes it difficult to effectively identify risky driving behaviors by the EL algorithm, while the DE algorithm can improve the properties of the classification algorithm. After optimizing the input feature parameters, the performance of the DE-EL recognition model improves, and the SMOTE-LGBM model is the best one with precision rate of 93.4%, recall rate of 92.1%, F1 -score of 0.927, and AUC value of 0.933. This model is applicable for recognizing, warning, intervening in risky driving behaviors in merging areas.
A method for recognizing risky driving behaviors using vehicle trajectory data is established to improve safety and prevent traffic accident in urban expressway merging areas. The characteristic thresholds of four types of risky driving behaviors are firstly determined using a risk assessment approach and the interquartile range method. Subsequently, drivers'risk scores (G) are calculated using the established spectrum of risky driving behaviors, enabling the classification of drivers as safe or risky. To balance the datasets, the driving risk samples are augmented by data equalization (DE) algorithms (ROS, ADASYN, and SMOTE). Combining ensemble learning (EL) algorithms (XGBoost, LGBM and AdaBoost) to build various DE-EL models for risky driving behaviors recognition. The Spearman correlation coefficient is used to optimize the input feature parameters, which include five categories: vehicle speed, acceleration and deceleration, lateral operation, position characteristics and time occupation ratio. The optimal recognition model is is determined based on precision rate, recall rate, F1 -score and AUC value. The results show that the level of driver risk is most strongly correlated with driver lateral operation and less so with vehicle speed in merging areas. The unbalanced trajectory dataset makes it difficult to effectively identify risky driving behaviors by the EL algorithm, while the DE algorithm can improve the properties of the classification algorithm. After optimizing the input feature parameters, the performance of the DE-EL recognition model improves, and the SMOTE-LGBM model is the best one with precision rate of 93.4%, recall rate of 92.1%, F1 -score of 0.927, and AUC value of 0.933. This model is applicable for recognizing, warning, intervening in risky driving behaviors in merging areas.
2024, 42(6): 31-41.
doi: 10.3963/j.jssn.1674-4861.2024.06.004
Abstract:
Civil aviation passengers are the main implementers of civil aviation security measures. Therefore, in order to accurately assess the risk level of civil aviation passengers, a civil aviation passenger risk assessment method based on the fusion of multi-risk factors is proposed. The risk factors associated with passengers are identified through statistical analysis, regulation and expert investigation. According to the characteristics, the risk factors associated with passengers are categorized into three main parts: possibility, hazard and severity. Combined with the control measures, a risk index system for civil aviation passengers based on multi-risk factors is constructed, which contains 7 first-level indicators and 18 second-level indicators. The interval analytic hierarchy process can fully account for the uncertainty and fuzziness of expert judgments, while the set value statistics method allows for the quantitative representation of fuzzy indicators. By combining the advantages of these two methods, a quantitative analysis method based on the combination of internal analytic hierarchy process and set value statistics method are applied to calculate the weight coefficients of the risk indicators. To meet practical application requirements, passenger security data are collected throughout the passenger journey. And a risk assessment method for civil aviation passengers, based on the fusion of multi-risk factors, is proposed to enable dynamic quantitative risk assessments throughout the entire process. The proposed method is validated using a constructed validation dataset. The experimental results show that the recall rate for high-risk passengers reached 92%, with no high-risk passengers being assessed as low risk. The recall rate for medium-risk passengers reached 96%, with only 2% of medium-risk passengers assessed as low risk. The recall rate for low-risk passengers also reached 96%, with no low-risk passengers assessed as high risk. The proposed method enables a dynamic quantification assessment of civil aviation passenger risks, effectively integrating expert knowledge and indicator characteristics. This provides a theoretical foundation for a more comprehensive, rational, and scientifically-driven analysis of risks associated with civil aviation passengers.
Civil aviation passengers are the main implementers of civil aviation security measures. Therefore, in order to accurately assess the risk level of civil aviation passengers, a civil aviation passenger risk assessment method based on the fusion of multi-risk factors is proposed. The risk factors associated with passengers are identified through statistical analysis, regulation and expert investigation. According to the characteristics, the risk factors associated with passengers are categorized into three main parts: possibility, hazard and severity. Combined with the control measures, a risk index system for civil aviation passengers based on multi-risk factors is constructed, which contains 7 first-level indicators and 18 second-level indicators. The interval analytic hierarchy process can fully account for the uncertainty and fuzziness of expert judgments, while the set value statistics method allows for the quantitative representation of fuzzy indicators. By combining the advantages of these two methods, a quantitative analysis method based on the combination of internal analytic hierarchy process and set value statistics method are applied to calculate the weight coefficients of the risk indicators. To meet practical application requirements, passenger security data are collected throughout the passenger journey. And a risk assessment method for civil aviation passengers, based on the fusion of multi-risk factors, is proposed to enable dynamic quantitative risk assessments throughout the entire process. The proposed method is validated using a constructed validation dataset. The experimental results show that the recall rate for high-risk passengers reached 92%, with no high-risk passengers being assessed as low risk. The recall rate for medium-risk passengers reached 96%, with only 2% of medium-risk passengers assessed as low risk. The recall rate for low-risk passengers also reached 96%, with no low-risk passengers assessed as high risk. The proposed method enables a dynamic quantification assessment of civil aviation passenger risks, effectively integrating expert knowledge and indicator characteristics. This provides a theoretical foundation for a more comprehensive, rational, and scientifically-driven analysis of risks associated with civil aviation passengers.
2024, 42(6): 42-54.
doi: 10.3963/j.jssn.1674-4861.2024.06.005
Abstract:
Safety is the prerequisite and baseline for the development of the low-altitude economy, and the challeng-es of safety supervision in future low-altitude airspace operations are receiving increasing attention. Addressing the difficulties faced in urban low-altitude airspace safety management, such as high airspace complexity, a wide vari-ety of aircraft types, high airspace usage density, numerous cybersecurity and data privacy risks, complex system in-tegration and interoperability, and substantial differences in laws, regulations, and standards. This paper considers the evolving trend in aviation safety management systems (SMS), which is shifting from single to diversified super-visory targets and from post-event management to real-time management. It proposes a conceptual framework for an urban low-altitude safety management system (LASMS), encompassing operational roles and structures for low-altitude airspace, safety performance indicators for urban air mobility (UAM), identification of low-altitude risk sources, risk monitoring, risk assessment, and risk mitigation. The core of LASMS is safety risk manage-ment, which emphasizes the identification, monitoring, assessment, and mitigation of risks to achieve near-real-time safety supervision of low-altitude aircraft throughout pre-flight, in-flight, and post-flight phases.In terms of manage-ment approaches and operational models, LASMS integrates multi-domain collaboration, distributed architec-tures, digital monitoring, and mitigation mechanisms to meet the rapid response requirements of future low-altitude operations. It enhances autonomy and automation, strengthens proactive safety control before and after flights, and ensures near-real-time safety management during flights. The discussion highlights key directions for the develop-ment of LASMS, driven by New Quality Productivity through technological innovation, alongside advancements in aviation safety management and operational models. The introduction of LASMS offers new perspectives and meth-odologies for low-altitude safety regulation, supporting the safe, efficient, and sustainable development of low-alti-tude airspace in the future.
Safety is the prerequisite and baseline for the development of the low-altitude economy, and the challeng-es of safety supervision in future low-altitude airspace operations are receiving increasing attention. Addressing the difficulties faced in urban low-altitude airspace safety management, such as high airspace complexity, a wide vari-ety of aircraft types, high airspace usage density, numerous cybersecurity and data privacy risks, complex system in-tegration and interoperability, and substantial differences in laws, regulations, and standards. This paper considers the evolving trend in aviation safety management systems (SMS), which is shifting from single to diversified super-visory targets and from post-event management to real-time management. It proposes a conceptual framework for an urban low-altitude safety management system (LASMS), encompassing operational roles and structures for low-altitude airspace, safety performance indicators for urban air mobility (UAM), identification of low-altitude risk sources, risk monitoring, risk assessment, and risk mitigation. The core of LASMS is safety risk manage-ment, which emphasizes the identification, monitoring, assessment, and mitigation of risks to achieve near-real-time safety supervision of low-altitude aircraft throughout pre-flight, in-flight, and post-flight phases.In terms of manage-ment approaches and operational models, LASMS integrates multi-domain collaboration, distributed architec-tures, digital monitoring, and mitigation mechanisms to meet the rapid response requirements of future low-altitude operations. It enhances autonomy and automation, strengthens proactive safety control before and after flights, and ensures near-real-time safety management during flights. The discussion highlights key directions for the develop-ment of LASMS, driven by New Quality Productivity through technological innovation, alongside advancements in aviation safety management and operational models. The introduction of LASMS offers new perspectives and meth-odologies for low-altitude safety regulation, supporting the safe, efficient, and sustainable development of low-alti-tude airspace in the future.
2024, 42(6): 55-63.
doi: 10.3963/j.jssn.1674-4861.2024.06.006
Abstract:
The takeover performance of drivers is of great significance for the safety, driving experience, and acceptance of conditionally automated vehicles. To study the impacts of driver behavior on takeover performance, a comprehensive evaluation representation index, takeover performance level (TOPL), is proposed, and a model based on an improved EWM-TOPSIS method is constructed to evaluate TOPL. The model determines the objective weight of each index using the entropy weight method (EWM), and then codes and maps each index based on the positive and negative ideal solutions in the technique for order preference by similarity to ideal solution (TOPSIS) model, thereby constructing the TOPL evaluation model. To verify the effectiveness of the model, 46 drivers participated in a human-machine co-driving takeover experiment, from which multidimensional evaluation indicators representing the safety, comfort, and smoothness of driver takeover performance are extracted. The study examines non-driving-related tasks by drivers during takeover and the impacts of the lead time for takeover requests on the level of driver takeover performance. Furthermore, the study analyzed the significant impacts of driver age and standard non-driving-related task performance on TOPL. The results show that both driver age and non-driving-related task performance scores significantly impact TOPL. Additionally, significant differences in driver mileage are observed between the mileage ranges of 50 000 to 100 000 km, 0 to 50 000 km, and 100 000 to 1 000 000 km. A significant negative correlation exists among the maximum yaw rate, maximum lateral acceleration, maximum lateral velocity, throttle depth standard deviation, and TOPL, whereas the time to reach the takeover boundary is significantly positively correlated with TOPL. In relation to varying takeover time budgets and the performance in completing non-driving tasks, TOPL exhibited the minimum takeover time budget of 4 s, and its takeover performance level is observed to be lower under conditions of emergency takeover. Additionally, when the driver's score in non-driving task completion fell below 60, TOPL recorded the highest values, and the TOPL decreases as the score increases.
The takeover performance of drivers is of great significance for the safety, driving experience, and acceptance of conditionally automated vehicles. To study the impacts of driver behavior on takeover performance, a comprehensive evaluation representation index, takeover performance level (TOPL), is proposed, and a model based on an improved EWM-TOPSIS method is constructed to evaluate TOPL. The model determines the objective weight of each index using the entropy weight method (EWM), and then codes and maps each index based on the positive and negative ideal solutions in the technique for order preference by similarity to ideal solution (TOPSIS) model, thereby constructing the TOPL evaluation model. To verify the effectiveness of the model, 46 drivers participated in a human-machine co-driving takeover experiment, from which multidimensional evaluation indicators representing the safety, comfort, and smoothness of driver takeover performance are extracted. The study examines non-driving-related tasks by drivers during takeover and the impacts of the lead time for takeover requests on the level of driver takeover performance. Furthermore, the study analyzed the significant impacts of driver age and standard non-driving-related task performance on TOPL. The results show that both driver age and non-driving-related task performance scores significantly impact TOPL. Additionally, significant differences in driver mileage are observed between the mileage ranges of 50 000 to 100 000 km, 0 to 50 000 km, and 100 000 to 1 000 000 km. A significant negative correlation exists among the maximum yaw rate, maximum lateral acceleration, maximum lateral velocity, throttle depth standard deviation, and TOPL, whereas the time to reach the takeover boundary is significantly positively correlated with TOPL. In relation to varying takeover time budgets and the performance in completing non-driving tasks, TOPL exhibited the minimum takeover time budget of 4 s, and its takeover performance level is observed to be lower under conditions of emergency takeover. Additionally, when the driver's score in non-driving task completion fell below 60, TOPL recorded the highest values, and the TOPL decreases as the score increases.
2024, 42(6): 64-73.
doi: 10.3963/j.jssn.1674-4861.2024.06.007
Abstract:
To overcome the shortcomings of the current specifications that use deterministic model to design the acceleration lane length, considering different ramp design speeds, the reasonable length of acceleration lane is investigated to meet the requirements of traffic safety and efficiency. The functional function of the acceleration lane length is established by using the length calculation model based on vehicle merging theory and introducing the reliability theory. Statistical inference is conducted on related parameters such as the minimum merging speed in the functional function. Random variables are generated and substituted into the Monte Carlo method for solving, to estimate the reliable probability of the acceleration lane length under different mainline and ramp design speeds. Combined with the standard for reliability design standard of structure and the reliability probability greater than 95%, the recommended values of the superhighway acceleration lane length corresponding to the main line design speed of 140 km/h and the ramp design speed of 30, 40, 50, 60 km/h are obtained. The rationality of the recommended value is verified by Simulation of Urban Mobility (SUMO), and the results show that the reliability probability of the acceleration lane increases as the acceleration lane length increases, and tends to be stable after reaching a certain value. The acceleration lane length is affected by the mainline design speed and the ramp design speed, and is negatively correlated with the ramp design speed under a given service level and target reliability index. Compared with the deterministic model, the design of acceleration lane length through reliability theory and traffic simulation model is more flexible and reliable.
To overcome the shortcomings of the current specifications that use deterministic model to design the acceleration lane length, considering different ramp design speeds, the reasonable length of acceleration lane is investigated to meet the requirements of traffic safety and efficiency. The functional function of the acceleration lane length is established by using the length calculation model based on vehicle merging theory and introducing the reliability theory. Statistical inference is conducted on related parameters such as the minimum merging speed in the functional function. Random variables are generated and substituted into the Monte Carlo method for solving, to estimate the reliable probability of the acceleration lane length under different mainline and ramp design speeds. Combined with the standard for reliability design standard of structure and the reliability probability greater than 95%, the recommended values of the superhighway acceleration lane length corresponding to the main line design speed of 140 km/h and the ramp design speed of 30, 40, 50, 60 km/h are obtained. The rationality of the recommended value is verified by Simulation of Urban Mobility (SUMO), and the results show that the reliability probability of the acceleration lane increases as the acceleration lane length increases, and tends to be stable after reaching a certain value. The acceleration lane length is affected by the mainline design speed and the ramp design speed, and is negatively correlated with the ramp design speed under a given service level and target reliability index. Compared with the deterministic model, the design of acceleration lane length through reliability theory and traffic simulation model is more flexible and reliable.
Journal of Transport Information and Safety
(Founded in 1983 bimonthly )
Former Name：Computer and Communications
Supervised by：Ministry of Education of P. R. CHINA
Sponsored by：Wuhan University of Technology
Network of Computer Application Information in Transportation
In Association With：Intelligent Transportation Committee of China Association of Artificial Intelligence
Editor-in-Chief：ZHONG Ming
Edited and Published by：Editorial Office of Transport Information and Safety
Address：No. 1178，Heping Avenue, Wuchang, Wuhan, CHINA
Postcode：430063
Tel：027-86580355
E-mail：jtjsj@vip.163.com
Website：http://www.jtxa.net/
Postal Code：38-94
Domestic Issue：
CN 42-1781/U
Publication No.：ISSN 1674-4861
Indexed In
- Chinese Core Journal in “Integrated Transportation” category
- Chinese Science Citation Database (CSCD)
- Core Science and Technology Journals
- Chinese Scientific and Technological Papers and Citations (CSTPCD)
- Class A of Research Center for Chinese Science Evaluation (RCCSE)
- Chinese Academic Journal Comprehensive Evaluation Database (CAJ-CED)
- Chinese Core Journals (Selection) Database
- Chinese Scientific and Technological Periodicals Database
- China National Knowledge Infrastructure (CNKI)
- Chinese Academic Journals (CAJ-CD)
- Chinese Lifelong Education Academic Research Database
- Japan Science and Technology Agency (JST)
- World Journal Clout Index Report (2020 STM)
