Traffic Risk Assessment Research Articles

Score-based Graph Learning for Urban Flow Prediction

Accurate urban flow prediction (UFP) is crucial for a range of smart city applications such as traffic management, urban planning, and risk assessment. To capture the intrinsic characteristics of urban flow, recent efforts have utilized spatial and temporal graph neural networks to deal with the complex dependence between the traffic in adjacent areas. However, existing graph neural network based approaches suffer from several critical drawbacks, including improper graph representation of urban traffic data, lack of semantic correlation modeling among graph nodes, and coarse-grained exploitation of external factors. To address these issues, we propose DiffUFP , a novel probabilistic graph-based framework for UFP. DiffUFP consists of two key designs: (1) a semantic region dynamic extraction method that effectively captures the underlying traffic network topology, and (2) a conditional denoising score-based adjacency matrix generator that takes spatial, temporal, and external factors into account when constructing the adjacency matrix rather than simply concatenation in existing studies. Extensive experiments conducted on real-world datasets demonstrate the superiority of DiffUFP over the state-of-the-art UFP models and the effect of the two specific modules.

Dynamic traffic graph based risk assessment of multivehicle lane change interaction scenarios

Vehicles' lane-changing behavior can potentially result in traffic conflicts and crash risks, particularly in scenarios with interactions among multiple vehicles. To assess the crash risk of multi-vehicle interaction lane-changing (MILC) scenarios, this study presents a dynamic traffic graph-based risk assessment method. First, a method for constructing dynamic scene graphs is proposed, along with graph-based indicators for assessing scene and scenario risks. Second, the Gaussian mixture model-latent Dirichlet allocation (GMM-LDA) algorithm is utilized to cluster risk sequences of MILC scenarios, enabling the classification of scenario risks into different levels. The method considers both dynamic and static elements in these scenarios, as well as the spatial relationships among these elements. A case study was conducted to illustrate this approach at a weaving area in China. The findings reveal that diverging segments have the highest probability of high-risk MILC scenarios. Furthermore, the likelihood of high-risk scenarios involving consecutive lane-changing maneuvers is higher compared to single lane changes. Left lane-changing behavior exhibits a higher probability of high-risk scenarios compared to right lane-changing. The proposed risk assessment method facilitates the identification and construction of high-risk MILC scenarios. It also enables the exploration of the risk evolution process.

A traffic dynamic operation risk assessment method using driving behaviors and traffic flow Data: An empirical analysis

Presently, traffic safety analysis is mainly based on accident-based indicators, but they are incidental and small probability events, making safety analysis based on accident-related data difficult to achieve a comprehensive application in network size, and to realize risk assessment before accidents occur. To this end, this study innovatively develops a metric named Traffic Dynamic Operation Risk (TDOR) based on aggressive driving behaviors (ADBs) and traffic flow data for traffic safety evaluation. And Non-Negative Matrix Factorization (NMF) is adopted to explore the quantitative risk under the coupling of multiple risk factors. The results show that: 1) segments with high TDOR are always concentrated in a certain area and in a spatial distribution of Gaussian, and the peaks of these distributions are almost the assesses of transportation hubs or complex intersections; 2) traffic volume and coefficient of speed variation are the significant risk factors at ordinary sections and branches, while traffic volume and speed difference between upstream are the largest contributions at intersections; 3) roads with more accidents are associated with a higher TDOR, but the relationship between the two is not completely linearly correlated. The experimental results show that it is reasonable and feasible to use ADBs and traffic flow parameters to quantify traffic safety risks. Compared with other matrix factorization methods, the importance of variables based on NMF is more interpretable and more consistent with the change pattern of risk variables. The method proposed in this paper can change the previous traffic risk assessment pattern based on accident-related indicators and provide a basis for pre-accident risk prevention.

Gated Spatial–Temporal Merged Transformer Inspired by Multimask and Dual Branch for Traffic Forecasting

As an essential part of intelligent transportation system (ITS), traffic forecasting has provided crucial role for traffic management and risk assessment. However, complex spatial–temporal dependencies, heterogeneity, dynamicity, and periodicity of traffic data influence the traffic forecasting performance. Consequently, we propose a novel effective gated spatial–temporal merged transformer (GSTMT) inspired by multimask and dual branch for accurate traffic forecasting in this paper. Specifically, we first conduct a concatenation of gated spatial static mask transformer (GSSMT) and gated spatial dynamic mask transformer (GSDMT) with residual network. The GSSMT and GSDMT evolve from the traditional transformer by making preferable modifications that include gated linear unit (GLU), multimask mechanism including static mask matrix (SMM) and dynamic mask matrix (DMM), and spatial attention (SA). Among them, GLU is to promote the performance of capturing spatial dependency, dynamicity, and heterogeneity due to advanced performance for controlling information flow through layers. Additionally, by developing multimask mechanism including two novel SMM and DMM, the proposed GSTMT can precisely model the static and dynamic spatial structure for effectively highlighting static dependency and dynamicity. And SA is injected for enhancing the ability of capturing spatial dependency of GSSMT and GSDMT. Secondly, we develop a dual‐branch gated temporal transformer (DBGTT) for capturing temporal dependency, heterogeneity, dynamicity, and periodicity via incorporating the GLU and mixed time series decomposition (MTD) into traditional transformer. Similarly, we also introduce the GLU for empowering DBGTT with capability of capturing temporal dependency, dynamicity, and heterogeneity. In addition, MTD, which brings dual‐branch mechanism, can enhance the DBGTT for capturing more detailed temporal information via exploiting global and periodic profile of traffic data. At last, some experiments, which are performed on several real‐world traffic datasets, demonstrate the better results over classic traffic forecasting methods.

Traffic Safety Risk Assessment for Selected Roads in Al-Qadisiyah Province

Road risk assessments use the same methodology as regular risk assessments and describe all of the dangers that are connected to drivers who use their vehicles for daily-related objectives. These risks include the distance traveled, the duration of the trip, the planned breaks, the driver’s posture, the sorts of routes, and the available driving options. The manuscript explored traffic crashes, the geographical distribution of crashes, and the road characteristics to identify the riskiest roads in Al-Qadisiyah Province. Data was collected from Al-Diwaniyah Teaching Hospital, and the data was divided into internal regions with 5996 crashes and external regions with about 6867 crashes. After compiling, indexing, and dividing the data, it was found that the critical crash times are at the beginning and end of the official working hours and at the time of rest after working hours. Likewise, the highest number of injuries are related to motorcyclists with 2447 crashes. It was also found that people (22-35) years old have the largest number of crashes followed by people 18 years old. After calculating the total number of accidents and the rate of accidents for all the roads selected for the study, the results indicated that the Diwaniyah-Daghara road had the highest number of accidents than the rest of the selected roads, as the number of accidents was 921 accidents, followed by the second place in terms of the number of accidents, the Diwaniyah-Sunya road, and after calculating the amount of danger for all roads ( There are 7 external roads and 3 internal roads). It is followed in second place by the Diwaniyah-Shafi’iyyah road with a crash severity of 15.05, and in third place by the Diwaniya-Daghara road with a severity of 13.65, whereas, Al-Askari road was ranked third with the number of crashes of 671, and now it ranks fifth with a severity of 8.31.

Microscopic Traffic Risk Assessment at Signalized Intersections of a Bus Rapid Transit System

Microscopic Traffic Risk Assessment at Signalized Intersections of a Bus Rapid Transit System

Spatio-temporal characteristics of global maritime ship casualties

Maritime transportation safety of ships is important for international trade. Analyzing the spatio-temporal characteristics of global maritime ship casualties is the basis for maritime ship traffic planning, risk assessment and prevention. Based on the global maritime ship casualty data from 2000 to 2019, the number of the ship casualties were count by detailed event type, year, and month. Kernel density estimation of four periods were carried out. Sea areas around the English Channel, and the Aegean Sea were the hotspots from 2000 to 2019. The Korea Strait, Gulf of Saint Lawrence, Gulf of Alaska, Malacca Strait, and sea areas near Shanghai were also the hotspots in some of the four periods from 2000 to 2019.

Traffic Risk Assessment of Lane-Changing Process in Urban Inter-Tunnel Weaving Segment

This study aims to assess the traffic risk of the lane-changing (LC) process in the urban inter-tunnel weaving (UIW) segment. Time to collision (TTC) and extended time to collision (ETTC) are selected as indices for traffic risk assessment. An instantaneous traffic risk level classification method integrating Pareto’s law and the K-means clustering algorithm is proposed. Based on the classification results, the study also proposes an overall LC risk assessment method. Field-collected trajectory data are used to evaluate and characterize the traffic risk associated with the LC process. The instantaneous traffic risk analysis shows that the high-risk state accounts for a high percentage of the LC process in the UIW segment, and the front vehicle on the starting lane has the highest potential for conflict with the target vehicle. The overall risk index analysis shows that the risk distribution of the LC process is significantly clustered in the weaving segment and that the safety level of the UIW segment needs to be improved. This study quantifies the safety level and analyzes the characteristics of traffic risks of the LC process in the UIW segment to provide a decision basis for the development of assisted driving schemes and improvement of traffic safety management in the UIW segment.

A Superposition Assessment Method of Road Crash Risk and Congestion Risk: An Empirical Analysis

In road transport systems, various traffic risks in certain condition could produce joint actions, which increases the complexity of traffic risk assessment. Previous single risk assessment fails to reflect the superposition effect of multi-type traffic risks, so the result may underestimate or overrate the total risk strength of transport system. To address this problem, a novel risk assessment perspective that aims to evaluate the superposition effect of several traffic risks is studied. In this study, the risk quantification and standardization for single traffic risks is conducted first. Then a GARCH-VaR model is developed to explore the superposition impact of these single traffic risks. The GARCH-VaR model integrates the VaR theory and GARCH model, from which the superposition traffic risk is obtained by assigning every single traffic risk a reasonable weight. Finally, an improved k-means clustering algorithm is proposed to classify the superposition risk level. Empirical results demonstrate that the superposition risk of crash risk and congestion risk is lower than a single traffic risk in certain condition, which attributes to the weak interactions between various traffic risks. This finding illustrates the superposition risk does not necessarily go up with the increase of the risk category. Then the superposition risks are classified into high-risk level, moderate-risk level, and low-risk level, among which the classification accuracy of high-risk level is 92.85%-95.23%. The proposed method provides a theoretical reference for collaborative assessment of multi-type traffic risks, and the results could be potentially used in the comprehensive management of traffic risks.

Analysis of Perception Accuracy of Roadside Millimeter-Wave Radar for Traffic Risk Assessment and Early Warning Systems.

Millimeter-wave (MMW) radar is essential in roadside traffic perception scenarios and traffic safety control. For traffic risk assessment and early warning systems, MMW radar provides real-time position and velocity measurements as a crucial source of dynamic risk information. However, due to MMW radar's measuring principle and hardware limitations, vehicle positioning errors are unavoidable, potentially causing misperception of the vehicle motion and interaction behavior. This paper analyzes the factors influencing the MMW radar positioning accuracy that are of major concern in the application of transportation systems. An analysis of the radar measuring principle and the distributions of the radar point cloud on the vehicle body under different scenarios are provided to determine the causes of the positioning error. Qualitative analyses of the radar positioning accuracy regarding radar installation height, radar sampling frequency, vehicle location, posture, and size are performed. The analyses are verified through simulated experiments. Based on the results, a general guideline for radar data processing in traffic risk assessment and early warning systems is proposed.

Operational Design Domain-Driven Coverage for the Safety Argumentation of Automated Vehicles

Automated Vehicles aim to increase road safety as automated driving systems (ADS) take over the human driving task in the operational design domain (ODD), introducing severe challenges for safety validation. Pure driving over many kilometers to gather enough evidence for a safety argument is not feasible. Scenario-based testing is an approach to overcome this, but challenges like parameter discretization still prevail, hindering safety assurance. This work proposes contributions towards a traceable and efficient safety argumentation for ADS built upon ODD coverage. First, ODD coverage is thoroughly quantified across all scenario levels, assuming distribution functions’ availability for the scenario parameters. Secondly, a sampling method for n-dimensional scenario parameter distributions is proposed. The provided algorithms adapt an initial k-means clustering using pre-defined boundary conditions requiring significantly fewer scenarios. Furthermore, a risk metric for urban intersections is presented for scenario evaluation. The risk metric consists of two parts, scene prediction of traffic participants (TPs) and risk assessment. The scene prediction uses a manoeuvre-based motion model with a data-driven approach towards trajectory prediction, increasing the validity. For the risk assessment, a probabilistic risk prediction for the TPs is performed for each scenario scene. The risk metric shows a reasonable tradeoff between sensitivity and specificity, outperforming time-to-collision. These contributions are exemplarily applied at an intersection using a simplified setup for generating TPs and ego vehicle trajectories. The results indicate that an increased safety argumentation is enabled using the proposed methods alongside a coverage process, facilitating further research.

Failure Mode and Effects Analysis (FMEA) for Traffic Risk Assessment Based on Unbalanced Double Hierarchy Linguistic Term Set

Failure Mode and Effects Analysis (FMEA) for Traffic Risk Assessment Based on Unbalanced Double Hierarchy Linguistic Term Set

A Framework for Auditing Multilevel Models using Explainability Methods

Multilevel models (MLMs) are increasingly deployed in industry across different functions. Applications usually result in binary classification within groups or hierarchies based on a set of input features. For transparent and ethical applications of such models, sound audit frameworks need to be developed. In this paper, an audit framework for technical assessment of regression MLMs is proposed. The focus is on three aspects: model, discrimination, and transparency & explainability. These aspects are subsequently divided into sub-aspects. Contributors, such as inter MLM-group fairness, feature contribution order, and aggregated feature contribution, are identified for each of these sub-aspects. To measure the performance of the contributors, the framework proposes a shortlist of KPIs, among others, intergroup individual fairness (DiffInd_MLM) across MLM-groups, probability unexplained (PUX) and percentage of incorrect feature signs (POIFS). A traffic light risk assessment method is furthermore coupled to these KPIs. For assessing transparency & explainability, different explainability methods (SHAP and LIME) are used, which are compared with a model intrinsic method using quantitative methods and machine learning modelling. Using an open-source dataset, a model is trained and tested and the KPIs are computed. It is demonstrated that popular explainability methods, such as SHAP and LIME, underperform in accuracy when interpreting these models. They fail to predict the order of feature importance, the magnitudes, and occasionally even the nature of the feature contribution (negative versus positive contribution on the outcome). For other contributors, such as group fairness and their associated KPIs, similar analysis and calculations have been performed with the aim of adding profundity to the proposed audit framework. The framework is expected to assist regulatory bodies in performing conformity assessments of AI systems using multilevel binomial classification models at businesses. It will also benefit providers, users, and assessment bodies, as defined in the European Commission’s proposed Regulation on Artificial Intelligence, when deploying AI-systems such as MLMs, to be future-proof and aligned with the regulation.

A Framework for Auditing Multilevel Models using Explainability Methods

Multilevel models (MLMs) are increasingly deployed in industry across different functions. Applications usually result in binary classification within groups or hierarchies based on a set of input features. For transparent and ethical applications of such models, sound audit frameworks need to be developed. In this paper, an audit framework for technical assessment of regression MLMs is proposed. The focus is on three aspects: model, discrimination, and transparency & explainability. These aspects are subsequently divided into sub-aspects. Contributors, such as inter MLM-group fairness, feature contribution order, and aggregated feature contribution, are identified for each of these sub-aspects. To measure the performance of the contributors, the framework proposes a shortlist of KPIs, among others, intergroup individual fairness (DiffInd_MLM) across MLM-groups, probability unexplained (PUX) and percentage of incorrect feature signs (POIFS). A traffic light risk assessment method is furthermore coupled to these KPIs. For assessing transparency & explainability, different explainability methods (SHAP and LIME) are used, which are compared with a model intrinsic method using quantitative methods and machine learning modelling.
 Using an open-source dataset, a model is trained and tested and the KPIs are computed. It is demonstrated that popular explainability methods, such as SHAP and LIME, underperform in accuracy when interpreting these models. They fail to predict the order of feature importance, the magnitudes, and occasionally even the nature of the feature contribution (negative versus positive contribution on the outcome). For other contributors, such as group fairness and their associated KPIs, similar analysis and calculations have been performed with the aim of adding profundity to the proposed audit framework. The framework is expected to assist regulatory bodies in performing conformity assessments of AI systems using multilevel binomial classification models at businesses. It will also benefit providers, users, and assessment bodies, as defined in the European Commission’s proposed Regulation on Artificial Intelligence, when deploying AI-systems such as MLMs, to be future-proof and aligned with the regulation.

Traffic Inflow and Outflow Forecasting by Modeling Intra- and Inter-Relationship Between Flows

Forecasting traffic inflows and outflows is crucial for intelligent transportation applications such as traffic management and risk assessment. Recently, deep learning models, which focus on capturing spatio-temporal correlations between stations (locations) by constructing Spatio-Temporal Feature Learners (STFL), have achieved promising performance in traffic inflows and outflows prediction. However, two unresolved issues limit the performance of these models. i) dynamic and heterogeneous intra- and inter-relationships between flows are ignored, and ii) the STFL in these models cannot capture the global information. To address the above issues, we propose a novel deep Spatio-Temporal Network framework based on Multi-Relational learning (MR-STN) for predicting traffic inflows and outflows. Specifically, a multi-relational learning module is designed to comprehensively model three kinds of relationships between flows while extracting diverse spatio-temporal features. In this module, an enhanced STFL is developed to capture both local and global information. Then, a feature fusion module is introduced to extract fused features for inflows and outflows respectively via a gated fusion mechanism. On this basis, the prediction module uses fusion features to generate future inflows and outflows. Finally, we implement the proposed framework with four state-of-the-art graph-based deep spatio-temporal models to demonstrate its generality and superiority. Extensive experiments on three datasets show that the proposed framework can significantly boost the performance of existing models.

Traffic Risk Assessment Based on Warning Data

To address the issues of insufficient danger excavation and long data collection period in traditional traffic risk assessment methods, this paper proposes a risk assessment method based on driver’s improper driving behavior and abnormal vehicle state warning data. Meanwhile, this paper analyses the built environment’s impact on traffic risk using the spatial econometric model. Firstly, a risk assessment system with the relative incidence of driver’s improper driving behavior (eye closure, yawn, and looking away) and abnormal vehicle state (rapid acceleration, rapid deceleration, and lane departure) warnings as assessment indicators is constructed. Then, the risk responsibility weights of each warning type were determined using the entropy weight method. The risk classification thresholds were determined based on the Gaussian Mixture Model algorithm. Finally, a spatial econometric model was used to quantify the impact of built environment factors characterized by Point of Interest (POI) data on regional traffic risk, with the results of risk class classification as the dependent variable. The data of bus vehicle warnings in Zhenjiang, Jiangsu Province, are employed as an example for validation. The geographic cell of 1 km × 1 km scale is applied as the basic risk assessment unit. The results show that the optimal risk classification threshold for road traffic risk levels I and II is 1.92, the accuracy rate of class classification is 79.3%; the optimal risk classification threshold for levels II and III is 0.75, and the accuracy rate of class classification is 83.4%. The number of residential areas, Point of Interest (POI) mixing degree, and bus stops were significantly and positively correlated with transit traffic risk. The study results provide references for developing customized accident prevention measures and the appropriate setting of urban supporting facilities.

Temporal Shift and Spatial Attention-Based Two-Stream Network for Traffic Risk Assessment

On-board vision based traffic risk assessment is a challenging task for intelligent driving systems, which has some special challenges including spatial-temporal feature extraction, different judgements of risks, real-time requirement, lacking data, etc. To overcome these difficulties, we propose a novel <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Temporal Shift and Spatial Attention based Two-stream Network</i> (TSSAT-Net) for on-board vision based traffic risk assessment. Firstly, we build new judgement measures that integrate actual driving experience and scenario complexity, and release an on-board vision based traffic risk assessment dataset. Secondly, a novel <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">weighted Temporal Shift Module</i> (weighted-TSM) based two-stream network is proposed; unlike previous methods that rely on complex and time-consuming 3D CNN or LSTM calculation, the proposed two-stream network can effectively extract spatial-temporal features using a weighted temporal shift mechanism with just 2D CNN calculation requirement. Thirdly, a spatial and channel attention mechanism is proposed to make the TSSAT-Net more focus on the features closely related to traffic risks, avoiding redundant information in complex traffic scenarios. Experiments based on the released comprehensive dataset show that our method achieves the state-of-the-art classification accuracy in real-time.

A method to extract the Quaternion Ship Domain parameters from AIS data

The ship domain concept is of great interest for ship traffic modelling, risk assessment and intelligent collision avoidance. The paper proposes and applies a method to define AIS data-based empirical polygonal ship domains, based on traffic density matrices that are derived around each reference ship from an AIS dataset. A modified Quaternion Ship Domain allowing for different shapes for each quadrant is proposed, which results in a better fitting to the empirical domain. The parameters of Quaternion Ship Domains that best fit the empirical polygonal domains are determined for cargo ships and tankers of different lengths. Violations of the Quaternion Ship Domain are then used as an indicator of collision risk that is graphically represented in the study area, providing important information to support maritime traffic monitoring and control tasks.

096 Maintenance IVIg safe prescribing – audit of proforma and traffic light risk assessment system in NHNN

IntroductionWe recently published safety data on maintenance IVIg therapy for inflammatory neuropa- thies in similar patient cohorts from NHNN and the Manchester Neurosciences group [1,2]. Based on our findings the following clinical practice changes have been introduced:Routine monitoring and proactive treatment of vascular risk factors A traffic light system for guidance on appropriate blood testing.MethodsAnalysis of 2 weeks of IVIg admissions in NHNN prior to and within a month of the introduction of the proforma. Ethics was granted by the clinical governance committee.Results69 patient episodes were identified. 63(91.3%)day-care admissions, 6(8.7%)inpatient. 34 female (49.3%).18 patients(26.1%) had bloods taken prior to administration, 60(87%) and 30(43.5%) were screened for symptoms of venous and arterial thromboembolism. 2 (2.9%) and 0 were asked about VTE and ATE risk factors. 63 (91.3%) were asked about infectious symptoms. After introduction of the proforma screening for VTE, TTE and infections symptoms and risk improved to 100%. Aprropriate pre-IVIg bloods were taken in 4(6%).ConclusionIVIg is effective and low risk therapy for inflammatory neuropathy, however rare and serious complications can occur. We created this proforma to optimise safety monitoring in longterm mainte- nance therapy with reassuring improvements in this pilot review.milo.delaney@nhs.net

Predicting Citywide Crowd Flows in Irregular Regions Using Multi-View Graph Convolutional Networks

Being able to predict the crowd flows in each and every part of a city, especially in irregular regions, is strategically important for traffic control, risk assessment, and public safety. However, it is very challenging because of interactions and spatial correlations between different regions. In addition, it is affected by many factors: i) multiple temporal correlations among different time intervals: closeness, period, trend; ii) complex external influential factors: weather, events; iii) meta features: time of the day, day of the week, and so on. In this paper, we formulate crowd flow forecasting in irregular regions as a spatio-temporal graph (STG) prediction problem in which each node represents a region with time-varying flows. By extending graph convolution to handle the spatial information, we propose using spatial graph convolution to build a multi-view graph convolutional network (MVGCN) for the crowd flow forecasting problem, where different views can capture different factors as mentioned above. We evaluate MVGCN using four real-world datasets (taxicabs and bikes) and extensive experimental results show that our approach outperforms the adaptations of state-of-the-art methods. And we have developed a crowd flow forecasting system for irregular regions that can now be used internally.