Using bus critical driving events as surrogate safety measures for pedestrian and bicycle crashes based on GPS trajectory data

Analysis of harsh braking and harsh acceleration occurrence via explainable imbalanced machine learning using high-resolution smartphone telematics and traffic data

Harsh driving events such as harsh brakings (HBs) and harsh accelerations (HAs) are promising Surrogate Safety Measures, already extensively utilised in road safety research. However, their occurrence relative to normal driving conditions has not been the explicit target of research, as they are typically used as inputs for crash prediction. The present study addresses this research gap by investigating factors influencing HB and HA occurrence using real-time naturalistic driving telematics data recorded from smartphones, traffic data and road geometry & network characteristics data. These multisource data were matched in order to capture the specific circumstances under which HBs and HAs occur. The utilized telematics dataset included trips from 314 anonymous drivers in an urban arterial of Athens, Greece. Subsequently, Synthetic Minority Oversampling TEchnique (SMOTE) was applied due to class imbalance and then binary classification was conducted to detect factors leading to HB and HA occurrence. Imbalanced Machine Learning (ML) XGBoost algorithms predicted over 75% of HBs and over 84% of HAs for the test dataset, indicating suitability for real-time monitoring. The algorithms were also augmented with SHapley Additive exPlanation (SHAP) values, aiming to increase outcome explainability. Results reveal strong nonlinear effects on harsh event occurrence, with individual speed and traffic flow parameters showing the highest influence, followed by exposure parameters such as segment length and pass count. Network characteristics such as number of lanes, and speed limit had limited influence on HA and HB occurrence, as did behaviors such as mobile phone engagement and speeding.

Beyond 1D and oversimplified kinematics: A generic analytical framework for surrogate safety measures

This paper presents a generic analytical framework tailored for surrogate safety measures (SSMs) that is versatile across various highway geometries, capable of encompassing vehicle dynamics of differing dimensionality and fidelity, and suitable for dynamic, real-world environments. The framework incorporates a generic vehicle movement model, accommodating a spectrum of scenarios with varying degrees of complexity and dimensionality, facilitating the estimation of future vehicle trajectory evolution. It establishes a generic mathematical criterion to denote potential collisions, characterized by the spatial overlap between a vehicle and any other entity. A collision risk is present if the collision criterion is met at any non-negative estimated future time point, with the minimum threshold representing the remaining time to collision. The framework's proficiency spans from conventional one-dimensional (1D) SSMs to extended multi-dimensional, high-fidelity SSMs. Its validity is corroborated through simulation experiments that assess the precision of the framework when linearization is performed on the vehicle movement model. The outcomes showcase remarkable accuracy in estimating vehicle trajectory evolution and the time remaining before potential collisions occur, comparing to high-accuracy numerical integration solutions. The necessity of higher-dimensional and higher-fidelity SSMs is highlighted through a comparison of conventional 1D SSMs and extended three-dimensional (3D) SSMs. The results showed that using 1D SSMs over 3D SSMs could be off by 300% for Time-to-Collision (TTC) values larger than 1.5 s and about 20% for TTC values below 1.5 s. In other words, conventional 1D SSMs can yield highly inaccurate and unreliable results when assessing collision proximity and substantially misjudge the count of conflicts with predefined threshold (e.g., below 1.5s). Furthermore, the framework's practical application is demonstrated through a case study that actively evaluates all potential conflicts, underscoring its effectiveness in dynamic, real-world traffic situations.

Evaluation of Roadside LiDAR-Based and Vision-Based Multi-Model All-Traffic Trajectory Data

Trajectory data has gained increasing attention in the transportation industry due to its capability of providing valuable spatiotemporal information. Recent advancements have introduced a new type of multi-model all-traffic trajectory data which provides high-frequency trajectories of various road users, including vehicles, pedestrians, and bicyclists. This data offers enhanced accuracy, higher frequency, and full detection penetration, making it ideal for microscopic traffic analysis. In this study, we compare and evaluate trajectory data collected from two prevalent roadside sensors: LiDAR and camera (computer vision). The comparison is conducted at the same intersection and over the same time period. Our findings reveal that current LiDAR-based trajectory data exhibits a broader detection range and is less affected by poor lighting conditions compared to computer vision-based data. Both sensors demonstrate acceptable performance for volume counting during daylight hours, but LiDAR-based data maintains more consistent accuracy at night, particularly in pedestrian counting. Furthermore, our analysis demonstrates that, after applying smoothing techniques, both LiDAR and computer vision systems accurately measure vehicle speeds, while vision-based data show greater fluctuations in pedestrian speed measurements. Overall, this study provides insights into the advantages and disadvantages of LiDAR-based and computer vision-based trajectory data, serving as a valuable reference for researchers, engineers, and other trajectory data users in selecting the most appropriate sensor for their specific needs.

Effect of signal timing on vehicles' near misses at intersections

Driving characteristics often vary between the different states of the signal. During red and yellow phase, drivers tend to speed up and reduce the following distance which in turn increases the possibility of rear end crashes. Intersection safety, therefore, relies on the correct modelling of signal phasing and timing parameters, and how drivers respond to its changes. This paper aims to identify the relationship between surrogate safety measures and signal phasing. Unmanned aerial vehicle (UAV) video data has been used to study a major intersection. Post encroachment time (PET) between vehicles was calculated from the video data as well as speed, heading and relevant signal timing parameters such as all red time, red clearance time, yellow time, etc. Random parameter ordered logit model was used to model the relationship between PET and signal timing parameters. Overall, the results showed that yellow time and red clearance time is positively related to PETs. The model was also able to identify certain signal phases that could be a potential safety hazard and would need to be retimed by considering the PETs. The odds ratios from the models also indicate that increasing the mean yellow and red clearance times by one second can improve the PET levels by 10% and 3%, respectively.

Do footbridge and underpass improve pedestrian safety? A Hong Kong case study using three-dimensional digital map of pedestrian network

Hong Kong is a compact city with high activity and travel intensity. In the past decades, many footbridges and underpasses were installed to reduce the pedestrian-vehicle conflicts on urban roads. However, it is rare that the effects of configuration of pedestrian network on pedestrian crashes are investigated. In Hong Kong, many footbridges and underpasses are connected to major transport hubs and commercial building development and become parts of giant elevated and underground walkway systems. It is challenging to characterize such a complicated pedestrian network. In this study, a three-dimensional digital map is applied to estimate the connectivity and accessibility of pedestrian network, and measure the relationship between pedestrian network characteristics and pedestrian safety at the macroscopic level. Hence, the effects of footbridge and underpass on pedestrian safety are examined. For example, comprehensive built environment, pedestrian network, traffic, and crash data are aggregated to 379 grids (0.5 km × 0.5 km). Then, multivariate Poisson lognormal regression approach is applied to model fatal and severe injury (FSI) and slight injury pedestrian crashes, with which the effects of unobserved heterogeneity, spatial correlation, and correlation between crash counts are accounted. Results indicate that population density, traffic volume, walking trip, footpath density, node density, number of vertices per footpath segment, bus stop, metro exit, residential area, commercial area, and government and utility area are positively associated with pedestrian crashes. In contrast, average gradient, accessibility of footbridge, accessibility of underpass, and number of crossings per road segment are negatively associated with pedestrian crashes. In other word, pedestrian safety would be improved when footbridge and underpass are more accessible. Findings have implications for the design and planning of pedestrian network to promote walkability and improve pedestrian safety.

Understanding the impact of vehicle dynamics, geometric and non-geometric roadway attributes on surrogate safety measure using connected vehicle data

Traditional safety research mostly relies on accident data to analyze the precedents to a crash. Alternatively, surrogate safety measures have the potential to proactively evaluate safety events. The era of connected vehicles and smart sensing has brought about tremendous innovations in safety research. GPS data from such vehicles form a useful case of big data analytics where surrogate safety measures have largely been unexplored. In this paper, we propose time to collision estimation from connected vehicle GPS data. The vehicle dynamics such as speed, acceleration, yaw rate, etc. are then coupled with geometric and non-geometric roadway attributes to understand the contributing factors for a traffic conflict. The dataset contains 2,568,421 GPS points from 14,753 unique journeys. 1:4 ratio of conflict to non-conflict events was used to select 15,258 samples with 28 independent vehicle dynamics, geometric, and non-geometric variables. Binary logit model was used to investigate the relationship of these variables with conflicts. Model results showed that out of 28 independent variables, 6 independent variables and 7 interaction variables were found significant. The results showed some interesting and unique relations of these variables with conflicts. Based on these significant variables, k-means clustering was performed to understand the threshold for the significant values for which the number of conflicts is significantly increased. Results from k-means clustering and two sample binomial proportion t-tests revealed that when absolute acceleration crossed 0.8 m/s², conflict probability increased by 8 percentage points.​ Moreover, when the yaw rate crossed 8 degrees/s, the conflict probability doubled. Besides, vehicles traveling at more than 140% of the recommended speed limit increased conflict probability by 7 percentage points.

Detection of anomalies in cycling behavior with convolutional neural network and deep learning

Background

Cycling has always been considered a sustainable and healthy mode of transport. With the increasing concerns of greenhouse gases and pollution, policy makers are intended to support cycling as commuter mode of transport. Moreover, during Covid-19 period, cycling was further appreciated by citizens as an individual opportunity of mobility. Unfortunately, bicyclist safety has become a challenge with growing number of bicyclists in the 21st century. When compared to the traditional road safety network screening, availability of suitable data for bicycle based crashes is more difficult. In such framework, new technologies based smart cities may require new opportunities of data collection and analysis.

Methods

This research presents bicycle data requirements and treatment to get suitable information by using GPS device. Mainly, this paper proposed a deep learning-based approach "BeST-DAD" to detect anomalies and spot dangerous points on map for bicyclist to avoid a critical safety event (CSE). BeST-DAD follows Convolutional Neural Network and Autoencoder (AE) for anomaly detection. Proposed model optimization is carried out by testing different data features and BeST-DAD parameter settings, while another comparison performance is carried out between BeST-DAD and Principal Component Analysis (PCA).

Result

BeST-DAD over perform than traditional PCA statistical approaches for anomaly detection by achieving 77% of the F-score. When the trained model is tested with data from different users, 100% recall is recorded for individual user's trained models.

Conclusion

The research results support the notion that proper GPS trajectory data and deep learning classification can be applied to identify anomalies in cycling behavior.

Driver behavior indices from large-scale fleet telematics data as surrogate safety measures

Large-scale telematics data enable a high-resolution inference of road network's safety conditions and driver behavior. Although many researchers have investigated how to define meaningful safety surrogates and crash predictors from telematics, no comprehensive study analyzes the driver behavior derived from large-scale telematics data and relates them to crash data and the road networks in metropolitan cities. This study extracts driver behavior indices (e.g., speed, speed variation, hard braking rate, and hard acceleration rate) from large-scale telematics data, collected from 4000 vehicles in New York City five boroughs. These indices are compared to collision frequencies and collision rates at the street level. Moderate correlations were found between the safety surrogate measures and collision rates, summarized as follows: (i) When normalizing crash frequencies with traffic volume, using a traffic AADT model, safety-critical regions almost remain the same. (ii) The correlation magnitude of hard braking and hard acceleration varies by road types: hard braking clusters are more indicative of higher collision rates on highways, whereas hard acceleration is a stronger hazard indicator on non-highway urban roads. (iii) Locations with higher travel times coincide with locations of high crash incidence on non-highway roads. (iv) However, speeding on highways is indicative of collision risks. After establishing the spatial correlation between the driver behavior indices and crash data, two prototype safety metrics are proposed: speed corridor maps and hard braking and hard acceleration hot-spots. Overall, this paper shows that data-driven network screening enabled by telematics has great potential to advance our understanding of road safety assessment.

The influence of traffic-infrastructure factors on pedestrian accidents at the macro-level: The geographically weighted regression approach

INTRODUCTION

Walking is an active way of moving the population, but in recent years there have been more pedestrian casualties in traffic, especially in developing countries such as Serbia. Macro-level road safety studies enable the identification of influential factors that play an important role in creating pedestrian safety policies.

METHOD

This study analyzes the impact of traffic and infrastructure characteristics on pedestrian accidents at the level of traffic analysis zones. The study applied a geographically weighted regression approach to identify and localize all factors that contribute to the occurrence of pedestrian accidents. Taking into account the spatial correlations between the zones and the frequency distribution of accidents, the geographically Poisson weighted model showed the best predictive performance.

RESULTS

This model showed 10 statistically significant factors influencing pedestrian accidents. In addition to exposure measures, a positive relationship with pedestrian accidents was identified in the length of state roads (class I), the length of unclassified streets, as well as the number of bus stops, parking spaces, and object units. However, a negative relationship was recorded with the total length of the street network and the total length of state roads passing through the analyzed area.

CONCLUSION

These results indicate the importance of determining the categorization and function of roads in places where pedestrian flows are pronounced, as well as the perception of pedestrian safety near bus stops and parking spaces.

PRACTICAL APPLICATIONS

The results of this study can help traffic safety engineers and managers plan infrastructure measures for future pedestrian safety planning and management in order to reduce pedestrian casualties and increase their physical activity.

Spatial influence of engineering construction on traffic accidents, a case study of Jinan

Due to urban construction, engineering transport vehicles are gradually increased on roads, which might speed up traffic accident risks. To investigate the influence of urban construction on traffic accidents, this paper adopted 1977 traffic accidents of engineering transport vehicles and 220 engineering construction projects for correlation analysis. First, considering three degrees (Major, Ordinary and Minor) of accidents, the spatial autocorrelation test of engineering transport vehicle accidents is carried out by using spatial econometric. Then to further evaluate and analyze the spatial regression model, the optimal model is selected to analyze the spatial influence of the floor area of different types of engineering construction projects on the accidents of engineering transport vehicles. The results show that the accident of engineering transport vehicles itself is spatially dependent, that is, the higher the severity of the accident, the more concentrated it is in space, and there is a significant spatial positive correlation with engineering construction projects. And the floor areas of synthetic land, residential land, commercial land and land for roads and transportation facilities have significant spatial effects on engineering transport vehicle accidents, and the indirect effects are also concerned. The increase of floor area of roads and transportation facilities is more likely to induce accidents of engineering transport vehicles. For every 10,000 square meters of the floor area of roads and transportation facilities, there are 12.66 accidents of engineering transport vehicles in the region and its neighboring areas.

Effect of urban street trees on pedestrian safety: A micro-level pedestrian casualty model using multivariate Bayesian spatial approach

In the past decades, trees were considered roadside hazard. Street trees were removed to provide clear zone and improve roadside safety. Nowadays, street trees are considered to play an important role in urban design. Also, street tree is considered a traffic calming measure. Studies have examined the effects of urban street trees on driver perception, driving behaviour, and general road safety. However, it is rare that the relationship between urban street trees and pedestrian safety is investigated. In this study, a micro-level frequency model is established to evaluate the effects of tree density and tree canopy cover on pedestrian injuries, accounting for pedestrian crash exposure based on comprehensive pedestrian count data from a state in Australia, Melbourne. In addition, effects of road geometry, traffic characteristics, and temporal distribution are also considered. Furthermore, effects of spatial dependency and correlation between pedestrian casualty counts of different injury severity levels are accounted using a multivariate Bayesian spatial approach. Results indicate that road width, bus stop, tram station, on-street parking, and 85th percentile speed are positively associated with pedestrian casualty. In contrast, pedestrian casualty decreases when there is a pedestrian crosswalk and increases in tree density and canopy. Also, time variation in pedestrian injury risk is significant. To sum up, urban street trees should have favorable effect on pedestrian safety. Findings are indicative to optimal policy strategies that can enhance the walking environment and overall pedestrian safety. Therefore, sustainable urban and transport development can be promoted.

Bayesian spatial correlation, heterogeneity and spillover effect modeling for speed mean and variance on urban road networks

Analyzing speed mean and variance is vital to safety management in urban roadway networks. However, modeling speed mean and variance on structured roads could be influenced by the spatial effects, which are rarely addressed in the existing studies. The inadequacy may lead to biased conclusions when considering vehicle speed as a surrogate safety measure. The current study focuses on developing a Bayesian modeling approach with three types of spatial effects, i.e., spatial correlation, spatial heterogeneity, and spillover effect. To capture the spatial correlation, the study employs the intrinsic conditional autoregressive (ICAR) models, spatial lag models (SLM), and spatial error models (SEM). Spatial heterogeneity and spillover effect are considered by the random parameters approach and spatially lagged covariates (SLCs). Speed data are collected from the float cars running on 134 urban arterials in Chengdu, China. The results indicate that the random parameters ICAR model with SLCs (RPICAR-SLC) outperforms others in terms of goodness-of-fit, accuracy, and efficiency for modeling speed mean, while the random parameters ICAR model (RPICAR) is the best for modeling speed variance. Moreover, RPICAR-SLC and RPICAR models are beneficial to address spatial correlation of residuals, explaining the unobserved influence among the observations, and are less likely to cause biased or overestimated parameters. The study also discusses how traffic conditions, road characteristics, traffic management strategies, and facilities on roadway networks influence speed mean and variance. The findings highlight the importance of multi-type spatial effects on modeling speed mean and variance along the structured roadways.

An Advanced Machine Learning Approach to Predicting Pedestrian Fatality Caused by Road Crashes: A Step toward Sustainable Pedestrian Safety

More than 8000 pedestrians were killed due to road crashes in Australia over the last 30 years. Pedestrians are assumed to be the most vulnerable users of roads. This susceptibility of pedestrians to road crashes conflicts with sustainable transportation objectives. It is critical to know the causes of pedestrian injuries in order to enhance the safety of these vulnerable road users. To achieve this, traditional statistical models are used frequently. However, they have been criticized for their inflexibility in handling outliers and missing or noisy data, and their strict pre-assumptions. This study applied an advanced machine learning algorithm, a Bayesian neural network, which has the characters of both Bayesian theory and neural networks. Several structures of this model were built, and the best structure was selected, which included three hidden neuron layers—sixteen hidden nodes in the first layer and eight hidden nodes in the second and third layers. The performance of this model was compared with the performances of some other machine learning techniques, including standard Bayesian networks, a standard neural network, and a random forest model. The Bayesian neural network model outperformed the other models. In addition, a study on the importance of the features showed that the individuals’ characteristics, time, and circumstantial factors were essential. They greatly increased model performance if the model used them. This research lays the groundwork for using machine learning approaches to alleviate pedestrian deaths caused by road accidents.