Crash Occurrence Research Articles

Estimating operating speed for county road segments – Evidence from Italy

• Operating speed is used to check road design and posted speed limits consistency. • Usually, the 85° percentile of the operating speed (V 85 ) is considered as crucial. • V 85 is estimated as a function of road design and functional features. • New parameters are included to estimate V 85 , compared to the past literature. • Considering the Province of Brescia (Italy), two models are calibrated and tested. Vehicle operating speed is a crucial factor for road safety, as it strictly affects occurrence and severity of crashes. Usually, 85th percentile of the operating speed distributions (i.e., V 85 ) in free-flow traffic condition is widely accepted as a base value of consistency evaluation for homogenous portion of existing roads. Although the computation of V 85 is simple, many road authorities cannot collect speed data for each road. Therefore, providing prediction models could be a useful tool to investigate the relationship between V 85 and road characteristics. The literature proposed several models to account it. However, to the best of our knowledge, the effects of some road geometric characteristics, road markings and signs, traffic data, type of terrain and the simultaneous consideration of different road categories on the V 85 prediction were not completely analyzed. This paper fills this gap by isolating key variables that mostly affect V 85 . In doing so, 60 000+ car spot speed data were collected along the county road network of the province of Brescia (Italy), and then processed by multiple regression models. The main findings show that V 85 increases owing to the presence of a wider or paved shoulder, visible road median markings, a higher number of lanes and a higher percentage of cars with respect to the total traffic flow. Conversely, V 85 decreases as the road axis curvature, the number of accesses and rate of forbidden overtaking increase. In addition, the presence of visible road external markings and the surrounding mountainous terrain contribute to decreasing V 85 . The overall findings may support road authorities to verify roads’ operating conditions and, possibly, adjust the speed limits, especially for existing roads.

Counterfactual safety benefits quantification method for en-route driving behavior interventions

Driving behavior intervention is a dominant traffic safety countermeasure being implemented that has substantially reduced crash occurrence. However, during implementation, the intervention strategy faces the curse of dimensionality as there are multiple candidate intervention locations with various intervention measures and options. Quantifying the interventions’ safety benefits and further implementing the most effective ones could avoid too frequent interventions which may lead to counterproductive safety impacts. Traditional intervention effects quantification approaches rely on observational data, thus failing to control confounding variables and leading to biased results. In this study, a counterfactual safety benefits quantification method for en-route driving behavior interventions was proposed. Empirical data from online ride-hailing services were employed to quantify the safety benefits of en-route safety broadcasting to speed maintenance behavior. Specifically, to effectively control the impacts of confounding variables on the quantification results of interventions, the “if without intervention” case of the intervention case is inferred based on the structural causality model according to the Theory of Planned Behavior (TPB). Then, a safety benefits quantification method based on Extreme Value Theory (EVT) was developed to connect changes of speed maintenance behavior with crash occurrence probabilities. Furthermore, a closed-loop evaluation and optimization framework for the various behavior interventions was established and applied to a subset of Didi’s online ride-hailing service drivers (more than 1.35 million). Analyses results indicated safety broadcasting could effectively reduce driving speed by approximately 6.30 km/h and contribute to an approximate 40% reduction in speeding-related crashes. Besides, empirical application results showed that the whole framework contributed to a remarkable reduction in the fatality rate per 100 million km, from an average of 0.368 to 0.225. Finally, directions for future research in terms of data, counterfactual inference methodology, and research subjects have been discussed.

Short-Duration Crash Modeling to Understand the Impact of Operating Speed on Freeway Crashes During COVID-19

Gaining an understanding of speed–crash relationships is a critical issue in highway safety research. Because of the ongoing pandemic (COVID-19) there has been a reduction in traffic volume, and some early studies explain that speeding in an environment with less traffic is associated with a high number of crashes, especially fatal and serious injury crashes. This study aims to quantify the impact of operating speed on traffic crash occurrences. The study conflated several databases (speed data, roadway inventory data, and crash data) that contain data from Dallas, Texas, spanning from 2018 to 2020, to examine the speed–crash association. Using the negative binomial Lindley regression model, this study showed that the trends of crash prediction models vary over the years (2018, 2019, and 2020) by different injury severity levels (i.e., fatal crashes, fatal and incapacitating injury crashes). The 2020 models show that operating speed measures (i.e., average operating speed) have a significant impact on crash frequencies. The magnitudes of the speed measures show variations across the models at different injury severity levels.

Examination of factors associated with fault status and injury severity in intersection-related rear-end crashes: Application of binary and bivariate ordered probit models

Rear-end crashes are a relatively common crash type and often occur at or near intersections. Although rear-end crashes are generally less severe than some other crash types, there were still 2,346 fatal and 595,000 injury rear-end crashes in the US in 2019 alone. These crashes are generally caused by one at-fault driver who strikes a leading vehicle, and it may be useful to assess factors associated with a driver being at-fault. Additionally, it is important to analyze factors associated with injury severity outcomes in order to develop countermeasures aimed at preventing severe injuries. As such, this study investigates factors related to fault status and injury severity (and the interrelation between the two) in two-vehicle intersection-related rear-end crashes using data from a southwestern US state. A binary probit model was estimated to assess factors associated with fault status, while a bivariate ordered probit model was estimated to assess factors associated with driver injury severity by fault status. Importantly, by modelling the injury severity of both crash-involved drivers jointly, potential within-crash correlation can be accounted for. The results of the fault status model indicated numerous factors were associated with a fault status including vehicle type, driver age, and driver impairment or distraction. The results of the bivariate injury severity model indicated numerous factors were significantly associated with injury severity and importantly, differences were observed between at-fault and not-at-fault drivers. Ultimately, the results of this study may assist in development of targeted countermeasures aimed at reducing both crash occurrence and severe injury outcomes.

Road Adhesion Coefficient Estimation Based on Vehicle-Road Coordination and Deep Learning

Accurate estimation of the road adhesion coefficient can help drivers and vehicles perceive changes in road state effectively, reducing the occurrence of traffic crashes accordingly. Therefore, this paper proposes a road adhesion coefficient estimation method based on vehicle-road coordination and deep learning. Firstly, a vehicle-based data feedback system combined with a vehicle-road network cloud is introduced, and CarSim simulation is used to expand the data set and train the model effectively. Then, the dynamic analysis of the whole vehicle is carried out, and the vehicle operation data related to the adhesion coefficient are obtained as the input of the estimation model. Then a combined model of road adhesion coefficient estimation based on self-attention (SA), convolutional neural network (CNN), and long short-term memory (LSTM) is established, to reduce the instability of the prediction, Q-learning is used to optimize the weight of the model. Finally, the model is verified by the simulation data and the actual vehicle-based data. The results show that the vehicle-based data feedback system combined with the vehicle-road network Ccloud is effective, and compared with other commonly used model, the estimation model proposed in this paper can effectively predict the road adhesion coefficient.

Spatial pattern identification and crash severity analysis of road traffic crash hot spots in Ohio

Safety experts and transportation departments are focused on reducing road accidents and their societal and economic effects. The most crucial step in establishing a successful road safety practice is identifying dangerous highway zones through the study of crashes and looking at how the location of accidents relates to surrounding geography and other factors. Using the latest cutting-edge GIS analytical methods, this study aims to map the locations of accident hot spots and evaluate the severity and spatial extent of crash occurrences in Ohio. Road traffic crash (RTC) data has been analyzed using sophisticated GIS-based hot spot analysis for decades by safety researchers. Using four years' worth of crash data from the state of Ohio and spatial autocorrelation analysis, this study aims to show how a GIS technique can be used to find places where accidents are likely to happen (2017–2020). The study analyzed and ranked crash hotspot areas using the matching severity levels of RTCs. Cluster zones of high and low crash severity were discovered using the spatial autocorrelation tool and the Getis Ord Gi* statistics tool to evaluate the distribution of RTCs. The analysis used Getis Ord Gi*, the crash severity index, and Moran's I spatial autocorrelation of accident events. The findings indicated that these techniques were useful for identifying and rating crash hotspot locations. Since the sites of the identified accident hotspots are located in significant cities in the state of Ohio, such as Cleveland, Cincinnati, Toledo, and Columbus, the organizations in charge of traffic management should make it their top priority to minimize the negative socioeconomic impact that RTCs have and should also conduct a thorough investigation. This study's contribution is the incorporation of crash severity into hot spot analysis using GIS, which could lead to better-informed decision-making in the realm of highway safety.

Measurement error models for spatial network lattice data: Analysis of car crashes in Leeds

Abstract Road casualties represent an alarming concern for modern societies. During the last years, several authors proposed sophisticated approaches to help authorities implement new policies. These models were usually developed considering a set of socio-economic variables and ignoring the measurement error, which can bias the statistical inference. This paper presents a Bayesian model to analyse car crash occurrences at the network-lattice level, taking into account measurement error in the spatial covariate. The suggested methodology is exemplified by considering the collisions in the road network of Leeds (UK) during 2011–2019. Traffic volumes are approximated using an extensive set of counts obtained from mobile devices and the estimates are adjusted using a spatial measurement error correction.

Predicting injury-severity for cyclist crashes using natural language processing and neural network modelling

The use of machine learning techniques in safety research has increased as has the interest in using new data sources. This study’s unique contribution is the application of text mining—focusing on perceived cyclist safety and crash occurrence in an urban environment. We analysed crash data collected by the emergency forces in the Capital Region of Denmark from 2013 to 2017 and self-reported textual data provided by cyclists from 2018 to 2019. The analysis included natural language processing and topic modelling to identify Latent Dirichlet Allocation (LDA) topics from self-reports, representing environment characteristics that cyclists’ perceive as unsafe. A multi-output neural network regression model is applied to predict the injury-severity distribution of cyclists involved in crashes (measured by emergency response level [ERL]) based on the obtained topic distributions together with additional variables like cycle flow. We identified six LDA topics which address buses and cycle paths, conflicts with parked cars, roundabouts and inadequate maintenance, fast-moving cars and lack of cycle path, school zones and heavy traffic, and intersections and interactions with vehicles. Cycle flow was found to be the highest impacter on ERL prediction. However, other factors also impacted ERLs, especially school zones and heavy traffic. The results bring new insights into safety perception and actual safety for cyclists. The results contribute to a novel procedure for the joint correlation analysis using machine learning techniques on self-reported textual data thereby providing a better tool for infrastructure planning. The findings show the importance of including perceived safety in crash modelling and that authorities should focus on safety around schools and in intersections in order to improve safety for cyclists in a urban environment.

Avoiding acid crash: From apple pomace hydrolysate to butanol through acetone-butanol-ethanol fermentation in a zero-waste approach

Apple pomace (AP) is a lignocellulosic residue from the juice and cider industries that can be valorized in a multi-product biorefinery to generate multiple value-added compounds, including biofuels such as butanol. Butanol is produced biologically by acetone-butanol-ethanol (ABE) fermentation using bacteria of the genus Clostridium from sugar-based feedstocks. In this study, AP hydrolysate was used as a substrate for producing butanol by ABE fermentation. Various environmental factors influence the amount of butanol produced, but only under certain conditions the so-called 'acid crash', an undesirable phenomenon characterized by a total arrest of cell growth and solvent production, can be avoided. Operational parameters that may influence the prevention of acid crash occurrence, such as pH, CaCO3 concentration and culture temperature, were optimized in C. beijerinckii CECT 508 cultures applying a Box-Behnken experimental design. The mathematical model of the fermentation found the optimal conditions of pH 7, 6.8 g/L of CaCO3 and 30 °C, and this was validated in an independent experiment carried out at the optimal conditions, reaching 10.75 g/L of butanol. Also, the comparison of butanol production between the supernatant of the AP hydrolysate (10.57 g/L) and the full hydrolysate with solids (11.69 g/L) indicated that it is possible to eliminate the centrifugation step after hydrolysis, which may allow to reduce process costs and the full utilization of apple pomace, aiming a zero-waste approach.

Developing Safety Performance Functions and Crash Modification Factors for Urban Roundabouts in Heterogeneous Non-Lane-Based Traffic Conditions

This study aims to develop safety performance functions (SPFs) and crash modification factors (CMFs) for the safety assessment of roundabouts as a whole and their components, especially at entry, exit, and circulating lanes. This study uses historical crash data collected over five years (2015–2019) from 21 roundabouts (78 approaches) situated in some of the major cities in India. SPF and CMF models were developed using negative binomial and cross-sectional approaches. Results show that the percentage of motorized two-wheelers, average daily traffic, central island diameter, entry angle, weaving width, departure width, number of lanes at approach, exit angle, exit width, posted speed limit, weaving length, circulating roadway width, road surface condition, number of circulatory lanes, central island height, and number of legs contribute to the crash occurrence in the roundabout vicinity. In addition to this, circulating roadway width, average daily traffic, and posted speed limit are the most influencing risk factors across the entire roundabout vicinity. Furthermore, an interesting fact is that, given the asymmetrical impact of geometric and traffic factors, the overall crash rate varies across roundabout segments. The findings of this study may be useful for updating the current design guidelines for roundabouts, considering the safety perceptive. Besides, the proposed SPF and CMF tools could be used to investigate the likelihood of crashes at roundabouts. Moreover, this model would help safety experts to implement adequate safety treatment in the vicinity of roundabouts under heterogenous non-lane-based traffic conditions.

Examining the characteristics between time and distance gaps of secondary crashes

Abstract Understanding the characteristics of time and distance gaps between the primary (PC) and secondary crashes (SC) is crucial for preventing SC ccurrences and improving road safety. Although previous studies have tried to analyse the variation of gaps, there is limited evidence in quantifying the relationships between different gaps and various influential factors. This study proposed a two-layer stacking framework to discuss the time and distance gaps. Specifically, the framework took random forests (RF), gradient boosting decision tree (GBDT) and eXtreme gradient boosting as the base classifiers in the first layer and applied logistic regression (LR) as a combiner in the second layer. On this basis, the local interpretable model-agnostic explanations (LIME) technology was used to interpret the output of the stacking model from both local and global perspectives. Through SC dentification and feature selection, 346 SCs and 22 crash-related factors were collected from California interstate freeways. The results showed that the stacking model outperformed base models evaluated by accuracy, precision, and recall indicators. The explanations based on LIME suggest that collision type, distance, speed and volume are the critical features that affect the time and distance gaps. Higher volume can prolong queue length and increase the distance gap from the SCs to PCs. And collision types, peak periods, workday, truck involved and tow away likely induce a long-distance gap. Conversely, there is a shorter distance gap when secondary roads run in the same direction and are close to the primary roads. Lower speed is a significant factor resulting in a long-time gap, while the higher speed is correlated with a short-time gap. These results are expected to provide insights into how contributory features affect the time and distance gaps and help decision-makers develop accurate decisions to prevent SCs.

Monitoring Framework for Riding Safety of Delivery Scooters using 100 Naturalistic Riding Study (NRS) Data

A traffic safety issue of two-wheeled delivery scooters is emerging because of the rapid increase in demand for food delivery services. In particular, the strict restriction of delivery time leads to aggressive and dangerous riding behavior that causes a high risk of crash occurrence. Systematic traffic safety management is required to effectively prevent crashes of delivery scooters. The objective of this study is to develop a monitoring framework for riding safety that informs when, where, and how serious safety problems occur. High-resolution riding behavior data obtained by an inertial measurement unit sensor installed on delivery scooters, as part of the Korean 100 naturalistic riding study (K-100NRS), were used for developing the methodology. The proposed monitoring framework consists of two components: an unsafe riding event detection algorithm and a method to identify the spatial and temporal identification of riding risks. The ratio of frequency of unsafe events to total riding time for each rider is defined as a monitoring index, which is referred to as the riding risk index in this study. Approximately 95% detection accuracy was achievable by the developed detection algorithm. In addition, the level of riding safety for each rider was evaluated based on the proposed methodology. As an application, a visualization of detected unsafe events was presented for the purpose of riding safety monitoring.

Predicting crash occurrence at intersections in Texas: an opportunity for machine learning

ABSTRACT This paper studies the frequency of traffic crashes at intersections across Texas by employing Zero-inflated Negative Binomial (ZINB) and Negative Binomial-Lindley (NB-L) generalized linear models, as well as various tree-based machine learning (ML) methods, namely Random Forests (RF), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Bayesian Additive Regression Trees (BART) to predict the frequency of crashes at intersections. Official crash reports from 2010 through 2019 were linked to Texas' over 700,000 intersections. RF provided best prediction performance (using R-square and Root Mean Square Error metrics) while serving well for highly imbalanced crash data (with many zero cases). Sensitivity analysis highlights the practical significance of signalized intersection, annual average daily traffic, number of lanes at intersection approach, and other covariates.

Modelling and Mitigating Secondary Crash Risk for Serial Tunnels on Freeway via Lighting-Related Microscopic Traffic Model with Inter-Lane Dependency.

This paper models and mitigates the secondary crash (SC) risk for serial tunnels on the freeway which is incurred by traffic turbulence after primary crash (PC) occurrence and location-heterogeneous lighting conditions along serial tunnels. A traffic conflict approach is developed where SC risk is quantified using a surrogate safety measure based on the simulated vehicle trajectories after PC occurs from a lighting-related microscopic traffic model with inter-lane dependency. Numerical examples are presented to validate the model, illustrate SC risk pattern over time, and evaluate the countermeasures for SC, including adaptive tunnel lighting control (ATLC) and advanced speed and lane-changing guidance (ASLG) for connected vehicles (CVs). The results demonstrate that the tail of the stretching queue on the PC occurrence lane, the adjacent lane of the PC-incurred queue, and areas near tunnel portals are high-risk locations. In serial tunnels, creating a good lighting condition for drivers is more effective than advanced warnings in CVs to mitigate SC risk. Combined ATLC and ASLG is promising since ASLG informs CVs of an immediate response to traffic turbulence on the lane where PC occurs and ATLC alleviates SC risks on adjacent lanes via smoothing the lighting condition variations and reducing inter-lane dependency.

Modelling Road Work Zone Crashes’ Nature and Type of Person Involved Using Multinomial Logistic Regression

The sustainable development goals “Good health and well-being” and “Sustainable cities and communities” of the United Nations and World Health Organization, alert governments and researchers and raise awareness about road safety problems and the need to mitigate them. In Portugal, after the economic crisis of 2008–2013, a significant amount of road assets demand investment in maintenance and rehabilitation. The areas where these actions take place are called work zones. Considering the particularities of these areas, the proposed work aims to identify the main factors that impact the occurrence of work zones crashes. It uses the statistical technique of multinomial logistic regression, applied to official data on road crashes occurred in mainland Portugal, during the period of 2010–2015. Usually, multinomial logistic regression models are developed for crash and injury severity. In this work, the feasibility of developing predictive models for crash nature (collision, run off road and running over pedestrians) and for type of person involved in the crash (driver, passenger and pedestrian), considering only one covariate (the number of persons involved in the crash), was studied. For the two predictive models obtained, the variables road environment (urban/rural), horizontal geometric design (straight/curve), pavement grip conditions (good/bad), heavy vehicle involvement, and injury severity (fatalities, serious and slightly injuries), were identified as the preponderant factors in a universe of 230 investigated variables. Results point to an increase of work zone crash probability due to driver actions such as running straight and excessive speed for the prevailing conditions.

How effective is reducing traffic speed for safer work zones? Methodology and a case study in Pennsylvania

Transportation agencies post and enforce reduced speed limits in work zones to ensure work zone safety, since traffic speed is found to be associated with work zone crash risks. However, prior findings on the relationship between speed and crash rate in work zones are inconsistent. This may be attributed to the methods of statistical associations between traffic speed and crash risks that do not necessarily discover true causal relations. In fact, work zone presence could lead to the reduction of actual traffic speed that influences crash risks, where it may also directly impose effects on crash risks as a result of work zone configurations. The actual traffic speed (not posted speed limit) is also known as a “mediator” where work zones can indirectly impact the crash risks. It is challenging to rigorously separate the causal effect of traffic speed on work zone crash risk from that directly caused by work zones. The underlying causal relation could help to determine what reduced post speed limit (with enforcement) is necessary to ensure work zone safety under the most desired “actual traffic speed”. This study proposes to use the sequential g-estimation and the regression discontinuity design to estimate the controlled direct effect of traffic speed on work zone crashes. Two research gaps are identified and filled: inaccurate inferences of the effect of reduced speed limit in work zones as a result of ignoring (1) potential post-treatment bias since traffic speed is a mediator; and (2) potential confounding bias caused by unobservable roadway characteristics. The proposed methodology was applied to 4008 work zones in Pennsylvania from 2015 to 2017, and the results were validated through a series of robustness tests. The results indicate that the direct causal effect of the presence of work zones on crash risk is significantly positive when the traffic speed is relatively low (i.e., lower than 55 mph in this case study), while traffic speed has a positive causal effect on crash occurrences when the actual traffic speed is high (i.e., greater or equal to 55 mph). It suggests that strictly enforcing reduced posted speed limits in work zones is particularly effective when the actual traffic speed is greater than 55 mph. This is particularly true on roadways with high traffic volume (i.e., AADT > 20,000 vehicles per day), long, and daytime work zones (i.e., > 3000 m). On the other hand, the effect of enforcing reduced speed on work zone safety is unclear when the actual speed is already low. In this case, improving work zone configurations and driving behaviors may be more effective in reducing crash risks.

Factors Contributing to Crashes on Low-Volume Unpaved Roads

Unpaved roads have different characteristics to paved roads. A key way of investigating potential risk factors is to analyze traffic crashes that have occurred on unpaved roads. The objective of this study was to estimate the influence of different factors on crash occurrence on unpaved roads. Five years (2016–2020) of traffic crash data from Kansas were collected and analyzed by applying binary logistic regression. Results showed that 23 factors were statistically significant among the 25 factors analyzed, which were categorized according to driver, road, and crash characteristics. Factors resulting in a higher likelihood of occurrence included the presence of farm equipment, the vicinity of yards and fields, and railroad crossings. Several factors were found to result in a low likelihood of occurrence, for example, roads with more than two lanes, interchanges, ramps, existence of a median, and low volume of traffic. However, widening the road may not guarantee crash reduction on unpaved roads. An effective step to reduce the likelihood of crashes could be proper educational programs targeting teen drivers to make them aware of the dangers of driving on unpaved roads. It is also recommended that traffic control devices should be situated at railroad crossings and locations with nearby access to farms and agricultural land. In addition, a further study could be conducted to estimate the site-specific road width and speed limits.

Application of LiDAR Data for Deep Learning Based Near Crash Prediction at Signalized Intersection

Near crash events are often regarded as an excellent surrogate measure for traffic safety research because they include abrupt changes in vehicle kinematics that can lead to deadly accident scenarios. In this paper, we introduced machine learning and deep learning algorithms for predicting near crash events using LiDAR data at a signalized intersection. To predict a near crash occurrence, we used essential vehicle kinematic variables such as lateral and longitudinal velocity, yaw, tracking status of LiDAR, etc. A deep learning hybrid model Convolutional Gated Recurrent Neural Network (CNN + GRU) was introduced, and comparative performances were evaluated with multiple machine learning classification models such as Logistic Regression, K Nearest Neighbor, Decision Tree, Random Forest, Adaptive Boost, and deep learning models like Long Short-Term Memory (LSTM). As vehicle kinematics changes occur after sudden brake, we considered average deceleration and kinematic energy drop as thresholds to identify near crashes after vehicle braking time . We looked at the next 3 seconds of this braking time as our prediction horizon. All models work best in the next 1-second prediction horizon to braking time. The results also reveal that our hybrid model gathers the greatest near crash information while working flawlessly. In comparison to existing models for near crash prediction, our hybrid Convolutional Gated Recurrent Neural Network model has 100% recall, 100% precision, and 100% F1-score: accurately capturing all near crashes. This prediction performance outperforms previous baseline models in forecasting near crash events and provides opportunities for improving traffic safety via Intelligent Transportation Systems (ITS).

Optimal Ambulance Positioning for Road Accidents With Deep Embedded Clustering

The number of casualties and fatalities brought on by road accidents is one of the most significant concerns in the modern world. Instead of dispatching ambulances only at the time of demand, pre-positioning them can reduce the response time and provide prompt medical attention. Deep learning techniques hold great potential and have proven to be essential for problem-solving and decision-making in the field of healthcare services. This study introduces a deep-embedded clustering-based approach to predict optimal locations for ambulance positing. Various factors and patterns in a geographical region greatly influence the occurrence of road crashes, hence understanding such relationships while model building is crucial. The present study also emphasizes the need of preserving such patterns during model building to ensure real-time results and implements them with the help of another deep-learning-based model, Cat2Vec. The proposed framework is also compared with traditional clustering algorithms like K-means, GMM, and Agglomerative clustering. Moreover, to calculate response time and distance in real time, a novel scoring function has also been introduced for the performance evaluation of various algorithms. The proposed ambulance-positing system exhibits remarkable performance, achieving an accuracy of 95% with k-fold cross-validation and a novel distance score of 7.581 proving the use of the proposed approach is better than all the other traditional algorithms used.

Road Infrastructure Inspections to Assess the Road Network According to the iRAP/EuroRAP methodology

The project aims at making a quality and quantity safety assessment of some road infrastructures of the Italian primary network according to the iRAP/EuroRAP methodology, with the objective of understanding which investments and speeds should be put in place to save lives and work towards international road safety targets. The indicator used for the assessment is the five-star rating system (5 stars = safe road, 1 star = unsafe road with major critical issues). The main result from this evaluation is the Star Rating, a simple and objective evaluation of the road safety level for vehicle occupants, motorcyclists, cyclists and pedestrians. It represents an objective measure of the probability of a road crash occurrence, as well as of its seriousness. A further result is the preparation of the Safer Roads Investment Plans (SRIP), which include a series of countermeasures to make the assessed roads safer. The preliminary activity to select the road sections to be inspected consisted in drafting a crash risk rate map of the Trans-European Road Network in Italy. The road traffic crash data evaluated regard the last three-year period (2017-2019). The study of the crash rate risk map of the Italian region Lazio allowed to identify about 300 km of road network, specifically 95.8 km of single carriageway roads and 113.5 km of dual carriageway roads. Inspections were carried out by FRED Engineering company; the collected data were then processed through the ViDA software in order to be assessed according the iRAP methodology. The results show a high risk level on the entire road network inspected for all road users. In total, 63% of the examined road network were rated 1 or 2 stars for vehicle occupants, but for motorcyclists the percentage of critical sections rises to 93%. The iRAP process ends up with the Investment Plans for the assessed road network, which include the possible countermeasures to be used in the various road sections for their Star Rating improvement. The objective is that all the roads are rated three stars or better. In light of these findings, a whole series of sensitivity analysis was carried out to highlight the importance and the impact of the input data on the deliverables. The considerations arising from this analysis will also be used to propose changes and/or possible releases of the ViDA assessment software.