Road Network Safety Research Articles

Seismic fragility and risk assessment of Reinforced Concrete bridges undergoing elastomeric bearing deformations induced by landslide

The paper presents a study on the seismic fragility of Reinforced Concrete (RC) bridges isolated by elastomeric bearing devices subjected to differential displacements induced by slow-moving landslides. The seismic behaviour of isolated bridges is ruled by the performance of elastomeric bearings to reduce and dissipate earthquake actions. These bridges are subjected to service loads that usually are accounted for in design, but possible additional actions from the surrounding environment, such as landslides affecting substructure components, can seriously undermine the seismic response. The paper describes a practical approach to investigate the seismic fragility and risk of RC bridges isolated by elastomeric bearings, which may undergo early deformations induced by the differential displacements of substructure components. On the basis of previous existing studies, the proposed methodology is based on numerical modelling accounting for landslide-induced substructure displacements and proper modifications on the constitutive law and hysteretic response of the elastomeric bearings. Subsequently, after establishing specific limit-states, nonlinear time history analyses of the seismic response are used to estimate fragility curves and risk indicators. The study points out that it is possible to quantify the influence of landslide-induced effects on seismic fragility and risk by using only two numerical models, in order to provide decision support to transportation authority responsible for ensuring the safety of bridges and road networks. The proposed approach has been tested on a real-life case study, the Santo Stefano Viaduct in Italy, which was subjected in the past to relevant deformations of the elastomeric bearings due to an active landslide phenomenon.

The integrated methodology for assessing the safety of the road network infrastructure in Romania.

Abstract Romania has the highest road fatality rate in the EU and the lowest perception of road quality. This study presents the implementation of a preliminary procedure and tools provided by the European Commission for the safety assessment of the DN2-E85 road infrastructure, which covers 472.23 km. This road was selected due to the high number of road deaths between 2017 and 2022. The research focuses on the application of both proactive and reactive methodologies as required by Directive (EU) 2019/1936, which requires full road network safety assessments by 2024, with subsequent assessments every five years. The proactive methodology assesses the built-in road safety of the road infrastructure based on design parameters, while the reactive methodology is based on historical data on accidents and traffic flows. The integration of these methodologies allows the classification of road segments into five risk levels. Preliminary results indicate that approximately 59% of the length of the DN2-E85 road is classified as “very high priority”, highlighting significant safety deficiencies, which require actions to immediately improve traffic safety. This study highlights the need for systematic road infrastructure safety assessments and prioritisation of high-risk segments to reduce road fatalities and improve overall road safety. The findings serve as crucial information for road safety auditors and the Romanian Road Authority - ARR, supporting the identification of high-risk areas and the allocation of resources to improve safety. In addition, this research provides a basic basis for future adaptations of road infrastructure safety assessment guidelines, considering the specific characteristics of national and county roads. By aligning with EU directives and national standards, the study aims to increase road safety and reduce the incidence of serious accidents in Romania. The insights gained from this research are essential for developing effective road safety strategies and implementing remedial measures that address the most dangerous segments of the road network.

Road infrastructure maintenance: Operative method for interventions’ ranking

Planned maintenance of transportation infrastructure is a milestone in maintaining the functionality and safety of road networks. This paper is part of this process and aims to propose an easily applicable and versatile operational methodology for prioritizing maintenance interventions generally scheduled on road networks of considerable extent. An operational methodology for ranking and prioritizing maintenance interventions is proposed; this method is applicable to road networks of such size that direct inspection of each situation is impossible. The core of the paper is the analytical description of this methodology, based on a weighted sum function of three blocks: i) Category − is a score related to the purpose of the intervention; ii) Asset − is a score due to the road on which the intervention is located (considering Average Daily Traffic, Accidentality, Social Cost, Road Type, Routes); iii) Typology − is a score related to the element on which the intervention is being carried out. After describing the parameters and the implementation procedure for each block, the calibration of the relative weights is described, and a sensitivity analysis is performed. In the case study, the proposed methodology is applied to the ANAS corporate network in Italy. This case study will highlight the usefulness, versatility, and operability of the methodology with GIS (Geographic Information System) tools for implementing thematic maps. A concluding section concerns the addition of a scoring block − Spatial Context − as an additional differentiating factor due to the spatial context of each road.

Systematic review, evaluation and comparison of different approaches for the implementation of road network safety analysis

IntroductionRoad safety is still a major issue all around the world. The capability to analyze the road network and identify high risk sections is crucial in road safety management. Therefore, it is essential for road administrations, practitioners, and researcher to have a clear and practical framework of the available road network safety analysis procedures. The aim of this study is to provide such a framework by carrying out an exhaustive analysis of the main procedures available all around the world. MethodThe proposed literature review has started considering a web search on Web of Science (WoS). Then, a systematic review of each publication has been carried out using the Bibliometrix software, to identify the main characteristics of the publications within the specific topic. Then, the most relevant and widespread safety analysis procedures have been considered and the following aspects have been analyzed: the type of approach (crash analysis, crash prediction models procedures, based on road safety inspections, etc.), which and how many data are required (crashes, traffic, visual inspections, geometrical data, etc.), which is the effectiveness of the procedure, and which are the segmentation criteria used (fixed length, variable length based on geometry, traffic, etc.). ResultsTen different procedures for road network safety analysis have been considered for detailed analysis. The research findings highlight that each procedure has its own pros and cons. ConclusionsThe choice of the best procedure to use is highly related to the characteristics of the road network that need to be analyzed, to the availability of data, and to the main elements the Road Authorities (RA) wants to give priority to. Practical applicationsThis collection and review of different procedures will be of great interest for RAs, practitioners, and researchers in the process of selecting the most useful procedure to use to carry out a road network safety analysis.

Predictive models for flexible pavement fatigue cracking based on machine learning

Pavement performance prediction is crucial for ensuring the longevity and safety of road networks. In our extensive study, we employ a diverse array of techniques to enhance fatigue performance models in flexible pavements. The methodology begins with Random Forest feature selection, identifying the top 15 critical variables that significantly impact pavement performance. These variables form the basis for subsequent model development. Our investigation into model performance indicates the superiority of advanced machine learning methods such as Regression Trees (RT), Gaussian Process Regression (GPR), Support Vector Machines (SVM), Ensemble Trees (ET), and Artificial Neural Networks (ANN) over traditional linear regression methods. This consistent outperformance underscores their potential to reshape forecasting accuracy. Through extensive model optimization, we reveal robust performance across both complete and selected feature sets, emphasizing the importance of meticulous feature selection in enhancing forecast accuracy. The accuracy of our best optimized machine learning model is highlighted by its Performance Measurement metrics: RMSE of 22.416, MSE of 502.46, R-squared of 0.80848, and MAE of 8.9958. Additionally, comparative analysis with previous empirical models demonstrates that our best optimized machine learning model outperforms existing empirical models. This work underscores the significance of feature curation in pavement performance prediction, highlighting the potential of sophisticated modeling methodologies. Embracing cutting-edge technologies facilitates data-driven decisions, ultimately contributing to the development of more robust road networks, enhancing safety, and prolonging lifespan.

Road infrastructure safety assessment using the integrated method - case study DN2.

This study aims to practically test, identify vulnerabilities and analyses the limits of working tools for assessing road network safety and validate the integrated method proposed by the European Commission in the context of different technical classes of national roads in Romania. The research aims to adapt, convert, and transform the calculation values of the formulas of the proactive evaluation tool to the values used by national norms for road design and construction. 2 evaluation parameters are analysed, which represent the width of the traffic lane, respectively the widths and type of shoulders. On the other hand, the study is a tool for analysing road infrastructure safety, for efficiently allocating resources and for prioritising specific road safety inspections on the most dangerous sections of roads. The case study is the comparison of the results obtained from the safety assessment of DN 2 road infrastructure, both by the proposed test method and by the method adopted by the European Commission following Member States’ comments.

Assessing road roughness using UAV-derived dense point clouds

The quality and safety of road networks are of paramount importance in modern transportation infrastructure. Road surface conditions, particularly road roughness, significantly impact vehicular travel safety, user comfort, vehicle operating costs, and overall road infrastructure maintenance. Traditional methods for road roughness analysis, such as manual inspections or image annotation, often present limitations in terms of data completeness, efficiency, and cost-effectiveness, especially for extensive road networks. This study investigates the potential of Unmanned Aerial Vehicles (UAVs) equipped with Structure-from-Motion (SfM) derived point clouds to transform road roughness assessment. By leveraging the capabilities of UAVs, including rapid data acquisition and high-resolution imagery, and employing SfM to generate detailed point clouds, this research aims to provide a comprehensive analysis of road surface conditions. The study, conducted on a road segment within the Harran University Osmanbey campus, systematically examines road roughness at different kernel sizes: 30 cm (smaller), 50 cm (moderate), and 75 cm (larger). Through this investigation, insights are gained into how different scales of analysis influence roughness measurements. The findings highlight the potential of UAV-derived point clouds as a promising avenue for road roughness analysis, offering transportation authorities and road administrators an efficient and cost-effective means of maintaining and enhancing road networks. The integration of this technology could lead to the development of safer, more efficient, and economically sustainable road transportation systems, benefiting both road users and infrastructure managers. As research and technological advancements in UAV-based road roughness assessment continue to progress, the potential for revolutionizing road management practices becomes increasingly apparent, ultimately leading to improved road quality and enhanced travel experiences for road users.

ПРОЄКТУВАННЯ АВТОМАГІСТРАЛЕЙ КОНТИНЕНТАЛЬНОГО, СУБКОНТИНЕНТАЛЬНОГО ТА ТРАНСРЕГІОНАЛЬНОГО СПОЛУЧЕННЯ В РОЗРІЗІ ПОЛОЖЕНЬ ЗАКОНОДАВЧИХ АКТІВ ЄС

Introduction. The introduction to the paper highlights the importance of the design and construction of highways of various link functions levels as a key factor in modern integration processes and also emphasizes the role of highways for substantial increasing of the road network safety. Problem statement. The issues of the paper concern aspects of highways design based on the experience of European colleagues in the context of the provisions of the relevant legislative acts of EU. Purpose. The goal of the paper is to analyze the main provisions for the design of continental, subcontinental and transregional highways considering, within the format of the publication, the design features of the highways elements which are universal for various design systems. Results. The highways categorization regarding their link functions levels and with this categorization linked classification by design classes were reviewed which accept the highways jurisdiction and the build-up areas related location and also the corresponding restrictions on vehicle speed limits. The highways characteristics were defined allowing the determination of highways as a separate category of motor roads in the world-wide practice of the road building industry.

Application of artificial intelligence in road network inventory and network-wide road safety assessment

This research paper examines the application of artificial intelligence (AI) in road network inventory and network-wide road safety assessment. An overview of current research related to this field is presented and various aspects of the use of AI in road infrastructure and safety assessment are analysed. In today’s world, where the road network continues to develop and grow, the use of AI can offer significant advantages in the inventory and assessment of road infrastructure and safety. AI can be used to process large volumes of data collected from various sources such as geographic data, photos, documentation and more. One of the main aspects that the article looks at is the use of AI to automatically process data and create a digital inventory of the road network. AI systems can analyse geographic data and photos to identify and classify roads, road signs, markings, and other elements of road infrastructure. This can facilitate engineers and competent authorities in the process of road inventory and maintenance. Another important aspect discussed in the paper is the use of AI for the general assessment of road safety. AI models can analyse road infrastructure inventory data, as well as traffic data, crashes, and other factors, to provide a comprehensive assessment of road network safety. This allows the competent authorities to identify vulnerable places, carry out preventive measures and plan appropriate interventions aimed at improving road safety. In conclusion, the paper highlights the possibilities and advantages of using artificial intelligence in road network inventory and network-wide road safety assessment. Such an approach can contribute to more efficient management of road infrastructure and improvement of road safety.

Pothole Detection in Roads using Pretrained Model and Cloud Computing

Abstract—The fundamental objective of this project is to make use of the advanced capabilities offered by technology that is cur- rently available on the market in order to locate and accurately identify potholes. The research identifies potholes in real-time video feeds obtained from vehicles by employing YOLOv8, a dependable pre-trained model for object detection. Utilising an Internet of Things (IoT) gateway, which creates a connection with Kinesis Video Streams in order to collect the video data, makes the procedure simpler and more efficient.The combination of the YOLOv8 algorithm with the Amazon SageMaker platform enables the accurate detection and localization of potholes within the frames of a particular film. The project makes use of the computing power made available by Amazon Web Services (AWS) in order to make the effective processing and analysis of video data inside a cloud-based environment possible.After the algorithm has determined that potholes are present, it will proceed to take precise notes of the coordinates that correlate to each individual hole. The data described above is gathered and saved within the environment provided by AWS, which provides helpful insightsfor operations relating to maintenance and repair. Because of the combination of pretrained models, cloud-based infrastructure, and Internet of Things (IoT) components, a dependable and scalable solution for the prompt identification of potholes has been produced. This has resulted in an improvement in both the safety of road networks and their maintenance. Index Terms—pothole detection, deep learning, cloud comput- ing, object detection, pretrained models, convolutional neural networks

Improvement of road infrastructure on the example of the Center-South transport corridor of the Akchatau-Akzhal section

The study investigates the enhancement of road infrastructure in the Center-South transport corridor of the Akchatau-Akzhal section, addressing the challenges posed by rapid road pavement deterioration due to increased traffic flow. By analyzing the natural and climatic conditions of the area, optimal concentrations of additives were determined to improve the properties of bitumen and asphalt concrete, with a focus on increasing strength and durability. Specifically, the addition of monoethanolamine to bitumen at a concentration of 0.08% led to notable improvements in key properties. The needle penetration depth at 25°C decreased from 80 to 71, indicating enhanced consistency. Moreover, the ring and ball softening point increased from 52 to 56, demonstrating increased resistance to temperature variations. Stretchability at 40 improved from 65 to 70, highlighting enhanced flexibility and durability. The study emphasizes the critical importance of quality construction and regular maintenance to ensure the durability and resilience of road networks to various factors. By utilizing innovative technologies and materials, such as modified binders with additives, the study showcases the potential to significantly enhance the performance, safety, and efficiency of road networks while reducing costs and environmental impact. The findings underscore the need for continued research and implementation of optimized solutions to improve road infrastructure sustainability and longevity.

CGAN-EB: A non-parametric empirical Bayes method for crash frequency modeling using conditional generative adversarial networks as safety performance functions

In this paper, a new non-parametric empirical Bayes approach called CGAN-EB is proposed for approximating empirical Bayes (EB) estimates in traffic locations (e.g., road segments) which benefits from the modeling advantages of deep neural networks, and its performance is compared in a simulation study with the traditional approach based on negative binomial model (NB-EB). The NB-EB uses negative binomial model in order to model the crash data and is the most common approach in practice. To model the crash data in the proposed CGAN-EB, conditional generative adversarial network is used, which is a powerful deep neural network based method that can model any types of distributions. A number of simulation experiments are designed and conducted to evaluate the CGAN-EB performance in different conditions and compare it with the NB-EB. The results show that CGAN-EB performs as well as NB-EB when conditions favor the NB-EB model (i.e. data conform to the assumptions of the NB model) and outperforms NB-EB in experiments reflecting conditions frequently encountered in practice, specifically low sample means, and when crash frequency does not follow a log-linear relationship with covariates.

The contribution of the frequency ratio model and the prediction rate for the analysis of landslide risk in the Tizi N'tichka area on the national road (RN9) linking Marrakech and Ouarzazate

Road infrastructure is vital for economic development, connecting various locations. However, in Morocco, landslides pose recurring challenges to road projects due to factors like lithology, climate, rift structures, and high altitudes in the High Atlas Mountains. Developing susceptibility maps for landslides is crucial to anticipate and take appropriate actions. National Road Number 9, particularly the Tizi N'tichka region in the High Atlas, experiences significant landslide issues. This study used frequency ratio (RF) and prediction rate (PR) techniques to map landslide susceptibility along this road section connecting Marrakech and Ouarzazate. By analyzing thirteen factors, including elevation, curvature, precipitation, slope, and land use, a landslide sensitivity index (LSI) was created. A landslide inventory of 214 locations was prepared, with 70% (150 events) used for model training and 30% (64 events) for validation. The resulting sensitivity map classified areas into five categories of landslide susceptibility. The model's effectiveness was evaluated using the receiver operating characteristic (ROC) curve technique, yielding an AUC value of 92.3% during validation. The findings demonstrate the efficacy of RF and PR methods in landslide susceptibility mapping. It helps identify high-risk areas along National Road Number 9 in the Tizi N'tichka region, enabling proactive measures for mitigating landslide impacts on road infrastructure. These outcomes serve as a foundational basis for conducting further research and verifying the performance of alternative methods such as the susceptibility index model (SII), the inventory validation (IV) model, and the weight of evidence (WoE) model Overall, this research contributes to better anticipation and management of landslides, ensuring the reliability and safety of road networks in the studied region and beyond the geographical boundaries.

Determination of Safety-Oriented Pavement-Friction Performance Ratings at Network Level Using a Hybrid Clustering Algorithm

Pavement friction plays a crucial role in ensuring the safety of road networks. Accurately assessing friction levels is vital for effective pavement maintenance and for the development of management strategies employed by state highway agencies. Traditionally, friction evaluations have been conducted on a case-by-case basis, focusing on specific road sections. However, this approach fails to provide a comprehensive assessment of friction conditions across the entire road network. This paper introduces a hybrid clustering algorithm, namely the combination of density-based spatial clustering of applications with noise (DBSCAN) and Gaussian mixture model (GMM), to perform pavement-friction performance ratings across a statewide road network. A large, safety-oriented dataset is first generated based on the attributes possibly contributing to friction-related crashes. One-, two-, and multi-dimensional clustering analyses are performed to rate pavement friction. After using the Chi-square test, six ratings were identified and validated. These ratings are categorized as (0, 20], (20, 25], (25, 35], (35, 50], (50, 70], and (70, ∞). By effectively capturing the hidden, intricate patterns within the integrated, complex dataset and prioritizing friction-related safety attributes, the hybrid clustering algorithm can produce pavement-friction ratings that align effectively with the current practices of the Indiana Department of Transportation (INDOT) in friction management.

THE INTERACTION OF THE FUNCTIONAL CLASSIFICATION OF STREETS AND ROADS AND THE URBAN ENVIRONMENT

The article considers issues aimed at improving conditions and traffic safety of street and road networks in cities and the possibility of using the functional classification of streets and roads. The development of cities is inextricably linked to the improvement of street and road networks. It is the street-road network that is the chain that connects it with the general ways of communication. The city cannot exist without public roads that provide a large amount of transportation, cargo and passengers, which are distributed among the functional zones of the city. The current regulatory document provides for the distribution of streets and roads, according to the classification into categories, but, unfortunately, their functional component is missing. In Ukraine, works related to the introduction of changes to the regulatory document are underway and are aimed at developing the functional purpose of streets and roads. The norms of the «Committee on Urban Territories», which belongs to the world-famous road association «PIARS» and the work of the special project «ARTISTS», are defined in the European classification. Attention should be paid to the significant variety of features in the European classification. It should be noted that in the USA and Canada, the functional classification provides for the functions of the specified road, and the main feature is «traffic service – access service». The US uses classifications based on the administrative level of the state, subject to the Department of Transportation "DOT" with mandatory consideration of the requirements of counties and municipal agencies. Great importance is attached to the requirements of the «Green book» – a green book belonging to the American Association of Highway and Transportation Officials (AASHTO). Canada also has its own distinctions for the preparation of functional classifications, which are based on the «Manual on geometric standards for the design of Canadian roads». They share similar features with the US in terms of defining three categories of streets, namely: Arterial Streets, Collector Streets and Local Streets. Also attracting attention are developments according to pedestrian traffic and low-white population groups. No less interesting are the features of the planning infrastructure in Western Australia. A comfortable environment is declared the official urban planning policy of the State Planning Commission of Western Australia (Western Australian Planning Commission). The concepts of creating a «livable environment» and «livable streets» were considered. In order to create a comfortable environment for living, attractive public spaces, preservation of the environment, the reasons for the concept were also economic factors. The main tasks of designing street and road networks, as well as directions and measures for their solution, are taken into account in the PIARC applications on the functional classification of city streets and roads. These recommendations systematize and summarize the classifications used by many countries in the process of designing street and road networks. Special attention is paid to main arterial streets, as well as architectural, landscape and urban design, safety and organization of traffic and pedestrian traffic. Keywords: street and road network, traffic safety, functional classification, pedestrian flows, project solutions.

LoS-Map Construction for Proactive Relay of Opportunity Selection in 6G V2X Systems

Recent advances in Vehicle-to-Everything (V2X) technology and the upcoming sixth-generation (6G) network will dawn a new era for vehicular services with enhanced communication capabilities. Connected and Autonomous Vehicles (CAVs) are expected to deliver a new transportation experience, increasing the safety and efficiency of road networks. The use of millimeter-wave (mmW) frequencies guarantees a huge amount of bandwidth ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$&gt;$</tex-math></inline-formula> 1GHz) and a high data rate ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$&gt;$</tex-math></inline-formula> 10 Gbit/s), which are required for CAVs applications. However, high frequency is impaired by severe path loss, and line of sight (LoS) propagation can be easily blocked by static and dynamic obstacles. Several solutions are being investigated, and the most promising one exploits relays. However, traditional relay schemes react to link failure and leverage instantaneous information, which impedes efficient relay selection in highly mobile and complex networks, such as vehicular scenarios. In this context, we propose a novel proactive relaying strategy that exploits the cooperation between CAVs and environment information to predict the dynamic <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LoS-map</i> , which describes the links' evolution in time. The proactive relaying schemes exploit the dynamic <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LoS-map</i> to maximize the network connectivity. A novel framework integrating realistic mobility patterns and geometric channel propagation models is proposed to analyze the performance in different scenarios. Numerical simulations suggest that a novel proactive relaying strategy that exploits the cooperation between CAVs and environment information to predict the dynamic <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LoS-map</i> , which describes the links' evolution in time. .

Detection of Road Condition Defects Using Multiple Sensors and IoT Technology: A Review

The transportation efficiency and driving safety of road networks, which play an essential role in economic prosperity, are impacted significantly by damage and defects on the road surface. In current practice, it can take weeks or even months before related government departments repair such road conditions, mainly due to lack of awareness of any damage. This paper reviews the current status and limitation of a framework for sensors devices and assessment of road surface conditions. The review also incorporates the most relevant machine learning-based methods, challenges, and future trends to underpin large-scale deployment of road defects automation identification. It is expected that the technology can provide both qualitative and quantitative information about the road surface condition and thus enable timely maintenance to improve transportation efficiency and driving safety.

Integrated seismic vulnerability assessment of road network in complex built environment toward more resilient cities

The road network is recognized as an important infrastructure system that is playing an essential role in making cities more sustainable and resilient. Hence, it is crucial to increase the safety and resiliency of urban road networks against external shocks such as earthquakes, by ensuring that they function efficiently within the complex-built environment systems in that they reside. Previous research on disaster risk management for road networks focused mainly on the assessment of the physical vulnerability for one criterion, without considering multiple vulnerability criteria of the road infrastructure and its interaction with the built environment. The primary goal of this research is to present an integrated vulnerability assessment approach based on intrinsic and eccentric characteristics of road networks. The proposed method employs two Vulnerability Indexes (VI); the first one assesses the Intrinsic Seismic Vulnerability (ISVI) of the network that considers the direct physical damage of the roadway system, while the second one, is the Eccentric Seismic Vulnerability (ESVI) that is based on the damage of the surrounding damaged buildings surrounding the roads. Subsequently, the correlation between the assessed indexes is utilized to provide a more holistic assessment tool in support of emergency and evacuation plans during earthquake incidents. These indexes are applied to assess the accessibility to emergency critical service centres based on a territorial framework for an urban area. The methodology and case study show the importance of the integrated seismic vulnerability assessment in the resilience of critical city infrastructure, for enhancing emergency access and implementing effective risk mitigation measures.

Real-time safety analysis using autonomous vehicle data: a Bayesian hierarchical extreme value model

This study proposes an approach for real-time road network safety analysis using autonomous vehicles (AVs) generated data. The approach utilises a Bayesian hierarchical spatial random parameter extreme value model (BHSRP). The model simultaneously addresses the scarcity and non-stationarity of conflict extremes and unobserved spatial heterogeneity. Two real-time safety metrics are estimated: the risk of crash (RC) and return level (RL). The RC and RL were applied to three months AVs data for evaluating the real-time safety level of an urban corridor in Palo Alto, California. The indicator time to collision (TTC) was used to characterise traffic conflicts. The conflict extreme was defined as the maxima of negated TTC in a 20-min interval (block). The results show that RC can differentiate the block-level risk level, while RL can reflect safety levels among blocks. For the RC, the hot (crash risk prone) segments and intersections are associated with more severe conflict frequency.

IoT for measuring road network quality index

Egypt has been fighting the issue of ensuring road safety‚ reducing accidents‚ preserving the lives of citizens since its inception. For these reasons‚ precisely identifying the road condition‚ followed by effective and timely maintenance and rehabilitation measures‚ leads to an increase in the road network's safety level and lifespan. This paper presents a multi-input deep learning framework that combines BiLSTM and Depthwise separable convolution to work in parallel for automatic recognition of road surface quality and different road anomalies. Furthermore, we performed an investigation to compare deep networks approaches against other traditional approaches using real-time data sensed and collected from the Egyptian road network. The proposed deep model has achieved an average accuracy of 93.1%‚ which is superior compared to other evaluated approaches. Finally, we utilized the proposed model to estimate a road quality index in the Egyptian cities.