Road Safety Risk Evaluation Using GIS-Based Data Envelopment Analysis—Artificial Neural Networks Approach

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

Introduction

Road 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.

Method

The 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.).

Results

Ten 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.

Conclusions

The 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 applications

This 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.

An application of the hybrid AHP-PROMETHEE approach to evaluate the severity of the factors influencing road accidents

The evaluation of the severity of the factors influencing road accidents with a detailed severity distribution is critical to plan evidence-based road safety improvements and strategies. However, currently available studies use statistical and machine learning (ML) models to evaluate the severity of factors causing road accidents without a detailed severity distribution. Further, most of these available models require significant pre-data processing and have certain data-centric limitations. However, the multi criteria decision-making (MCDM) techniques have the potential to combine expert opinions for robust analysis without any pre-data processing calculations. Thus, this study uses a hybrid analytic hierarchy process (AHP) and the preference ranking organisation method for enrichment evaluation (PROMETHEE) approach to analyse the severity of factors and characteristics that influence road accidents within the Gujarat state, using injury types as criteria and minor road accident influencing factors as alternatives. These 82 minor factors have been further characterised into 18 characteristics and 4 major factors. Further, AHP integrated 40 expert inputs to determine criterion weights, while PROMETHEE ranked all minor variables. Then, after applying k-mean clustering, each ranked factor has been classified as very severe, moderately severe, or severe. The result clearly highlights that overspeeding, male gender, and clear weather conditions have been concluded to be the highly severe factors for Gujarat state. Thus, by providing a clear severity analysis and distribution of factors influencing road accidents, the proposed research may help government stakeholders, researchers, and politicians build severity-based road safety reforms and strategies with clarity.

Risk Assessment of Import Cold Chain Logistics Based on Entropy Weight Matter Element Extension Model: A Case Study of Shanghai, China

The development of world trade and fresh-keeping technology has led to the rapid development of international cold chain logistics. However, the novel coronavirus epidemic continues to spread around the world at the present stage, which challenges disease transmission control and safety supervision of international cold chain logistics. Constructing an Import Cold Chain Logistics Safety Supervision System (ICCL-SSS) is helpful for detecting and controlling disease import risk. This paper constructs an evaluation index system of ICCL safety that comprehensively considers the potential risk factors of three ICCL processes: the logistics process in port, the customs clearance process, and the logistics process from port to door. The risk level of ICCL-SSS is evaluated by combining the Extension Decision-making Model and the Entropy Weight Method. The case study of Shanghai, China, the world's largest city of ICCL, shows that the overall risk level of ICCL-SSS in Shanghai is at a moderate level. However, the processes of loading and unloading, inspection and quarantine, disinfection and sterilization, and cargo storage are at high risk specifically. The construction and risk assessment of ICCL-SSS can provide theoretical support and practical guidance for improving the safety supervision ability of ICCL regulation in the post-epidemic era, and helps the local government to scientifically formulate ICCL safety administration policies and accelerate the development of world cold chain trade.

Input/Output Variables Selection in Data Envelopment Analysis: A Shannon Entropy Approach

The purpose of this study is to provide an efficient method for the selection of input–output indicators in the data envelopment analysis (DEA) approach, in order to improve the discriminatory power of the DEA method in the evaluation process and performance analysis of homogeneous decision-making units (DMUs) in the presence of negative values and data. For this purpose, the Shannon entropy technique is used as one of the most important methods for determining the weight of indicators. Moreover, due to the presence of negative data in some indicators, the range directional measure (RDM) model is used as the basic model of the research. Finally, to demonstrate the applicability of the proposed approach, the food and beverage industry has been selected from the Tehran stock exchange (TSE) as a case study, and data related to 15 stocks have been extracted from this industry. The numerical and experimental results indicate the efficacy of the hybrid data envelopment analysis–Shannon entropy (DEASE) approach to evaluate stocks under negative data. Furthermore, the discriminatory power of the proposed DEASE approach is greater than that of a classical DEA model.

Evaluation of Contributing Factors Affecting Number of Vehicles Involved in Crashes Using Machine Learning Techniques in Rural Roads of Cosenza, Italy

The evaluation of road safety is a critical issue having to be conducted for successful safety management in road transport systems, whereas safety management is considered in road transportation systems as a challenging task according to the dynamic of this issue and the presence of a large number of effective parameters on road safety. Therefore, the evaluation and analysis of important contributing factors affecting the number of vehicles involved in crashes play a key role in increasing the efficiency of road safety. For this purpose, in this research work, two machine learning algorithms, including the group method of data handling (GMDH)-type neural network and a combination of support vector machine (SVM) and the grasshopper optimization algorithm (GOA), are employed. Hence, the number of vehicles involved in an accident is considered to be the output, and the seven factors affecting transport safety, including Daylight (DL), Weekday (W), Type of accident (TA), Location (L), Speed limit (SL), Average speed (AS), and Annual average daily traffic (AADT) of rural roads in Cosenza, southern Italy, are selected as the inputs. In this study, 564 data sets from rural areas were investigated, and the relevant, effective parameters were measured. In the next stage, several models were developed to investigate the parameters affecting the safety management of road transportation in rural areas. The results obtained demonstrated that the “Type of accident” has the highest level and “Location” has the lowest importance in the investigated rural area. Finally, although the results of both algorithms were the same, the GOA-SVM model showed a better degree of accuracy and robustness than the GMDH model.

Formulating a GIS-based geometric design quality assessment model for Mountain highways

Highways play an important role in China's economic development, especially in mountainous regions. In reality, design of mountainous highways can be a challenging task due to complex geological and topographic conditions. From the safety perspective, it is also important that road geometric design defects and potential accident blind spots can be reasonably identified from the design. To this end, this study formulated an innovative Geographic Information System (GIS)-based geometric design quality assessment model for mountain highways. First, a fault tree analysis (FTA) was conducted to identify a series of highway design risk factors. Second, a decision-making trial and evaluation laboratory (DEMATEL) technique was employed to derive the factors' weight and sensitivity. Third, road driving suitability, traffic safety sensitivity, design risk factors, and effective distance were taken into account to formulate a design quality assessment model. Forth, two case studies based on a mountainous highway located in southwest China were conducted to validate this model. The case studies established that improving geometric design quality can significantly improve the road traffic safety of mountainous highways. It is also revealed that the existence of steep slopes, tunnels, and rapid horizontal and vertical alignment change can considerably compromise the geometric design quality (GDQ), therefore, configuring these parameters is worth of further investigation. Last but not least, this study provides essential knowledge to the regime of accident prevention, high-risk road section location and mapping, traffic safety management, and design of smart transport systems.

Accident risk analysis based on motorway exposure: an application of benchmarking technique for human safety

Accident risk analysis for human safety and infrastructural improvement are key requirements of the engineering sector. The purpose of this paper is to identify and prioritize problematic segments of roads based upon the risk evaluation concept and to focus on the severity of accidents regarding human life loss and easy manoeuvring. This study includes the concept of considering road segments as decision-making units for application of data envelopment analysis (DEA) technique which has no compulsion of the distribution function and critical assumptions, unlike the multiple regression models. According to the proposed methodology, a section of Motorway (M-2) Lahore-Islamabad has been analyzed. Out of 200 segments under consideration, 99 segments were selected with at least one accident and one injury or fatality. Furthermore, for risk calculation and ranking of road segments, the DEA technique along with the cross-risk matrix method was applied. This optimization technique could not only be helpful in ranking but also technical decision-making and prioritizations for safety improvement, policymaking and budget allocation.

Performance Evaluation of Bus Rapid Transit System: A Comparative Analysis of Alternative Approaches for Energy Efficient Eco-Friendly Public Transport System

The development of the bus rapid transit system (BRTS) is tremendously growing in developing countries of the world. In large cities, the projection of transportation intends to enhance economic growth and changes the image of the city for both residents and outsiders. The purpose of this research was to study the application of alternative options for energy efficient BRTS in developing countries. The BRTS has some of its accessibility patterns that relate to the socio-economic strata. A decision-making efficiency analysis methodology has been applied to analyze the comparative analysis of both conventional fuel and hybrid bus systems for the Multan city of Pakistan. The section-wise application of a hybrid energy-based bus system has been analyzed in comparison to the conventional bus system. Out of 21 stations, the efficiency-wise hybrid bus system remained superior or equivalent to the standard value of 1 except one midpoint section. The finding of the analysis indicates that the hybrid mechanism of buses can not only replace a conventional fuel-based system, but will also help as an energy-efficient and eco-friendly economical solution. This study will help to revolutionize the bus rapid transit system in developing countries.

Performance Evaluation of Sustainable Soil Stabilization Process Using Waste Materials

The process of soil stabilization is a fundamental requirement before road infrastructure development is possible. Different binding materials have been used worldwide as soil stabilizers. In this study, water treatment waste (i.e., alum sludge (AS)) was used as a soil stabilizer. Alum sludge can work not only as a low-cost soil stabilizer but also can solve the problem of waste management at a large scale. Utilization of alum waste can be a sustainable solution and environmentally friendly exercise. Thus, in consideration of the pozzolanic properties of alum, it was applied as a binder, similar to cement or lime, to stabilize the soil with the addition of 2%, 4%, 6%, 8%, and 10% of dry soil by weight. To analyze the resulting improvement in soil strength, the California Bearing Ratio (CBR) test was conducted in addition to three other tests (i.e., particle size analysis, Atterberg’s limits test, and modified proctor test). The soil bearing ratio was significantly improved from 6.53% to 16.86% at the optimum level of an 8% addition of alum sludge. Furthermore, the artificial neural networks (ANNs) technique was applied to study the correlations between the CBR and the physical properties of soil, which showed that, at 8% optimum alum sludge, maximum dry density, optimum moisture content, and plasticity index were also at maximum levels. This study will help in providing an eco-friendly soil stabilization process as well as a waste management solution.

Road Infrastructure Analysis with Reference to Traffic Stream Characteristics and Accidents: An Application of Benchmarking Based Safety Analysis and Sustainable Decision-Making

Road infrastructure sustainability is directly associated with the safety of human beings. As a transportation engineer and policymaker, it is necessary to optimize the funding mechanism for road safety improvement by identifying problematic road segments. Infrastructure improvement is one of the key targets for efficient road safety management. In this study, data envelopment analysis (DEA) technique has been applied in combination with a geographical information system (GIS) to evaluate the risk level of problematic segments of a 100 km-long motorway (M-2) section. Secondly, the cross efficient method has been used to rank the risky segments for prioritization and distribution of funding to improve the road safety situation. This study will help in efficiently identifying the risky segments for safety improvement and budget allocation prioritization. GIS map will further improve the visualization and visibility of problematic segments to easily locate the riskiest segments of the motorway.

Relationship between road traffic features and accidents: An application of two-stage decision-making approach for transportation engineers

INTRODUCTION

An efficient decision-making process is one of the major necessities of road safety performance analysis for human safety and budget allocation procedure.

METHOD

During the road safety analysis procedure, data envelopment analysis (DEA) supports policymakers in differentiating between risky and safe segments of a homogeneous highway. Cross-risk, an extension of the DEA models, provides more information about risky segments for ranking purpose. After identification of risky segments, the next goal is to identify the factors that are major contributors in making that segment risky.

RESULTS

This research proposes a methodology to analyze road safety performance by using a combination of DEA with the decision tree (DT) technique. The proposed methodology not only provides a facility to identify problematic road segments with the help of DEA but also identifies contributing factors with the help of DT. Practical applications: The applicability of the proposed model will help policymakers to identify the major factors contributing to road accidents and analysis of safety performance of road infrastructure to allocate the budget during the decision-making process.

A Damage Identification Approach for Offshore Jacket Platforms Using Partial Modal Results and Artificial Neural Networks

This paper presents a damage identification method for offshore jacket platforms using partially measured modal results and based on artificial intelligence neural networks. Damage identification indices are first proposed combining information of six modal results and natural frequencies. Then, finite element models are established, and damages in structural members are assumed by reducing the structural elastic modulus. From the finite element analysis for a training sample, both the damage identification indices and the damages are obtained, and neural networks are trained. These trained networks are further tested and used for damage prediction of structural members. The calculation results show that the proposed method is quite accurate. As the considered measurement points of the jacket platform are near the waterline, the prediction errors keep below 8% when the damaged members are close to the waterline, but may rise to 16.5% when the damaged members are located in deeper waters.

Stability Prediction Model of Roadway Surrounding Rock Based on Concept Lattice Reduction and a Symmetric Alpha Stable Distribution Probability Neural Network

To combat the uncertainty of the multiple factors affecting roadway surrounding rock stability, five initial indexes are selected for reduction according to concept lattice theory: rock quality designation (RQD), uniaxial compressive strength (Rc), the integrity coefficient of rock mass, groundwater seepage, and joint condition. The aim of this study is to compute correlation coefficients among various indexes and verify the effectiveness of lattice reduction. Alpha stable distribution is used to replace the commonly used Gauss distribution in probabilistic neural networks. A prediction model for the stability of roadway surrounding rock is then established based on a concept lattice and improved probabilistic neural network. 100 groups of training sample data are plugged into this model one by one to examine its rationality. The established model is employed for engineering application prediction with ten indiscriminate sample groups from the Jianlinshan mining area of the Daye iron mine, revealing accuracy of up to 90%. This demonstrates that our prediction model based on a concept lattice and improved probabilistic neural network has high reliability and applicability.