Road Black Spots Research Articles

Identification of Road Black Spots Based on the Sliding Window Optimization and Safety Performance Function Development

The sliding window method is a road network screening approach commonly used for identifying black spots. Previous studies have indicated that the selection of window length significantly impacts the black spot identification process. This research proposes a new method that optimizes the sliding window framework by examining its characteristics. The optimization methodology employed in this study is as follows: Firstly, the road is segmented, and for each segment, different scenarios of window lengths are chosen using the Density-Based Spatial Clustering of Applications with Noise algorithm. Next, a Safety Performance Function is developed to calculate the predicted and expected number of crashes, as well as the Potential Safety Improvement, for each window movement across all selected scenarios within the segment. Subsequently, the average differences are calculated using the analysis of variance, and the window length with the lowest dispersion of difference values from the mean is identified as the optimal length for each segment. The case study yielded noteworthy results, indicating that the utilization of the sliding window with optimal lengths led to the identification of 122 high-risk black spot-candidates. These points exhibit a higher crash density, effective length, and greater value in quantitative evaluation tests compared to the results obtained using windows with common fixed lengths.

Leveraging Positive-Unlabeled Learning for Enhanced Black Spot Accident Identification on Greek Road Networks

Identifying accidents in road black spots is crucial for improving road safety. Traditional methodologies, although insightful, often struggle with the complexities of imbalanced datasets, while machine learning (ML) techniques have shown promise, our previous work revealed that supervised learning (SL) methods face challenges in effectively distinguishing accidents that occur in black spots from those that do not. This paper introduces a novel approach that leverages positive-unlabeled (PU) learning, a technique we previously applied successfully in the domain of defect detection. The results of this work demonstrate a statistically significant improvement in key performance metrics, including accuracy, precision, recall, F1-score, and AUC, compared to SL methods. This study thus establishes PU learning as a more effective and robust approach for accident classification in black spots, particularly in scenarios with highly imbalanced datasets.

Long-Term-Based Road Blackspot Screening Procedures by Machine Learning Algorithms

Screening procedures in road blackspot detection are essential tools for road authorities for quickly gathering insights on the safety level of each road site they manage. This paper suggests a road blackspot screening procedure for two-lane rural roads, relying on five different machine learning algorithms (MLAs) and real long-term traffic data. The network analyzed is the one managed by the Tuscany Region Road Administration, mainly composed of two-lane rural roads. An amount of 995 road sites, where at least one accident occurred in 2012–2016, have been labeled as “Accident Case”. Accordingly, an equal number of sites where no accident occurred in the same period, have been randomly selected and labeled as “Non-Accident Case”. Five different MLAs, namely Logistic Regression, Classification and Regression Tree, Random Forest, K-Nearest Neighbor, and Naïve Bayes, have been trained and validated. The output response of the MLAs, i.e., crash occurrence susceptibility, is a binary categorical variable. Therefore, such algorithms aim to classify a road site as likely safe (“Accident Case”) or potentially susceptible to an accident occurrence (“Non-Accident Case”) over five years. Finally, algorithms have been compared by a set of performance metrics, including precision, recall, F1-score, overall accuracy, confusion matrix, and the Area Under the Receiver Operating Characteristic. Outcomes show that the Random Forest outperforms the other MLAs with an overall accuracy of 73.53%. Furthermore, all the MLAs do not show overfitting issues. Road authorities could consider MLAs to draw up a priority list of on-site inspections and maintenance interventions.

Identifying Urban Road Black Spots with a Novel Method Based on the Firefly Clustering Algorithm and a Geographic Information System

With the rapid development of urban road traffic, there are a certain number of black spots in an urban road network. Therefore, it is important to create a method to effectively identify the urban road black spots in order to quickly and accurately ensure the safety of residents and maintain the sustainable development of a city. In this study, a GIS (geographic information system) and the Firefly Clustering Algorithm are combined. On the one hand, a GIS can accurately extract the distance between accident points through its spatial analysis function, overcoming the disadvantage of the accident data not usually including the specific location data. On the other hand, the Firefly Clustering Algorithm can be used to comprehensively extract the characteristics of accident points, which is particularly suitable for the identification of black spots. In order to verify the feasibility of the proposed method, this research compares the identification effect between the OD (origin–destination) cost distance calculated by GIS and the Euclidean distance. The results show that the Euclidean distance is smaller than the OD cost distance and that the accident search method based on the Euclidean distance can overestimate the number of black spots, especially for intersections. Therefore, the proposed method based on the Firefly Clustering Algorithm and GIS can not only contribute to identifying urban road black spots but also plays an auxiliary role in reducing urban road crashes and maintaining sustainable urban development.

교차로에서의 도로·교통안전시설물의 교통사고 감소효과도 추정

교통사고 잦은 곳 개선사업은 교통사고 예방을 위하여 도로상에 도로안전 관련 시설물을 설치함으로써 도로 환경적 요인에 대한 결함을 제거하는 대표적 교통안전개선사업이다. 그러나 개선사업으로 인해 설치된 각 시설물들에 대한 효과평가에 대한 연구는 미비하였다. 따라서 본 연구에서 도로 교통안전 관련 시설물의 교통사고 감소효과도를 추정하기 위하여 최근 2004년부터 2013년까지 교통사고 잦은 곳 개선사업 공사가 완료된 4,171개 지점을 대상으로 비교그룹방법을 활용하여 5가지 시설물에 대한 교통사고 감소효과도를 추정하였다. 분석 결과, 전체 교통사고에 대해서는 교통섬 4.45%, 표지병 32.17%, 과속단속카메라 24.13% 사고감소 효과를 나타냈으며, 반면 무단횡단금지시설 0.61%, 미끄럼방지포장은 1.67% 만큼 증가한 것으로 나타났다. 또한 표지병, 무단횡단금지시설, 미끄럼방지포장과 같이 국토교통부의 "도로안전시설 설치 및 관리지침"에서 특정유형의 교통사고 예방에 효과가 있다고 언급된 시설물들의 교통사고 감소효과도를 추가적으로 분석하였다. 그 결과, 표지병은 악천후 시 교통사고에 대해서 52.96%, 무단횡단금지시설은 차대보행자 교통사고에 대해서 62.77%, 미끄럼방지포장은 추돌사고에 대해서 26.60%의 순수 교통사고 감소효과가 있는 것으로 분석되었다. Accident Black Spot Improvement Project is the representative road safety intervention to eliminate environmental risk factors on the roadway by installing road safety facilities. Although it is one of the main road safety projects in Korea, there has been a lack of effort analyzing the traffic accident reduction effects of this project. In this study, therefore, we selected 4,171 road black spots from 2004 to 2013 and investigated the traffic accident reduction effects of 5 road safety facilities by using "Comparison Group(C-G)" method. Through the analysis, it was found that the number of traffic accidents were lowered by 4.45% with traffic islands, 32.17% with road paved markers, and 24.13% with speed cameras, respectively. However, 0.61% with pedestrian fencing and 1.67% with skid resistant pavement were increased on the other hand. In addition, we also analyzed traffic accident reduction facilities' performance on specific types of collision mentioned in manual on road safety facilities by Ministry of Land, Infrastructure and Transport. It was shown that the number of bad weather traffic accidents were reduced by 52.96% with road paved markers, pedestrians accidents were reduced by 62.77% with pedestrian fencing and rear-end collisions were reduced by 26.00% with skid resistant pavement.

Accident Analysis and Highway Safety

Since 2010, Federal Route FT050 (Jalan Batu Pahat-Kluang) has undergone many changes, including the improvement of geometric features (i.e., construction of median, dedicated U-turns and additional lanes) and upgrading the quality of the road surface. Unfortunately, even with these enhancements, accidents continue to occur along this route. This study covered both accident analysis and blackspot study. Accident point weightage was used to identify blackspot locations. The results reveal hazardous road locations and blackspot ranking along the route.

Decision support model for prioritizing railway level crossings for safety improvements: Application of the adaptive neuro-fuzzy system

Every year, more than 400 people are killed in over 1.200 accidents at road-rail level crossings in the European Union (European Railway Agency, 2011). Together with tunnels and specific road black spots, level crossings have been identified as being a particular weak point in road infrastructure, seriously jeopardizing road safety. In the case of railway transport, level crossings can represent as much as 29% of all fatalities caused by railway operations. In Serbia there are approximately 2.350 public railway level crossings (RLC) across the country, protected either passively (64%) or by active systems (25%). Passive crossings provide only a stationary sign warning of the possibility of trains crossing. Active systems, by contrast, activate automatic warning devices (i.e., flashing lights, bells, barriers, etc.) as a train approaches. Securing a level crossing (whether it has an active or passive system of protection) is a material expenditure, and having in mind that Serbian Railways is a public company directly financed from the budget of the Republic of Serbia, it cannot be expected that all unsecured level crossings be part of a programme of securing them. The most common choice of which level crossings to secure is based on media and society pressure, and on the possible consequences of a rise in the number of traffic accidents at the level crossings. The process of selecting a level crossing where safety equipment will be installed is accompanied by a greater or lesser degree of uncertainty of the essential criteria for making a relevant decision. In order to exploit these uncertainties and ambiguities, fuzzy logic is used in this paper. Here also, modeling of the Adaptive Neuro Fuzzy Inference System (ANFIS) is presented, which supports the process of selecting which level crossings should receive an investment of safety equipment. The ANFIS model is a trained set of data which is obtained using a method of fuzzy multi-criteria decision making and fuzzy clustering techniques. 20 experts in road and rail traffic safety at railway level crossings took part in the study. The ANFIS model was trained with the experiential knowledge of these experts and tested on a selection of rail crossings in the Belgrade area regarding an investment of safety equipment. The ANFIS model was tested on 88 level crossings and a comparison was made between the data set it produced and the data set obtained on the basis of predictions made by experts.

Safety at Level Crossings

Every year, more than 400 people are killed in over 1200 accidents at road-rail level crossings in the European Union. Together with tunnels and specific road black spots, level crossings (LC) have been identified as being a particular weak point in road infrastructure, seriously jeopardizing road safety. Safety at LC is a single part of a wider picture of transport safety within the whole transport system. For many years, governments as well as the rail industry and road organizations have been implementing a variety of countermeasures to improve railway level crossing safety. Despite the fact that these actions are substantial and have resulted in a continuing decrease in the number and the severity of level crossing accidents, LC are still identified as being a weak point in road infrastructure, seriously jeopardizing road safety. This constitutes a difficult problem to be solved by Rail companies. Indeed, they cannot control the actions of road vehicle drivers and pedestrians at level crossings.

Road Macula Analysis and Evaluation

The subject Introduced the analysis method of the black-spot, established the black-spot discriminant model, And gave its algorithm. According to the characteristics of China's traffic flow, we develope black-spot database, so that the work of the black-spot identification can be quickly carried out。The Road black-spot traffic accidents describes the road sections which have significantly higher accident rate than the average level . Road black-spots identification, analysis and processing are widely considered to be the most efficient way to prevent traffic accidents. The identification of Road accident black-spots is the concern of road design, road safety review, operation management, and security studies , The research studies of road black-spot identification,and determines risk road sections, so that countermeasures can be put forward, and we can achieve the goals of design improvement, strengthen management, improvement of road safety operation environment, decrease of the number of traffic accidents and improvement of the whole road traffic safety performance.

Towards safer level crossings: existing recommendations, new applicable technologies and a proposed simulation model

Abstract Every year, more than 400 people are killed in over 1,200 accidents at road-rail level crossings in the European Union. Together with tunnels and specific road black spots, level crossings have been identified as being a particular weak point in road infrastructure, seriously jeopardizing road safety. In the case of railway transport, level crossings can represent as much as 29% of all fatalities caused by railway operations. Up to now, the only effective solution appears to involve upgrading level crossing safety systems even though in more than 90% of cases the primary accident cause is inadequate or improper human behavior rather than any technical, rail-based issue. This article provides results of research done on possible technological solutions to reduce the number of accidents at level crossings and demonstrate the effectiveness of the latter. Elements of these recommendations and related research activities constitute the main focus of the research work described in this paper. It is organized as follows: In Section 2, we consider statistical data related to LX accidents in certain given European countries. These statistics as well as a European Commission Directive related to safety targets are analyzed and the main trends are drawn. The study was carried out on the basis of the classification by the European Railway Agency of active LXs and passive LXs. These results form the foundation for the work described in Section 3. Section 3 focuses on advanced technology to improve LXs safety. The main thrust of the study is to evaluate low-cost, standard technology that can contribute to a direct decrease in the number of accidents, at an affordable cost. Existing surveillance technologies already used in rail or road transport are first considered. To facilitate LX bi-modality, special emphasis is put on technical solutions which have already demonstrated high efficiency in both environments. In Section 4, the mode of operation of each potential solution is modeled and evaluated considering several operational scenarii, in order to evaluate the aggregate benefits of all the input. Setting models to describe the dynamics surrounding the LX environment will prepare a basis to support the decision making process of a joint rail and road sector strategy on how to control LXs. Finally, section 5 brings the study to a close with a list of the main areas in which to concentrate our future work.