Analyzing traffic violation behavior at urban intersections: A spatio-temporal kernel density estimation approach using automated enforcement system data

Capturing signals of road traffic safety risk: based on the spatial-temporal correlation between traffic violations and crashes

OBJECTIVE

The paper aims to explore the possibility of using traffic violations as indicators for spatial-temporal risk of traffic safety within road network constraints, identify key types of traffic violations that indicate spatial-temporal risks in road traffic safety, and investigate their distribution patterns at the road section level.

METHODS

Firstly, we employ the Ripley's K function with network constraints and utilize rigorous statistical inference to thoroughly examine the spatial-temporal correlation between various types of traffic violations and crashes, identifying key types that exhibit significant correlation with crashes. Secondly, we combine Ripley's K function with network constraints, Network Kernel Density Estimation, and Local Moran's Index, to identify high-incidence road sections of these violations. Building upon this foundation, we introduce the concept of Influence Intensity for Land Use Type, which leverages Point of Interest information to analyze the land use characteristics at the road section level, revealing the distribution patterns of these key traffic violations.

RESULTS

Analysis of actual data from Shenzhen, China reveals a total of 17 key traffic violations significantly correlated with crashes of varying severity across different time scenarios in the spatial ranges of 2.1-3.8 kilometers. These include types that are typically considered to have a relatively low likelihood of directly causing crashes that deserve more attention. These key traffic violations tend to aggregate in road sections categorized as "Business & Finance" and "Public Transport Infrastructure." Furthermore, in contrast to weekdays, weekends witness a higher number of key traffic violation types with more pronounced spatial aggregation characteristics, and the land use type of aggregation areas shifts from "Public Administration & Services" to "Public Green Spaces & Attractions" and "Residence & Living."

CONCLUSIONS

This study demonstrates that particular traffic violations can serve as signals for road traffic safety risk within specific space-time scopes, and the spatial-temporal aggregation patterns of these key traffic violations are closely linked to the urban land use. This finding can offer theoretical support for utilizing key traffic violations in real-time monitoring and early warning of road traffic crashes, while also providing inspiration for exploring the causes of these traffic violations from a land use perspective.

Prediction and interpretive of motor vehicle traffic crashes severity based on random forest optimized by meta-heuristic algorithm

Providing accurate prediction of the severity of traffic collisions is vital to improve the efficiency of emergencies and reduce casualties, accordingly improving traffic safety and reducing traffic congestion. However, the issue of both the predictive accuracy of the model and the interpretability of predicted outcomes has remained a persistent challenge. We propose a Random Forest optimized by a Meta-heuristic algorithm prediction framework that integrates the spatiotemporal characteristics of crashes. Through predictive analysis of motor vehicle traffic crash data on interstate highways within the United States in 2020, we compared the accuracy of various ensemble models and single-classification prediction models. The results show that the Random Forest (RF) model optimized by the Crown Porcupine Optimizer (CPO) has the best prediction results, and the accuracy, recall, f1 score, and precision can reach more than 90 %. We found that factors such as Temperature and Weather are closely related to vehicle traffic crashes. Closely related indicators were analyzed interpretatively using a geographic information system (GIS) based on the characteristic importance ranking of the results. The framework enables more accurate prediction of motor vehicle traffic crashes and discovers the important factors leading to motor vehicle traffic crashes with an explanation. The study proposes that in some areas consideration should be given to adding measures such as nighttime lighting devices and nighttime fatigue driving alert devices to ensure safe driving. It offers references for policymakers to address traffic management and urban development issues.

Investigating the temporal dynamics of motor vehicle collision density patterns in urban road networks - A case study of New York

INTRODUCTION

Motor vehicle collisions are a leading source of mortality and injury on urban highways. From a temporal perspective, the determination of a road segment as being collision-prone over time can fluctuate dramatically, making it difficult for transportation agencies to propose traffic interventions. However, there has been limited research to identify and characterize collision-prone road segments with varying collision density patterns over time.

METHOD

This study proposes an identification and characterization framework that profiles collision-prone roads with various collision density variations. We first employ the spatio-temporal network kernel density estimation (STNKDE) method and time-series clustering to identify road segments with different collision density patterns. Next, we characterize collision-prone road segments based on spatio-temporal information, consequences, vehicle types, and contributing factors to collisions. The proposed method is applied to two-year motor vehicle collision records for New York City.

RESULTS

Seven clusters of road segments with different collision density patterns were identified. Road segments frequently determined as collision-prone were primarily found in Lower Manhattan and the center of the Bronx borough. Furthermore, collisions near road segments that exhibit greater collision densities over time result in more fatalities and injuries, many of which are caused by both human and vehicle factors.

CONCLUSIONS

Collision-prone road segments with various collision density patterns over time have distinct differences in the spatio-temporal domain and the collisions that occur on them.

PRACTICAL APPLICATIONS

The proposed method can help policymakers understand how collision-prone road segments change over time, and can serve as a reference for more targeted traffic treatment.

A simple method for mapping winter recreational fishing ecosystem services supply in lakes. A contribution to mapping freshwater ecosystem services

Although urban areas negatively impact the environment, they supply a wide range of ecosystem services (ES), mainly cultural ones. Recreation near urban green areas is widespread, including fishing. In northern latitudes, during the winter, lakes are frozen, and several urban dwellers practice ice fishing. Although this activity is well known, no attempts were made to assess and map winter recreational fishery ES supply in lakes. In this work, we developed a methodology to map this ES, taking an urban lake in Vilnius (Lithuania) as an example. A standardized protocol was developed using an unmanned aerial vehicle (proximal sensing), further georeferencing and correcting the gathered images, vectorizing the fishing ice holes, and mapping them using two different methods: Kernel and Point Density. The method developed in this work can be applied in northern areas to identify recreational fishing ES during the winter.•A novel method was developed to map winter recreational fishery ES supply in lakes;•High-resolution images were taken from an unmanned aerial vehicle to identify fishing ice holes in an urban lake.•The method maps a cultural ES, which is trendy in northern latitudes.

Planning traffic surveillance in Spain: How to optimize the management of police resources to reduce road fatalities

Although traffic police enforcement is widely recognized as a key action in the road safety field, it can be a costly policy to implement. In addition, governments often impose budget constraints that can limit the resources available for activities such as law enforcement and surveillance. To evaluate the impact of human traffic control resources planning on traffic fatalities on Spanish NUTS-3 regions interurban roads, this paper uses an econometric model to investigate the performance of police enforcement intensity by focusing on two crucial traffic law infractions (i.e., speeding and drunk driving). After controlling for a range of economic, demographic, climate, and risk exposure variables, results highlight the relevance of visible, human, and in-person traffic law enforcement through regular vehicle patrols for reducing traffic crashes, with a non-significant effect of automatic enforcement. Our findings have important implications for traffic police resource management regarding the effective maintenance of patrol cars and plans to digitalize and automatize police administrative tasks and procedures.

Inclusive green growth for sustainable development of cities in China: spatiotemporal differences and influencing factors

Inclusive green growth (IGG) based on coordinating the society, economy, and environment is a new way to reach sustainable development. However, there is a lack of relevant research in developing countries. To bridge this gap, based on a comprehensive index that includes economy, social, and environment, this study evaluates the urban inclusive green growth index (IGGI) of 282 in China from 2003 to 2020 and analyzes the spatiotemporal dynamics and regional differences. Moreover, the spatial Durbin model is employed to explore the plausible influencing factors of urban IGGI in China. The main results show an increasing trend of IGGI in Chinese cities and imbalanced spatiotemporal dynamics. Furthermore, the econometric regress results show that upgrade of industrial structure, opening up, human capital, and urban innovation have significant positive impact on urban IGGI, while the administrative capacity of the government and urban industrialization show negative impact on urban IGGI; human capital not only affects the local IGGI but also has significant spatial spillover effects to the surrounding cities. This finding provides new evidence for China to achieve its 2030 sustainable development goals and sheds lights on how policy can be improved to boost IGGI levels and achieve carbon neutrality in 2060.

Applying OHSA to Detect Road Accident Blackspots

With increasing numbers of crashes and injuries, understanding traffic accident spatial patterns and identifying blackspots is critical to improve overall road safety. This study aims at detecting blackspots using optimized hot spot analysis (OHSA). Traffic accidents were classified by their participants and severity to explore the relationship between blackspots and different types of accidents. Based on the outputs of incremental spatial autocorrelation, OHSA was then implemented on different types of accidents. Finally, the performance of OHSA in evaluating the road safety level of the proposed RBT index are examined using a binary correlation analysis (i.e., R² = 0.89). The results show that: (1) The optimal scale distance varies from 0.6 km to 2.8 km and is influenced by the distance of the travel mode. (2) Central cities, with 54.6% of the total accidents, experiences more rigorous challenges regarding traffic safety than satellite cities. (3) There are many types of black spots in vulnerable communities, but in some specific areas, there are only black spots of non-motor vehicle accidents. Considering the practical significance of the above results, policy makers and traffic engineers are expected to give higher attention to central cities and vulnerable communities or prioritize the implementation of relevant optimization measures.

Black-Spot Analysis in Hungary Based on Kernel Density Estimation

Between 2010 and 2020 in the European Union, 30% of road accidents resulted in the death of a pedestrian or a cyclist. Accidents of unprotected pedestrians and cyclists are the reason why it is essential to introduce road safety measures. In our paper, we identify and rank black spots using an innovative reactive approach based on statistics. We elaborate on the mathematical methodological considerations through the processing of real-life empirical data in a Matlab environment. The applied black-spot analysis is based on a Kernel density estimate method, and the importance of the kernel functions and bandwidth are elaborated. Besides, special attention is devoted to the distorting effect of annual average daily traffic. The result of our research is a new methodology by which the real locations of the examined black spots can be determined. Furthermore, the boundaries of the critical sections and the extent of the formation of black spots can be determined by the introduced mathematical methods. With our innovative model, the black spots can be ranked, and the locations having the highest potential for improvement can be identified. Accordingly, optimal measures can be determined considering social-economic and sustainability aspects.

Automatic detection system of speed violations in a traffic based on deep learning technique

With the growth in vehicular traffic, there is a greater risk of road accidents. Over speeding, intoxicated driving, driver distractions, red-light runners, ignoring safety equipment such as seat belts and helmets, non-adherence to lane driving, and improper overtaking are the leading causes of accidents. Speed violation, in particular, has a significant influence on today’s transportation. Also, detecting this speed violation and punishing this violator are more time-consuming tasks. For that reason, a novel automatic speed violation detection in traffic based on Deep learning is proposed in this paper. This proposed method is separated into two working modules: object detection and license plate recognition. The object detection module uses the most efficient PP YOLO neural networks. It utilizes open ALPR (Automatic License Plate Recognition) for the vehicle’s number plate identification, which passes the traffic above maximum speed. With the number plate details, the authorities can take action against the rule violator with less time and effort. The simulation results show that the proposed automatic speed violation detection system also has an accuracy rate of 98.8% for speed violation detection and 99.3% for license plate number identification, demonstrating that the approach described in this work has a higher performance in terms of accuracy. Furthermore, the proposed technique was compared to recent existing results.

Spatiotemporal Heterogeneity of Agricultural Land Eco-Efficiency: A Case Study of 128 Cities in the Yangtze River Basin

Analysis of spatiotemporal heterogeneity and evolutionary characteristics of agricultural land eco-efficiency is of great significance for achieving a rational use of natural resources and coordinated development of the agricultural economy as well as the ecological environment. In this study, we construct the “ecological space–agricultural production–carbon emission” framework, incorporate carbon emission intensity as an undesired output into the evaluation index system of agricultural land eco-efficiency, calculate the eco-efficiency of agricultural land in 128 cities in the Yangtze River basin from 2009 to 2018 by adopting the super-efficiency SBM model, and discuss the spatial and temporal changes using methodology such as hotspot analysis and kernel density estimation by ArcGIS. The results show the following. The overall trend of agricultural land eco-efficiency in the Yangtze River basin is increasing year by year and still has potential for improvement. However, there are significant discrepancies among cities, with the eco-efficiency of the downstream being much higher than that of the midstream and upstream regions, and demonstrating the pattern of “big dispersion–small agglomeration”. Some cities are still facing pressure to improve the eco-efficiency of agricultural land. Correspondingly, this paper puts forward optimization recommendations: Firstly, the downstream cities should give full play to their geographical advantages, actively introduce advanced production technologies, and reasonably allocate agricultural resources. Secondly, the upstream and midstream regions should formulate reasonable regional strategies in accordance with their natural resource endowments to improve the ecological benefits of agricultural land and narrow the regional disparities. This paper gives targeted policy recommendations at the levels of paying attention to education of farmers, providing incentives for ecological planting, strengthening agricultural infrastructure construction, reasonably controlling the use of agricultural materials, and increasing investment in agricultural pollutant emission management.

Integrating Spatial Modelling and Space-Time Pattern Mining Analytics for Vector Disease-Related Health Perspectives: A Case of Dengue Fever in Pakistan

The spatial–temporal assessment of vector diseases is imperative to design effective action plans and establish preventive strategies. Therefore, such assessments have potential public health planning-related implications. In this context, we here propose an integrated spatial disease evaluation (I-SpaDE) framework. The I-SpaDE integrates various techniques such as the Kernel Density Estimation, the Optimized Hot Spot Analysis, space–time assessment and prediction, and the Geographically Weighted Regression (GWR). It makes it possible to systematically assess the disease concentrations, patterns/trends, clustering, prediction dynamics, and spatially varying relationships between disease and different associated factors. To demonstrate the applicability and effectiveness of the I-SpaDE, we apply it in the second largest city of Pakistan, namely Lahore, using Dengue Fever (DF) during 2007–2016 as an example vector disease. The most significant clustering is evident during the years 2007–2008, 2010–2011, 2013, and 2016. Mostly, the clusters are found within the city’s central functional area. The prediction analysis shows an inclination of DF distribution from less to more urbanized areas. The results from the GWR show that among various socio-ecological factors, the temperature is the most significantly associated with the DF followed by vegetation and built-up area. While the results are important to understand the DF situation in the study area and have useful implications for public health planning, the proposed framework is flexible, replicable, and robust to be utilized in other similar regions, particularly in developing countries in the tropics and sub-tropics.

Analysis and prediction of intersection traffic violations using automated enforcement system data

The automated enforcement system (AES) is an effective way of supplementing traditional traffic enforcement, and the traffic violation data from AES can also be effectively used for safety research. In this study, traffic violation data were used to analyze the influencing factors associated with traffic violations and to predict the probability of violations at intersections. The potential factors influencing violations include 24 independent factors related to time, space, traffic and weather. Results from a logistic model showed that the midday period, weekends, residential districts, collector roads, congested traffic conditions, high traffic flow, lower wind speed and low temperature would increase the probability of traffic violations. The probability of violations was predicted by the random forest algorithm, which was proven to be the best traffic violation prediction model among logistic regression, Gaussian naive Bayes, and support vector machine. Moreover, the proximity weighted synthetic oversampling technique (ProWSyn) method was applied to reduce the impact of the imbalance ratio (IR) and improve the model's prediction performance. The receiver operating characteristics (ROC) curves and Precision-Recall (PR) curves illustrated that the random forest algorithm using oversampling data had the best classifier prediction performance than undersampling data. The area under curve (AUC) and out-of-bag (OOB) error with IR = 1 reached 0.914 and 0.0787, which showed the better performance of the random forest algorithm using ProWSyn in dealing with imbalanced traffic violation data.

Regional difference decomposition and its spatiotemporal dynamic evolution of Chinese agricultural carbon emission: considering carbon sink effect

The current study aims to analyze the regional differences and spatiotemporal dynamic evolution of carbon emission intensity (CEI) and carbon emission per capita (CEPC) of planting industry with consideration of carbon sink effect. The results indicate that: (i) The CEI and CEPC of China's planting industry present significant non-equilibrium distribution characteristic during the investigate period, provinces with high CEI are mainly distributed in major agricultural provinces, while high CEPC provinces are mainly located in northeast and individual central provinces with large planting industry. (ii) Inter-regional difference is the principal course of the total differences, the CEI Theil index demonstrates gradient decreasing pattern of "western > central > eastern > northeast," the contribution rate of CEI Theil index shows "northeast > eastern > central > western," the CEPC Theil index shows the spatial pattern of "northeast > central > western > eastern," and the contribution rate of CEPC Theil index presents the spatial pattern of "eastern > central > western > northeast." (iii) The dynamic evolution of CEI and CEPC curve presents polarization or multipolar differential phenomenon accompanies with distinct gradient characteristics, the regional difference of agglomeration level in CEI is gradually narrowing, while the CEPC gradually expanding and the dispersion level is increasing, which implies the "intra-regional convergence and inter-regional divergence." Consequently, differential carbon reduction policies have been put forward according to the study findings.