From theory to deep learning: Understanding the impact of geographic context factors on traffic violations

Wang X., Zhang X., Pei Y.

During rapid urbanization and increase in motorization, it becomes particularly important to understand the relationships between traffic safety and risk factors in order to provide targeted improvements and policy recommendations. Violations and police enforcement are key variables, but the endogenous relationship between crashes and violations has made these variables unreliable and has limited their use. To manage this problem, this study developed a systematic approach for the joint modeling of crashes and violations to identify crash and violation hotspots and examine the mechanisms underlying macro-level contributing factors. Socio-economic, road network, public facility, traffic enforcement, and land use intensity data from 115 towns in Suzhou, China, were collected as independent variables. A bivariate negative binomial spatial conditional autoregressive model (BNB-CAR) and the potential for safety improvement (PSI) method were adopted to identify crash-prone and violation-prone areas, and an interpretable machine learning framework was applied to explore the factors’ effects by area. Results showed that the proposed framework was able to accurately identify problem areas and quantify the impact of key factors, which, in Suzhou, were the number of traffic police and their daily patrol time. Considering such enforcement-related information provided important insights into reducing crash and violation frequency; for example, keeping the number of traffic police and daily patrol time under certain thresholds (number of police lower than 11 and patrol time lower than 2.3 h in this sample) was as effective as increasing these numbers for reducing the probability of high-crash and high-violation areas. The proposed approach can help traffic administrators identify the key contributing factors, especially enforcement factors, in crash-prone and violation-prone areas and provide guidelines for improvement.

Alkaabi K.

Despite the significant efforts made by the government to reduce traffic accidents in the UAE, there is still a need to understand the root causes of these accidents. Therefore, this research paper investigates the various causes of road accidents in Abu Dhabi city, including circumstantial factors, demographic characteristics, traffic violations, accident faults, and driver behavior. The study employs a GIS statistical approach, namely spatial autocorrelation analysis, to identify the hotspots of traffic accidents in the city for the year 2014. Additionally, a questionnaire survey was conducted in 2017 among drivers involved in road accidents in Abu Dhabi City, which was divided into six major categories: accident-related, seatbelt-related, speed-related, policy-related, and general socio-related. The responses of 1,072 drivers were analyzed using logistical regression models, revealing careless driving as the primary reason for city road accidents. The study also found that age and driving experience had a significant impact on accident probability, indicating that middle-aged drivers were more likely to be involved in accidents and that the risk rate decreased as driving experience increased. The study concludes with suggestions for preventive measures to improve traffic safety in Abu Dhabi City. Finally, the study evaluated the hypothesis that most accidents occur near central business districts using 2014 crash data for Abu Dhabi city. The findings demonstrate the effectiveness of the Getis-Ord Gi* statistic method in pinpointing and ranking high-density vehicle crash areas near the central business district of Abu Dhabi urban settings.

Tian Y., Yao X.A., Madden M., Grundstein A.

Physical activity could improve individual health and reduce the risk of all-cause mortality. However, for health-promoting urban environments, some questions require further exploration. For instance, how urban form facilitates or constrains outdoor activities? How local meteorology modulates the urban form-outdoor exercise relationship? In this study, we apply a crowdsourced database, Strava, for outdoor exercisers in Atlanta, Georgia, to investigate the synergic effects of meteorological factors on the urban form-outdoor exercise relationship by developing two groups of models; one considers wind factors, and the other does not. The results show that the wind-related group outperforms their counterparts, especially for commute exercisers (R2 = 0.77 vs. R2 = 0.39), males (R2 = 0.51 vs. R2 = 0.39), and age groups of 13–19 (R2 = 0.61 vs. R2 = 0.25), demonstrating that incorporating local meteorological factors into urban form modeling can better reveal outdoor activity patterns. Besides, the urban form could impact the location preferences of individual exercisers, and such impact varies among different subgroups (e.g., seniors consider convenience, safety, and comfort more than young exercisers do). In addition, places become attractive for outdoor exercisers only when multiple urban form requirements are met (e.g., accessibility to public parks and proximity to residential communities). Finally, according to the non-monotonic and marginal effects, the impacts of urban form and meteorological factors on trip volume are only evident within specific ranges. These findings could help decision-makers make informed plans to promote more active and healthier communities.

Sandoval-Pineda A., Pedraza C., Darghan A.E.

The urban structure of a city, defined by its inhabitants, daily movements, and land use, has become an environmental factor of interest that is related to traffic accidents. Traditionally, macro modeling is usually implemented using spatial econometric methods; however, techniques such as support vector regression have proven to be efficient in identifying the relationships between factors at the zonal level and the frequency associated with these events when considering the autocorrelation between spatial units. As a result of this, the main objective of this study was to evaluate the impact of socioeconomical, land use, and mobility variables on the frequency of traffic accidents through the analysis of area data using spatial and vector support regression models. The spatial weighting matrix term was incorporated into the support vector regression models to compare the results against those that ignore it. The urban land of Bogotá, disaggregated into the territorial units of mobility analysis, was delimited as a study area. Two response variables were used: the traffic accidents index on the road perimeter and the traffic accidents index with deaths on the road perimeter, to analyze the total number of traffic accidents and the deaths caused by them. The results indicated that the rate of trips per person by taxi and motorcycle had the greatest impact on the increase in total accidents and deaths caused by them. Support vector regression models that incorporate the spatial structure allowed the modeling of the spatial dependency between spatial units with a better fit than the spatial regression models.

Yan H., Ma X., Pu Z.

Traffic forecasting has attracted considerable attention due to its importance in proactive urban traffic control and management. Scholars and engineers have exerted considerable efforts in improving the performance of traffic forecasting algorithms in terms of accuracy, reliability, and efficiency. Spatial feature representation of traffic flow is a core component that greatly influences traffic forecasting performance. In previous studies, several spatial attributes of traffic flow are ignored due to the following issues: a) traffic flow propagation does not comply with the road network, b) the spatial pattern of traffic flow varies over time, and c) single adjacent matrix cannot handle the complex and hierarchical urban traffic flow. To address the abovementioned issues, this study proposes a novel traffic forecasting algorithm called traffic transformer, which achieves great success in natural language processing. The multihead attention mechanism and stacking layers enable the transformer to learn dynamic and hierarchical features in sequential data. Two components, namely, global encoder and global–local decoder, are proposed to extract and fuse the spatial patterns globally and locally. Experimental results indicate that the proposed traffic transformer outperforms state-of-the-art methods. The learned dynamic and hierarchical features of traffic flow can help achieve a better understanding of spatial dependency of traffic flow for effective and efficient traffic control and management strategies.

Rezaei Ghahroodi Z., Eftekhari Mahabadi S., Bourbour S., Safarkhanloo H., Zeynali S.

Traffic rules violations in urban areas, which can cause traffic crashes and unsafe situations, are a major issue nowadays. The present paper aims to analyze the frequency of traffic violations in Tehran city, Iran, over a five-year period (March 2016- March 2021). The data is obtained via road traffic violation monitoring system which can capture and process various traffic violations. This database, containing about 97 million violations committed by about 16 million drivers, is explored applying three statistical approaches. In the first approach, some multiplicative SARIMA and Bayesian Spatio-temporal models are fitted to the monthly violations. Also, in the second approach, the K-means clustering algorithm is applied to discover homogeneous districts of Tehran Municipality regarding their number of violations and their number of violations per camera towers meter during the study. Finally, in the third approach, a random-effect zero-truncated one-inflated Poisson model is proposed to study factors affecting driver's number of violations over time.

Cheng Z., Zhang L., Zhang Y., Wang S., Huang W.

Hall J.D., Madsen J.M.

Although behavioral interventions are designed to seize attention, little consideration has been given to the costs of doing so. We estimated these costs in the context of a safety campaign that, to encourage safe driving, displays traffic fatality counts on highway dynamic message signs for 1 week each month. We found that crashes increase statewide during campaign weeks, which is inconsistent with any benefits. Furthermore, these effects do not persist beyond campaign weeks. Our results show that behavioral interventions, particularly negatively framed ones, can be too salient, crowding out more important considerations and causing interventions to backfire—with costly consequences.

Luan S., Ke R., Huang Z., Ma X.

• Bayesian inference and deep learning is integrated for traffic congestion modeling; • A dynamic Bayesian graph convolutional network (DBGCN) is proposed. • The DBGCN outperforms the state-of-the-art prediction models. • The DBGCN can simulate congestion evolution via dynamic adjacency matrix. • The change of congestion source location leads to different congestion patterns. Congestion, whether recurrent or non-recurrent, propagates through the road network. The process of congestion propagation from a particular road to its neighbors can be regarded as a kind of message passing with a directed relationship. Existing methods have created a solid foundation for characterizing congestion propagation; however, they are either built upon simplified assumptions in traffic flow theory or predefined relationships among road sections, which would lead to downgraded accuracy in practice. This paper proposes a dynamic Bayesian graph convolutional network (DBGCN), which integrates Bayesian inference into a deep learning framework. Therefore, the rules of congestion propagation in the network can be actively learned from the observed data instead of predefining them based on prior knowledge. Experimental results on 971 testbeds in a regional road network in Beijing demonstrate that DBGCN outperforms the state-of-the-art models in inferring the congestion propagation spatiotemporal coverage and reveals variations in congestion propagation patterns according to the road network structure. Furthermore, the proposed model can simulate the congestion propagation process in customized scenarios by learning the latent congestion propagation rules. The results in different scenarios show that the change of congestion source location leads to distinct congestion magnitude, and the propagation of congestion will eventually stop at the road sections with strong shunting effect.

Javid M.A., Ali N., Abdullah M., Campisi T., Shah S.A., Suparp S.

Speeding is one of the risky behaviors which results in accident involvement causing fatalities and severe injuries. This paper aimed to identify the significant socio-economic characteristics of drivers concerning their speeding behavior and crash involvement. A questionnaire was designed consisting of driver’s demographic features, involvement in an accident, penalty on speed violations, and statements on speeding behavior in terms of exceeding the speed limits by 10 km/h or more on roads with different speed limits of 60, 80, 100, and 120 km/h per standard operating speeds on various road types in Pakistan. This survey was conducted in Lahore city and a total of 551 usable samples were obtained. A latent variable of drivers’ speeding behavior was introduced; factor loadings were estimated, and an observed variable of drivers’ crash experience was defined as the drivers’ crash involvement. Ordered regression analysis using the probit function was conducted on speeding behavior and crash involvement. The ordinal analysis revealed that the drivers’ age, gender, marital status, employment, vehicle engine size, type of vehicle they drive, and driving frequency per day are good predictors of speeding behavior. Similarly, male drivers’ age, vehicle engine size, and type of vehicle they drive were significant predictors of their likelihood to be involved in an accident. The young, single, and male drivers and drivers of cars with an engine capacity above 1.5 L were more likely to speed and be involved in crashes. These findings provide a clear understanding of a specific group of drivers who have a higher probability of speeding and crash involvement. There is a need to focus on specific demographic factors in the formulation of traffic safety policies and managing speedy drivers’ behaviors.

Ayele Atumo E., Jiang X., Fu C.

Asadianfam S., Shamsi M., Kenari A.R.

Maintaining a fluid and safe traffic is a major challenge for human societies because of its social and economic impacts. Various technologies have considerably paved the way for the elimination of traffic problems and have been able to effectively detect drivers’ violations. However, the high volume of the real-time data collected from surveillance cameras and traffic sensors along with the data obtained from individuals have made the use of traditional methods ineffective. Therefore, using Hadoop for processing large-scale structured and unstructured data as well as multimedia data can be of great help. In this paper, the TVD-MRDL system based on the MapReduce techniques and deep learning was employed to discover effective solutions. The Distributed Deep Learning System was implemented to analyze traffic big data and to detect driver violations in Hadoop. The results indicated that more accurate monitoring automatically creates the power of deterrence and behavior change in drivers and it prevents drivers from committing unusual behaviors in society. So, if the offending driver is identified quickly after committing the violation and is punished with the appropriate punishment and dealt with decisively and without negligence, we will surely see a decrease in violations at the community level. Also, the efficiency of the TVD-MRDL performance increased by more than 75% as the number of data nodes increased.

Cai L., Janowicz K., Mai G., Yan B., Zhu R.

Islam M.M., Alharthi M., Alam M.M.

The potential costs of road traffic accidents (RTAs) to society are immense. Yet, no study has attempted to examine the impact of climate change on RTAs in Saudi Arabia, though RTA-leading deaths are very high, and the occurrence of climatic events is very frequent. Therefore, this study aims to assess the impact of climate change on RTAs in Saudi Arabia and to recommend some climate change mitigation and adaptation policies to make roads safe for all. This study employed annual data from 13 regions of Saudi Arabia, from 2003 to 2013. The data were analyzed on the basis of panel regression models—fixed effect, random effect, and the pooled ordinary least square. The findings show that temperature, rainfall, sandstorms, and number of vehicles were statistically and significantly responsible for RTAs in Saudi Arabia in the study period. This study also found that RTAs both inside and outside cities significantly caused injuries, but only RTAs inside cities significantly caused death. Furthermore, the death from RTAs injuries was found to be statistically significant only for motor vehicle accidents. The findings will assist policymakers in taking the right courses of action to mitigate the negative impacts of climate change through understanding climate influence on RTAs.

Hammad H.M., Ashraf M., Abbas F., Bakhat H.F., Qaisrani S.A., Mubeen M., Fahad S., Awais M.

Road traffic accidents (RTAs) are among the life-threatening issues facing rural as well as sub-/urban communities. Several factors contribute to RTAs ranging from human to technical and natural/environmental impacts. Anthropogenic air pollution and corresponding environmental factors also increase the probability of RTAs. Current study reports the relationship of the weather conditions to RTAs. The study establishes the relevancy of different weather conditions like rainfall, temperature, fog, and wind storm with the incidences of RTAs in rural and urban settings of Vehari, Punjab—Pakistan. The results of the study showed that rainfall, severe coldness, fog, and heat conditions were directly related with the occurrence of RTAs. The percentage of RTAs which occurred due to fog, rainfall, temperature, and other weather-related factors was 34, 25, 21, and 20%, respectively. The age of the driver significantly correlated (R2 = 0.60) with RTAs; the drivers in the age group 40–60 years caused the least RTAs during their drive. Since the smaller vehicles were involved in maximum RTAs, it relates negatively (R2 = 0.82) to vehicles power. Among different vehicles motor bikes were involved in most (42%) of the reported RTAs. Therefore, during severe weather conditions, vehicles with smaller size and young drivers must be dealt with carefully while interacting (crossing, overtaking, and maneuvering) on the roads regardless of rural or urban conditions. Factors including civic sense, traffic education, vehicle size, drivers’ maturity, road conditions, and environmental impacts may be considered while designing traffic rules and traffic aware campaigns specific for developing countries such as Pakistan.