Adaptive urban traffic signal control based on enhanced deep reinforcement learning.

One of the focal points in the field of intelligent transportation is the intelligent control of traffic signals (TS), aimed at enhancing the efficiency of urban road networks through specific algorithms. Deep Reinforcement Learning (DRL) algorithms have become mainstream, yet they suffer from inefficient training sample selection, leading to slow convergence. Additionally, enhancing model robustness is crucial for adapting to diverse traffic conditions. Hence, this paper proposes an enhanced method for traffic signal control (TSC) based on DRL. This approach utilizes dueling network and double q-learning to alleviate the overestimation issue of DRL. Additionally, it introduces a priority sampling mechanism to enhance the utilization efficiency of samples in memory. Moreover, noise parameters are integrated into the neural network model during training to bolster its robustness. By representing high-dimensional real-time traffic information as matrices, and employing a phase-cycled action space to guide the decision-making of intelligent agents. Additionally, utilizing a reward function that closely mirrors real-world scenarios to guide model training. Experimental results demonstrate faster convergence and optimal performance in metrics such as queue length and waiting time. Testing experiments further validate the method's robustness across different traffic flow scenarios.

Crash severity analysis: A data-enhanced double layer stacking model using semantic understanding.

The crash severity analysis is of significant importance in traffic crash prevention and emergency resource allocation. A range of innovations offers potential traffic crash severity prediction models to improve road safety. However, the semantic information inherent in traffic crash data, which is crucial in enabling a deeper understanding of its underlying factors and impacts, has yet to be fully utilized. Moreover, traffic crash data are commonly characterized by a small sample size, which leads to sample imbalance problem resulting in prediction performance decline. To tackle these problems, we propose a semantic understanding-based data-enhanced double-layer stacking model, named EnLKtreeGBDT, for crash severity prediction. Specifically, to fully leverage the inherent semantic information within traffic crash data and analyze the factors influencing crashes, we design a semantic enhancement module for multi-dimensional feature extraction. This module aims to enhance the understanding of crash semantics and improve prediction accuracy. Then we introduce a data enhancement module that utilizes data denoising and migration techniques to address the challenge of data imbalance, reducing the prediction model's dependence on large sample crash data. Furthermore, we construct a two-layer stacking model that combines multiple linear and nonlinear classifiers. This model is designed to augment the capability of learning linear and nonlinear mixed relationships, thereby improving the accuracy of predicting the severity of crashes on complex urban roads. Experiments on historical datasets of UK road safety crashes validate the effectiveness of the proposed model, and superior performance of prediction precision is achieved compared with the state-of-the-arts. The ablation experiments on both semantic and data enhancement modules further confirm the indispensability of each module in the proposed model.

Towards Efficient Risky Driving Detection: A Benchmark and a Semi-Supervised Model.

Risky driving is a major factor in traffic incidents, necessitating constant monitoring and prevention through Intelligent Transportation Systems (ITS). Despite recent progress, a lack of suitable data for detecting risky driving in traffic surveillance settings remains a significant challenge. To address this issue, Bayonet-Drivers, a pioneering benchmark for risky driving detection, is proposed. The unique challenge posed by Bayonet-Drivers arises from the nature of the original data obtained from intelligent monitoring and recording systems, rather than in-vehicle cameras. Bayonet-Drivers encompasses a broad spectrum of challenging scenarios, thereby enhancing the resilience and generalizability of algorithms for detecting risky driving. Further, to address the scarcity of labeled data without compromising detection accuracy, a novel semi-supervised network architecture, named DGMB-Net, is proposed. Within DGMB-Net, an enhanced semi-supervised method founded on a teacher-student model is introduced, aiming at bypassing the time-consuming and labor-intensive tasks associated with data labeling. Additionally, DGMB-Net has engineered an Adaptive Perceptual Learning (APL) Module and a Hierarchical Feature Pyramid Network (HFPN) to amplify spatial perception capabilities and amalgamate features at varying scales and levels, thus boosting detection precision. Extensive experiments on widely utilized datasets, including the State Farm dataset and Bayonet-Drivers, demonstrated the remarkable performance of the proposed DGMB-Net.

Optimization of Signal Timing for Urban Expressway Exit Ramp Connecting Intersection.

To alleviate the traffic problems of congestion and queue overflow on a mainline at the intersection of an urban expressway exit ramp articulation during peak hours, a bi-level programming optimization model of signal timing is proposed. The lower-level optimization objective is to maximize the capacity of the expressway exit ramp that articulates with the entrance road, while the upper-level optimization objective is to minimize the average vehicle delay and the number of stops per vehicle, taking into account the queue length in the direction of the ramp and other directions. The particle swarm optimization algorithm is selected to solve the proposed model, applied to a real case, and is validated using MATLAB and VISSIM simulation platforms. The simulation results show that the average vehicle delay and the number of stops per vehicle in the exit ramp on the expressway are reduced by 22.09% and 18.60%, while those in the intersection area are reduced by 20.96% and 17.19%, respectively. The conclusion indicates that the signal timing scheme obtained by this method can effectively improve the traffic efficiency at the intersection of the exit ramp on the expressway and alleviate the problem of congestion and the overflow of the exit ramp back to the mainline.

Traffic assignment in urban transportation network problem with emission constraints in China: a cooperative game theory.

Traffic assignment in urban transport planning is the process of allocating traffic flows in a network. Traditionally, traffic assignment can reduce travel time or travel costs. As the number of vehicles increases and congestion causes increased emissions, environmental issues in transportation are gaining more and more attention. The main objective of this study is to address the issue of traffic assignment in urban transport networks under an abatement rate constraint. A traffic assignment model based on cooperative game theory is proposed. The influence of vehicle emissions is incorporated into the model. The framework consists of two parts. First, the performance model predicts travel time based on the Wardrop traffic equilibrium principle, which reflects the system travel time. No travelers can experience a lower travel time by unilaterally changing their path. Second, the cooperative game model gives link importance ranking based on the Shapley value, which measures the average marginal utility contribution of links of the network to all possible link coalitions that include the link, and assigns traffic flow based on the average marginal utility contribution of a link with system vehicle emission reduction constraints. The proposed model shows that traffic assignment with emission reduction constraints allows more vehicles in the network with an emission reduction rate of 20% than traditional models.

Human-machine coordination in mixed traffic as a problem of Meaningful Human Control.

The urban traffic environment is characterized by the presence of a highly differentiated pool of users, including vulnerable ones. This makes vehicle automation particularly difficult to implement, as a safe coordination among those users is hard to achieve in such an open scenario. Different strategies have been proposed to address these coordination issues, but all of them have been found to be costly for they negatively affect a range of human values (e.g. safety, democracy, accountability…). In this paper, we claim that the negative value impacts entailed by each of these strategies can be interpreted as lack of what we call Meaningful Human Control over different parts of a sociotechnical system. We argue that Meaningful Human Control theory provides the conceptual tools to reduce those unwanted consequences, and show how "designing for meaningful human control" constitutes a valid strategy to address coordination issues. Furthermore, we showcase a possible application of this framework in a highly dynamic urban scenario, aiming to safeguard important values such as safety, democracy, individual autonomy, and accountability. Our meaningful human control framework offers a perspective on coordination issues that allows to keep human actors in control while minimizing the active, operational role of the drivers. This approach makes ultimately possible to promote a safe and responsible transition to full automation.

A two-phase clustering approach for traffic accident black spots identification: integrated GIS-based processing and HDBSCAN model.

Identifying black spots effectively and accurately is a pivotal and challenging task to improve road traffic safety. A novel black spot identification model is proposed by integrating the GIS-based processing with hierarchical density-based spatial clustering of applications with noise. Additionally, the optimal clustering parameters are determined based on an internal validation indicator called the density-based clustering validation index to minimize the impact of subjectivity in parameter selection. The model is validated by collecting 3536 accident data from 1 August to 31 October 2020 in Hangzhou, China, and eventually identifies 39 black spots. The results show that: (1) The number of accidents contained in black spots account for 75% of all accidents, while the length of network in the black spots only account for 23.26% of the total road network length. (2) Compared with the conventional density-based spatial clustering of applications with noise model and K-means model, the proposed model achieves the best performance with more accidents gathered per unit road length. (3) The sample survey with 6 onsite of the identified black spots indicates that the proposed model has high recognition accuracy and recommend these sites for further investigation.

Urban workers' cardiovascular health due to exposure to traffic-originated PM2.5 and noise pollution in different microenvironments.

The cardiovascular health of the people in urbanised cities is linked to traffic air, and noise pollution. This study investigated the cardiovascular health of people working in two microenvironments such as street (vendors) and workplace (office workers) whose blood pressure (BP) and heart rate (HR) might be affected due to regular exposure to PM2.5 and traffic noise. The PM2.5 and noise levels measurements, face-to-face questionnaire survey and health check-ups were carried out on working days from 10 A.M. to 8 P.M. in Jan-Dec 2019. The data was analysed by various statistical approaches in which the link between the traffic-borne PM2.5 and noise level at 1/3rd octave frequencies has been established with the participants' BP and HR considering the demographic, socio-contextual, habitual and annoyance perception factors. The median measure of PM2.5 and noise levels violated the WHO and NAAQS limits, i.e. 106.67 µg/m3 at street level and 33.33 µg/m3 at office indoor; and 71.35 dB (A) at the street and 65.78 dB (A) at office indoor. The results further showed that the workers working in traffic corridors had abnormally high BP and HR. The systolic BP, diastolic BP and HR values were higher than normal in male workers than female workers. The influence of low noise spectrum (50-630 Hz) was mostly observed. Therefore, the combined effect of PM2.5 > 50 µg/m3 and noise spectrum (63 and 100 Hz) > 30 dB (A) significantly affect office workers' health in traffic corridors. The hearing aids, breathing troubles in the traffic corridor and annoyance perception also influenced the BP and HR of the respondents. The results are indicative and might be helpful in urban environmental planning to improve the well-being of urban traffic corridor users.

School Surrounding Region Traffic Commuting Analysis Based on Simulation.

Student commuting is an important part of urban travel demand and private car commuting plays an important role in urban traffic, especially in areas near schools. Since parents, especially the parents of elementary and junior high school students, prefer to drive rather than take public transport, there will be a negative effect on traffic management. To address the challenge, a simulation model is established based on schools' surrounding regions to analyze traffic status. Specifically, the model focuses on urban construction and transportation near the entrance of schools and neighborhoods. In addition, four variable parameters consisting of the directional hourly volume, the parking demand of delivery vehicles, the distance between the school and intersection, and the average parking time for pick-up vehicles are set as influence factors, while traffic efficiency, energy consumption, and pollutant emissions are considered as the evaluation criteria of our model. Extensive simulated experiments show that comparing different scenarios, the traffic state of schools' surrounding areas can achieve much better performance when the distance between entrances and intersections is 400 m under the 1000 pcu/h condition. This research can provide a scientific basis for school regional traffic management and organization optimization.

Biomonitoring of Exposure to Urban Pollutants and Oxidative Stress during the COVID-19 Lockdown in Rome Residents.

BACKGROUND: The objective of this study is to evaluate the effects of traffic on human health comparing biomonitoring data measured during the COVID-19 lockdown, when restrictions led to a 40% reduction in airborne benzene in Rome and a 36% reduction in road traffic, to the same parameters measured in 2021. METHODS: Biomonitoring was performed on 49 volunteers, determining the urinary metabolites of the most abundant traffic pollutants, such as benzene and PAHs, and oxidative stress biomarkers by HPLC/MS-MS, 28 elements by ICP/MS and metabolic phenotypes by NMR. RESULTS: Means of s-phenylmercaputric acid (SPMA), metabolites of naphthalene and nitropyrene in 2020 are 20% lower than in 2021, while 1-OH-pyrene was 30% lower. A reduction of 40% for 8-oxo-7,8-dihydroguanosine (8-oxoGuo) and 8-oxo-7,8-dihydro-2-deoxyguanosine (8-oxodGuo) and 60% for 8-oxo-7,8-dihydroguanine (8-oxoGua) were found in 2020 compared to 2021. The concentrations of B, Co, Cu and Sb in 2021 are significantly higher than in the 2020. NMR untargeted metabolomic analysis identified 35 urinary metabolites. Results show in 2021 a decrease in succinic acid, a product of the Krebs cycle promoting inflammation. CONCLUSIONS: Urban pollution due to traffic is partly responsible for oxidative stress of nucleic acids, but other factors also have a role, enhancing the importance of communication about a healthy lifestyle in the prevention of cancer diseases.

The Influence of Environmental Polycyclic Aromatic Hydrocarbons (PAHs) Exposure on DNA Damage among School Children in Urban Traffic Area, Malaysia.

This study aimed to investigate the association between particulate PAHs exposure and DNA damage in Malaysian schoolchildren in heavy traffic (HT) and low traffic (LT) areas. PAH samples at eight schools were collected using a low volume sampler for 24 h and quantified using Gas Chromatography-Mass Spectrometry. Two hundred and twenty-eight buccal cells of children were assessed for DNA damage using Comet Assay. Monte-Carlo simulation was performed to determine incremental lifetime cancer risk (ILCR) and to check the uncertainty and sensitivity of the estimated risk. Total PAH concentrations in the schools in HT area were higher than LT area ranging from 4.4 to 5.76 ng m-3 and 1.36 to 3.79 ng m-3, respectively. The source diagnostic ratio showed that PAHs in the HT area is pyrogenic, mainly from diesel emission. The 95th percentile of the ILCR for children in HT and LT area were 2.80 × 10-7 and 1.43 × 10-7, respectively. The degree of DNA damage was significantly more severe in children in the HT group compared to LT group. This study shows that total indoor PAH exposure was the most significant factor that influenced the DNA damage among children. Further investigation of the relationship between PAH exposure and genomic integrity in children is required to shed additional light on potential health risks.

Impact of COVID-19 on adolescent travel behavior.

INTRODUCTION: The outbreak of COVID-19 has significantly impacted travel behavior. However, few studies have analyzed the impact of COVID-19 on adolescent travel behavior. This article analyzed the impact of COVID-19 on adolescent travel behavior using questionnaire survey data. METHODS: This paper first used confirmatory factor analysis (CFA) to explore the psychological factors related to the adolescents' perceptions about the severity of COVID-19. The study then established a logit model to study the effects of COVID-19 in different phases (before, during, and after the epidemic peak), demographic characteristics, and the role of psychological factors on their travel behavior. RESULTS: The results show that the phase of COVID-19 did not significantly impact the adolescents' choice of short-distance travel. The frequency of outings per week, the number of exercise sessions per week, and willingness to travel by public transportation decreased significantly in the outbreak phase. Meanwhile, the perception of the severity of COVID-19 significantly impacted adolescent travel behavior. CONCLUSION: This research demonstrates that COVID-19 has led adolescents to reduce their frequency of outings, and they try not to use public transportation. Adolescents appear to be traveling more cautiously in the outbreak phase and the post-epidemic phase.

Dynamic balance between demand-and-supply of urban taxis over trajectories.

Urban taxi serves as an irreplaceable tool in public transportation systems. The balancing of demand-and-supply can be of significant social benefit, for which the equilibrium method for urban taxis, especially with dynamic trip demands, is not well studied yet. In this paper, we formally define the equilibrium problem and propose a coarse-grained dynamic balancing algorithm. It efficiently evaluates the trip demand distribution pattern and schedules supplies to more unbalanced regions. We first propose a density-based blocking algorithm to detect regions that are with more travel demands. A trip demand merging strategy is then proposed, which checks the correlation of trip demands to merge the trips into ones. To reduce the computation load, a lazy trip correlation strategy is devised to speed up the merging process. By calculating the defined balance factor, a scheduling algorithm is proposed to realize the trip merge and supply translocation based balancing approach. We evaluated our approach using a month of global positioning system (GPS) trajectories generated by 13,000 taxis of Shanghai. By learning the spatiotemporal distribution of historical taxi demand-and-supplies, we simulated an inflated trip demand platform. Tested on this platform with extensive experiments, the proposed approach demonstrates its effectiveness and scalability.

Missing Traffic Data Imputation with a Linear Generative Model Based on Probabilistic Principal Component Analysis.

Even with the ubiquitous sensing data in intelligent transportation systems, such as the mobile sensing of vehicle trajectories, traffic estimation is still faced with the data missing problem due to the detector faults or limited number of probe vehicles as mobile sensors. Such data missing issue poses an obstacle for many further explorations, e.g., the link-based traffic status modeling. Although many studies have focused on tackling this kind of problem, existing studies mainly focus on the situation in which data are missing at random and ignore the distinction between links of missing data. In the practical scenario, traffic speed data are always missing not at random (MNAR). The distinction for recovering missing data on different links has not been studied yet. In this paper, we propose a general linear model based on probabilistic principal component analysis (PPCA) for solving MNAR traffic speed data imputation. Furthermore, we propose a metric, i.e., Pearson score (p-score), for distinguishing links and investigate how the model performs on links with different p-score values. Experimental results show that the new model outperforms the typically used PPCA model, and missing data on links with higher p-score values can be better recovered.

Vulnerability and Resilience of Urban Traffic to Precipitation in China.

The concept of Healthy Cities, introduced by the World Health Organization, demonstrates the value of health for the whole urban system. As one of the most important components of urban systems, transportation plays an important role in Healthy Cities. Many transportation evaluation systems focus on factors such as road networks, parking spaces, transportation speed, accessibility, convenience, and commuting time, while the vulnerability and resilience of urban transportation are rarely evaluated. This study presents the preliminary progress in the evaluation of traffic vulnerability and resilience during precipitation events in 39 Chinese cities. Traffic congestion index data, derived from the Baidu Map Smart Transportation Platform, and rainfall data, derived from NASA's global precipitation measurement, are utilized. Traffic vulnerability index, traffic resilience index, and the corresponding quantitative methods are proposed, and the analysis results are presented. This study is of value in improving the understanding of urban traffic vulnerability and resilience, and in enabling the quantitative evaluation of them in urban health assessment and the Healthy Cities program.

Identification of Metal Contamination Sources and Evaluation of the Anthropogenic Effects in Soils near Traffic-Related Facilities.

Traffic-related facilities typically have much lower metal emissions than other sources; however, they can be numerous and widespread as well. Subdividing pollution sources is necessary to assess soil contamination characteristics and identify sources according to the contamination cause. Anthropogenic contamination by metals was quantitatively determined using contamination factor (Cf) and evaluated using multivariate analysis. More than half of the concentrations for Zn, Pb, and Cu in soils were higher than that in the natural background (NB). Cf of metals was, in decreasing order, Zn > Pb = Cu > Ni = As. Zn, Pb, and Cu were identified as anthropogenic contaminants in correlation analysis. Principal component analysis showed that the two main contamination causes were coarse particles from the maintenance or crushing activities of vehicles and nonexhaust/exhaust emissions. Clusters were classified according to those two anthropogenic and lithogenic causes and included Group I (Zn, Pb, and Cu in garages, auto repair shops, and auto salvage yards), Group II (Zn, Pb, and Cu in parking lots, driving schools, and roadsides), and Group III (As and Ni with high lithogenic properties). Anthropogenic input and sources of soil contamination by metals in traffic-related facilities were appropriately estimated through the combination of Cf and multivariate analysis.

The effect of Covid-19 lockdown on airborne particulate matter in Rome, Italy: A magnetic point of view.

Between 9 March and 18 May 2020, strict lockdown measures were adopted in Italy for containing the COVID-19 pandemic: in Rome, despite vehicular traffic on average was more than halved, it was not observed a evident decrease of the airborne particulate matter (PM) concentrations, as assessed by air quality data. In this study, daily PM10 filters were collected from selected automated stations operated in Rome by the regional network of air quality monitoring: their magnetic properties - including magnetic susceptibility, hysteresis parameters and FORC (first order reversal curves) diagrams - were compared during and after the lockdown, for outlining the impact of the COVID-19 measures on airborne particulate matter. In urban traffic sites, the PM10 concentrations did not significantly change after the end of the lockdown, when vehicular traffic promptly returned to its usual levels; conversely, the average volume and mass magnetic susceptibilities approximately doubled, and the linear correlation between volume magnetic susceptibility and PM10 concentration became significant, pointing out the link between PM10 concentrations and the increasing levels of traffic-related magnetic emissions. Magnetite-like minerals, attributed to non-exhaust brakes emissions, dominated the magnetic fraction of PM10 near urban traffic sites, with natural magnetic components emerging in background sites and during exogenous dusts atmospheric events. Magnetic susceptibility constituted a fast and sensitive proxy of vehicular particulate emissions: the magnetic properties can play a relevant role in the source apportionment of PM10, especially when unsignificant variations in its concentration levels may mask important changes in the traffic-related magnetic fraction. As a further hint, increasing attention should be drawn to the reduction of brake wear emissions, that are overcoming by far fuel exhausts as the main particulate pollutant in traffic contexts.

Scalable Data Model for Traffic Congestion Avoidance in a Vehicle to Cloud Infrastructure.

Traffic congestion experience in urban areas has negative impact on our daily lives by consuming our time and resources. Intelligent Transportation Systems can provide the necessary infrastructure to mitigate such challenges. In this paper, we propose a novel and scalable solution to model, store and control traffic data based on range query data structures (K-ary Interval Tree and K-ary Entry Point Tree) which allows data representation and handling in a way that better predicts and avoids traffic congestion in urban areas. Our experiments, validation scenarios, performance measurements and solution assessment were done on Brooklyn, New York traffic congestion simulation scenario and shown the validity, reliability, performance and scalability of the proposed solution in terms of time spent in traffic, run-time and memory usage. The experiments on the proposed data structures simulated up to 10,000 vehicles having microseconds time to access traffic information and below 1.5 s for congestion free route generation in complex scenarios. To the best of our knowledge, this is the first scalable approach that can be used to predict urban traffic and avoid congestion through range query data structure traffic modelling.

Exploring the effect of urban traffic development on PM2.5 pollution in emerging economies: fresh evidence from China.

Urban traffic congestion and haze pollution have become the main obstacles to the development of most cities in emerging economies. It is not clear how urban traffic development processes impact on PM2.5 concentration for the cities of emerging economies. Motivated by exploring the relationship between urban traffic development and PM2.5 pollution, 30 provinces in China (a representative emerging economy) from 2007 to 2016 were taken as examples, and threshold regression model and geographically temporally weighted regression model were used to explore the nonlinear relationship and their spatio-temporal heterogeneity. These empirical researches demonstrated that the impact of urban traffic development on PM2.5 pollution has a significant threshold effect. That is, when the road area crosses the threshold, it will significantly aggravate the regional PM2.5 pollution. Meanwhile, regional economic development also shows a significant threshold effect. Moreover, the relationship between urban traffic development and PM2.5 pollution in various Chinese provinces presents significant spatial heterogeneity. Specifically, the Chinese provinces are divided into four categories, and urban planning should be designed for different types for the sustainable development of the economy and environment. Our results not only contribute to advancing the existing literature, but also merit particular attention from urban planners in emerging economies.

Air pollution levels near crossroads with different traffic density and the estimation of health risk.

The aim of this study was to determine the influence of traffic density on air pollutant levels as well as to analyse the spatial and temporal distribution of particulate pollutants and their health risk. The following species related to traffic pollution were measured: PM10, elemental and organic carbon and polycyclic aromatic hydrocarbons (PAHs) in PM10 and gas pollutants (SO2, NO2 and CO). The measurements were carried out at four crossroad sites in the city. Samples of PM10 were collected over three periods (6 am to 2 pm, 2 pm to 10 pm and 10 pm to 6 am) on working days and weekends. Statistically significant differences were found between sampling sites for all pollutant concentrations, except for NO2. The highest mass concentrations of PM10, carbon and PAHs were observed in the south of the city with the highest traffic density. Concentrations of gasses (CO and NO2) showed high values in morning and in the late afternoon and evening (west and east). At all measuring sites, the highest concentration of particle-bound pollutants was mostly recorded during morning and afternoon, except at the south, where elevated PAHs concentrations were recorded during night period, which indicated that residential heating takes up a portion of pollution sources in this area. Although for most of the pollutants the concentrations varied during the day, statistically significant differences between sampling periods were not found. The highest health risk was obtained at the south, where it was scored as significant.