Adaptive forward collision warning system for hazmat truck drivers: Considering differential driving behavior and risk levels.

The risky driving behavior of hazmat truck drivers is a crucial factor in many severe traffic accidents. In-vehicle Advanced Driving Assistance Systems (ADAS), integrating vehicle active safety and driver assistance technology, has been installed into hazmat trucks aiming to reduce driving risks during emergencies. This paper presents an enhanced dynamic Forward Collision Warning (FCW) model tailored for hazmat truck drivers with different driving characteristics and risk levels. Our objective is to determine the optimal moment to alert drivers during risky situations. The novelty of our approach lies in analyzing the driver's response mechanism to the warning by considering their characteristics and real-time driving risk levels. We employ a multi-objective optimization method that integrates real-time driving risk, driver acceptance, and driving comfort to calculate the optimal warning time. Our findings indicate that the appropriate warning time is similar for all drivers under high-level risks, while significant differentiation exists for different driver categories under mid-level and low-level risks. Additionally, aggressive drivers tend to follow leading vehicles closely and exhibit lower deceleration intentions when faced with dangers compared to normal and cautious drivers. Our research outcomes enable the development of user profiles for hazmat truck drivers based on extensive historical driving records, facilitating the analysis of driver response differences to FCWs. This enhances driving safety and improves driver trust in ADAS systems.

Development of a spectrum-based ship fuel sulfur content real-time evaluation method.

Although maritime transport plays an essential role in the global economy, it inevitably imposes negative impacts on our living environment, especially for ships using fuel with high sulfur content. Nowadays, ship emission monitoring highly depends on manual inspection, which is time-consuming and labor-intensive. This study proposes a decision framework based on spectrum technology and the sulfur­carbon ratio method to measure the ship fuel sulfur content. Specifically, after the Gaussian plume model optimization from four aspects, a multistep-based emission contribution evaluation method is developed to improve the evaluation accuracy. The proposed framework is validated by a suspected ship and a series of exempted ships from the Maritime Safety Administration in Nanjing, China. The validation results imply that the proposed framework has a certain enhancement in detection rate, evaluation accuracy and extensibility. It may provide an efficient and accurate supervision approach for the Maritime Safety Administration on ship fuel sulfur content measurement.

A long-term perspective on the COVID-19: The bike sharing system resilience under the epidemic environment.

Introduction: The sudden COVID-19 pandemic poses a fresh and tough challenge to bike sharing systems (BSS). With this epidemic as a shock event, this paper aspires to shed light on the phenomenon of changing demand and usage regularity in New York City's BSS under the epidemic environment, spanning a period of 18 months. Methods: Technically, BSS's normal performance and the timely responses to the outbreak could be conceptualized as having four different stages. One provides a comparative analysis of bike sharing spatial-temporal mobility patterns and connectivity of the bike sharing usage network, before and during the public health crisis with a macroscopic perspective. Also, a multivariate investigation of user and trip characteristics on BSS is conducted to uncover the difference in the frequency of outdoor and sojourn time between various user communities. Results: Due to the impact of the outbreak, BSS registered severe ridership drops, yet it quickly recovered to the pre-pandemic levels within months. The decline of bike sharing usage was felt throughout all the areas during the outbreak. However, there were places where BSS ridership actually increased, particularly in the areas near supermarkets, parks and hospitals. The less densely connected network of the bike sharing usage has also resulted in a reduction in users' destination heterogeneity. This study also finds evidence of the significant gender, age and cycling pattern gaps in response to potential risk. Conclusions: Investigating the dynamics of bike sharing usage will help to comprehend how the serious pandemic caused by COVID-19 impacts people's daily mobility. Practically, this work hopes to provide insights into adapting this unprecedented pandemic so as to respond to similar events in the future.

Unraveling nonlinear and interaction effects of various determinants on bus gaseous emissions.

Urban transit buses equipped with large-displacement engines operate on circular routes several times throughout the day, emitting large amounts of environmentally hazardous exhaust. Hence, understanding the intricate associations between bus emissions and multiple contributors is beneficial for creating sustainable transportation systems, while previous studies focusing on statistical methods fail to unravel them. This paper innovatively leverages the bagged decision tree approach to delineate such complex relationships based on the data collected from CNG-fueled and diesel-powered buses. Relative importance indicates that velocity appears to be the primary factor and is therefore selected as the research objective. Results suggest that the effects of different contributors on bus emissions present nonlinear patterns. More specifically, the influence of speed on CO, CO2, and NOx exhaust generally reveals an increasing-stabilizing tendency while that of HC represents a decreasing-stabilizing mode. Besides, the phenomenon of synergies between determinants is also prevalent, for instance, buses within high-speed and large-slope conditions tend to produce more emissions. These findings can provide nuanced guidance for policy-making and bus route planning issues in consideration of environmental protection and pollution mitigation.

Estimating gaseous pollutants from bus emissions: A hybrid model based on GRU and XGBoost.

In urban areas, traffic-related contamination is one of the main contributors to environmental deterioration, and the pollution from public transit buses is a major component. To mitigate these impacts, it is essential to estimate bus emissions and analyze their characteristics. This paper proposes a hybrid model based on gated recurrent unit (GRU) and extreme gradient boosting (XGBoost), termed GRU-XGB, to predict gaseous pollutants from bus emissions (CO, CO2, HC, NOX) under real conditions. On-road experimental data collected from CNG-fueled and diesel-powered buses in Zhenjiang was used as a case study to verify the model's effectiveness. A comparison between the proposed and other state-of-the-art models reveals that GRU-XGB performs best for all evaluation metrics on both microscopic and aggregative levels, with an average correlation coefficient above 0.98 and an average MAPE lower than 9%. Moreover, the results of estimation errors analysis suggest that the real conditions of bus stations are more complicated than those of intersections and road sections. In most cases, however, the emission factors produced from intersections are proven to be the highest. Furthermore, operating patterns are shown to be the most significant factors, with relative importance equal to 45.09% and 71.68% for CNG and diesel buses, respectively. Besides, the results also indicate that humidity has little impact on this issue, while the influence of temperature is obvious, with relative importance equal to 17.56% and 9.41% for CNG and diesel buses, separately. Such findings can provide theoretical guidance for both emission estimation and environmental protection. Also, it is applicable for the management of accurate monitoring from an urban-level and can be integrated into emission simulation tools.

Exploring the influence of contributing factors and impact degree on bus emissions in real-world conditions.

Buses in urban have environmental problems because they are mostly having higher emission factors and pollution levels. This study analyzed the contributing factors on bus emissions including NOX, CO, HC, and CO2 and further evaluated the impact degree of these factors. A back-propagation neural network (BPNN) was applied, and the results showed that the composition of pollutant emissions for different fuel types was various. BPNN can be utilized to solve the multifactor, uncertainty, and nonlinearity problems without making any prior presumptions about the data distribution. Among them, diesel buses under EURO-IV and EURO-V emission standards were more likely to produce higher emissions of CO and NOX. By contrast, the emission level of CO and NOX for compressed natural gas bus was lower, but the emission level of CO2 and HC was heavier. In this study, nine variables, namely, speed, acceleration, passenger load, past speed, past acceleration, acceleration time, delay time, stops, and location were selected to investigate their effects on bus emissions. The results showed that factors delay time, location, and stops had the strongest impacts on bus emissions. By contrast, bus emissions were not sensitive to past speed and passenger load. In addition, to fully understand the influence of contributing factors, the impact degree of all these factors on bus emissions was summarized in this study.

Nighttime safety evaluation for signalized intersections at the signal cycle level based on rear-end conflict models considering lighting and traffic conditions.

Objective: The primary objective of this study is to explore the effects of the lighting level on nighttime safety of signalized intersections based on conflict models under traffic conditions varying in cycles.Method: Nighttime data were collected from a field study at six signalized intersections in Nanjing, Jiangsu Province in China. Nighttime rear-end conflict models were developed by adopting the generalized linear model (GLM) approach to relate the frequency of rear-end traffic conflicts to lighting level, traffic volume and platoon ratio at the signal cycle level.Results: The final model consisting of all explanatory variables, including lighting level, traffic volume, and platoon ratio demonstrates a better performance of safety evaluation when compared to the model considering traffic volume only and the model with traffic volume and an additional variable of lighting or traffic conditions. Nighttime safety of signalized intersections is expected to improve with larger platoon ratios and higher lighting levels. A potential application of the final model was further explored by benefit-cost analyses. The analyses provided a hypothetical recommended lighting level under various traffic volumes and platoon ratios when safety benefit equals lighting system cost.Conclusions: Nighttime safety can be evaluated using the developed rear-end conflict models, which relate the number of rear-end conflicts to traffic and lighting variables. The number of rear-end conflicts can be calculated by the final conflict model with lighting level, traffic volume, and platoon ratio. The developed model can be potentially applied to provide further insights on the lighting management for intersection safety optimization with traffic conditions varying in signal cycles via vehicle-to-infrastructure (V2I) communications.

Understanding the Usage Patterns of Bicycle-Sharing Systems to Predict Users' Demand: A Case Study in Wenzhou, China.

Bicycle-sharing systems (BSSs) have become a prominent feature of the transportation network in many cities. Along with the boom of BSSs, cities face the challenge of bicycle unavailability and dock shortages. It is essential to conduct rebalancing operations, the success of which largely depend on users' demand prediction. The objective of this study is to develop users' demand prediction models based on the rental data, which will serve rebalancing operations. First, methods to collect and process the relevant data are presented. Bicycle usage patterns are then examined from both trip-based aspect and station-based aspect to provide some guidance for users' demand prediction. After that, the methodology combining cluster analysis, a back-propagation neural network (BPNN), and comparative analysis is proposed to predict users' demand. Cluster analysis is used to identify different service types of stations, the BPNN method is utilized to establish the demand prediction models for different service types of stations, and comparative analysis is employed to determine if the accuracy of the prediction models is improved by making a distinction among stations and working/nonworking days. Finally, a case study is conducted to evaluate the performance of the proposed methodology. Results indicate that making a distinction among stations and working/nonworking days when predicting users' demand can improve the accuracy of prediction models.

Estimation of bus emission models for different fuel types of buses under real conditions.

Urban buses are heavy vehicles that move frequently throughout the day, and most of them are propelled by heavy-duty diesel engines. For these reasons, they have energy and environmental impacts that should not be ignored. Consequently, the primary objectives of this study were to compare the changes in bus speed, acceleration, and emissions between bus stops, intersections, and road sections by applying statistical methods; and to develop a vehicle specific power (VSP)-based artificial neural network (ANN) model to estimate emissions of CO, HC, NOX, and CO2 for four different fuel types of buses including gas-electric hybrid electric buses (GEHE bus), compressed natural gas buses (CNG bus), EURO 4 heavy-duty diesel engine buses (EURO 4 bus), and EURO 5 heavy-duty diesel engine buses (EURO 5 bus). The results of t-tests (with p-values varying between <0.001 and 0.026, which were not >0.050) showed that the differences in emissions between different locations and between different fuel types of buses were all statistically significant. In addition, to evaluate the performance of the proposed method, a polynomial regression model using linear, quadratic, and cubic terms of transient speed and acceleration was utilized for comparison. According to the results, the proposed method had more accurate and reliable estimation, which increased the lower 10% of absolute percentage error (Lower-10% APE) by 65.2%; reduced mean absolute percentage error (MAPE) by 41.4%, root mean squared error (RMSE) by 44.9%, and mean absolute error (MAE) by 43.5%; and increased R-squared from 0.659 to 0.781.

Evaluating the influence of road lighting on traffic safety at accesses using an artificial neural network.

OBJECTIVES: This article focuses on the effect of road lighting on road safety at accesses to quantitatively analyze the relationship between road lighting and road safety. METHODS: An artificial neural network (ANN) was applied in this study. This method is one of the most popular machine learning methods and does not require any predefined assumptions. This method was applied using field data collected from 10 road segments in Nanjing, Jiangsu Province, China. RESULTS: The results show that the impact of road lighting on road safety at accesses is significant. In addition, road lighting has a greater influence when vehicle speeds are higher or the number of lanes is greater. A threshold illuminance was also found, and the results show that the safety level at accesses will become stable when reaching this value. CONCLUSIONS: Improved illuminance can decrease the speed variation among vehicles and improve safety levels. In addition, high-grade roads need better illuminance at accesses. A threshold value can also be obtained based on related variables and used to develop scientific guidelines for traffic management organizations.

Crash data modeling with a generalized estimator.

The investigation of relationships between traffic crashes and relevant factors is important in traffic safety management. Various methods have been developed for modeling crash data. In real world scenarios, crash data often display the characteristics of over-dispersion. However, on occasions, some crash datasets have exhibited under-dispersion, especially in cases where the data are conditioned upon the mean. The commonly used models (such as the Poisson and the NB regression models) have associated limitations to cope with various degrees of dispersion. In light of this, a generalized event count (GEC) model, which can be generally used to handle over-, equi-, and under-dispersed data, is proposed in this study. This model was first applied to case studies using data from Toronto, characterized by over-dispersion, and then to crash data from railway-highway crossings in Korea, characterized with under-dispersion. The results from the GEC model were compared with those from the Negative binomial and the hyper-Poisson models. The cases studies show that the proposed model provides good performance for crash data characterized with over- and under-dispersion. Moreover, the proposed model simplifies the modeling process and the prediction of crash data.

Examining drivers' eye glance patterns during distracted driving: Insights from scanning randomness and glance transition matrix.

INTRODUCTION: Visual attention to the driving environment is of great importance for road safety. Eye glance behavior has been used as an indicator of distracted driving. This study examined and quantified drivers' glance patterns and features during distracted driving. METHOD: Data from an existing naturalistic driving study were used. Entropy rate was calculated and used to assess the randomness associated with drivers' scanning patterns. A glance-transition proportion matrix was defined to quantity visual search patterns transitioning among four main eye glance locations while driving (i.e., forward on-road, phone, mirrors and others). All measurements were calculated within a 5s time window under both cell phone and non-cell phone use conditions. RESULTS: Results of the glance data analyses showed different patterns between distracted and non-distracted driving, featured by a higher entropy rate value and highly biased attention transferring between forward and phone locations during distracted driving. Drivers in general had higher number of glance transitions, and their on-road glance duration was significantly shorter during distracted driving when compared to non-distracted driving. CONCLUSIONS: Results suggest that drivers have a higher scanning randomness/disorder level and shift their main attention from surrounding areas towards phone area when engaging in visual-manual tasks. PRACTICAL APPLICATIONS: Drivers' visual search patterns during visual-manual distraction with a high scanning randomness and a high proportion of eye glance transitions towards the location of the phone provide insight into driver distraction detection. This will help to inform the design of in-vehicle human-machine interface/systems.

A spectral power analysis of driving behavior changes during the transition from nondistraction to distraction.

OBJECTIVE: This article investigated and compared frequency domain and time domain characteristics of drivers' behaviors before and after the start of distracted driving. METHOD: Data from an existing naturalistic driving study were used. Fast Fourier transform (FFT) was applied for the frequency domain analysis to explore drivers' behavior pattern changes between nondistracted (prestarting of visual-manual task) and distracted (poststarting of visual-manual task) driving periods. Average relative spectral power in a low frequency range (0-0.5 Hz) and the standard deviation in a 10-s time window of vehicle control variables (i.e., lane offset, yaw rate, and acceleration) were calculated and further compared. Sensitivity analyses were also applied to examine the reliability of the time and frequency domain analyses. RESULTS: Results of the mixed model analyses from the time and frequency domain analyses all showed significant degradation in lateral control performance after engaging in visual-manual tasks while driving. Results of the sensitivity analyses suggested that the frequency domain analysis was less sensitive to the frequency bandwidth, whereas the time domain analysis was more sensitive to the time intervals selected for variation calculations. Different time interval selections can result in significantly different standard deviation values, whereas average spectral power analysis on yaw rate in both low and high frequency bandwidths showed consistent results, that higher variation values were observed during distracted driving when compared to nondistracted driving. CONCLUSIONS: This study suggests that driver state detection needs to consider the behavior changes during the prestarting periods, instead of only focusing on periods with physical presence of distraction, such as cell phone use. Lateral control measures can be a better indicator of distraction detection than longitudinal controls. In addition, frequency domain analyses proved to be a more robust and consistent method in assessing driving performance compared to time domain analyses.

Effects of speed-control measures on the safety of unsignalized midblock street crossings in China.

OBJECTIVE: The primary objective of this study was to evaluate the effects of different speed-control measures on the safety of unsignalized midblock street crossings. METHODS: In China, it is quite difficult to obtain traffic crash and conflict data for pedestrians using such crossings, mainly due to the lack of traffic data management and organizational issues. In light of this, the proposed method did not rely on such data, but considered vehicle speed, which is a leading contributing factor of pedestrian safety at mid blocks. To evaluate the speed reduction effects at different locations, the research team utilized the following methods in this study: (1) testing speed differences-on the basis of the collected data, statistical analysis is conducted to test the speed differences between upstream and crosswalk, upstream and downstream, and downstream and crosswalk; and (2) mean distribution deviation-this value is calculated by taking the difference in cumulative speed distributions for the two different samples just mentioned. In order to better understand the variation of speed reduction effects at different distances from speed-control facilities, data were collected from six types of speed-control measures with a visual range of 60 m. RESULTS: The results showed that speed humps, transverse rumble strips, and speed bumps were effective in reducing vehicle speeds. Among them speed humps performed the best, with reductions of 21.1% and 20.0% from upstream location (25.01 km/h) and downstream location (24.66 km/h) to pedestrian crosswalk (19.73 km/h), respectively. By contrast, the speed reduction effects were minimal for stop and yield signs, flashing yellow lights, and crossings without treatment. CONCLUSIONS: Consequently, in order to reduce vehicle speeds and improve pedestrian safety at mid blocks, several speed-control measures such as speed humps, speed bumps, and transverse rumble strips are recommended to be deployed in the vicinity of pedestrian crosswalks.

Modeling level-of-safety for bus stops in China.

OBJECTIVE: Safety performance at bus stops is generally evaluated by using historical traffic crash data or traffic conflict data. However, in China, it is quite difficult to obtain such data mainly due to the lack of traffic data management and organizational issues. In light of this, the primary objective of this study is to develop a quantitative approach to evaluate bus stop safety performance. METHODS: The concept of level-of-safety for bus stops is introduced and corresponding models are proposed to quantify safety levels, which consider conflict points, traffic factors, geometric characteristics, traffic signs and markings, pavement conditions, and lighting conditions. Principal component analysis and k-means clustering methods were used to model and quantify safety levels for bus stops. RESULTS: A case study was conducted to show the applicability of the proposed model with data collected from 46 samples for the 7 most common types of bus stops in China, using 32 of the samples for modeling and 14 samples for illustration. Based on the case study, 6 levels of safety for bus stops were defined. Finally, a linear regression analysis between safety levels and the number of traffic conflicts showed that they had a strong relationship (R(2) value of 0.908). CONCLUSIONS: The results indicated that the method was well validated and could be practically used for the analysis and evaluation of bus stop safety in China. The proposed model was relatively easy to implement without the requirement of traffic crash data and/or traffic conflict data. In addition, with the proposed method, it was feasible to evaluate countermeasures to improve bus stop safety (e.g., exclusive bus lanes).

Empirical investigation on safety constraints of merging pedestrian crowd through macroscopic and microscopic analysis.

A recent crowd stampede during a New Year's Eve celebration in Shanghai, China resulted in 36 fatalities and over 49 serious injuries. Many of such tragic crowd accidents around the world resulted from complex multi-direction crowd movement such as merging behavior. Although there are a few studies on merging crowd behavior, none of them have conducted a systematic analysis considering the impact of both merging angle and flow direction towards the safety of pedestrian crowd movement. In this study, a series of controlled laboratory experiments were conducted to examine the safety constraints of merging pedestrian crowd movements considering merging angle (60°, 90° and 180°) and flow direction under slow running and blocked vision condition. Then, macroscopic and microscopic properties of crowd dynamics are obtained and visualized through the analysis of pedestrian crowd trajectory data derived from video footage. It was found that merging angle had a significant influence on the fluctuations of pedestrian flows, which is important in a critical situation such as emergency evacuation. As the merging angle increased, mean velocity and mean flow at the measuring region in the exit corridors decreased, while mean density increased. A similar trend was observed for the number of weaving and overtaking conflicts, which resulted in the increase of mean headway. Further, flow direction had a significant impact on the outflow of the individuals while blocked vision had an influence on pedestrian crowd interactions and merging process. Finally, this paper discusses safety assessments on crowd merging behaviors along with some recommendations for future research. Findings from this study can assist in the development and validation of pedestrian crowd simulation models as well as organization and control of crowd events.

Goodness-of-fit testing for accident models with low means.

The modeling of relationships between motor vehicle crashes and underlying factors has been investigated for more than three decades. Recently, many highway safety studies have documented the use of negative binomial (NB) regression models. On rare occasions, the Poisson model may be the only alternative especially when crash sample mean is low. Pearson's X(2) and the scaled deviance (G(2)) are two common test statistics that have been proposed as measures of goodness-of-fit (GOF) for Poisson or NB models. Unfortunately, transportation safety analysts often deal with crash data that are characterized by low sample mean values. Under such conditions, the traditional test statistics may not perform very well. This study has three objectives. The first objective is to examine all the traditional test statistics and compare their performance for the GOF of accident models subjected to low sample means. Secondly, this study proposes a new test statistic that is not dependent on the sample size for Poisson regression model, as opposed to the grouped G(2) method. The proposed method is easy to use and does not require grouping data, which is time consuming and may not be feasible to use if the sample size is small. Moreover, the proposed method can be used for lower sample means than documented in previous studies. Thirdly, this study provides guidance on how and when to use appropriate test statistics for both Poisson and negative binomial (NB) regression models.

Safety impact of Gateway Monuments.

Gateway Monuments are free standing roadside structures or signage that communicate the name of a city, country or township to motorists. The placement of such monuments within state-controlled right-of-way is a relatively recent occurrence in California. As a result, the California Department of Transportation (Caltrans) initiated research to quantify the impacts that this type of signage may or may not have on crashes in their vicinity. To date, no specific research has examined the impact such features have on crashes. To determine whether these features impacted safety, the before-after study method using the Empirical Bayes technique was used, with reference groups and Safety Performance Functions adapted from existing studies, eliminating the need to calibrate new models. Results indicated that, on an individual basis, no deterioration in safety was observed at any monument site. When all sites were examined collectively (using two different scenarios), the calculated index of effectiveness values were 0.978 and 0.680, respectively, corresponding to 2.2% and 32.0% reductions in crashes. In addition to the EB method, naïve study methods (with and without AADT taken into account) were applied to the study data. Results (crash reductions) from these methods also showed that the presence of Gateway Monuments did not have negative impact on traffic safety. However, the use of EB technique should be very careful employed when adopting reference groups from different jurisdictions, as these may affect the validity of EB results. In light of these results, Caltrans may continue to participate in the Gateway Monument Program at its discretion with the knowledge that roadway safety is not impacted by monuments.

Estimating the variance in before-after studies.

PROBLEM: To simplify the computation of the variance in before-after studies, it is generally assumed that the observed crash data for each entity (or observation) are Poisson distributed. Given the characteristics of this distribution, the observed value (x(i)) for each entity is implicitly made equal to its variance. However, the variance should be estimated using the conditional properties of this observed value (defined as a random variable), that is, f(x(i)/mu(i)), since the mean of the observed value is in fact unknown. METHOD: Parametric and non-parametric bootstrap methods were investigated to evaluate the conditional assumption using simulated and observed data. RESULTS: The results of this study show that observed data should not be used as a substitute for the variance, even if the entities are assumed to be Poisson distributed. Consequently, the estimated variance for the parameters under study in traditional before-after studies is likely to be underestimated. CONCLUSIONS: The proposed methods offer more accurate approaches for estimating the variance in before-after studies.