Semi and Nonparametric Conditional Probability Density, a Case Study of Pedestrian Crashes

Background: Kernel-based methods have gained popularity as employed model residual’s distribution might not be defined by any classical parametric distribution. Kernel-based method has been extended to estimate conditional densities instead of conditional distributions when data incorporate both discrete and continuous attributes. The method often has been based on smoothing parameters to use optimal values for various attributes. Thus, in case of an explanatory variable being independent of the dependent variable, that attribute would be dropped in the nonparametric method by assigning a large smoothing parameter, giving them uniform distributions so their variances to the model’s variance would be minimal. Objectives: The objective of this study was to identify factors to the severity of pedestrian crashes based on an unbiased method. Especially, this study was conducted to evaluate the applicability of kernel-based techniques of semi- and nonparametric methods on the crash dataset by means of confusion techniques. Methods: In this study, two non- and semi-parametric kernel-based methods were implemented to model the severity of pedestrian crashes. The estimation of the semi-parametric densities is based on the adoptive local smoothing and maximization of the quasi-likelihood function, which is similar somehow to the likelihood of the binary logit model. On the other hand, the nonparametric method is based on the selection of optimal smoothing parameters in estimation of the conditional probability density function to minimize mean integrated squared error (MISE). The performances of those models are evaluated by their prediction power. To have a benchmark for comparison, the standard logistic regression was also employed. Although those methods have been employed in other fields, this is one of the earliest studies that employed those techniques in the context of traffic safety. Results: The results highlighted that the nonparametric kernel-based method outperforms the semi-parametric (single-index model) and the standard logit model based on the confusion matrices. To have a vision about the bandwidth selection method for removal of the irrelevant attributes in nonparametric approach, we added some noisy predictors to the models and a comparison was made. Extensive discussion has been made in the content of this study regarding the methodological approach of the models. Conclusion: To summarize, alcohol and drug involvement, driving on non-level grade, and bad lighting conditions are some of the factors that increase the likelihood of pedestrian crash severity. This is one of the earliest studies that implemented the methods in the context of transportation problems. The nonparametric method is especially recommended to be used in the field of traffic safety when there are uncertainties regarding the importance of predictors as the technique would automatically drop unimportant predictors.

Understanding Gender, Income and Travel Behavior in Casablanca City – Morocco

Objective: The purpose of this paper is to extend the research on gendered differences in travel behavior in developing countries by analyzing travel behavior variability within as well as across gender and income groups in the case of Casablanca city. Methods: Data from the 2018 Casablanca Travel Survey show that overall, women are less mobile than men, make fewer work-related trips and more household maintenance trips, but these differences are heterogeneously distributed across income groups. With the increase in income, women tend to carry out more trips than men; the inverse is observed for the middle- and low-income categories. Results: While for the lowest income groups, walking is the most predominant mode for both men and women, we notice that the private car has the highest modal share within the highest income groups as with the increase in household income, both genders avoid non-motorized transport modes. The particular status of women in some households as breadwinners and reproducers as well as the socio-cultural context of the city shape their mobility and the choice of their activities. Conclusion: Hence, these findings suggest, from a policy perspective, that the public transit system along with spatial planning strategies need to be improved to help overcome women's mobility constraints, especially when they belong to low-income households so they can fully access the city amenities and opportunities. On the other hand, transport policies need to be not only gender-sensitive but also “vulnerable groups” sensitive as mobility impediments are similarly experienced by males and females in some contexts.

Characteristics and Potential Impacts of Rest Areas Proximate to Roadways: A Review

Objective: Rest areas are one of the most common roadside service facilities designated for parking and resting purposes. They are considered crucial components in the roadway network since they provide road users with a safe and comfortable place nearby the mainline. Obtaining extensive information on the planning, advantages, and potential effects of rest areas will help establish a better understanding of their characteristics and essential benefits. This will enable decision-makers and safety engineers to implement effective policies. Therefore, this paper reviews the literature on the development and impact of rest areas close to roadways. The objectives of this paper are as follows: to discuss the potential positive and negative effects of rest areas, to determine major challenges, to provide recommendations for implementing such facilities based on the literature search, and to fill a research gap. Methods: The review focuses on articles and reports addressing the features and impacts of rest areas and parking facilities published in English. The literature on parking demands related to rest area facilities is not within the scope of this research. Results: The challenges and recommendations concerning the development and safety aspects of rest areas are critically discussed. The review of numerous studies concerning the safety and operation of rest areas has revealed conflicting results. Although several studies found that establishing rest area facilities proximate to roadway segments positively impacts safety and operation, some indicated that such facilities might pose safety and operation risks along adjacent sections. Thus, this paper highlights a gap in the research area, determining the distribution patterns of crashes occurring along the proximate segments of rest areas. Conclusion: Although rest areas do help in mitigating fatigue-related crashes, the review highlights that future research should investigate the relationship between roadway features and collisions occurring along nearby segments of rest areas to fully understand the safety effects of rest areas nearby the mainline. This work is beneficial for decision-makers and safety engineers since it provides valuable information in terms of the planning features of rest areas and parking facilities, along with their essential impact.

The Need of E-ticket to Support the Public Bus Service Improvement Policy in a Developing Country

Background: Public buses are a major transportation mode in large cities in the developing country Indonesia. Nevertheless, most societies still use passenger cars. Therefore, the road authority has developed an important policy to improve public bus services soon. One of the public bus services is to change the bus operational system, including the manual ticketing system to an electronic ticket (e-ticket) system. In order to make the policy succeed, the road authority should ask for passengers’ opinions. Objective: The purposes of this study are to ensure that the bus e-ticket is needed to support the policy and then to determine important priority factors of bus e-ticket implementation. Methods: The data were collected using a direct survey with a questionnaire in large cities, Surabaya and Denpasar in Indonesia. A total of 565 bus passengers participated in this survey. An analysis was conducted through cross tabulation between the respondents’ demographic data and their perceived level of need and priority of implementation with regard to various factors of the e-ticket system. The Simple Additive Weighting method was used to determine the important priority factors. Results: Results indicated that a bus e-ticket needed for the cross tabulation average value is more than 3.60 out of 5.00 for all factors. Furthermore, the three highest values of factors based on the Simple Additive Weighting method are ease of access, availability of the bus routes information, and affordability of the e-ticket price. Conclusion: Since respondents indicate that the e-ticket is needed and is a priority, then the policy is beneficial not only to improve bus services in Indonesia but also in other developing countries with similar traffic and geometric conditions.

Travel Mode Choice Modeling: Predictive Efficacy between Machine Learning Models and Discrete Choice Model

Background: A complex travel behaviour among users is intertwined with many factors. Traditionally, the exploration in travel mode choice modeling has been dominated by the Discrete Choice model, nonetheless, owing to the advancement in computational techniques, machine learning has gained traction in understanding travel behavior. Aim: This study aims at predicting users’ travel model choice by means of machine learning models against a conventional Discrete Choice Model, i.e., Binary Logistic Regression. Objective: To investigate the comparison between machine learning models, namely Neural Network, Random Forest, Decision Tree, and Support Vector Machine against the Discrete Choice Model (Binary Logistic Regression) in the prediction of travel mode choice amongst Kuantan City. Methodology: The dataset was collected in Kuantan City, Malaysia, through the Revealed/Stated Preferences (RP/SP) Survey. The data collected was split into a ratio of 80:20 for training and testing before evaluating them between the aforesaid models. The hyperparameters of the models were set to default. The performance of the models is evaluated based on classification accuracy. Results: It was shown in the present study that the Neural Network Model is able to attain a higher prediction accuracy as compared to Binary Logistic Regression (Discrete Choice Model) in classifying mode choice of Kuantan users either to choose public transport or private vehicles as daily transportation. Feature importance technique is crucial for identifying the significant features in modelling travel mode choice. It is demonstrated that the Neural Network Model can yield exceptional classification of mode choice up to 73.4% and 72.4% of training and testing data, respectively, by considering the features identified via the feature importance technique, suggesting the viability of the proposed technique in supporting an informed decision. Conclusion: The findings highlight the strengths and limitations of the Machine Learning Technique as well as the Discrete Choice Model in modeling travel mode choice. It was shown that Machine Learning models have the capability to provide better prediction that could assist the urban transportation planning among policymakers. Meanwhile, it could be also demonstrated that the Discrete Choice Model (Binary Logistic Regression) is helpful in getting a better understanding in expressing the inference relationship between variables for improvising the future transportation system.

The Role of Transport in Reverse Distribution Chains

Reverse distribution operations have become significant to the manufacturers in supporting the firms to achieve the circularity of products in the reverse flow chains. There are four main components of the reverse distribution chains; inbound and outbound transportation, collection of returns, centralised returns centres, and recovery process. Transport is essential by reducing the lead time and transportation cost of the used and the recovered products. Therefore, it is pertinent that the manufacturers continue endeavouring for the sustainable transportation process in each of the components to ensure the success of the reverse distribution chains.

Reducing Vehicle Submersions and Consequent Fatalities on Highway I-75 in Florida (Alligator Alley): Effectiveness of a Cable Safety Barrier System

Objective: We evaluated the effectiveness of a Cable Safety Barrier (CSB) system in preventing Run-Off-Road (ROR) Vehicle Immersions (VIs) and fatalities in canals along the I-75 freeway (Alligator Alley) in Collier County, Florida. The CSB system, which runs along both sides of the 80-km stretch of freeway and was installed between 2003 and 2004. Methods: Data from the Fatal Analysis Reporting System (FARS) were used to compare annual VIs and VI fatalities between pre-installation of the CSB system (1995-2002) to post-installation (2005-2012). As well, post-installation data from the Florida Department of Transport (FDOT) (2007-2011) and police reports were reviewed to determine the number of, and manner in which, vehicles were either contained by, or crossed, the CSB by either penetrating or overriding the barriers. Results: Pre- to post-installation, total accidents increased from 81.4/y to 106.2/y, accidents resulting in VIs decreased from 13.8% to 2.4%, and accidents resulting in VI fatalities decreased from 3.4% to 0.4% (FDOT). Fatal vehicle immersions decreased from 2.4/y to 0.9/y (P<0.01) and vehicle immersion fatalities decreased from 3.3/y to 1.4/y (P<0.05) (FARS). Post-installation, 531 accidents occurred with 110 ROR vehicles travelling towards the canals; 91 vehicles contacted the CSB with only 14 vehicles (15.4%) penetrating the barrier, and 7 (7.7%) overriding the barrier (FDOT). Conclusion: The CSB system along I-75 in Collier County dramatically decreased ROR vehicles from reaching the parallel canals, and consequent vehicle immersion fatalities. Results support the installation of lateral CSB systems on other high-risk roadways to reduce ROR crashes into water, or with other secondary hazards.

Pedestrian Compliance at Signalized Intersections along Major Arterials

Background: Pedestrian non-compliance at signalized crossings is unsafe and considered one of the causes of pedestrian crashes. The speed limit on most major urban roads is 60 km/hr or less. However, the speed on some urban roads is higher in some countries. In this case, the situation is more unsafe and increases the possibility of fatal injuries or fatalities in the case of a crash. Therefore, it is expected that the pedestrians will be more cautious on these roads. Aim: This study aims to explore pedestrian compliance at signalized intersections on major arterials with 80 km/hr speeds in Qatar. Methods: Video data were collected for pedestrian movements at multiple intersections. Results: The study reported a 68.1 percent compliance rate at the study locations. The results also revealed that 14.6 percent of the pedestrians crossed during the Flashing Don’t Walk interval and 17.3 percent crossed during the Steady Don’t Walk interval. These rates are considered high compared to other countries. Several variables that may influence pedestrians’ behavior were investigated. Binary and ordinal logistic regression models were developed to describe the pedestrian crossing behavior as a function of these variables. Conclusion: Male and middle-age pedestrians were more likely to cross during these two intervals. The analysis showed that female pedestrians, elder pedestrians, pedestrians crossing in groups, pedestrians waiting before crossing, and pedestrians crossing against a flow of other pedestrians are more likely to comply and cross during the Walk interval compared to other groups. Several solutions were proposed in the study to increase compliance rates.

High-Occupancy Vehicle Lane Enforcement System

Introduction: An automatic High-Occupancy Vehicle (HOV) lane enforcement system is developed and evaluated. Current manual enforcement practices by the police bring about safety concerns and unnecessary traffic delays. Only vehicles with more than five passengers are permitted to use HOV lanes on freeways in Korea. Hence, detecting the number of passengers in HOVs is a core element for their development. Methods: For a quick detection capability, a YOLO-based passenger detection model was built. The system comprises three infrared cameras: two are for compartment detection and the other is for number plate recognition. Multiple infrared illuminations with the same frequency as the cameras and laser sensors for vehicle detection and speed measurement are also employed. Results: The performance of the developed system is evaluated with real-world data collected on proving ground. As a result, it showed a passenger detection error of nine percent on average. The performances revealed no difference in vehicle speeds and the number of passengers according to ANOVA tests. Conclusion: Using the developed system, more efficient and safer HOV lane enforcement practices can be made.

The Energy Consumption of Passenger Vehicles in a Transformed Mobility System with Autonomous, Shared and Fit-For-Purpose Electric Vehicles in the Netherlands

Aims: This article explores the tank-to-wheel energy consumption of passenger transport at full adoption of fit-for-purpose shared and autonomous electric vehicles. Background: The energy consumption of passenger transport is increasing every year. Electrification of vehicles reduces their energy consumption significantly but is not the only disruptive trend in mobility. Shared fleets and autonomous driving are also expected to have large impacts and lead to fleets with one-person fit-for-purpose vehicles. The energy consumption of passenger transport in such scenarios is rarely discussed and we have not yet seen attempts to quantify it. Objective: The objective of this study is to quantify the tank-to-wheel energy consumption of passenger transport when the vehicle fleet is comprised of shared autonomous and electric fit-for-purpose vehicles and where cheap and accessible mobility leads to significantly increased mobility demand. Methodology: The approach consists of four steps. First, describing the key characteristics of a future mobility system with fit-for-purpose shared autonomous electric vehicles. Second, estimating the vehicle miles traveled in such a scenario. Third, estimating the energy use of the fit-for-purpose vehicles. And last, multiplying the mileages and energy consumptions of the vehicles and scaling the results with the population of the Netherlands. Results: Our findings show that the daily tank-to-wheel energy consumption from Dutch passenger transport in full adoption scenarios of shared autonomous electric vehicles ranges from 700 Wh to 2200 Wh per capita. This implies a reduction of 90% to 70% compared to the current situation. Conclusion: Full adoption of shared autonomous electric vehicles could increase the vehicle-miles-travelled and thus energy use of passenger transport by 30% to 150%. Electrification of vehicles reduces energy consumption by 75%. Autonomous driving has the potential of reducing the energy consumption by up to 40% and implementing one-person fit-for-purpose vehicles by another 50% to 60%. For our case study of the Netherlands, this means that the current 600 TJ/day that is consumed by passenger vehicles will be reduced to about 50 to 150 TJ/day at full adoption of SAEVs.