Search

Natural disasters may require that the residents of the affected area be evacuated immediately using a potentially damaged infrastructure. In this paper, we developed a mesoscopic simulation modeling approach for modeling traffic flow over a large geographic area and involving many people and vehicles. This study proposed a novel model, namely, Colored Deterministic and Stochastic Petri Net (CDSPN), which can mesoscopically provide an individual vehicular traffic dynamic. Each vehicle has a unique identifier, speed, distance to go, assigned target, and a specific route. It also proposed a method to automatically construct a Petri net model that represents the evacuation of Guilford County (GC), North Carolina, from standard Geographic Information Systems (GIS) shapefiles. We showed that this model could successfully simulate the dynamics of hundreds of thousands of vehicles moving on the highway system towards pre-specified safe targets such as medical facilities, exit points, or designated shelters. The vehicles are assumed to obey traffic laws, and the model reflects the complexities of the actual highway systems. The developed software can be used to analyze in reasonable detail the evacuation process, such as identifying bottlenecks and estimating efficiency and the time needed. An explicit list of 18 assumptions is stated and discussed. The Petri net for GC evacuation is reasonably massive, consisting of 35,476 places and 43,540 transitions with 531,595 colored tokens, where each token represents a vehicle in GC. We simulate the evacuation, develop statistics, and evaluate patterns of evaluation. We found that the evacuation took about 8.7 h.

The paper develops models for modeling the availability of bikes in the San Francisco Bay Area Bike Share System (BSS) applying machine learning at two levels: network and station. Investigating BSSs at the station-level is the full problem that would provide policymakers, planners, and operators with the needed level of details to make important choices and conclusions. We used Random Forest and Least-Squares Boosting as univariate regression algorithms to model the number of available bikes at the station-level. For the multivariate regression, we applied Partial Least-Squares Regression (PLSR) to reduce the needed prediction models and reproduce the spatiotemporal interactions in different stations in the system at the network-level. Although prediction errors were slightly lower in the case of univariate models, we found that the multivariate model results were promising for the network-level prediction, especially in systems where there are a relatively large number of stations that are spatially correlated. Moreover, results of the station-level analysis suggested that demographic information and other environmental variables were significant factors to model bikes in BSSs. We also demonstrated that the available bikes modeled at the station-level at time (Formula presented.) had a notable influence on the bike count models. Station neighbors and prediction horizon times were found to be significant predictors, with 15 minutes being the most effective prediction horizon time.

Substantial research is required to ensure that micro-mobility ride sharing provides a better fulfilment of user needs. This study proposes a novel crowdsourcing model for the ride-sharing system where light vehicles such as scooters and bikes are crowdsourced. The proposed model is expected to solve the problem of charging and maintaining a large number of light vehicles where these efforts will be the responsibility of the crowd of suppliers. The proposed model consists of three entities: suppliers, customers, and a management party responsible for receiving, renting, booking, and demand matching with offered resources. It can allow suppliers to define the location of their private e-scooters/e-bikes and the period of time they are available for rent. Using a dataset of over 9 million e-scooter trips in Austin, Texas, we ran an agent-based simulation six times using three maximum battery ranges (i.e., 35, 45, and 60 km) and different numbers of e-scooters (e.g., 50 and 100) at each origin. Computational results show that the proposed model is promising and might be advantageous to shift the charging and maintenance efforts to a crowd of suppliers.

E-scooter-sharing and e-bike-sharing systems are accommodating and easing the increased traffic in dense cities and are expanding considerably. However, these new micro-mobility transportation modes raise numerous operational and safety concerns. This study analyzes e-scooter and dockless e-bike sharing system user behavior. We investigate how average trip speed change depending on the day of the week and the time of the day. We used a dataset from the city of Austin, TX from December 2018 to May 2019. Results show that the trip average speed for e-bikes ranges between 3.01 and 3.44 m/s, which is higher than that for e-scooters (2.19 to 2.78 m/s). Results also show a similar speed pattern for the average speed of e-bikes and e-scooters throughout the days of the week and a different speed pattern for the average speed of e-bikes and e-scooters over the hours of the day. We found that users tend to ride e-bikes and e-scooters with a slower average speed for recreational purposes compared to when they are ridden for commuting purposes. Results also show that the different users’ speeds in this mixed traffic stream of Austin City should be considered in the policymaking process. It must be recognized that the disparity in speeds might increase the odds of creating the conditions for a crash between different modes in roads. This study is a building block in this field, which serves as a first of its kind, and sheds the light of significant new understanding of this emerging class of shared-road users.

Unpredictable and heterogeneous weather conditions and road incidents are common factors that impact highway traffic speeds. A better understanding of the interplay of different factors that affect roadway traffic speeds is essential for policymakers to mitigate congestion and improve road safety. This study investigates the effect of precipitation and incidents on the speed of traffic in the eastbound direction of I-64 in Virginia. To the best of our knowledge, this is the first study that studies the relationship between precipitation and incidents as factors that would have a combined effect on traffic stream speeds. Furthermore, using a mixture model of two linear regressions, we were able to model the two different regimes that the traffic speed could be classified into, namely, free-flow and congested. Using INRIX traffic data from 2013 through 2016 along a 25.6-mi section of Interstate 64 in Virginia, results show that the reduction of traffic speed only due to incidents ranges from 41% to 75% if the road is already congested. In this case, precipitation was found to be statistically insignificant. However, regardless of the incident impact, the effect of light rain in free-flow conditions ranges from insignificant to a 4% speed reduction while the effect of heavy rain ranges from a 0.6% to a 6.5% speed reduction when the incident severity is low but has a roughly double effect when the incident severity is high.

Substantial research is required to ensure that micro-mobility ride sharing provides a better fulfilment of user needs. This study proposes a novel crowdsourcing model for the ride-sharing system where light vehicles such as scooters and bikes are crowdsourced. The proposed model is expected to solve the problem of charging and maintaining a large number of light vehicles where these efforts will be the responsibility of the crowd of suppliers. The proposed model consists of three entities: suppliers, customers, and a management party responsible for receiving, renting, booking, and demand matching with offered resources. It can allow suppliers to define the location of their private e-scooters/e-bikes and the period of time they are available for rent. Using a dataset of over 9 million e-scooter trips in Austin, Texas, we ran an agent-based simulation six times using three maximum battery ranges (i.e., 35, 45, and 60 km) and different numbers of e-scooters (e.g., 50 and 100) at each origin. Computational results show that the proposed model is promising and might be advantageous to shift the charging and maintenance efforts to a crowd of suppliers.

A traditional road diet design converts a four-lane two-way road to a three-lane road consisting of two through lanes and a center two-way left turn lane. This paper introduces a new application of the road diet design in an urban corridor. Specifically, the new application converts a four-lane two-way road into a two-lane two-way road with full-time parking lanes in both directions. The paper analyzed the traffic impacts of the road diet application on the corridor of New Jersey Avenue, northwest, in the city of Washington, District of Columbia. The corridor included five signalized and one unsignalized intersections. Before-and-after analyses using Synchro 11 simulation and Site-Specific Empirical Bayes analysis were used to evaluate and compare existing and proposed scenarios. The proposed scenario provided various benefits including offering accessibility to the businesses in the area and acting as a traffic calming strategy. For signalized intersections, the overall performance remained the same for most intersections except for one intersection (on P Street), as it is significantly impacted by the road diet design due to the dramatic increase of traffic volumes in its minor streets as a result of diverting traffic volumes from the unsignalized intersection for left and through movements. Results showed that the use of a road diet design enhanced the unsignalized intersection performance due to the traffic volume divergence from its minor streets and enhanced the safety of the study area by decreasing the annual number of predicted crashes. To achieve better operational benefits and reflect traffic demands, the paper recommends to re-optimize signal timings when a road diet design is adopted.

As the Autonomous Vehicle (AV) industry is rapidly advancing, the classification of non-motorized (vulnerable) road users (VRUs) becomes essential to ensure their safety and to smooth operation of road applications. The typical practice of non-motorized road users’ classification usually takes significant training time and ignores the temporal evolution and behavior of the signal. In this research effort, we attempt to detect VRUs with high accuracy be proposing a novel framework that includes using Deep Transfer Learning, which saves training time and cost, to classify images constructed from Recurrence Quantification Analysis (RQA) that reflect the temporal dynamics and behavior of the signal. Recurrence Plots (RPs) were constructed from low-power smartphone sensors without using GPS data. The resulted RPs were used as inputs for different pre-trained Convolutional Neural Network (CNN) classifiers including constructing 227 × 227 images to be used for AlexNet and SqueezeNet; and constructing 224 × 224 images to be used for VGG16 and VGG19. Results show that the classification accuracy of Convolutional Neural Network Transfer Learning (CNN-TL) reaches 98.70%, 98.62%, 98.71%, and 98.71% for AlexNet, SqueezeNet, VGG16, and VGG19, respectively. Moreover, we trained resnet101 and shufflenet for a very short time using one epoch of data and then used them as weak learners, which yielded 98.49% classification accuracy. The results of the proposed framework outperform other results in the literature (to the best of our knowledge) and show that using CNN-TL is promising for VRUs classification. Because of its relative straightforwardness, ability to be generalized and transferred, and potential high accuracy, we anticipate that this framework might be able to solve various problems related to signal classification.

As the Autonomous Vehicle (AV) industry is rapidly advancing, the classification of non-motorized (vulnerable) road users (VRUs) becomes essential to ensure their safety and to smooth operation of road applications. The typical practice of non-motorized road users’ classification usually takes significant training time and ignores the temporal evolution and behavior of the signal. In this research effort, we attempt to detect VRUs with high accuracy be proposing a novel framework that includes using Deep Transfer Learning, which saves training time and cost, to classify images constructed from Recurrence Quantification Analysis (RQA) that reflect the temporal dynamics and behavior of the signal. Recurrence Plots (RPs) were constructed from low-power smartphone sensors without using GPS data. The resulted RPs were used as inputs for different pre-trained Convolutional Neural Network (CNN) classifiers including constructing 227 × 227 images to be used for AlexNet and SqueezeNet; and constructing 224 × 224 images to be used for VGG16 and VGG19. Results show that the classification accuracy of Convolutional Neural Network Transfer Learning (CNN-TL) reaches 98.70%, 98.62%, 98.71%, and 98.71% for AlexNet, SqueezeNet, VGG16, and VGG19, respectively. Moreover, we trained resnet101 and shufflenet for a very short time using one epoch of data and then used them as weak learners, which yielded 98.49% classification accuracy. The results of the proposed framework outperform other results in the literature (to the best of our knowledge) and show that using CNN-TL is promising for VRUs classification. Because of its relative straightforwardness, ability to be generalized and transferred, and potential high accuracy, we anticipate that this framework might be able to solve various problems related to signal classification.

Bike-sharing systems (BSSs) operators tend to spend a great amount of time and effort to satisfy users. Accurately measuring the quality-of-service (QoS) of each station in a BSS will advance this mission. Moreover, measuring the QoS and using it to study the spatial dependencies in a BSS allows operators to better manage the system. The traditionally-known QoS measurement reported in the literature is based on the proportion of problematic stations, which are defined as those with no bikes or docks available to users. The authors investigated the traditionally-known QoS measurement, and it was found neither exposes the spatial dependencies between stations nor does it discriminate between stations in a BSS. This study proposes a novel QoS measurement, namely Optimal Occupancy that captures the impact of heterogeneity of bike-sharing systems (BSSs) and reflect the spatial dependencies between the stations. Optimal Occupancy is defined as the ratio of the total time a station is functional during a given interval to the length of the interval, in which it also redefines problematic stations. The authors applied geo-statistics to explore the spatial configuration of Optimal Occupancy variations and model variograms for spatial prediction. Results revealed that the Optimal Occupancy is beneficial for operators, would result in better prediction of the QoS at nearby locations, and can be used to predict candidate spots for new stations in an existing BSS. For example, the proposed QoS for Station 50 was improved after adding a new nearby station, increasing QoS from 0.52 to 0.84 for a Monday and Tuesday of July, respectively.

In the next few decades, many traditional cities will be turned into smart cities, which are greener, safer, and faster. This transformation is supported by recent advances in information and communication technology (ICT) in addition to the expected fast spread of the Internet of Things and big data analytics. Smart cities will mitigate some of the negative impacts of traditional cities, which consume 75% of the world’s resources and energy and produce 80% of the greenhouse gases (Mohanty et al. 2006). Smart cities have many components, including smart transportation. Smart transportation will integrate different transportation networks and allow them to work together so travelers and commuters can enjoy seamless multi-mode trips based on their preferences. Consequently, more commuters will be inspired to use public transportation systems and many traffic-related problems such as congestion will be relaxed. The last mile problem is a pressing problem that needs to be solved in order for different transportation networks to work together efficiently. This problem is defined as “the short distance between home and public transit or transit stations and the workplace, which may be too far to walk.” One solution to this

With the fast advancements of the Autonomous Vehicle (AV) industry, detection of Vulnerable Road Users (VRUs) using smartphones is critical for safety applications of Cooperative Intelligent Transportation Systems (C-ITSs). This study explores the use of low-power smartphone sensors and the Recurrence Quantification Analysis (RQA) features for this task. These features are computed over a thresholded similarity matrix extracted from nine channels: accelerometer, gyroscope, and rotation vector in each direction (x, y, and z). Given the high-power consumption of GPS, GPS data is excluded. RQA features are added to traditional time domain features to investigate the classification accuracy when using binary, four-class, and five-class Random Forest classifiers. Experimental results show a promising performance when only using RQA features with a resulted accuracy of 98. 34% and a 98. 79% by adding time domain features. Results outperform previous reported accuracy, demonstrating that RQA features have high classifying capability with respect to VRU detection.