Transportation Commons^™

A Survey On Modern Deep Neural Network For Traffic Prediction: Trends, Methods And Challenges, David Alexander Tedjopumomo, Zhifeng Bao, Baihua Zheng, Farhana Murtaza Choudhury, Kai Qin

Research Collection School Of Computing and Information Systems

In this modern era, traffic congestion has become a major source of negative economic and environmental impact for urban areas worldwide. One of the most efficient ways to mitigate traffic congestion is through future traffic prediction. The field of traffic prediction has evolved greatly ever since its inception in the late 70s. Earlier studies mainly use classical statistical models such as ARIMA and its variants. Then, researchers started to focus on machine learning models due to their power and flexibility. As theoretical and technological advances emerge, we enter the era of deep neural network, which gained popularity due to its …

A Field Study In An Urban Area: Examining Distracted Pedestrian Unsafe Crossing Behavior, Emma Hood

Undergraduate Research Symposium

A field study examining distracted pedestrian unsafe crossing behavior in an urban area. The study is among the first to contribute knowledge to environmental alterations impact on crossing behavior. Portions of the abstract are a part of a manuscript that will be submitted to Psi Chi Journal of Psychological Research for undergraduate students.

Addressing Gendered Harassment And Women's Travel Needs, Madeline Brozen

PSU Transportation Seminars

This presentation will cover experiences, disparities, and solutions to gendered travel differences. Madeline will discuss research from a worldwide survey of harassment on public transit with specific insights from Los Angeles and research from two agency-led studies in Los Angeles. The talk will cover the large issues that make women's travel needs distinct from their male counter-parts - safety and complex travel patterns and some promising solutions for addressing these disparities.

Streamlining Project Development Through Planning & Environmental Linkages, Karen Hadley, Brett Lackey

Purdue Road School

As transportation agencies continue to explore ways to be more efficient in the project development process, they are embracing integrated methodologies like planning and environmental linkages. This tool is practical, yet highly effective and inclusive, and teams across the country are experiencing its value. This presentation will highlight a variety of use cases, discuss lessons learned and best practices, and specifically address how planning and environmental linkages can be applied in Indiana and the Midwest.

The Rise Of Southern Nevada As A Cluster For Metropolitan Transit Technology Innovations, Arthur C. Nelson

Policy Briefs and Reports

Southern Nevada is emerging as the nation’s leader in private sector-driven innovations in transportation technologies. From the humble beginnings of a monorail system serving a portion of major hotel and gaming venues along the Las Vegas Strip, now supplemented by an array of people movers, Southern Nevada continues to attract transit innovations in tunneling, Hyperloop, and driverless vehicle delivery technologies. The region may soon anchor a high-speed rail system connecting Southern Nevada to Los Angeles. The purpose of this briefing paper is to frame the nature of this emerging transportation cluster and the opportunities this creates for Southern Nevada to …

Webinar: Exploring Data Fusion Techniques To Derive Bicycle Volumes On A Network, Sirisha Kothuri, Joe Broach, Kate Hyun

TREC Webinar Series

Planners and decision makers have increasingly voiced a need for network-wide estimates of bicycling activity. Such volume estimates have for decades informed motorized planning and analysis but have only recently become feasible for non-motorized travel modes. Recently, new sources of bicycling activity data have emerged such as Strava, Streetlight, and GPS-enabled bike share systems. These emerging data sources have potential advantages as a complement to traditional count data, and have even been proposed as replacements for such data, since they are collected continuously and for larger portions of local bicycle networks. However, the representativeness of these new data sources has …

Congestion Costs And Scheduling Preferences Of Car Commuters In California: Estimates Using Big Data, Jinwon Kim, Jucheol Moon

Mineta Transportation Institute

On average, California car commuters waste 4–5 minutes per morning commute due to congestion. Multiplied across all California car commuters, those few minutes entail a yearly total of approximately 2.3 billion hours of time wasted, costing 6 billion dollars. The objective of this study is to quantify congestion costs and determine how commuters adapt to the level of congestion they face (i.e., commuters’ scheduling utility functions). To that end, this research developed a model of trip scheduling under congestion to construct California commuters’ travel-time profiles, i.e., the menu of travel times that each individual would likely face according to alternate …

Optimizing Multimodal Transportation Access To Support Commuting Among Low-Income Transit Riders With Social Distancing, Shailesh Chandra, Vivek Mishra

Mineta Transportation Institute

During the COVID-19 pandemic, LA Metro has encouraged social distancing among passengers—especially at stations of high-demand routes—and has increased fixed-route transit (FRT) services. However, potential impacts of social distancing on the performance of FRT services remain mostly unknown. This research evaluates the accessibility of FRT buses with social distancing using the ridership data collected on four FRT routes: 105, 108, 111, and 115 of the LA Metro's A Line stations located in low-income neighborhoods. This research shows that social distancing of six feet can impact FRT's accessibility to destination stations, and maximum accessibility is achieved only for a certain number …

Examining The Effects Of Precision Scheduled Railroading On Intercity Passenger And High-Speed Rail Service, John G. Green, Francis J. Miller

Mineta Transportation Institute

More than just scheduling terminal-to-terminal trips for trains, “Precision Scheduled Railroading” (PSR) creates entire point-to-point trip plans for individual railroad shipments. Since precision execution was first put into practice, the benefits to shipment arrival reliability and to freight railroads’ profitability have been demonstrated by its use in several Class One freight railroads. However, the effects of the PSR operating strategy on passenger railway operations in shared freight/passenger corridors has not been studied in detail. This research examines the effects of PSR railroad operations on passenger railways, including measuring “Host Railroad Minutes of Delay per 10,000 Train-Miles” and “On-Time Performance” of …

Examining The Effects Of A Bike And E-Bike Lending Program On Commuting Behavior, Dillon T. Fitch, Zeyu Gao, Lucy Noble, Terry Mac

Mineta Transportation Institute

In 2015, Google added a new transportation demand management (TDM) program to increase bike commuting to their two main campuses in Mountain View and Sunnyvale, California. An initial survey of employees indicated that bike ownership and worry about maintenance were primary bicycling barriers. With this information, Google began a program that loaned high-quality electric-assisted and conventional bicycles for a period of six months at no cost to interested employees. This research evaluates the effectiveness of the program at changing travel behavior to the corporate campuses by using self-reported and smartphone-integrated travel data. The lending program at Google represents one of, …

The Impact Of Ride-Hail Surge Factors On Taxi Bookings, Sumit Agarwal, Ben Charoenwong, Shih-Fen Cheng, Jussi Keppo

Research Collection School Of Computing and Information Systems

We study the role of ride-hailing surge factors on the allocative efficiency of taxis by combining a reduced-form estimation with structural analyses using machine-learning-based demand predictions. Where other research study the effect of entry on incumbent taxis, we use higher frequency granular data to study how location-time-specific surge factors affect taxi bookings to bound the effect of customer decisions while accounting for various confounding variables. We find that even in a unique market like Singapore, where incumbent taxi companies have app-based booking systems similar to those from ride-hailing companies like Uber, the estimated upper bound on the cross-platform substitution between …

Heterogeneous Attentions For Solving Pickup And Delivery Problem Via Deep Reinforcement Learning, Jingwen Li, Liang Xin, Zhiguang Cao, Andrew Lim, Wen Song, Jie Zhang

Research Collection School Of Computing and Information Systems

Recently, there is an emerging trend to apply deep reinforcement learning to solve the vehicle routing problem (VRP), where a learnt policy governs the selection of next node for visiting. However, existing methods could not handle well the pairing and precedence relationships in the pickup and delivery problem (PDP), which is a representative variant of VRP. To address this challenging issue, we leverage a novel neural network integrated with a heterogeneous attention mechanism to empower the policy in deep reinforcement learning to automatically select the nodes. In particular, the heterogeneous attention mechanism specifically prescribes attentions for each role of the …

Exploring Data Fusion Techniques To Estimate Network-Wide Bicycle Volumes, Sirisha Kothuri, Joseph Broach, Nathan Mcneil, Kate Hyun, Stephen Mattingly, Md. Mintu Miah, Krista Nordback, Frank Proulx

TREC Final Reports

This research developed a method for evaluating and integrating emerging sources (Strava, StreetLight, and Bikeshare) of bicycle activity data with conventional demand data (permanent counts, short-duration counts) using traditional (Poisson) and advanced machine learning techniques. First, a literature review was conducted, along with cataloging and evaluating available third-party data sources and existing applications. Next, six sites (Boulder, Charlotte, Dallas, Portland, Bend, and Eugene) that represented a variety of contexts (urban, suburban) and geographical diversity were selected. Of these, Boulder, Charlotte and Dallas constituted the basic sites, where one year of data (i.e., 2019) was used for modeling. Portland, Bend, and …

Car Accidents, Smartphone Adoption And 3g Coverage, Jonathan Hersh, Bree J. Lang, Matthew Lang

Economics Faculty Articles and Research

This paper examines the relationship between smartphone use by drivers and traffic accidents in California between 2001 and 2013. In order to estimate smartphone use, we first show that widespread adoption of modern smartphones began in 2009 after the release of the iPhone 3G and T-Mobile G1. This information is combined with annual 3G coverage maps that are constructed from cellular tower information in a machine learning framework. In a difference-in-differences framework, we estimate the combined effect of smartphone adoption and 3G coverage along quarter-mile road segments. Controlling for census tract population density, road and year fixed effects, Poisson regression …

Webinar: Is Transit-Oriented Development Affordable For Low And Moderate Income Households?, Reid Ewing, Justyna Kaniewska

TREC Webinar Series

Transportation and land use planning, as a field, is shifting away from segregated uses connected by highways and streets to more compact, mixed-use developments connected by high-quality transit. This new paradigm has brought special attention to transit-oriented developments (TOD), which are sometimes touted as being among the most affordable, efficient places to live. But how affordable are they, and who has the power to effect change? This study examines housing costs for households living in TODs.

Oral Presentations: Social Sciences I, Olivia Maurer, Kaden Grace, Ryan Wallace

Mississippi Undergraduate Honors Conference

Video provided above is of Olivia Maurer's presentation.

Video of Kaden Grace's presentation is available here.

Video of Ryan Wallace's presentation is available here.

Reckoning With Induced Vehicle Travel, Jamey Volker

PSU Transportation Seminars

Empirical research shows that expanding roadway capacity induces more driving - the so-called "induced travel" phenomenon. However, environmental impact assessments and cost-benefit analyses of roadway capacity expansion projects have historically ignored, underestimated, or misestimated this induced travel effect. As a result, they frequently overestimate the projects' potential to relieve congestion and reduce air pollution. That spurred our team at the National Center for Sustainable Transportation (UC Davis) to develop an online tool to facilitate estimation of induced vehicle travel from capacity expansion projects. This presentation will explain the induced travel phenomenon, introduce our induced travel calculator and its offshoots, …

Comprehensive Performance Assessment Of Passive Crowdsourcing For Counting Pedestrians And Bikes, Wen Cheng, Yongping Zhang, Edward Clay

Mineta Transportation Institute

Individuals who walk and cycle experience a variety of health and economic benefits while simultaneously benefiting their local environments and communities. It is essential to correctly obtain pedestrian and bicyclist counts for better design and planning of active transportation-related facilities. In recent years, crowdsourcing has seen a rise in popularity due to the multiple advantages relative to traditional methods. Nevertheless, crowdsourced data have been applied in fewer studies, and their reliability and performance relative to other conventional methods are rarely documented. To this end, this research examines the consistency between crowdsourced and traditionally collected count data. Additionally, the research aims …

Development Of Guidelines For Collecting Transit Ridership Data, Hong Yang, Kun Xie, Sherif Ishak, Qingyu Ma, Yang Liu

Computational Modeling & Simulation Engineering Faculty Publications

Transit ridership is a critical determinant for many transit applications such as operation optimizations and project prioritization under performance-based funding mechanisms. As a result, the quality of ridership data is of utmost importance to both transit administrative agencies and transit operators. Many transit operators in Virginia report their ridership data to the Department of Rail and Public Transportation (DRPT) and the National Transit Database (NTD). However, with no specific guidelines available to transit agencies in Virginia for collecting ridership data, the heterogeneous mixture of diverse data collection methods and technologies has often raised concerns about the consistency and quality of …

Is Transit-Oriented Development Affordable For Low And Moderate Income Households?, Reid Ewing, Sadegh Sabouri, Justyna Kaniewska, Hassan Ameli, Wookjae Yang, Fatemeh Kiani, Junsik Kim, Douty Chibamba

TREC Final Reports

The transportation and land use planning paradigm is shifting away from segregated uses connected by highways and roads to more compact, mixed-use developments connected by high-quality transit. This new paradigm has brought transit-oriented development (TOD) to the fore, and researchers continue to highlight advantages of this style of well-integrated land use and transportation planning. When it comes to affordability, what counts isn’t housing costs alone but the combination of housing plus transportation costs (H+T). If TODs do, in fact, command higher rents due to increased transit accessibility, this creates an issue of social equity, especially if higher housing costs are …