Computer Engineering Commons^™

Are Ride-Hailing Services Safer Than Taxis? A Multivariate Spatial Approach With Accomodation Of Exposure Uncertainty, Guocong Zhai, Kun Xie, Hong Yang, Di Yang

Civil & Environmental Engineering Faculty Publications

Despite many research efforts on ride-hailing services and taxis, limited studies have compared the safety performance of the two modes. A major challenge is the need for reliable mode-specific exposure data to model their safety outcomes. Moreover, crash frequencies of the two modes by injury severities tend to be spatially and inherently correlated. To fully address these issues, this study proposes a novel multivariate conditional autoregressive model considering measurement errors in mode-specific exposures (MVCARME). More specially, a classical measurement error structure is used to accommodate the uncertainty of mode-specific exposures estimated, and a multivariate spatial specification is adopted to capture …

Monocular Camera Viewpoint-Invariant Vehicular Traffic Segmentation And Classification Utilizing Small Datasets, Amr Yousef, Jeff Flora, Khan Iftekharuddin

Electrical & Computer Engineering Faculty Publications

The work presented here develops a computer vision framework that is view angle independent for vehicle segmentation and classification from roadway traffic systems installed by the Virginia Department of Transportation (VDOT). An automated technique for extracting a region of interest is discussed to speed up the processing. The VDOT traffic videos are analyzed for vehicle segmentation using an improved robust low-rank matrix decomposition technique. It presents a new and effective thresholding method that improves segmentation accuracy and simultaneously speeds up the segmentation processing. Size and shape physical descriptors from morphological properties and textural features from the Histogram of Oriented Gradients …

Data-Driven Framework For Understanding & Modeling Ride-Sourcing Transportation Systems, Bishoy Kelleny

Civil & Environmental Engineering Theses & Dissertations

Ride-sourcing transportation services offered by transportation network companies (TNCs) like Uber and Lyft are disrupting the transportation landscape. The growing demand on these services, along with their potential short and long-term impacts on the environment, society, and infrastructure emphasize the need to further understand the ride-sourcing system. There were no sufficient data to fully understand the system and integrate it within regional multimodal transportation frameworks. This can be attributed to commercial and competition reasons, given the technology-enabled and innovative nature of the system. Recently, in 2019, the City of Chicago the released an extensive and complete ride-sourcing trip-level data for …

Data-Driven Operational And Safety Analysis Of Emerging Shared Electric Scooter Systems, Qingyu Ma

Computational Modeling & Simulation Engineering Theses & Dissertations

The rapid rise of shared electric scooter (E-Scooter) systems offers many urban areas a new micro-mobility solution. The portable and flexible characteristics have made E-Scooters a competitive mode for short-distance trips. Compared to other modes such as bikes, E-Scooters allow riders to freely ride on different facilities such as streets, sidewalks, and bike lanes. However, sharing lanes with vehicles and other users tends to cause safety issues for riding E-Scooters. Conventional methods are often not applicable for analyzing such safety issues because well-archived historical crash records are not commonly available for emerging E-Scooters.

Perceiving the growth of such a micro-mobility …

Supporting Transportation System Management And Operations Using Internet Of Things Technology, Hong Yang, Yuzhong Shen, Mecit Cetin, Zhenyu Wang

Computational Modeling & Simulation Engineering Faculty Publications

Low power wide-area network (LPWAN) technology aims to provide long range and low power wireless communication. It can serve as an alternative technology for data transmissions in many application scenarios (e.g., parking monitoring and remote flood sensing). In order to explore its feasibility in transportation systems, this project conducted a review of relevant literature to understand the current status of LPWAN applications. An online survey that targeted professionals concerned with transportation was also developed to elicit input about their experiences in using LPWAN technology for their projects. The literature review and survey results showed that LPWAN’s application in the U.S. …

Save-T: Safety Analysis Visualization And Evaluation Tool, Yuan Zhu, Sami Demiroluk, Kaan Ozbay, Kun Xie, Hong Yang, Di Sha

Civil & Environmental Engineering Faculty Publications

Traffic crashes are one of the biggest issues which constitute a threat to lives of the motorists and disrupt operations of the transportation system. To reduce the number of crashes and alleviate their impacts, it is necessary to scrutinize the factors contributing to the risk of traffic crashes. Lately, visual analytics tools become very popular for data exploration and obtaining insights from the data. In this paper, a new web-based data visualization tool called Safety Analysis Visualization and Evaluation Tool (SAVE-T) was introduced. This tool enables users to interactively create queries and visually explore the results. By utilizing an online …

An Accurate Vegetation And Non-Vegetation Differentiation Approach Based On Land Cover Classification, Chiman Kwan, David Gribben, Bulent Ayhan, Jiang Li, Sergio Bernabe, Antonio Plaza

Electrical & Computer Engineering Faculty Publications

Accurate vegetation detection is important for many applications, such as crop yield estimation, landcover land use monitoring, urban growth monitoring, drought monitoring, etc. Popular conventional approaches to vegetation detection incorporate the normalized difference vegetation index (NDVI), which uses the red and near infrared (NIR) bands, and enhanced vegetation index (EVI), which uses red, NIR, and the blue bands. Although NDVI and EVI are efficient, their accuracies still have room for further improvement. In this paper, we propose a new approach to vegetation detection based on land cover classification. That is, we first perform an accurate classification of 15 or more …

Vegetation Detection Using Deep Learning And Conventional Methods, Bulent Ayhan, Chiman Kwan, Bence Budavari, Liyun Kwan, Yan Lu, Daniel Perez, Jiang Li, Dimitrios Skarlatos, Marinos Vlachos

Electrical & Computer Engineering Faculty Publications

Land cover classification with the focus on chlorophyll-rich vegetation detection plays an important role in urban growth monitoring and planning, autonomous navigation, drone mapping, biodiversity conservation, etc. Conventional approaches usually apply the normalized difference vegetation index (NDVI) for vegetation detection. In this paper, we investigate the performance of deep learning and conventional methods for vegetation detection. Two deep learning methods, DeepLabV3+ and our customized convolutional neural network (CNN) were evaluated with respect to their detection performance when training and testing datasets originated from different geographical sites with different image resolutions. A novel object-based vegetation detection approach, which utilizes NDVI, computer …

Hurricane Evacuation Modeling Using Behavior Models And Scenario-Driven Agent-Based Simulations, Yuan Zhu, Kun Xie, Kaan Ozbay, Hong Yang

Computational Modeling & Simulation Engineering Faculty Publications

Transportation modeling and simulation play an important role in the planning and management of emergency evacuation. It is often indispensable for the preparedness and timely response to extreme events occurring in highly populated areas. Reliable and robust agent-based evacuation models are of great importance to support evacuation decision making. Nevertheless, these models rely on numerous hypothetical causal relationships between the evacuation behavior and a variety of factors including socio-economic characteristics and storm intensity. Understanding the impacts of these factors on evacuation behaviors (e.g., destination and route choices) is crucial in preparing optimal evacuation plans. This paper aims to contribute to …

Integrating A Simple Traffic Incident Model For Rapid Evacuation Analysis, Andrew J. Collins, R. Michael Robinson, Peter Foytik, Craig Jordan, Barry C. Ezell

VMASC Publications

Road transportation networks are a segment of society's critical infrastructure particularly susceptible to service disruptions. Traffic incidents disrupt road networks by producing blockages and increasing travel times, creating significant impacts during emergency events such as evacuations. For this reason, it is extremely important to incorporate traffic incidents in evacuation planning models. Emergency managers and decision makers need tools that enable rapid assessment of multiple, varied scenarios. Many evacuation simulations require high-fidelity data input making them impractical for rapid deployment by practitioners. Since there is such variation in evacuation types and the method of disruption, evacuation models do not require the …

Impact Of Data Resolution On Peak Hour Factor Estimation For Transportation Decisions, Jan-Mou Li, Lee D. Han, Chung-Hao Chen

Electrical & Computer Engineering Faculty Publications

Inductance loop detection systems serve as a primary data source to contemporary traffic information systems. Measures like 20-second or 30-second average velocity, flow, and lane occupancy can be aggregated from individual loop detector actuation sampled at 60 Hz typically. Practically, these measures would sometimes be further aggregated into a much lower, e.g. 15-minute, resolution and then the raw data were lost. Valuable traffic information like flow variation may be distorted when the lower resolution aggregation is practiced. A biased conclusion could be drawn from a data integration system consisted of this kind of distortions. Three approaches estimating a peak hour …

Solving The Vehicle Re-Identification Problem By Using Neural Networks, Tanweer Rashid

Computational Modeling & Simulation Engineering Theses & Dissertations

Vehicle re-identification is the process by which vehicle attributes measured at one point on a road network are compared to vehicle attributes measured at another point in an effort to match vehicles without using any unique identifiers such as license plate numbers. A match is made if the two measurements are estimated to belong to the same vehicle. Vehicle attributes can be sensor readings such as loop induction signatures, or they can also be actual vehicle characteristics such as length, weight, number of axles, etc. This research makes use of vehicle length, travel time, axle spacing and axle weights for …

Vehicular Ad Hoc Networks, Syed R. Rizvi, Stephan Olariu, Christina M. Oinotti, Shaharuddin Salleh, Mona E. Rizvi, Zainab Zaidi

Computer Science Faculty Publications

(First paragraph) Vehicular ad hoc networks (VANETs) have recently been proposed as one of the promising ad hoc networking techniques that can provide both drivers and passengers with a safe and enjoyable driving experience. VANETs can be used for many applications with vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications. In the United States, motor vehicle traffic crashes are the leading cause of death for all motorists between two and thirty-four years of age. In 2009, the National Highway Traffic Safety Administration (NHTSA) reported that 33,808 people were killed in motor vehicle traffic crashes. The US Department of Transportation (US-DOT) estimates that …