Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 21 of 21
Full-Text Articles in Engineering
Prediction Of Pedestrians' Red Light Violations Using Deep Learning, Shile Zhang
Prediction Of Pedestrians' Red Light Violations Using Deep Learning, Shile Zhang
Electronic Theses and Dissertations, 2020-
Pedestrians are regarded as Vulnerable Road Users (VRUs). Each year, thousands of pedestrians' deaths are caused by traffic crashes, which take up 16% of the total road fatalities and injuries in the U.S. (FHWA, 2018). Crashes can happen if there are interactions between VRUs and motorized transportation. And pedestrians' unexpected crossings, such as red-light violations at the signalized intersections, would expose them to motorized transportation and cause potential collisions. This thesis is intended to predict the pedestrians' red-light violation behaviors at the signalized crosswalks based on an LSTM (Long Short-term Memory) neural network. With video data collected from real traffic …
Modeling Of Incident Type And Incident Duration Using Data From Multiple Years, Sudipta Dey Tirtha
Modeling Of Incident Type And Incident Duration Using Data From Multiple Years, Sudipta Dey Tirtha
Electronic Theses and Dissertations, 2020-
We develop a model system that recognizes the distinct traffic incident duration profiles based on incident type. Specifically, a copula-based joint framework with a scaled multinomial logit model (SMNL) system for incident type and a grouped generalized ordered logit (GGOL) model system for incident duration to accommodate for the impact of observed and unobserved effects on incident type and incident duration. The model system is estimated using traffic incident data from 2012 through 2017 for the Greater Orlando region, employing a comprehensive set of exogenous variables – incident characteristics, roadway characteristics, traffic condition, weather condition, built environment and socio-demographic characteristics. …
Bias And Sensitivity Of Nonlinear Models For Seismic Response Of Ordinary Standard Bridges, Andres Rodriguez Caballero
Bias And Sensitivity Of Nonlinear Models For Seismic Response Of Ordinary Standard Bridges, Andres Rodriguez Caballero
Electronic Theses and Dissertations, 2020-
The implementation of nonlinear structural analysis under large deformation demands has enabled more realistic response prediction in comparison with the classical linear approaches. However, the sensitivity to modeling assumptions, element and material formulations, implementations, and parameter selection may lead to unreliable results. While previous works have led to a better understanding of how to best model nonlinear static responses of bridge components and systems, the introduction of dynamic loads and the corresponding material hysteresis presents an additional source of variability in the nonlinear responses. The current research involves the analysis of two ordinary standard bridges in California under seismic load …
Numerical Analysis On The Geomechanical Mechanisms And Stability Of Sinkholes In Central Florida, Moataz Soliman
Numerical Analysis On The Geomechanical Mechanisms And Stability Of Sinkholes In Central Florida, Moataz Soliman
Electronic Theses and Dissertations, 2020-
Sinkholes are a common geohazard in karst areas that can threaten human life and causes significant damage to infrastructure. Approximately 18% of the United States falls into karst area where overburden soils are underlain by soluble carbonate rocks. In Florida, sinkhole-related insurance claims between 2006 and the third quarter of 2010 amounted to $1.4 billion according to the Florida Office of Insurance Regulation. Effective methods and tools for the sinkhole detection and characterization are necessary. Numerical analysis can play an important role in determining the stability of sinkholes and understanding the failure mechanism under varied subsurface geological conditions. In this …
The Impacts Of Wave Energy Conversion On Coastal Morphodynamics In A Changing Climate, Cigdem Ozkan
The Impacts Of Wave Energy Conversion On Coastal Morphodynamics In A Changing Climate, Cigdem Ozkan
Electronic Theses and Dissertations, 2020-
Fossil fuels, i.e., petroleum, natural gas, and coal, are the primary sources of global energy. Studies on the impacts of fossil fuels on climate change have shown the immediate need to reduce greenhouse gas emissions and adopt sustainable alternatives since these emissions result in warmer atmospheric temperatures, ocean acidification, glacier melting, sea level rise, and many other ramifications. In recent years, these alarming results have prompted governments worldwide to develop adaptation strategies for climate change, leading to increased investments in renewable energy resources. Globally, solar energy, wind energy, and hydropower have been the leading sources of renewable energy. Ocean wave …
Econometric Frameworks For Multivariate Models: Application To Crash Frequency Analysis, Tanmoy Bhowmik
Econometric Frameworks For Multivariate Models: Application To Crash Frequency Analysis, Tanmoy Bhowmik
Electronic Theses and Dissertations, 2020-
Econometric crash frequency models are a major analytical tool employed for examining the critical factors influencing crash occurrence. However, there are several methodological challenges associated with existing models suggesting a continual need to develop advanced econometric framework to address these gaps. The current dissertation contributes towards addressing the methodological challenges in crash frequency analysis for analyzing multiple crash frequency variables for the same study unit by proposing advanced econometric approaches. The first part of the dissertation contributes to safety literature by conducting a comparison exercise between the two major streams of multivariate approaches - (1) simulation-based approach and (2) analytical …
A Deep Learning Approach For Real-Time Crash Risk Prediction At Urban Arterials, Pei Li
A Deep Learning Approach For Real-Time Crash Risk Prediction At Urban Arterials, Pei Li
Electronic Theses and Dissertations, 2020-
Real-time crash risk prediction aims to predict the crash probabilities within a short time period, it is expected to play a crucial role in the advanced traffic management system. However, most of the existing studies only focused on freeways rather than urban arterials because of the complicated traffic environment of the arterials. This thesis proposes a long short-term memory convolutional neural network (LSTM-CNN) to predict the real-time crash risk at arterials. The advantage of this model is it can benefit from both LSTM and CNN. Specifically, LSTM captures the long-term dependency of the data while CNN extracts the time-invariant features. …
Traffic Speed Prediction And Mobility Behavior Analysis Using On-Demand Ride-Hailing Service Data, Jiechao Zhang
Traffic Speed Prediction And Mobility Behavior Analysis Using On-Demand Ride-Hailing Service Data, Jiechao Zhang
Electronic Theses and Dissertations, 2020-
Providing accurate traffic speed prediction is essential for the success of Intelligent Transportation Systems (ITS) deployments. Accurate traffic speed prediction allows traffic managers take proper countermeasures when emergent changes happen in the transportation network. In this thesis, we present a computationally less expensive machine learning approach XGBoost to predict the future travel speed of a selected sub-network in Beijing's transportation network. We perform different experiments for predicting speed in the network from future 1 min to 20 min. We compare the XGBoost approach against other well-known machine learning and statistical models such as linear regression and decision tree, gradient boosting …
Climatic And Topologic Controls On The Complexity Of River Networks, Sevil Ranjbar Moshfeghi
Climatic And Topologic Controls On The Complexity Of River Networks, Sevil Ranjbar Moshfeghi
Electronic Theses and Dissertations, 2020-
The emergence and evolution of channel networks are controlled by the competition between the hillslopes and fluvial processes on the landscape. Investigating the geomorphic and topologic properties of these networks is important for developing predictive models describing the network dynamics under changing environment as well as for quantifying the roles of processes in creating distinct patterns of channel networks. In this dissertation, the response of landscapes to changing climatic forcing via numerical-modeling and field observations was investigated. A new framework was proposed to evaluate the complexity of catchments using two different representations of channel networks. The structural complexity was studied …
Smartphone Sensor-Based Pedestrian Activity Recognition For P2v Communication And Warning System, Dhrubo Hasan Chowdhury
Smartphone Sensor-Based Pedestrian Activity Recognition For P2v Communication And Warning System, Dhrubo Hasan Chowdhury
Electronic Theses and Dissertations, 2020-
The ubiquity of smartphones has made a remarkable influence on everyone's day to day life. Variety of useful built-in sensors provide smartphones with a convenient floor for data collection and analysis. Application development based on the user's location and movement is not a difficult task nowadays. But injuries and deaths due to smartphone-distracted movement on roadways is on the increase. This study explores the capabilities of smartphone inertial sensors for pedestrian activity recognition. Smartphone distracted movements can be predicted from the associated pedestrian's posture, thus inertial sensors can provide effective solution for this specific task. Volunteers were asked to perform …
Evaluation Of Safety And Mobility Benefits Of Connected And Automated Vehicles By Considering V2x Technologies, Md Hasibur Rahman
Evaluation Of Safety And Mobility Benefits Of Connected And Automated Vehicles By Considering V2x Technologies, Md Hasibur Rahman
Electronic Theses and Dissertations, 2020-
The recent development in communication technologies facilitates the deployment of connected and automated vehicles (CAV) which are expected to change the future transportation system. CAV technologies enable vehicles to communicate with other vehicles through vehicle-to-vehicle (V2V) communications and the infrastructure through Vehicle-to-infrastructure (V2I) communications. Since the real-world CAV data is not currently available as of today, simulation is the most commonly used platform to evaluate the future V2X system. Although several studies evaluated the effectiveness of CAVs in a small roadway network, there is a lack of studies analyzing the impact of CAVs at the network level by considering both …
An Investigation Of Life Cycle Sustainability Implications Of Emerging Heavy-Duty Truck Technologies In The Age Of Autonomy, Burak Sen
Electronic Theses and Dissertations, 2020-
Heavy-duty trucks (HDTs) play a central role in U.S. freight transportation, carrying most of the goods across the country. The projected increase in freight activity (e.g. truck-miles-traveled) raises concerns regarding the potential sustainability impacts of the U.S. freight industry, marking HDTs as an ideal domain for improving the sustainability performance of U.S. freight transportation. However, the transition to sustainable trucking is a challenging task, for which multiple sustainability objectives must be considered and addressed under a variety of emerging HDT technologies while composing a sustainable HDT fleet. To gain insights into the sustainability implications of emerging HDT technologies as well …
Improving Traffic Safety And Efficiency By Adaptive Signal Control Systems Based On Deep Reinforcement Learning, Yaobang Gong
Improving Traffic Safety And Efficiency By Adaptive Signal Control Systems Based On Deep Reinforcement Learning, Yaobang Gong
Electronic Theses and Dissertations, 2020-
As one of the most important Active Traffic Management strategies, Adaptive Traffic Signal Control (ATSC) helps improve traffic operation of signalized arterials and urban roads by adjusting the signal timing to accommodate real-time traffic conditions. Recently, with the rapid development of artificial intelligence, many researchers have employed deep reinforcement learning (DRL) algorithms to develop ATSCs. However, most of them are not practice-ready. The reasons are two-fold: first, they are not developed based on real-world traffic dynamics and most of them require the complete information of the entire traffic system. Second, their impact on traffic safety is always a concern by …
A Corridor Level Gis-Based Decision Support Model To Evaluate Truck Diversion Strategies, Samar Younes
A Corridor Level Gis-Based Decision Support Model To Evaluate Truck Diversion Strategies, Samar Younes
Electronic Theses and Dissertations, 2020-
Increased urbanization, population growth, and economic development within the U.S. have led to an increased demand for freight travel to meet the needs of individuals and businesses. Consequently, freight transportation has grown significantly over time and has expanded beyond the capacity of infrastructure, which has caused new challenges in many regions. To maintain quality of life and enhance public safety, more effort must be dedicated to investigating and planning in the area of traffic management and to assessing the impact of trucks on highway systems. Traffic diversion is an effective strategy to reduce the impact of incident-induced congestion, but alternative …
Safety Evaluation Of Innovative Intersection Designs: Diverging Diamond Interchanges And Displaced Left-Turn Intersections, Ahmed Abdelrahman
Safety Evaluation Of Innovative Intersection Designs: Diverging Diamond Interchanges And Displaced Left-Turn Intersections, Ahmed Abdelrahman
Electronic Theses and Dissertations, 2020-
Diverging diamond interchanges (DDIs) and Displaced left-turn intersections (DLTs) are designed to enhance the operational performance of conventional intersections that are congested due to heavy left-turn traffic volumes. Since drivers are not familiar with these types of intersections, there is a need to evaluate their safety performance to validate their effect, and to estimate reliable and representative Crash Modification Factors (CMFs). The safety evaluation was conducted based on three common safety assessment methods, which are before-and-after study with comparison group, Empirical Bayes before-and-after method, and cross-sectional analysis. Furthermore, since DLTs showed poor safety performance, the study also investigated the operational …
Mobility-As-A-Service: Assessing Performance And Sustainability Effects Of An Integrated Multi-Modal Simulated Transportation Network, Mohamed El-Agroudy
Mobility-As-A-Service: Assessing Performance And Sustainability Effects Of An Integrated Multi-Modal Simulated Transportation Network, Mohamed El-Agroudy
Electronic Theses and Dissertations, 2020-
Advances in information technology services have seen profound impacts on the state of transport services in the urban traffic environment. Mobility-as-a-Service (MaaS) represents the digital consolidation of users, operators, and public-private managing entities to provide totally comprehensive, integrated trip-making services. Users now enjoy extra flexibility for trip-making with new modal alternatives such as micro-mobility (e.g Lime Bikes, Spin Scooters) and rideshare (e.g. Lyft, Uber). However, current knowledge on the performance and interactive effects of these newer alternative modes is vague if not inconsistent. As such, these effects were studied through micro-simulation analysis of a multi-modal urban corridor in Orlando, Florida. …
Modeling Flow And Nitrate Transport In Karst Groundwater Basins, Yuan Gao
Modeling Flow And Nitrate Transport In Karst Groundwater Basins, Yuan Gao
Electronic Theses and Dissertations, 2020-
Understanding the groundwater flow in karst aquifers and the effect of best management practices (BMPs) on nitrate decrease in spring discharge is critical for effective management and protection of karst water resources. However, the control on the conduit network's impacts on spring discharge and nitrate concentration is not fully understood, and the cumulative effects of BMP on reducing nitrate in karst groundwater systems have not been evaluated at the basin scale. In this dissertation, a coupled Conduit Flow Process (CFPv2) and Conduit Mass Three-Dimensional (CMT3D) model was applied to evaluate the biosorption-activated media (BAM)-based BMP on nitrate removal in Silver …
Subsurface Characterization Of Internally Eroded Soils In Karst Using The Cone Penetration Test, Ryan Shamet
Subsurface Characterization Of Internally Eroded Soils In Karst Using The Cone Penetration Test, Ryan Shamet
Electronic Theses and Dissertations, 2020-
Sinkholes are a major geohazard with life-threatening consequences when not properly detected and mitigated. Geologic conditions comprised of soluble bedrock (e.g., limestone or other carbonate-based lithologies) overlain by fine-grained sandy and clayey soils, are known internationally as "karst topography" and is generally characterized by such sinkholes, caves, sinking streams, and highly variable groundwater flow conditions. Karst sinkholes, however, are complex geohazards and are difficult to precisely characterize through geotechnical considerations alone. Deterministic methods (e.g., analytical and numerical solutions) may provide for a more robust analysis of internal soil erosion (known as soil raveling) but have limitations for the practical use …
Seismic Design Optimization Of Steel Structures Using Genetic Algorithm, Tiancheng Wang
Seismic Design Optimization Of Steel Structures Using Genetic Algorithm, Tiancheng Wang
Electronic Theses and Dissertations, 2020-
Current seismic codes do not incorporate a well-established methodology for the selection of passive dampers type and their topological distribution and properties along the height of structures. Achieving the intended performance is made more complicated when structures are subject to extreme events and operate well within their inelastic range. This thesis utilizes a self-organizing genetic algorithm (soGA) with probabilistic gene-by-gene crossover and an adaptive active ground motion subset scheme to efficiently find optimal designs of low-rise steel frames subject to large number of extreme ground motions. Different types of passive dampers were considered, while the steel frames were modeled using …
Understanding The Socio-Infrastructure Systems During Disaster From Social Media Data, Kamol Chandra Roy
Understanding The Socio-Infrastructure Systems During Disaster From Social Media Data, Kamol Chandra Roy
Electronic Theses and Dissertations, 2020-
Our socio-infrastructure systems are becoming more and more vulnerable due to the increased severity and frequency of extreme events every year. Effective disaster management can minimize the damaging impacts of a disaster to a large extent. The ubiquitous use of social media platforms in GPS enabled smartphones offers a unique opportunity to observe, model, and predict human behavior during a disaster. This dissertation explores the opportunity of using social media data and different modeling techniques towards understanding and managing disaster more dynamically. In this dissertation, we focus on four objectives. First, we develop a method to infer individual evacuation behaviors …
Advanced Econometic Models For Modeling Flows: Application To Shared Economy, Bibhas Dey
Advanced Econometic Models For Modeling Flows: Application To Shared Economy, Bibhas Dey
Electronic Theses and Dissertations, 2020-
Travel and tourism industry is undergoing transformation with the flourishing of online sharing economy marketplaces such as Bike Share services, Uber/Lyft (for taxi services), Eatwith (for community restaurants), and AirBnB (for accommodation). The current research effort contributes to literature on sharing economy service flow analysis by formulating and estiamting econometric approaches for analyzing frequency variables. The sharing economy alternatives investigated include: (a) accommodation service (AirBnB), (b) bikeshare service (Citi bike, NYC) and (c) ride hailing service (UBER/LYFT/Taxi). In the first part of the dissertation, we develop a copula based negative binomial count model framework to count AirBnB listings at census …