Engineering Commons^™

Visual Entailment: A Novel Task For Fine-Grained Image Understanding, Ning Xie, Farley Lai, Derek Doran, Asim Kadav

Computer Science and Engineering Faculty Publications

Existing visual reasoning datasets such as Visual Question Answering (VQA), often suffer from biases conditioned on the question, image or answer distributions. The recently proposed CLEVR dataset addresses these limitations and requires fine-grained reasoning but the dataset is synthetic and consists of similar objects and sentence structures across the dataset. In this paper, we introduce a new inference task, Visual Entailment (VE) - consisting of image-sentence pairs whereby a premise is defined by an image, rather than a natural language sentence as in traditional Textual Entailment tasks. The goal of a trained VE model …

Influence Of Process-Induced Shrinkage And Annealing On The Thermomechanical Behavior Of Glass Fiber-Reinforced Polypropylene, M. Mulle, H. Wafai, A. Yudhanto, G. Lubineau, R. Yaldiz, W. Schijve, N. Verghese

Mechanical and Aerospace Engineering Faculty Research & Creative Works

We investigate the influence of process-induced shrinkage and subsequent annealing on the thermomechanical behavior of unidirectional laminates made of continuous glass fiber-reinforced polypropylene (GFPP). We use two different industrial lamination processes: static hot-presses (SHP), and double-belt press (DBP) that are characterized by different cooling rates and pressure levels and most importantly, by the use of a closed mold in the case of SHP manufacturing. We measure the longitudinal and transverse shrinkage during the manufacturing and annealing processes using embedded fiber Bragg gratings (FBGs). The SHP molding reveals much lower induced shrinkage in GFPP as compared to the DBP process, although …

Numerical Simulations Of Flow Past A Triangular Airfoil And In A Sweeping Jet Actuator Using Different Turbulence Models, Han Yang

McKelvey School of Engineering Graduate Student Theses & Dissertations

The goal of this research is to perform 2D turbulent flow simulations to predict the flow past a triangular airfoil used for a Mars air vehicle and in a sweeping jet actuator used for active flow control. Simulations are performed using the commercial CFD software ANSYS Fluent.

The thesis consists of two parts. The first part of the thesis deals with the CFD simulations of a triangular airfoil in low-Reynolds-number compressible flow. This airfoil is one of the candidates for propeller blades on a possible future Martian air vehicle design. The aerodynamics and flow physics of the triangular airfoil is …

Sea Level Rise And Land Subsidence In Coastal Louisiana: Forecasting, Mapping And Identification Of At-Risk Transportation Infrastructure, Sanjay Tewari, Francis Manning, Wesley Palmer

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

The coast of Louisiana is under threat because of sea level rise and land subsidence. Sea water is encroaching deeper inland and as a result Louisiana is losing land at an alarming rate. The combined effect of sea level rise and land subsidence is variable spatially. This paper focuses on this combined effect in identifying the transportation infrastructure that is at risk of getting affected by the seawater inundation of the land.

This paper attempts to account for land elevation data monitored continuously at various locations along the coast of Louisiana and combining it with local sea level rise to …

Finding Truth In Fake News: Reverse Plagiarism And Other Models Of Classification, Matthew Przybyla, David Tran, Amber Whelpley, Daniel W. Engels

SMU Data Science Review

As the digital age creates new ways of spreading news, fake stories are propagated to widen audiences. A majority of people obtain both fake and truthful news without knowing which is which. There is not currently a reliable and efficient method to identify “fake news”. Several ways of detecting fake news have been produced, but the various algorithms have low accuracy of detection and the definition of what makes a news item ‘fake’ remains unclear. In this paper, we propose a new method of detecting on of fake news through comparison to other news items on the same topic, as …

Framework For Evaluation Of Flash Flood Models In Wildfire-Prone Areas, Brian Cunningham, David Benepe, Bryan Cikatz, Evangelos Giakoumakis

SMU Data Science Review

Abstract. In this paper, we present an innovative framework for evaluating the increased risk of flash flooding in areas that have been subjected to wildfires. Wildfires cause large-scale damage to an area’s soil and vegetation thus increasing both the likelihood and severity of flash flooding. Utilizing remote sensing to analyze aerial imagery of areas that have been affected by wildfires, we can investigate how much a landscape has changed and how that may adversely affect downstream areas in the event of a flash flooding event. There are currently no established frameworks from which downstream local officials can quickly assess the …

Pedestrian Safety -- Fundamental To A Walkable City, Joshua Herrera, Patrick Mcdevitt, Preeti Swaminathan, Raghuram Srinivas

SMU Data Science Review

In this paper, we present a method to identify urban areas with a higher likelihood of pedestrian safety related events. Pedestrian safety related events are pedestrian-vehicle interactions that result in fatalities, injuries, accidents without injury, or near--misses between pedestrians and vehicles. To develop a solution to this problem of identifying likely event locations, we assemble data, primarily from the City of Cincinnati and Hamilton County, that include safety reports from a five year period, geographic information for these events, citizen survey of pedestrian reported concerns, non-emergency requests for service for any cause in the city, property values and public transportation …

Comparative Study Of Sentiment Analysis With Product Reviews Using Machine Learning And Lexicon-Based Approaches, Heidi Nguyen, Aravind Veluchamy, Mamadou Diop, Rashed Iqbal

SMU Data Science Review

In this paper, we present a comparative study of text sentiment classification models using term frequency inverse document frequency vectorization in both supervised machine learning and lexicon-based techniques. There have been multiple promising machine learning and lexicon-based techniques, but the relative goodness of each approach on specific types of problems is not well understood. In order to offer researchers comprehensive insights, we compare a total of six algorithms to each other. The three machine learning algorithms are: Logistic Regression (LR), Support Vector Machine (SVM), and Gradient Boosting. The three lexicon-based algorithms are: Valence Aware Dictionary and Sentiment Reasoner (VADER), Pattern, …

Improving Vix Futures Forecasts Using Machine Learning Methods, James Hosker, Slobodan Djurdjevic, Hieu Nguyen, Robert Slater

SMU Data Science Review

The problem of forecasting market volatility is a difficult task for most fund managers. Volatility forecasts are used for risk management, alpha (risk) trading, and the reduction of trading friction. Improving the forecasts of future market volatility assists fund managers in adding or reducing risk in their portfolios as well as in increasing hedges to protect their portfolios in anticipation of a market sell-off event. Our analysis compares three existing financial models that forecast future market volatility using the Chicago Board Options Exchange Volatility Index (VIX) to six machine/deep learning supervised regression methods. This analysis determines which models provide best …

Recent Advances In Piezoelectric Wafer Active Sensors For Structural Health Monitoring Applications, Hanfei Mei, Mohammad Faisal Haider, Roshan Prakash Joseph, Asaad Migot, Victor Giurgiutiu

Faculty Publications

In this paper, some recent piezoelectric wafer active sensors (PWAS) progress achieved in our laboratory for active materials and smart structures (LAMSS) at the University of South Carolina: http: //www.me.sc.edu/research/lamss/ group is presented. First, the characterization of the PWAS materials shows that no significant change in the microstructure after exposure to high temperature and nuclear radiation, and the PWAS transducer can be used in harsh environments for structural health monitoring (SHM) applications. Next, PWAS active sensing of various damage types in aluminum and composite structures are explored. PWAS transducers can successfully detect the simulated crack and corrosion damage in aluminum …

Application Of Improved Feature Selection Algorithm In Svm Based Market Trend Prediction Model, Qi Li

Dissertations and Theses

In this study, a Prediction Accuracy Based Hill Climbing Feature Selection Algorithm (AHCFS) is created and compared with an Error Rate Based Sequential Feature Selection Algorithm (ERFS) which is an existing Matlab algorithm. The goal of the study is to create a new piece of an algorithm that has potential to outperform the existing Matlab sequential feature selection algorithm in predicting the movement of S&P 500 (^GSPC) prices under certain circumstances. The two algorithms are tested based on historical data of ^GSPC, and Support Vector Machine (SVM) is employed by both as the classifier. A prediction without feature selection algorithm …

Project Insight: A Granular Approach To Enterprise Cybersecurity, Sunna Quazi, Adam Baca, Sam Darsche

SMU Data Science Review

In this paper, we disambiguate risky activity corporate users are propagating with their software in real time by creating an enterprise security visualization solution for system administrators. The current problem in this domain is the lag in cyber intelligence that inhibits preventative security measure execution. This is partially due to the overemphasis of network activity, which is a nonfinite dataset and is difficult to comprehensively ingest with analytics. We address these concerns by elaborating on the beta of a software called "Insight" created by Felix Security. The overall solution leverages endpoint data along with preexisting whitelist/blacklist designations to unambiguously communicate …

Improving Gas Well Economics With Intelligent Plunger Lift Optimization Techniques, Atsu Atakpa, Emmanuel Farrugia, Ryan Tyree, Daniel W. Engels, Charles Sparks

SMU Data Science Review

In this paper, we present an approach to reducing bottom hole plunger dwell time for artificial lift systems. Lift systems are used in a process to remove contaminants from a natural gas well. A plunger is a mechanical device used to deliquefy natural gas wells by removing contaminants in the form of water, oil, wax, and sand from the wellbore. These contaminants decrease bottom-hole pressure which in turn hampers gas production by forming a physical barrier within the well tubing. As the plunger descends through the well it emits sounds which are recorded at the surface by an echo-meter that …

The Santa Clara, 2019-01-17, Santa Clara University

The Santa Clara

No abstract provided.

Absorber And Window Study – Cdsexte1-X/Cdte Thin Film Solar Cells, Chih-An Hsu

USF Tampa Graduate Theses and Dissertations

CdTe an II-VI semiconductor has been a leading thin film photovoltaic material due to its near ideal bandgap and high absorption coefficient [1]. The typical thin film CdTe solar cells have been of the superstrate configuration with CdS (Eg-2.42eV) as the n-type heterojunction partner. Due to the relatively narrow bandgap of CdS, a wider bandgap n-type window layer has recently emerged as a promising substitute: alloys of MgyZn1-yO have been successfully used as the emitter or window layer. The benefits in the usage of MgyZn1-yO (MZO) are its tunable bandgap and wide optical spectrum on optoelectronic devices. Due to an …

Coatings On Mammalian Cells: Interfacing Cells With Their Environment, Kara A. Davis, Pei-Jung Wu, Calvin F. Cahall, Cong Li, Anuhya Gottipati, Brad J. Berron

Chemical and Materials Engineering Faculty Publications

The research community is intent on harnessing increasingly complex biological building blocks. At present, cells represent a highly functional component for integration into higher order systems. In this review, we discuss the current application space for cellular coating technologies and emphasize the relationship between the target application and coating design. We also discuss how the cell and the coating interact in common analytical techniques, and where caution must be exercised in the interpretation of results. Finally, we look ahead at emerging application areas that are ideal for innovation in cellular coatings. In all, cellular coatings leverage the machinery unique to …

Direct-To-Patient Survey For Diagnosis Of Benign Paroxysmal Positional Vertigo, Heidi Richburg, Richard J. Povinelli, David Friedland

Electrical and Computer Engineering Faculty Research and Publications

Given the high incidence of dizziness and its frequent misdiagnosis, we aim to create a clinical support system to classify the presence or absence of benign paroxysmal positional vertigo with high accuracy and specificity. This paper describes a three-phase study currently underway for classification of benign paroxysmal positional vertigo, which includes diagnosis by a specialist in a clinical setting. Patient background information is collected by a survey on an Android tablet and machine learning techniques are applied for classification. Decision trees and wrappers are employed for their ability to provide information about the question set. One goal of the study …

Design Of Vibration Class Laboratory Assignments: Focusing On Broader Application, Ethan Wayne Cating

Graduate Theses - Mechanical Engineering

Courses in vibration taught at Rose-Hulman Institute of Technology are designed to blend classroom discussion of the science of vibration with practical, hands-on applications. The laboratory portion of the undergraduate course in vibration focuses on two areas: (1) system identification for single- and multi-degree-of-freedom systems in the frequency domain through sine-sweep shake testing; and (2) identifying natural frequencies and mode shapes for continuous systems via experimental modal analysis using frequency response data collected through a roving hammer test. Modal analysis is performed using an in-house MATLAB-based program known as Easy Modal Analysis Program (EMAP). The goals of this thesis are …

Open-Source Automated Chemical Vapor Deposition System For The Production Of Two-Dimensional Nanomaterials, Lizandra Williams-Godwin, Dale Brown, Richard Livingston, Tyler Webb, Lynn Karriem, Elton Graugnard, David Estrada

Materials Science and Engineering Faculty Publications and Presentations

The study of two- dimensional (2D) materials is a rapidly growing area within nanomaterials research. However, the high equipment costs, which include the processing systems necessary for creating these materials, can be a barrier to entry for some researchers interested in studying these novel materials. Such process systems include those used for chemical vapor deposition, a preferred method for making these materials. To address this challenge, this article presents the first open-source design for an automated chemical vapor deposition system that can be built for less than a third of the cost for a comparable commercial system. The materials and …

1938 - Quarterly Chapter Of State Mineralogist's Report Xxxiv, California Journal Of Mines And Geology

Miscellaneous Documents and Reports

Report of the development of mining resources and mining activities in each of the four field districts (Redding, Auburn, San Francisco and Los Angeles) were prepared by the District Engineer.

1920 - Irrigation Of Twelve Million Acres In The Valley Of California; Robert Bradford Marshall

Miscellaneous Documents and Reports

By 1920, California's potential wealth in land reached into billions of dollars; 12,000,000 acres of available agricultural lands remained practically untouched. Marshall proposed a large plan that would make the Valley of California the world's greatest garden. The engineering plans for such a project must be comprehensive, for their execution must not only assure the complete reclamation of 12,000,000 acres of valley lands but must also effectively and forever control the river floods and insure safe and continuous river navigation throughout the year. The hydro-electric current generated along most of the streams would furnish all the power necessary for construction …

Satellite-Based Assessment Of The August 2018 Flood In Parts Of Kerala, India, C. L. Vishnu, K. S. Sajinkumar, Thomas Oommen, R. A. Coffman, K. P. Thrivikramji, V. R. Rani, S. Keerthy

Michigan Tech Publications, Part 1

From 1 June to 29 August 2018, Kerala, a state in southwestern India, recorded 36% excess rainfall than normal levels, leading to widespread floods and landslides events and resulting in 445 deaths. In this study, satellite-based data were used to map the flood inundation in the districts of Thrissur, Ernakulam, Alappuzha, Idukki and Kottayam. Specifically, flood delineation was enabled with Sentinel-1A radar data of 21 August 2018 and was compared with an average pre-flood, water-cover map based on Modified Normalized Difference Water Index (MNDWI) that was developed using a January and February 2018 Sentinel-2A dataset. A 90% increase in water …

From Drought To Food-Energy-Water-Security Nexus: An Assessment Of Food Insecurity In The Middle East, Maysoun Ayad Hameed

Dissertations and Theses

Drought is an extreme climate phenomenon that happens slowly and periodically threatens the environmental and socio-economic sectors. Developing countries have experienced crucial conditions in meeting the needs for food, energy, and water security. Natural disasters contribute as risky sources of food insecurity and vulnerability in the Middle East. This dissertation presents a country-level review and quantitative assessment of the current issues associated with the Food-Energy-Water-Security (FEWS) Nexus in the Middle East. In this study, sixteen countries in the Middle East are chosen, namely, Arabian Peninsula, Iran, Syria, Lebanon, Israel, Palestine, Egypt, and Turkey. The most recent datasets are used to …

1921 - Petroleum Resources Of California, Bulletin 89

Miscellaneous Documents and Reports

By 1921, the increasing demand for petroleum and its products, and the inability of production to keep pace with requirements, for several years, resulted in widespread prospecting throughout the world for possible new oil fields. In California, "wild-cat" wells were being drilled in many localities, some of them in places where even a cursory inspection of the geology would tell the futility of looking for oil. This report aimed to furnish information as to the unfavorable as well as the favorable areas of development of additional petroleum resources in California. The purpose of the report was to briefly take stock …

Application Of Artificial Neural Networks To Assess Student Happiness, Gokhan Egilmez, Nadiye O. Erdil, Omid Mohammadi Arani, Mana Vahid

Mechanical and Industrial Engineering Faculty Publications

The purpose of this study is to develop an analytical assessment approach to identify the main factors that affect graduate students' happiness level. The two methods, multiple linear regression (MLR) and artificial neural networks (ANN), were employed for analytical modelling. A sample of 118 students at a small non-profit private university constituted the survey pool. Various factors including education, school facilities, health, social activities, and family were taken into consideration as a result of literature review in happiness assessment. A total of 32 inputs and one output variables were identified during survey design phase. The following survey conduction, data collection, …

1923 - Flow In California Streams, Bulletin No. 5, Appendix A, Report To The Legislature

Miscellaneous Documents and Reports

The legislature of 1921 appropriated $200,000 for an investigation of California's water resources by the State Department of Public Works, Division of Engineering and Irrigation. Accordingly, an engineering investigation was completed and a report on California's water resources transmitted to the legislature on January 1, 1923. The report addresses the geology, precipitation and run-off in California.

The Effect Of Cryogenic Thermal Cycling On Aging, Rejuvenation, And Mechanical Properties Of Metallic Glasses, Nikolai V. Priezjev

Mechanical and Materials Engineering Faculty Publications

The structural relaxation, potential energy states, and mechanical properties of a model glass subjected to thermal cycling are investigated using molecular dynamics simulations. We study a non-additive binary mixture which is annealed with different cooling rates from the liquid phase to a low temperature well below the glass transition. The thermal treatment is applied by repeatedly heating and cooling the system at constant pressure, thus temporarily inducing internal stresses upon thermal expansion. We find that poorly annealed glasses are relocated to progressively lower levels of potential energy over consecutive cycles, whereas well annealed glasses can be rejuvenated at sufficiently large …

Measurement And Analysis Of The Extreme Physical Shock Environment Experienced By Crane-Mounted Radiation Detection Systems, Matthew Boyd, Jennifer Erchinger, Craig M. Marianno, Gene Kallenbach

International Journal of Nuclear Security

At ports of entry, radiation detectors could be mounted on container gantry crane spreaders to monitor cargo containers entering and leaving the country. These detectors would have to withstand the extreme physical conditions experienced by these spreaders during normal operations. Physical shock data from the gable ends of a spreader were recorded during the loading and unloading of a cargo ship by two hard mounted PCB Piezotronics model 340A50 accelerometers and two Lansmont SAVER 9X30 units (with padding). The majority of large shocks were observed in the vertical direction. The Lansmont units recorded mean shocks of 22.215 ± 1.174 and …

A Framework For Evaluating Model-Driven Self-Adaptive Software Systems, Basel Magableh

Articles

In the last few years, Model Driven Development (MDD), Component-based Software Development (CBSD), and context-oriented software have become interesting alternatives for the design and construction of self-adaptive software systems. In general, the ultimate goal of these technologies is to be able to reduce development costs and effort, while improving the modularity, flexibility, adaptability, and reliability of software systems. An analysis of these technologies shows them all to include the principle of the separation of concerns, and their further integration is a key factor to obtaining high-quality and self-adaptable software systems. Each technology identifies different concerns and deals with them separately …

A Deep Recurrent Q Network Towards Self-Adapting Distributed Microservices Architecture (In Press), Basel Magableh

Articles

One desired aspect of microservices architecture is the ability to self-adapt its own architecture and behaviour in response to changes in the operational environment. To achieve the desired high levels of self-adaptability, this research implements the distributed microservices architectures model, as informed by the MAPE-K model. The proposed architecture employs a multi adaptation agents supported by a centralised controller, that can observe the environment and execute a suitable adaptation action. The adaptation planning is managed by a deep recurrent Q-network (DRQN). It is argued that such integration between DRQN and MDP agents in a MAPE-K model offers distributed microservice architecture …