Computer Sciences Commons^™

Towards Improving Accuracy And Interpretability Of Deep Learning Based On Satellite Image Classification, Yamile Patino Vargas

Dissertations and Theses

ABSTRACT

The study of satellite images provides a way to monitor changes in the surface of the Earth and the atmosphere. Convolutional Neural Networks (CNN) have shown accurate results in solving practical problems in multiple fields. Some of the more recognized fields using CNNs are satellite imagery processing, medicine, communication, transportation, and computer vision. Despite the success of CNNs, there remains a need to explain the network predictions further and understand what the network is determining as valuable information.

There are several frameworks and methodologies developed to explain how CNNs predict outputs and what their internal representations are [1, 4, …

Collaborative Artificial Intelligence Algorithms For Medical Imaging Applications, Naji Khosravan

Electronic Theses and Dissertations

In this dissertation, we propose novel machine learning algorithms for high-risk medical imaging applications. Specifically, we tackle current challenges in radiology screening process and introduce cutting-edge methods for image-based diagnosis, detection and segmentation. We incorporate expert knowledge through eye-tracking, making the whole process human-centered. This dissertation contributes to machine learning, computer vision, and medical imaging research by: 1) introducing a mathematical formulation of radiologists level of attention, and sparsifying their gaze data for a better extraction and comparison of search patterns. 2) proposing novel, local and global, image analysis algorithms. Imaging based diagnosis and pattern analysis are "high-risk" Artificial Intelligence …

Computer Vision-Based Traffic Sign Detection And Extraction: A Hybrid Approach Using Gis And Machine Learning, Zihao Wu

College of Graduate Studies: Theses & Dissertations

Traffic sign detection and positioning have drawn considerable attention because of the recent development of autonomous driving and intelligent transportation systems. In order to detect and pinpoint traffic signs accurately, this research proposes two methods. In the first method, geo-tagged Google Street View images and road networks were utilized to locate traffic signs. In the second method, both traffic signs categories and locations were identified and extracted from the location-based GoPro video. TensorFlow is the machine learning framework used to implement these two methods. To that end, 363 stop signs were detected and mapped accurately using the first method (Google …

Ifocus: A Framework For Non-Intrusive Assessment Of Student Attention Level In Classrooms, Narayanan Veliyath

College of Graduate Studies: Theses & Dissertations

The process of learning is not merely determined by what the instructor teaches, but also by how the student receives that information. An attentive student will naturally be more open to obtaining knowledge than a bored or frustrated student. In recent years, tools such as skin temperature measurements and body posture calculations have been developed for the purpose of determining a student's affect, or emotional state of mind. However, measuring eye-gaze data is particularly noteworthy in that it can collect measurements non-intrusively, while also being relatively simple to set up and use. This paper details how data obtained from such …

Women Leaders In Information Technology: A Phenomenological Study Of Their Career Paths, Michelle Newsome

Walden Dissertations and Doctoral Studies

In the United States, women remain underrepresented in senior level positions in the information technology (IT) field. Despite this challenge, a few women have successfully ascended into senior leadership in IT. Using the social cognitive theory as the conceptual framework, the purpose of this qualitative transcendental phenomenological study was to understand the lived experiences of senior women leaders in the IT field. The research question explored the lived personal and professional experiences of senior women leaders in IT to gain an understanding of their career advancement into senior leadership positions. Through the use of the modified Van Kaam method of …

Cybersecurity Strategies For Universities With Bring Your Own Device Programs, Hai Vu Nguyen

Walden Dissertations and Doctoral Studies

The bring your own device (BYOD) phenomenon has proliferated, making its way into different business and educational sectors and enabling multiple vectors of attack and vulnerability to protected data. The purpose of this multiple-case study was to explore the strategies information technology (IT) security professionals working in a university setting use to secure an environment to support BYOD in a university system. The study population was comprised of IT security professionals from the University of California campuses currently managing a network environment for at least 2 years where BYOD has been implemented. Protection motivation theory was the study's conceptual framework. …

Strategies To Recruit Skilled Workers In Manufacturing, Ina Renee Rawlinson

Walden Dissertations and Doctoral Studies

Manufacturing hiring managers in the United States who fail to implement adequate recruitment strategies for skilled production workers experience reduced profits and sustainability challenges. The purpose of this multiple case study was to explore the strategies that successful manufacturing hiring managers in North Carolina used to recruit skilled production workers to sustain business profitability. Inductive analysis was guided by the human capital theory, and trustworthiness of interpretations was strengthened by member checking. The population for the study consisted of 4 business leaders who demonstrated the use of effective recruitment strategies to sustain profitability in manufacturing businesses in southeastern North Carolina. …

Strategizing Effective Succession Planning For Information Technology Executives, Michael Barr

Walden Dissertations and Doctoral Studies

Organizations across the United States lose hundreds of millions of dollars each year due to the lack of effective succession planning for information technology executives. The purpose of this single case study was to explore strategies for the development and implementation of effective succession plans for future information technology executives. Bass and Avolio's transformational leadership theory was the conceptual framework for this study. The 3 participants were selected based upon their roles as executives in technology-related positions and their experiences with succession planning. Data were collected using semistructured interviews with these executives from a company headquartered in Kansas City, Missouri. …

Information Technology Outsourcing Strategies To Ensure Customer Satisfaction, Clyde Rajack

Walden Dissertations and Doctoral Studies

Many information technology (IT) outsourcing initiatives fail, resulting in a high impact on business results and customer satisfaction. Without effective strategies, business leaders who outsource their IT services are at considerable risk of failure and stakeholder dissatisfaction. The purpose of this multiple case study was to explore outsourcing strategies that IT managers in Southern Ontario, Canada, used to ensure customer satisfaction. Participants included 9 executives with experience in complex IT outsourcing initiatives. Stakeholder theory and transaction cost economics theory were the conceptual frameworks for the study. Data were gathered using semistructured interviews to query 8 topical areas including IT outsourcing …

Exploration Of K-5 Teacher Decision-Making Related To Student Use Of Technology, Eric Noel Rodriguez

Walden Dissertations and Doctoral Studies

Student technology literacy is critical for success in today’s world; however, little is understood about how teachers make the decision for students to use technology for learning due to limited empirical research on the topic of teacher decision-making regarding student use of information communication technologies (ICT). The purpose of this generic qualitative study was to explore the decision-making process of kindergarten to Grade 5 (K-5) teachers regarding implementation of ICT for student use at varying levels. The framework for this study comprised the substitution augmentation modification redefinition model and the technology acceptance model. The research questions focused on how teachers …

Cloud Computing Adoption In Afghanistan: A Quantitative Study Based On The Technology Acceptance Model, George T. Nassif

Walden Dissertations and Doctoral Studies

Cloud computing emerged as an alternative to traditional in-house data centers that businesses can leverage to increase the operation agility and employees' productivity. IT solution architects are tasked with presenting to IT managers some analysis reflecting cloud computing adoption critical barriers and challenges. This quantitative correlational study established an enhanced technology acceptance model (TAM) with four external variables: perceived security (PeS), perceived privacy (PeP), perceived connectedness (PeN), and perceived complexity (PeC) as antecedents of perceived usefulness (PU) and perceived ease of use (PEoU) in a cloud computing context. Data collected from 125 participants, who responded to the invitation through an …

Mirdriver: A Tool To Infer Copy Number Derived Mirna-Gene Networks In Cancer, Banabithi Bose, Serdar Bozdag

Computer Science Faculty Research and Publications

Copy number aberration events such as amplifications and deletions in chromosomal regions are prevalent in cancer patients. Frequently aberrated copy number regions include regulators such as microRNAs (miRNAs), which regulate downstream target genes that involve in the important biological processes in tumorigenesis and proliferation. Many previous studies explored the miRNA-gene interaction networks but copy number-derived miRNA regulations are limited. Identifying copy number-derived miRNA-target gene regulatory interactions in cancer could shed some light on biological mechanisms in tumor initiation and progression. In the present study, we developed a computational pipeline, called miRDriver which is based on the hypothesis that copy number …

Analyzing Happiness: Investigation On Happy Moments Using A Bag-Of-Words Approach And Related Ethical Discussions, Riddhiman Adib, Eyad Aldawood, Nathan Lang, Nina Lasswell, Shion Guha

Computer Science Faculty Research and Publications

In this research paper, we analyzed what moments and activities make people happy, based on a collection of happy moments. We are focusing on specific happy moments from a collection of text responses that people have shared through the crowd-sourcing platform: Amazon Mechanical Turk (MTurk). Using crowd-sourcing to collect our data allows us to advance our understanding of the cause of happiness, by focusing on words and real human experiences. Workers of MTurk were asked to reflect on what makes them happy in a given period and share three specific moments in complete sentences. Through text-based analysis, we will look …

Privacy, Michael Zimmer

Computer Science Faculty Research and Publications

Privacy is a difficult concept to singularly define. Its meaning, value, and level of protection vary across cultures and have evolved continuously over time. Yet, from an information policy and ethics perspective, privacy has had a central role to play throughout history, sparking considerable debate, and often rising in importance alongside technological development.

Visualization Of Large Time-Dependent Multidimensional Datasets Using Information Dashboards, Ankita Upadhyay

Graduate Research Theses & Dissertations

Visual summarization is the act of displaying the most important information in a single

view or on a single screen. There are many existing powerful and useful information visualization tools and techniques to visualize large datasets, but the major challenge in using

these visualization tools efficiently are assessing what is needed to create awareness,

where awareness is dependent on the situation and context of the user and surrounding

events.

For example, when a user is driving (context) and approaching an intersection (situation)

the traffic light being red creates an awareness that the driver needs to stop, or when a fire …

Simulating And Modelling Opinion Dynamics, Jennifer Heermance

Graduate Research Theses & Dissertations

The foundation of social media is conversation. Social media allows people to share ideas and opinions, as well as discuss those opinions. A point of intrigue for many social scientists is how those opinions change through interaction with others. What influences someone’s opinion? When is a person willing to adapt their opinion, and when does it remain the same? Is it possible to measure these opinion dynamics? Our overall goal is to develop a more comprehensive model for opinion dynamics. The first step of this process is to simulate data that can then be analyzed and used to develop a …

Using Machine Learning Models To Discover Promising Research, Akhil Pandey Akella

Graduate Research Theses & Dissertations

Endeavors to identify valuable research involve the factors of discovery, comprehensibility, and reproducibility. The purpose of this study is to assist scholars in finding research that is both promising and of high quality. I explain how we can approach the problem of reproducibility in relation to scholarly articles and propose gauging the public understanding of science as a way to determine the comprehensibility of given research articles. Additionally, I explain how the concept of long-term social media impact supports the discovery of scholarly articles likely to be impactful even with the passage of time. I build and describe machine-learning models …

Drawing Parallels Between Heuristics And Dynamic Programming, Margarita M. Dominguez

Honors College Theses

No abstract provided.

Analysis Of Lte Network Rf Performance In A Dense Urban Environment, Nicholas Krawczeniuk

Honors College Theses

No abstract provided.

Aligning Best Practices In Student Success And Career Preparedness: An Exploratory Study To Establish Pathways To Stem Careers For Undergraduate Minority Students, Kimberly D. Kendricks, Anthony A. Arment, K. V. Nedunuri, Cadance A. Lowell

Journal of Research in Technical Careers

Undergraduate minority retention and graduation rates in STEM disciplines is a nationally recognized challenge for workforce growth and diversification. The Benjamin Banneker Scholars Program (BBSP) was a five-year undergraduate study developed to increase minority student retention and graduation rates at an HBCU. The program structure utilized a family model as a vehicle to orient students to the demands of college. Program activities integrated best K-12 practices and workforce skillsets to increase academic preparedness and career readiness. Findings revealed that a familial atmosphere improved academic performance, increased undergraduate research, and generated positive perceptions of faculty mentoring. Retention rates among BBSP participants …

Using Reinforcement Learning In A Simulated Intelligent Tutoring System, Manohar Sai Jasti

Graduate Research Theses & Dissertations

I used reinforcement learning to investigate which categories of hints are most efficient in an intelligent tutoring system for human anatomy. Efficiency is defined as minimizing the time it takes the student to learn the material. When a student gives a wrong answer, the tutor can give them a text hint, a diagrammatic hint, or a video clip. Each type of hint takes a different amount of time to deliver and takes the student a different amount of time to understand.

I built a simulator for the intelligent tutoring system to collect data from simulated students. I implemented reinforcement learning, …

Volume 11, Jacob Carney, Ryan White, Joseph Hyman, Jenny Raven, Megan Garrett, Ibrahim Kante, Summer Meinhard, Lauren Johnson, William "Editha" Dean Howells, Laura Gottschalk, Christopher Siefke, Pink Powell, Natasha Woodmancy, Katharine Colley, Abbey Mays, Charlotte Potts

Incite: The Journal of Undergraduate Scholarship

Table of Contents:

Introduction, Dr. Roger A. Byrne, Dean

From the Editor, Dr. Larissa "Kat" Tracy

From the Designers, Rachel English, Rachel Hanson

Synthesis of 3,5-substituted Parabens and their Antimicrobial Properties, Jacob Coarney, Ryan White

Chernobyl: Putting "Perestroika" and "Glasnot" to the Test, Joseph Hyman

Art by Jenny Raven

Watering Down Accessibility: The Issue with Public Access to Alaska's Federal Waterways, Meagan Garrett

Why Has the Democratic Republic of the Congo outsourced its Responsibility to Educate its Citizens? Ibrahim Kante

Art by Summer Meinhard

A Computational Study of Single Molecule Diodes, Lauren Johnson

Satire of …

Quantifying Human Biological Age: A Machine Learning Approach, Syed Ashiqur Rahman

Graduate Theses, Dissertations, and Problem Reports (ETD)

Quantifying human biological age is an important and difficult challenge. Different biomarkers and numerous approaches have been studied for biological age prediction, each with its advantages and limitations. In this work, we first introduce a new anthropometric measure (called Surface-based Body Shape Index, SBSI) that accounts for both body shape and body size, and evaluate its performance as a predictor of all-cause mortality. We analyzed data from the National Health and Human Nutrition Examination Survey (NHANES). Based on the analysis, we introduce a new body shape index constructed from four important anthropometric determinants of body shape and body size: body …

Browsing Via Sonification, Taylor C. Cutlip

Graduate Theses, Dissertations, and Problem Reports (ETD)

Based on unexpected results in her previous research, Dr. Frances Van Scoy became inspired to develop a tool that allows the user to navigate spaces using auditory instead of visual cues to detect objects or anomalies in a given space in an effort to overcome the encountered obstacles. This problem report details the work of one of her grad students in exploring different open source software for developing the tool as well as research into gestures and other considerations when furthering this research into the third dimension at a future date.

Autonomous Systems With Reuse: A Survey On The State-Of-The-Practice, Denny Laverne Hood Iii

Graduate Theses, Dissertations, and Problem Reports (ETD)

This problem report presents the results of an anonymous online survey that was used to collect information about software systems that use model-based software engineering, contain autonomy and where software reuse plays an important role. Recent advancements in computation ability and the emergence of decision-making algorithms have increased interest in and use of autonomy in applications areas such as aeronautics, automotive, military, and space industries. In these application domains, autonomy is used to reduce costs, reduce reaction times, and improve performance. Due to the emerging nature of autonomy, very little research has been done regarding the level of autonomy of …

A Dual State Hierarchical Ensemble Kalman Filter Algorithm, William J. Cook, Jesse Johnson, Marko Maneta, Doug Brinkerhoff

Graduate Student Theses, Dissertations, & Professional Papers

Dynamic models that simulate processes across large geographic locations, such as hydrologic models, are often informed by empirical parameters that are distributed across a geographical area and segmented by geological features such as watersheds. These parameters may be referred to as spatially distributed parameters. Spatially distributed parameters are frequently spatially correlated and any techniques utilized in their calibration ideally incorporate existing spatial hierarchical relationships into their structure. In this paper, a parameter estimation method based on the Dual State Ensemble Kalman Filter called the Dual State Hierarchical Ensemble Kalman Filter (DSHEnKF) is presented. This modified filter is innovative in that …

Improve Operating Room Utilization Through Distributed Scheduling Workflow And Automation, Miteshkumar Mahendrabhai Vasoya

Browse all Theses and Dissertations

Operating room (OR) plays a crucial role in health care, contributing more than 50% of the hospital’s revenue and incurring over 35% of the hospital’s expense, ultimately determining the hospital’s profitability. Moreover, because the OR is a primary source of admissions, it is virtually impossible to streamline hospital‐wide workflow without first streamlining patient flow through the OR. Unfortunately, current OR scheduling practices often limit the utilization of OR, one of the most expensive resources in the health care industry, to around 60%. On the other hand, many patients have to wait an excessively long time before their surgeries can be …

Survey Of Biosynthetic Gene Clusters From Sequenced Myxobacteria And Analysis Of Potential Metabolic Diversity, Katherine C. Gregory

Honors Theses

The importance of natural product discovery to society is undeniable as natural products have seemingly infinite applications, particularly in regard to pharmacological use as antibacterial, antifungal, antiparasitic, anticancer and immunosuppressive agents. The search for new therapeutics and other new chemical commodities thus grows simultaneously with antibiotic resistance and commercial pressure on pharmaceutical research. However, the increasingly common phenomenon of natural product rediscovery continues to inhibit advancement in this field. We contend that the likelihood of rediscovery can be predicted by taxonomic distance between the bacteria in question and previously studied bacteria. That is, our data supports a correlation between chemical …

Improved N-Dimensional Data Visualization From Hyper-Radial Values, Todd J. Paciencia, Trevor J. Bihl, Kenneth W. Bauer

Faculty Publications

Higher-dimensional data, which is becoming common in many disciplines due to big data problems, are inherently difficult to visualize in a meaningful way. While many visualization methods exist, they are often difficult to interpret, involve multiple plots and overlaid points, or require simultaneous interpretations. This research adapts and extends hyper-radial visualization, a technique used to visualize Pareto fronts in multi-objective optimizations, to become an n-dimensional visualization tool. Hyper-radial visualization is seen to offer many advantages by presenting a low-dimensionality representation of data through easily understood calculations. First, hyper-radial visualization is extended for use with general multivariate data. Second, a method …

Security Bug Report Classification Using Feature Selection, Clustering, And Deep Learning, Tanner D. Gantzer

Graduate Theses, Dissertations, and Problem Reports (ETD)

As the numbers of software vulnerabilities and cybersecurity threats increase, it is becoming more difficult and time consuming to classify bug reports manually. This thesis is focused on exploring techniques that have potential to improve the performance of automated classification of software bug reports as security or non-security related. Using supervised learning, feature selection was used to engineer new feature vectors to be used in machine learning. Feature selection changes the vocabulary used by selecting words with the greatest impact on classification. Feature selection was able to increase the F-Score across the datasets by increasing the precision. We also explored …