Computer Sciences Commons^™

Simplification Of Robotics Through Autonomous Navigation, Grant Turner

Mahurin Honors College Capstone Experience/Thesis Projects

With self-driving vehicles, college campus food delivery, or even automated home vacuuming systems, robotics is undoubtedly becoming more prevalent in everyday society and it can be expected to continue with time. While many people are owners, users, or even just spectators of theses robotic products or services, there seems to be a negative perception of robotics that poses an intimidation factor regarding the attempt to understand the ideas driving technology. This perception tends to view robotics as machines that require rich education to understand the complexity and interworkings of, thus attempts understand the field are neglected.

To combat this line …

Why Gradient Descent -- Not The Best Optimization Technique -- Works Best In Neural Networks: Qualitative Explanation, Jonatan Contreras, Martine Ceberio, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

In a usual Numerical Methods class, students learn that gradient descent is not an efficient optimization algorithm, and that more efficient algorithms exist, algorithms which are actually used in state-of-the-art numerical optimization packages. On the other hand, in solving optimization problems related to machine learning -- and, in particular, in currently most efficient deep learning -- gradient descent (in the form of backpropagation) is much more efficient than any of the alternatives that have been tried. How can we reconcile these two statements? In this paper, we explain that, in reality, there is no contradiction here. Namely, in usual applications …

Why Question-Based Reasoning Leads To Constructive Approach To Knowledge, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

Once we have partial knowledge, what next question do we usually pursue? Empirical study shows, e.g., that if we know that A \/ B is true, but we do not know whether A is true or B is true, then the usual next step is to ask whether A is true or B is true. This selection of the next step is in line with the constructive approach to knowledge, in which when A \/ B is true, this means that we either know that A is true, or we know that B is true. In this paper, we provide …

Can Ideas Behind Ancient Egyptian Fractions Speed Up Modern Computers?, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

To divide two numbers a and b, modern computers use an algorithm which is more efficient that what we humans normally do: they compute a*(1/b), where for all sufficiently small integers b, the inverse 1/b is pre-computed. For fractions, when both a and b are integers, this algorithm requires only one multiplication. Can we make the procedure even faster by not using multiplication at all? To do this, we need to represent each fraction as the sum of inverses -- which, interestingly, is how ancient Egyptians represented fractions.

Interactive Agent-Based Simulation For Experimentation: A Case Study With Cooperatve Game Theory, Andrew J. Collins, Sheida Etemadidavan

Engineering Management & Systems Engineering Faculty Publications

Incorporating human behavior is a current challenge for agent-based modeling and simulation (ABMS). Human behavior includes many different aspects depending on the scenario considered. The scenario context of this paper is strategic coalition formation, which is traditionally modeled using cooperative game theory, but we use ABMS instead; as such, it needs to be validated. One approach to validation is to compare the recorded behavior of humans to what was observed in our simulation. We suggest that using an interactive simulation is a good approach to collecting the necessary human behavior data because the humans would be playing in precisely the …

Human Characteristics Impact On Strategic Decisions In A Human-In-The-Loop Simulation, Andrew J. Collins, Shieda Etemadidavan

Engineering Management & Systems Engineering Faculty Publications

In this paper, a hybrid simulation model of the agent-based model and cooperative game theory is used in a human-in-the-loop experiment to study the effect of human demographic characteristics in situations where they make strategic coalition decisions. Agent-based modeling (ABM) is a computational method that can reveal emergent phenomenon from interactions between agents in an environment. It has been suggested in organizational psychology that ABM could model human behavior more holistically than other modeling methods. Cooperative game theory is a method that models strategic coalitions formation. Three characteristics (age, education, and gender) were considered in the experiment to see if …

Blockchain For A Resilient, Efficient, And Effective Supply Chain, Evidence From Cases, Adrian Gheorghe, Farinaz Sabz Ali Pour, Unal Tatar, Omer Faruk Keskin

Engineering Management & Systems Engineering Faculty Publications

In the modern acquisition, it is unrealistic to consider single entities as producing and delivering a product independently. Acquisitions usually take place through supply networks. Resiliency, efficiency, and effectiveness of supply networks directly contribute to the acquisition system's resiliency, efficiency, and effectiveness. All the involved firms form a part of a supply network essential to producing the product or service. The decision-makers have to look for new methodologies for supply chain management. Blockchain technology introduces new methods of decentralization and delegation of services, which can transform supply chains and result in a more resilient, efficient, and effective supply chain. This …

Dependency-Based Reactive Change Propagation Design Pattern Applied To Environments With High Unpredictability, João Paulo Oliveira Marum

Electronic Theses and Dissertations

Transitional turbulence is a period of chaotic or unreliable variation in the state of a software system that results from changes in the system’s interconnected components. During these periods of instability, an external observer of the system’s state may “see” erroneous results. This is a problem that can affect visual user interfaces such as those in virtual and augmented reality applications and desktop or Web GUIs. In this research, we study two different reactive applications developed in C# on .NET. We reduce the transitional turbulence by augmenting the base applications with a dependency-graph-based event scheduling approach. The first study investigates …

View Synthesis Of Dynamic Scenes Based On Deep 3d Mask Volume, Kai-En Lin, Guowei Yang, Lei Xiao, Feng Liu, Ravi Ramamoorthi

Computer Science Faculty Publications and Presentations

Image view synthesis has seen great success in reconstructing photorealistic visuals, thanks to deep learning and various novel representations. The next key step in immersive virtual experiences is view synthesis of dynamic scenes. However, several challenges exist due to the lack of high-quality training datasets, and the additional time dimension for videos of dynamic scenes. To address this issue, we introduce a multi-view video dataset, captured with a custom 10-camera rig in 120FPS. The dataset contains 96 high-quality scenes showing various visual effects and human interactions in outdoor scenes. We develop a new algorithm, Deep 3D Mask Volume, which enables …

Towards Formally Verified Compilation Of Tag-Based Policy Enforcement, Chr Chhak, Andrew Tolmach, Sean Anderson

Computer Science Faculty Publications and Presentations

Hardware-assisted reference monitoring is receiving increasing attention as a way to improve the security of existing software. One example is the PIPE architecture extension, which attaches metadata tags to register and memory values and executes tag-based rules at each machine instruction to enforce a software-defined security policy. To use PIPE effectively, engineers should be able to write security policies in terms of source-level concepts like functions, local variables, and structured control operators, which are not visible at machine level. It is the job of the compiler to generate PIPE-aware machine code that enforces these source-level policies. The compiler thus becomes …

Unsupervised Meta-Learning, Siavash Khodadadeh

Electronic Theses and Dissertations, 2020-2023

Deep learning has achieved classification performance matching or exceeding the human one, as long as plentiful labeled training samples are available. However, the performance on few-shot learning, where the classifier had seen only several or possibly only one sample of the class is still significantly below human performance. Recently, a type of algorithm called meta-learning achieved impressive performance for few-shot learning. However, meta-learning requires a large dataset of labeled tasks closely related to the test task. The work described in this dissertation outlines techniques that significantly reduce the need for expensive and scarce labeled data in the meta-learning phase. Our …

Fpga-Augmented Secure Crash-Consistent Non-Volatile Memory, Yu Zou

Electronic Theses and Dissertations, 2020-2023

Emerging byte-addressable Non-Volatile Memory (NVM) technology, although promising superior memory density and ultra-low energy consumption, poses unique challenges to achieving persistent data privacy and computing security, both of which are critically important to the embedded and IoT applications. Specifically, to successfully restore NVMs to their working states after unexpected system crashes or power failure, maintaining and recovering all the necessary security-related metadata can severely increase memory traffic, degrade runtime performance, exacerbate write endurance problem, and demand costly hardware changes to off-the-shelf processors. In this thesis, we summarize and expand upon two of our innovative works, ARES and HERMES, to design …

Self-Governed Iot Networks: A Blockchain-Based Framework, Mehrdad Salimitari

Electronic Theses and Dissertations, 2020-2023

In the modern-day, IoT-enabled devices and sensors are growingly deployed in a variety of applications in consumer, commercial, industrial, and infrastructure spaces. Thus, decentralization of such networks for reducing the maintenance and repair costs is significantly gaining attention. In this dissertation, we investigate a variety of mathematical tools and technological advancements to design a secure, fully decentralized, and self-governed IoT network. On this path, the main challenge is ensuring the data integrity in IoT networks, securing the devices against a variety of attack scenarios, and preserving the privacy of the users. We begin by proposing a prospect theoretic method for …

Algorithms And Lower Bounds For Ordering Problems On Strings, Daniel Gibney

Electronic Theses and Dissertations, 2020-2023

This dissertation presents novel algorithms and conditional lower bounds for a collection of string and text-compression-related problems. These results are unified under the theme of ordering constraint satisfaction. Utilizing the connections to ordering constraint satisfaction, we provide hardness results and algorithms for the following: recognizing a type of labeled graph amenable to text-indexing known as Wheeler graphs, minimizing the number of maximal unary substrings occurring in the Burrows-Wheeler Transformation of a text, minimizing the number of factors occurring in the Lyndon factorization of a text, and finding an optimal reference string for relative Lempel-Ziv encoding.

Novel Deep Learning Methods For Medical Applications With Limited Data, Kaiyue Zhou

Wayne State University Dissertations

Deep learning has become an increasingly popular trend in recent years with applications in different domains including healthcare and medicine using numeric, spatially 2D and 3D, and time-series based video and audio data. However, data collection being the principal bottleneck for advancement in the life sciences, particularly in genomics, engineering, and healthcare, has led to incomplete and insufficient data, resulting in non-optimal deep learning model performances. Here, we propose solutions to overcome such data limitations when high dimensional medical data with limited sample sizes are present. These solutions include but not limited to multi-class learning, feature compression (\eg, auto-encoder), data …

Quantifying Shape Of Star-Like Objects Using Shape Curves And A New Compactness Measure, Gopal K. Mulukutla, Emese Hadnagy, Matthew Fearon, Edward Garboczi

All Materials

Shape is an important indicator of the physical and chemical behavior of natural and engineered particulate materials (e.g., sediment, sand, rock, volcanic ash). It directly or indirectly affects numerous microscopic and macroscopic geologic, environmental and engineering processes. Due to the complex, highly irregular shapes found in particulate materials, there is a perennial need for quantitative shape descriptions. We developed a new characterization method (shape curve analysis) and a new quantitative measure (compactness, not the topological mathematical definition) by applying a fundamental principle that the geometric anisotropy of an object is a unique signature of its internal spatial distribution …

Impact Of Information Breaches On Health Care Records, Anton Antony Arockiasamy

Walden Dissertations and Doctoral Studies

Although there were almost 3.5 million reported information breaches of health care data in the first quarter of 2019, health care providers do not know the extent of digital and nondigital breaches of patient medical records. The purpose of this quantitative, comparative study was to identify the difference between the individual patient records affected by digital versus nondigital breaches for three types of health care entities in the United States, health care providers, health care plans, and health care clearinghouses. Allman’s privacy regulation theory, the National Institute of Standards and Technology Privacy Framework, and ecological systems theory comprised the theoretical …

Successful Strategies For Adopting Open-Source Software, Balla Barro

Walden Dissertations and Doctoral Studies

Middle-level information systems managers (ISMs) in small-scale organizations often have challenges in determining the most appropriate strategy for adopting open-source software (OSS) in their organizations. The ISMs need to determine the right strategy for adopting OSS to protect the organizations’ information technology infrastructure. Grounded in the diffusion of innovation theory, the objective of this multiple case study was to explore strategies middle-level ISMs used to adopt OSS in their small-scale organizations. Six middle-level ISMs from three small-scale organizations with experience of not less than six years in OSS adoption strategy in the city of Frederick, Maryland, shared their strategies during …

Benefits Of Technology Integration In A Small Behavioral Health Organization, Tremaria Sweet

Walden Dissertations and Doctoral Studies

The current study sought to understand the significance of information systems (IS) planning in small-to-medium enterprise (SME) behavioral health agencies and the direct impact it has on organizational growth and performance. The research was guided by the Baldrige Excellence Framework. The study was based on a sample of one senior leader from one agency licensed to practice in three states in the eastern region of the United States. This exploratory case study involved using semi-structured interviews and internal archival data during the process of data collection. Information technology (IT) competence, skills, leadership, infrastructure, and awareness were emergent themes identified in …

Strategies Project Managers Use That Reduce Information Technology Project Failures In The Insurance Industry, Jamarcus Snipes

Walden Dissertations and Doctoral Studies

The worldwide failure rate of information technology (IT) projects is approximately 65%. Insurance project managers who fail to successfully implement IT projects negatively impact organizational performance and profitability. Grounded in the management by objectives theory, the purpose of this qualitative multiple case study was to explore strategies project managers use to reduce IT project failures in the insurance industry. The participants comprised four IT project managers in Alabama who successfully used strategies to reduce IT project failures in the insurance industry. Data were collected from virtual semistructured interviews, company documents, existing literature, and journal notes. Thematic analysis was used to …

Strategies For Implementing Internet Of Things Devices In Manufacturing Environments, Todd Efrain Hernandez

Walden Dissertations and Doctoral Studies

The Internet of Things (IoT) has been exploited as a threat vector for cyberattacks in manufacturing environments. Manufacturing industry leaders are concerned with cyberattacks because of the associated costs of damages and lost production for their organizations. Grounded in the general systems theory, the purpose of this multiple case study was to explore strategies electrical controls engineers use to implement secure IoT devices in manufacturing environments. The study participants were eight electrical controls engineers working in three separate manufacturing facilities located in the Midwest region of the United States. The data were collected by semistructured interviews and 15 organizational documents. …

Augmented Reality Headset Facilitates Exposure For Surgical Stabilization Of Rib Fractures, T. Sensing, Pratik Parikh, Claire Hardman, Thomas Wischgoll, Sadan Suneesh Menon

Computer Science and Engineering Faculty Publications

Recent advances in augmented reality (AR) technology have made it more accessible, portable, and powerful. AR headsets differentiate themselves from virtual reality in that they allow the wearer an unobstructed view of the “real world” but with an image superimposed upon it. The technology has many potential applications in medicine, including surgical planning, simulation, and medical education. The aim of this project was to provide proof of concept that using an AR headset during surgical stabilization of rib fractures (SSRF) is feasible. We theorized that the use of AR could allow for more precise localization of fractures, allowing for smaller …

Best Cybersecurity Practices For Companies, Post Van Buren, Mary Riley

Cybersecurity Undergraduate Research Showcase

Imagine this scenario: you are a small business owner, and you’ve just been informed of a network security breach. In your Zoom meeting with the IT Department, you learned the details: network activity logs revealed aberrant behavior after hours. Threat actors accessed systems containing sensitive information and downloaded copies of key files containing company trade secrets, market strategies, and customer data – all within a matter of minutes. Immediately, you review the consequences of the breach in your mind: reputational harm, monetary loss, and potential lawsuits. You ask the IT professional about the root cause of the breach. Was it …

Tackling Ai Bias With Gans, Noam Stanislawski

Cybersecurity Undergraduate Research Showcase

Throughout the relatively short history of artificial intelligence (AI), there has been a significant concern surrounding AI’s ability to incorporate and maintain certain characteristics which were not inherently modeled out in its coding. These behaviors stem from the prominent usage of neural network AI, which can inherit human biases from the input data it receives. This paper argues for two possible avenues to combat these biases. The first is to rethink the traditional framework for neural network projects and retool them to be usable by a Generative Adversarial Network (GAN). In a GAN’s zero-sum game, two network techniques can combat …

Leverage Psychological Factors Associated With Lapses In Cybersecurity In Organizational Management, Chad Holm

Cybersecurity Undergraduate Research Showcase

With computers being a standard part of life now with the evolution of the internet, many aspects of our lives have changed, and new ways of thinking must come. One of the biggest challenges in most cyber security problems is not related to the software or the hardware; it is the people that are using the computers to access the data and communicate with others, where the hackers could simply find a weak entry point that naturally exists and a weak link caused by human hands. The human factor as an “insider threat” will affect unauthorized access, credentials stealing, and …

On The Usage And Vulnerabilities Of Api Systems, Conner D. Yu

Cybersecurity Undergraduate Research Showcase

To some, Application Programming Interface (API) is one of many buzzwords that seem to be blanketed in obscurity because not many people are overly familiar with this term. This obscurity is unfortunate, as APIs play a crucial role in today’s modern infrastructure by serving as one of the most fundamental communication methods for web services. Many businesses use APIs in some capacity, but one often overlooked aspect is cybersecurity. This aspect is most evident in the 2018 misuse case by Facebook, which led to the leakage of 50 million users’ records.1 During the 2018 Facebook data breach incident, threat actors …

Reflection Of A Horizon Image On The Surface Of Water, Christopher S. Stuetzle, Steve Warner, John-Paul Mayer

Computer and Data Science Faculty Publications

We have created a piece of software that renders the reflection of a ”landscape” texture on a wavy fluid surface. The fluid is represented by a height field and a quad mesh. Waves are created by using wave particles, non-physical entities that determine the influence a wave has on the fluid around it. The scene is ray traced by sending a ray through each pixel, bouncing it off the water and against the texture backdrop. The color of the texture is quieried and influences the color of the water surface. Surface normals are calulated by interpolating vertex normals across each …

Maternal Proximity To Mountaintop Removal Mining And Birth Defects In Appalachian Kentucky, 1997-2003, Daniel B. Cooper

Theses and Dissertations--Public Health (M.P.H. & Dr.P.H.)

Background: Extraction of coal through mountaintop removal mining (MTR) alters many dimensions of the landscape, and explosive blasts, exposed rock, and coal washing have the potential to pollute air and water with substances known to increase risk of developmental and birth anomalies. Previous research suggests that infants born to mothers living in MTR coal mining counties have higher prevalence of most types of birth defects.

Objectives: This study seeks to examine further the relationship between MTR activity and birth defects by employing individual level exposure estimation through precise satellite data of MTR activity in the Appalachian region and maternal residence …

Cybersecurity: Building A Better Defense With A Great Offense, David M. Cooke

Cybersecurity Undergraduate Research Showcase

The current industry standard for cybersecurity is risk mitigation, which is the identification, evaluation, and categorization of threats that are posed to an organization's network. The goal is to prevent attacks and if an organization is attacked popular standard is to react and remedy the attack. This form of cyber defense isn’t very reassuring to an organization and its users, once an attack is executed based on a study conducted by Booz Allen the average time an advanced persistent threat (APT) dwells on a victims’ network before it’s discovered is 200-250 days. That’s plenty of time for a malicious third …

Binary State Distance Vector Routing: A Protocol For Near-Unicast Forwarding In Partitioned Networks, Ammar Farooq

Electronic Theses and Dissertations, 2020-2023

Ad-hoc networks are highly dynamic and can be disconnected/partitioned during their operations, particularly in delay-tolerant networks (DTNs) where infrastructure support is not entirely available. Even after several decades of research on DTN routing, there is still a need for routing protocols that operate effectively in network environments where disconnections, delays, and resource scarcity are common. Traditionally, DTN routing protocols use an epidemic routing strategy, where multiple copies of packets get forwarded to increase network reachability. However, these flooding-based strategies are seldom suitable in resource-constrained network settings. Other prominent DTN routing designs use distance vectors (DVs) that summarize global network reachability …