Digital Commons Network^™

Making Robotic Reinforcement Learning More Efficient: Analyzing The Serl Framework, Faris Jugovic, Cleiver Ruiz-Martinez, Ryan Vander Stelt

Student Scholar Symposium

Teaching robots through reinforcement learning (RL) has made great progress, but real-world training is still difficult. Robots need lots of practice to learn, rewards can be hard to define, and resetting the environment after each attempt is often a challenge. The Sample-Efficient Robotic Reinforcement Learning (SERL) framework helps solve these issues by offering a ready-to-use, open-source software package that makes RL more practical for real-world robotics.

This project explores SERL and how it improves robotic RL by making learning faster and more efficient. SERL includes smarter ways to reuse training data, automatic methods for understanding rewards from images, and a …

Improving Home Affordability In Greater Nashville Through Construction Efficiency And Innovations, Nate Mclain

Student Scholar Symposium

Engineering Greater Nashville Home Affordability

Long Term Financial Analysis For Opry Mills Hotel And Resort, Eli Lockert

Student Scholar Symposium

In 2024 a Lipscomb Senior Design team completed a design project for the Opryland Hotel. The project, aimed at reducing humidity levels in the large greenhouse-like atrium and overall power usage, included multiple phases and equipment. This research continues the work of that team in an effort to determine whether the proposed system is a cost-effective approach. The research specifically evaluates the system outlined in the Opryland Final Design Report, completed in April of 2024. Using a holistic approach, this study employs life-cycle cost analysis (LCCA) to assess the economic feasibility of the proposed system through various empirical methods. A …

Gamergate And The Woke Mind Virus, Gavin Graves

Undergraduate Research Symposium

This text concerns the formation of beliefs that would shape the 2014 harassment campaign of GamerGate. Specifically, how GamerGate was perpetuated by stereotypes and ideas in Geekdom that spanned from the 60’s Disco Demolition to the Internet’s Wild West that ended in 2013. These include ideas like simulated ethnicity, geek melodrama, nerd determinism, and nerd fatalism. It also discusses the views and beliefs on anonymity, critique, and social capitals of the Wild West Internet and how the changing views of these led to resentment that started the movement. Drawing from historical research, I studied the history of moral panics like …

Nazi Weapons: Bad People, Good Technology, Fabian Grabski

Undergraduate Research Symposium

This project explores the integration and historical significance of three iconic World War II-era German weapons: the V-2 rocket, the STG-44, and the MG-42. Each of these weapons helped revolutionized military technology in its own right, reshaping the battlefield dynamics and influencing future weapon design. The V-2 rocket, as one of the first long-range guided missiles, marked the dawn of modern missile technology, while the STG-44 is recognized as a precursor to the modern assault rifle, blending the characteristics of both submachine guns and rifles. The MG-42, with its high rate of fire and advanced design, set the standard for …

Pixel-Perfect Segmentation Of Solar Filaments, Jamie Harris

Undergraduate Research Symposium

The observation and classification of solar filaments has a drastic impact on the ability to predict solar-magnetic weather phenomena that threatens to put both satellite infrastructure and astronauts at risk. Using the Hɑ filter provided by the Global Oscillations Network Group (GONG), a network of six telescopes around the world dedicated to 24/7 surveillance of the sun, we are able to get images that clearly and prominently display filament activity. With the vast amount of images the GONG takes, it is not possible to manually analyze every image. Using the U-Net model for computer vision, we were able to train …

Face Value: A Computational Approach To Subjective Impressions Of Faces, Kevin Kpankou

Undergraduate Research Symposium

Various computational models of first impressions have been developed to uncover the mechanisms driving these judgments. However, the implicit notion of a singular ``human'' often overlooks meaningful individual differences in beliefs, attitudes, and associations, as well as culturally grounded group-level constructs. In this paper, we extend Cultural Consensus Theory (CCT) to estimate culturally shared beliefs about faces by incorporating latent constructs structured around interpretable facial features extracted via computer vision algorithms. We apply our model to a large-scale dataset of people’s first impressions of faces. Our approach reveals a robust mapping between facial features and culturally constructed impressions, allowing us …

Article Draft, Bob Schieffer

Bob Schieffer Vietnam War Collection

Article draft by Bob Schieffer about Major Bruce Miller in Vietnam.

Article Draft, Bob Schieffer

Bob Schieffer Vietnam War Collection

Bob Schieffer's notes of several soldiers in Vietnam.

Article Draft, Bob Schieffer

Bob Schieffer Vietnam War Collection

Article draft by Bob Schieffer of attempted kidnapping of soldiers cycle-os in Vietnam.

Article Draft, Bob Schieffer

Bob Schieffer Vietnam War Collection

Article draft by Bob Schieffer on several soldiers in Vietnam.

Article Draft, Bob Schieffer

Bob Schieffer Vietnam War Collection

Article draft by Bob Schieffer on several soldiers in Vietnam.

System And Method For Automatically Selecting Context-Aware Llms Using A Reward-Based Multi-Objective Learning Mechanism, Sumit Kumar, Shivam Mohan, Ravi Shanker Kumar Sinha, Dheeraj Dhamija, Soumendra Kumar Mishra

Defensive Publications Series

The present disclosure provides a method and a system for automatically selecting context-aware large language models (LLMs) using a reward-based multi-objective learning mechanism. The method includes receiving an input task and extracting a corresponding context vector comprising one or more contextual attributes. The method includes computing, for each of a plurality of LLMs, a confidence-adjusted expected performance score using the context vector, the score being generated using a contextual learning algorithm. The method includes selecting at least one of the plurality of LLMs having the highest confidence-adjusted expected reward for the input task. The method includes executing the selected LLMs …

Mission Command’S Asymmetric Advantage Through Ai-Driven Data Management, Sorin Adam Matei, Kyle Parris Reed

The US Army War College Quarterly: Parameters

Artificial intelligence can optimize mission command by condensing multisource field data that ascends the decision chain while distilling concise, decision-quality guidance to the tactical edge. Diverging from existing publications, this article positions information asymmetry as a defining pillar of mission command rather than a limitation. This article presents a condensation-distillation framework that manages complexity through data condensation, AI-driven distillation, and conceptual metrics to assess asymmetric information flows. Drawing on military doctrine, algorithmic-warfare literature, and current modernization programs, military practitioners will engage with a systems-thinking perspective, revealing how AI-enabled command and control can enhance decision clarity and reinforce the intent of …

Advanced Soliton Structures And Elliptic Wave Patterns In A Sixth-Order Nonlinear Schrödinger Equation Using Improved Modified Extended Tanh Function Method, Mina Fahim, Hamdy Mohamed Ahmed, Islam Samir, Kamal Dib

Basic Science Engineering

In this work, a sixth–order extension of the nonlinear Schrödinger equation (NLSE) within its integrable hierarchy is investigated to model higher–order nonlinear and dispersive effects relevant to optical fiber systems and nonlinear wave propagation. By employing the Improved Modified Extended Tanh Function Method, a comprehensive family of exact analytical solutions is derived, encompassing bright and dark solitons, singular soliton structures, and singular periodic solutions. In addition, solution families expressed in terms of Jacobi elliptic functions, Weierstrass doubly periodic elliptic functions, and exponential profiles are obtained. The novelty of this study lies in extending the analytical framework of the NLSE hierarchy …

Blockchain-Enabled Sustainability Of Li-Ion Batteries Supply Chain: Tracking And Sourcing Eco-Friendly Materials, Karim Moawad, Ahmad Musamih, Assia Chadly, Ahmad Mayyas, Khaled Salah, Raja Jayaraman, Mohammed Omar, Ibrar Yaqoob

Industrial Engineering: Faculty & Staff Publications

No abstract provided.

Recent Advancements Of Applied Robotics In Construction Project Management: A Life Cycle Perspective, Yifan Wang, Xiaoyu Hou, Tan Chen, Bo Xiao

Michigan Tech Publications

Robotic applications in the architecture, engineering, construction, and operation (AEC/O) industry have advanced rapidly, driven by innovations in sensing, artificial intelligence (AI), and automation. Yet, despite notable progress, existing studies are often confined to isolated systems, specific technologies, or individual project phases. This fragmentation has resulted in a diverse but disjointed body of knowledge, underscoring the need for a comprehensive synthesis that connects emerging practices into a holistic perspective. This study presents a systematic review of 315 peer-reviewed publications from 2016 to 2025, examined through a life cycle lens. A mixed-methods approach combining quantitative analysis with qualitative discussion is employed …

That’S Not Art! Artificial Intelligence And Its Role In The Arts, Molly Katherine Horn

Honors Program Theses and Projects

Artificial intelligence (AI) has been deeply integrated into our modern lives; from social media algorithms, to email summaries, to software that will write your essays, and even tools to photoshop relatives out of family photos. AI software is trained on countless data points. Famous artwork, philosophical texts, TikTok trends, movies, wars, and star-crossed stories. It is steadily becoming a collection of human history; learning and growing alongside us. Art, too, is a reflection of society; it informs us of our history, our cultures, our desires and dreams. Thus, it is only fitting that AI has become a tool to create …

Gauss’S Method For Orbital Determination, Milagros Tamara Giraldo

Honors Program Theses and Projects

Accurately predicting the orbital trajectory of celestial objects is essential for precise spacecraft navigation, planning planetary missions, avoiding potential collisions with space debris, and studying the long-term stability of planetary systems. Gauss’s method for orbital determination provides a way to predict the path of a celestial body accurately using only a small number of observations. In this project, we create an implementation that is not just a tool for executing Gauss’s method, but also an opportunity to study the formulation of the method itself. It allows for a practical and detailed examination of how different inputs, assumptions, and numerical choices …

The Feasibility Of Transaldolase Inhibitors As Anti-Cancer Therapeutics, Daniel Scot Baer

Chemistry and Biochemistry

Metabolism was a major focus of cancer research 100 years ago, but its prevalence declined in the latter part of the twentieth century. In the last several decades, however, it has become clear that cancer cells frequently modify their metabolic programs to enable both their survival and rapid proliferation. Transaldolase (TA), an enzyme within the pentose phosphate pathway, contributes to these outcomes when its activity is increased, yet for a variety of reasons inhibition of the enzyme has remained comparatively understudied. Since TA flux enables nucleotide production and high levels of NADPH synthesis, aberrant, cancer-causing signaling pathways often increase expression …

Cyber-Physical Framework For Smart Paint Manufacturing: Hybrid Integration Of Plc And Recipe Management Simulation, Stephen A. Michael, Anas M. Atieh, Emmanuel Nkwocha, Nathir A. Rawashdeh

Michigan Tech Publications

This study investigates the implementation of Industry 4.0 paradigms in the context of smart paint manufacturing, focusing on process control and recipe management through the integration of Ignition SCADA, a Siemens programmable logic controller (PLC), and a MySQL Workbench database. The developed architecture employs Ignition as an interoperable communication interface that facilitates bidirectional data exchange between the PLC and the database, thereby establishing a cyber-physical system for automated monitoring and control. The digital recipe management module formalizes paint formulations into parameterized datasets specifying paint and solvent ingredient ratios, process variables, and operational constraints, which are executed autonomously by the control …

Framing Of Immigration In The News And Its Effects On Social Media Discourse On The Southcoast Of Massachusetts, Mariel Surprenant

Political Science Undergraduate Theses

Why do immigrant communities often express anti-immigrant sentiment? This study will focus on examining what political discourse about immigration dominates the news ecosystem of the Southcoast of Massachusetts, and what effect that discourse has. Immigration in the U.S. has become an increasingly politicized issue, dominating political discourse, motivating voter behavior, and shaping regional political identities. This study will use content analysis of Southcoast newspapers to examine how the local news frames immigration and discourse analysis to examine the opinions of everyday citizens revealed as by their social media comments on posts about immigration by the same local news sources. The …

Comparative Analysis Of Machine Learning And Statistical Models For Railroad–Highway Grade Crossing Safety, Erickson Senkondo, Deo Chimba, Masanja Madalo, Afia Yeboah, Shala Blue

Civil and Architectural Engineering Faculty Research

Railroad-highway grade crossings (RHGCs) are critical points of conflict between roadway and rail systems, contributing to over 2000 crashes and 250 fatalities annually in the United States. This study applied machine learning methods (ML) techniques to model and predict crash frequency at RHGCs, using a comprehensive dataset from the Federal Railroad Administration (FRA) and Tennessee Department of Transportation (TDOT). The dataset included 807 validated crossings, incorporating roadway geometry, traffic volumes, rail characteristics, and control features. Five ML models—Random Forest, XGBoost, PSO-Elastic Net, Transformer-CNN, and Autoencoder-MLP—were developed and compared to a traditional Negative Binomial (NB) regression model. Results showed that ML …

Optimization Of Research Pipeline To Characterize The Effects Of Atp-Sensitive Potassium Channels Mutations On Native Skeletal Muscle Fibers And Evaluate Potential Drug Therapy, Yuezhou Chen

McKelvey School of Engineering Graduate Student Theses & Dissertations

The ATP-sensitive potassium (KATP) channel is a critical metabolic sensor in skeletal muscle, yet its definitive molecular composition and functional roles remain contested. In this study, I conclusively demonstrate that the Kir6.2/SUR2 complex forms sarcolemmal KATP channel in mouse fast-twitch muscle. Genetic knock-out (KO) of Kir6.2 (Kcnj11−/−) or SUR2 (Abcc9−/−) resulted in a similar phenotype with increased fatigue resistance and a pathological rise in unstimulated resting tension at high-frequency stimulation. In contrast, SUR1 (Abcc8−/−) KO was ineffective. Furthermore, a CRISPR/Cas9 knock-in mouse model of a human SUR2A truncation variant (KCGV/KCGV) recapitulated the abnormal force accumulation, demonstrating that even loss-of-function of …

Functional Characterization Of Abcc8 Mutations Potentially Linked To The Transition From Hyperinsulinemic Hypoglycemia To Diabetes, Hao Zhang

McKelvey School of Engineering Graduate Student Theses & Dissertations

ATP-sensitive potassium (KATP) channels, composed of the SUR1 and Kir6.2 subunits encoded by the ABCC8 and KCNJ11 genes, are critical regulators of membrane excitability and insulin secretion in pancreatic β-cells. Gain-of-function (GOF) mutations in these genes cause neonatal diabetes mellitus through impaired insulin secretion and persistent hyperglycemia, whereas loss-of-function (LOF) mutations lead to congenital hyperinsulinism (CHI) with hypoglycemia due to β-cell hyperexcitability. I have addressed a paradoxical form of maturity-onset diabetes of the young (MODY) arising from KATP mutations, in which patients transition from CHI to glucose intolerance later in life. My experiments indicate that many KATP mutations associated with …

The Perception Of Therapists About Compassion Fatigue And Burnout After Working With Victims Of Domestic Violence, Bernadine Edwards

Walden Dissertations and Doctoral Studies

This qualitative study involved gaining a better understanding of the perceptions of therapists who work with domestic violence victims, and how the therapists’ work may contribute to the development of compassion fatigue and burnout in the treating therapists. The goal was to gather firsthand data regarding the lived experiences of therapists. This study involved conducting semi-structured interviews with six counselors, listening to lived experiences, reading transcriptions, taking and reading notes in a journal during and after interviews, and analyzing data. The social ecological theory guided the study. The research identified 11 key themes highlighting the significant stress associated with this …

The Relationship Between K-12 Public School Funding, Per Pupil Expenditures, And Student Achievement, Regina R. Frazier-Bagley

Walden Dissertations and Doctoral Studies

Public school district leaders are challenged with funding K-12 education that creates the desired student academic performance. Grounded in student-based budgeting theory, this quantitative ex post facto study aimed to investigate the relationship between K–12 public school funding, per-pupil expenditures, student achievement, and graduation rates in Georgia. The study included secondary data from 51 North Georgia public school districts for the 2018–2019 school year. Multiple regression analysis was completed to examine the relationship between the independent variables—state funding, per-pupil expenditures, and academic achievement in math, science, and language arts—and the dependent variable: graduation rates. The results of the analysis were …

Employees’ Perceptions Of Leaders’ Diversity Training For Supporting Organizational Equity, Michelle L. Burchfield

Walden Dissertations and Doctoral Studies

Despite growing organizational attention to diversity, equity, and inclusion, some workplaces continued to struggle with embedding equitable practices. The research problem addressed in this study focused on understanding how employees perceived leaders’ diversity training and its effectiveness in supporting organizational equity. The purpose of this qualitative interpretative phenomenological study was to explore employees’ perspectives of leadership diversity training and its role in supporting organizational equity. Behavioral leadership theory and critical race theory grounded this study. The participants consisted of 10 employees with experience in leadership diversity training in Kentucky, Ohio, and Indiana. Data were collected using semistructured interviews. Seven most …

Effective Strategies To Reduce Burnout For Employees With High Workload Demands, Michelle Healy

Walden Dissertations and Doctoral Studies

Ineffective strategies to reduce burnout for employees can decrease productivity and quality of work, and can increase turnover. Event industry leaders who struggle to reduce burnout of employees with high workload demands are at risk of employee turnover. Grounded in the Job Demands-Resources (JD-R) model, the purpose of this qualitative, pragmatic inquiry research project was to explore effective strategies to reduce burnout for employees with high workload demands. The participants were eight event industry leaders who had effectively implemented strategies to reduce burnout. Data were collected using semistructured interviews and a review of public websites and documents. Using thematic analysis, …

Can Deep Reinforcement Learning Help Robots Avoid Unexpected Obstacles?, Rachel Lewis

Computer Science

As the utilization of deep reinforcement learning (DRL) for mobile robotics increases, it is vital to ensure that agents can navigate safely in their environments. As these robots are often costly and fragile, a key part of this task is examining path planning and collision avoidance. This project focuses on the behavior of several DRL agents such as Soft-Actor Critic (SAC) and Proximal Policy Optimizer (PPO) in dynamic environments, particularly with intermittent obstacles—those that may not always pose a threat to the agent. This project does not include training with agent sensors to detect moving hazards. Rather, this work was …