Digital Commons Network^™

Adaptive Generation In Evolutionary Robotics: From Adversarial Objects To Guided Optimization, Unknown Akshay

Dissertations - ALL

Evolution-inspired algorithms have proven effective for complex optimization problems butsuffer from computational inefficiency due to their reliance on random variation operators. This is problematic in domains where fitness evaluation depends on expensive procedures such as training a neural network or running a robot, either in simulation or on hardware. This dissertation presents novel approaches for evolutionary robotics that replace stochastic evolutionary operations with learned, adaptive strategies using reinforcement learning (RL), significantly improving search efficiency while maintaining population diversity.The first contribution is a voxel-based evolutionary framework for generating adversarial objects that challenge robotic grasping systems. By evolving objects with controlled similarity …

Optimized Beamforming And Network Slicing For Dense Urban 5g Deployments, Kwame S. Ibwe

Tanzania Journal of Science

Optimizing beamforming and network slicing is critical for enhancing spectral efficiency, energy efficiency, and resource distribution fairness in dense urban 5G networks. This paper proposes a hybrid genetic algorithm particle swarm optimization (GA-PSO) method to jointly optimize beamforming weights, bandwidth allocation, and power distribution, balancing computational efficiency with near optimal performance. The hybrid approach uses GA for global exploration and PSO for fast convergence, overcoming the limitations of standalone heuristic and exact optimization methods. Simulation experiments in a dense urban 5G network with massive MIMO base stations show that proposed method achieves up to 15% higher spectral efficiency and 18% …

Fine-Tuning Llama2 For Summarizing Discharge Notes: Evaluating The Role Of Highlighted Information, Mahshad Koohi Habibi Dehkordi, Yehoshua Perl, Fadi P. Deek, Hao Liu

School of Computing Faculty Scholarship and Creative Works

This study investigates whether incorporating highlighted information in discharge notes improves the quality of the summaries generated by Large Language Models (LLMs). Specifically, it evaluates the effect of using highlighted versus unhighlighted inputs for fine-tuning LLaMA2-13B model for summarization tasks. We fine-tuned LlaMA2-13B in two variants using MIMIC-IV-Ext-BHC dataset: one variant fine-tuned with the highlighted discharge notes (H-LLaMA), and the other on the same set of notes without highlighting (U-LLaMA). Highlighting was performed automatically using a Cardiology Interface Terminology (CIT) presented in our previous work. H-LLaMA and U-LLaMA were evaluated on a randomly selected test set of 100 discharge notes …

Advancements In Perfect Matchings Within Neutrosophic Fuzzy Graphs: Theory And Applications, Muhammad Saeed, Fatima Razaq

Neutrosophic Systems with Applications

Graph theory has been widely used in exemplifying relational structure, and a greater generalization to fuzzy and neutrosophic space enables the exemplification of uncertainty, indeterminacy, and inconsistency in complex systems. Some of these extensions include the neutrosophic fuzzy graphs that provide a more detailed description of the loose relations between the vertices and the edges. However, unlike in classical graph theory, where the concepts of matching and perfect matching are well developed, very little has been studied on how the two concepts can be extended to neutrosophic fuzzy graphs. To seal this gap, the current paper develops and defines the …

Integrating Mcdm Techniques For Optimized Task Offloading In Multi-Uav- Enaled Mobile Edge Computing System, Amira Salam

Neutrosophic Systems with Applications

Carefully choosing a task offloading strategy is crucial for optimizing task scheduling and offloading strategies in a multi-UAV system. Regarding cost, responsiveness, scalability, and data security, each strategy has pros and cons. As a result, selecting the best offloading technique is essential to multi-UAV mobile edge computing task scheduling optimization. A methodical and well-informed decision-making process accomplishes this.

The current study introduces a new hybrid methodology for the multi-criteria decision-making (MCDM) model, known as IVNs-DEMATEL-ANP-VIKOR. The purpose of this model is to find and choose an efficient task offloading strategy. With this method, we use IVNs-DEMATEL to show how different …

Mixed Linear Equation–Inequality Systems Over The Pura Vida Neutrosophic Algebra, Muhammad Rayyanu Abdullahi, Abdulhadi Aminu

Neutrosophic Systems with Applications

This paper proposes a neutrosophic extension of max-plus algebra for solving mixed systems of linear equations and inequalities.Classical max-plus algebra is a powerful tool for modeling synchronization in discrete-event systems LastNatpreClose LastNatClose, but it assumes fully deterministic data.To incorporate uncertainty and indeterminacy, we reformulate the framework so that coefficients and variables are expressed as neutrosophic numbers

γ+λI,γ,λ∈ℝ,I∈[0,1],

where I quantifies the degree of indeterminacy.

We redefine the max-plus semiring in this neutrosophic setting, extend solvability and uniqueness results, and adapt the ONEMLP-EI algorithm LastNatpreClose LastNatClose to handle neutrosophic …

Mapping Sustainability To Cybernetic-Generative Artificial Intelligence-Based Education: An Innovative Neutrosophic Orbifold-Lattice Methodology, Mona Mohamed, Ahmed A. Metwaly

Neutrosophic Systems with Applications

The lightning-fast development of artificial intelligence (AI), notably generative artificial intelligence (Gen AI) technologies, has intrigued multiple disciplines, particularly education. In this context, Large Language Models (LLMs) serve as beneficial cognitive resources that address knowledge deficits and provide tailored educational support for learners and staff. For learners, LLMs are regarded as knowledgeable educators who offer prompt, focused responses and rationales to tricky queries. Whereby LLMs for staff, Strength enhancer, automating tedious tasks, and creating intelligent resources.Gen AI’s rapid growth offers enormous obstacles for educational systems, compelling them to discover solutions for these obstacles.

Conceptually, cybernetics is leveraged for bridging the …

Neutrosophic Σ - Baire Spaces, R. Vijayalakshmi, F. Josephine Daisy, M. Simaringa

Neutrosophic Systems with Applications

A Neutrosophic Baire Space extends the concept of Baire Space from classical topology to the realm of neutrosophic topology which deals with sets and spaces where truth, falsehood and indeterminancy are explicitly considered. In this paper the concept of neutrosophic σ - baire spaces are introduced in Neutrosophic topological spaces. Also Neutrosophic σ - dense, Neutrosophic σ - nowhere dense, Neutrosophic σ -first category and Neutrosophic σ - second category sets are defined. Several characterizations of neutrosophic σ - baire spaces are investigated and explained using examples and the conditions under which a neutrosophic topological space becomes a neutrosophic σ …

Multipacking On Graphs And Euclidean Metric Space, Sk Samim Islam

Doctoral Theses

A multipacking in an undirected graph G = (V,E) is a set M ⊆ V such that for every vertex v ∈ V and for every integer r ≥ 1, the ball of radius r around v contains at most r vertices of M, that is, there are at most r vertices in M at a distance at most r from v in G. The multipacking number of G is the maximum cardinality of a multipacking of G and is denoted by mp(G). The MULTIPACKING problem asks whether a graph contains a multipacking of size at least k. For more …

Chaos Engineering In Multi-Gigahertz Solid-State Lasers: A Novel Approach To Optoelectronic Control, Mikhail V. Gorbunkov, Yulia Ya. Maslova, Yulia A. Sinichkina

Karbala International Journal of Modern Science

This paper presents a comprehensive study of a multi-gigahertz chaotic generator of light pulses based on solid-state laser sources, including fiber lasers, governed by carefully designed positive and negative feedback loops. It harnesses the inherent nonlinear dynamics within a solid-state laser controlled by a combination of two inertial feedback loops, enabling the realization of complex chaotic behavior, including the logistic map scenario, under moderate amplification conditions. The laser system dynamics are rigorously investigated through theoretical modeling, employing a nonlinear map approach, and high-resolution picosecond simulations. The results of our numerical simulations highlight the efficacy of fast electro-optical feedback system with …

Unveiling The Anticancer Potential Of Syzygium Cumini: In Silico Insights Into Its Mechanistic Action Against Non-Small Cell Lung Cancer, Nur Sofiatul Aini, Win Darmanto

Karbala International Journal of Modern Science

Non-small cell lung carcinoma (NSCLC) is the most periodic type of lung cancer and the second most diagnosed cancer globally. Syzygium cumini is plant that extensively used in cuisine and traditional medicine. However, its potential for NSCLC treatment has not yet been elucidated. This study determined the potential of S. cumini as anti-NSCLC using in silico approaches. The in silico study was applied to perform active compound analysis, selection of target candidates, network pharmacology, functional annotation, molecular docking, and molecular dynamics simulation, respectively. Based on open source databases, S. cumini contained 115 compounds and 14 of them predicted to have …

Three Decades Of Chinese Internet Technology: Social Risks And Prevention Pathways, Zhaokai Yin, Weifu Zhang

Bulletin of Chinese Academy of Sciences (Chinese Version)

With the rapid advancement and application of big data, artificial intelligence, and mobile Internet technologies, network technology has been driving social development, while its negative effects have gradually emerged. Based on a critical perspective and logical reasoning, this study systematically reviews the evolution and characteristic manifestations of social risks in China’s network technology over the past 30 years, revealing multiple hidden dangers it has caused in data governance, capital operation, and political communication. Under the new situation, to prevent and defuse the social risks of network technology, precise measures should be taken from aspects such as value guidance, institutional regulation, …

Application Of Reinforcement Learning To Precision Aerial Delivery System Control In Adverse Wind Conditions, Radman Zarbock

The Journal of Purdue Undergraduate Research

Precision aerial delivery systems (PADS) are a subset of airdropped parachute-leveraging package delivery systems that use autonomous guidance, navigation, and control (GNC) to reach targets with high degrees of accuracy. This technology emerged in the 1990s, and strides have been made since to improve the reliability of traditional physics-based controllers that guide PADS. However, these algorithms still struggle to deliver acceptable performance results when PADS are subjected to austere operating environments, such as those with unpredictable wind. Building on a foundational study in 2022 that used artificial intelligence (AI) and machine learning to improve PADS GNC performance, this study aims …

Amp: Single-Shot Ultra-Wide Fisheye-To-Cubemap Pnp Pose Estimation, Ryan M. Raettig, Richard R. Nyquist, Scott L. Nykl, Clark N. Taylor, Christine M. Schubert Kabban

Faculty Publications

Estimating the position and orientation of a rigid object from an image is critical for situational awareness in robotics and autonomous systems. This study explores relative pose estimation using an ultra-wide fisheye camera for unmanned aircraft inspection vehicles. Ultra-wide fisheye lenses introduce radial distortion and capture features beyond the rectilinear image plane, rendering rectilinear Perspective-n-Point (PnP) algorithms inadequate. Designing a bespoke ultra-wide fisheye localization algorithm requires consideration of both the feature detection method and the pose estimator itself. This study proposes a novel method that combines (1) a fisheye-to-cubemap reprojection, (2) a You Only Look Once (YOLO) convolutional neural network …

Validating Pharmacogenomics Generative Artificial Intelligence Query Prompts Using Retrieval-Augmented Generation (Rag), Ashley Rector, Beth Breeden, Jay Dorris

Student Scholar Symposium

This study evaluated the performance of Sherpa Rx, an artificial intelligence platform leveraging large language models and retrieval-augmented generation (RAG) for pharmacogenomics, by validating its performance across key response metrics. Sherpa Rx integrated Clinical Pharmacogenetics Implementation Consortium (CPIC) guidelines with Pharmacogenomics Knowledgebase (PharmGKB) data to generate contextually relevant responses. A dataset (N=260 queries) spanning 26 CPIC guidelines was used to evaluate drug-gene interactions, dosing recommendations, and therapeutic implications. In Phase 1, only CPIC data was embedded; Phase 2 additionally incorporated PharmGKB. Responses were scored on accuracy, relevance, clarity, completeness (5-point Likert scale), and recall. Wilcoxon signed-rank tests compared accuracy between …

A Teacher, Medical Advisor, And Comedian Walk Into A Bar: Table For One, Everything Ai Can Do, Lorelai M. Kline

Student Scholar Symposium

As Generative AI continues to rise in popularity, AI chatbots have emerged as a promising solution for addressing students’ real-world needs. This presentation investigates the development process behind a series of specialized, personality-driven AI assistants—created via the Boodlebox platform—and examines how these chatbots enhance educational experiences and practical applications. The research uses progressive design methodologies, including persona development, natural language processing optimization, and user-centric testing protocols. Examples of personal bots include a historical assistant that interprets contemporary social scenarios through an 18th- to 19th-century perspective and a Spanish-speaking chatbot that leverages playful sarcasm to foster deeper engagement. Preliminary findings show …

What Does Graptolite Origination And Extinction Reveal About The Cause Of The Late Ordovician Mass Extinction?, Charles E. Mitchell, H. David Sheets, Michael J. Melchin, Chris Holmden

Computer and Data Science Faculty Publications

Assesses the macroevolutionary turnover of paleotropical planktic graptolites during the Late Ordovician Mass Extinction (LOME) via automated sequencing and capture-mark-recapture modeling. Graptolites exhibited a succession of turnover pulses (sensu Elizabeth Vrba) that were coincident with the main phases of the Hirnantian glaciation and during which the Diplograptina experienced declining metapopulation size, elevated extinction, zero species originations, and ultimately, complete extermination. Concurrently, the Neograptina (latest Katian temperate zone immigrants) exhibit pulses of both extinction and adaptive radiation. Thus, the LOME involved intense species selection and the wholesale alteration of the clade diversity structure of a major element of the zooplankton. The …

Wild Robots: Humans, Wilderness, And Technology In Becky Chambers’ Monk And Robot Series, Melissa Moore

Honors Theses

As technology advances and the environment deteriorates, the way people view the relationships between technology, wilderness, and humans becomes essential for society to move forward. To investigate perceptions about technology’s place in an environmentally conscious society, this project examines manifestations of wilderness/wildness and technology in Becky Chambers’ Monk and Robot series through the lens of ecocriticism. Using Timothy Morton's concept of the ecological thought as a framework for analysis, the circumstances present in the novel suggest that the triangle separating humans, wilderness, and technology has actually collapsed, replaced by an enmeshment of technology, wilderness, and humanity.

Visualizing And Evaluating Binary Classifier Performance With Contingency Space, Colin D. Kehoe, Azim Ahmadzadeh

Undergraduate Research Symposium

Traditional metrics for evaluating binary classifiers, such as Accuracy, F1 Score, and True Skill Statistic (TSS), often obscure the underlying tradeoffs between true positive and true negative performance—particularly in imbalanced or high-stakes domains. This poster introduces the Contingency Space, a two-dimensional representation of classifier behavior defined by true positive rate (TPR) and true negative rate (TNR). Within this space, scalar performance metrics become geometric surfaces, revealing how scores vary across the entire landscape of possible classifier outputs.

We present a Python package that implements this framework, enabling users to map model predictions into the Contingency Space, visualize metric surfaces …

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 …

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 …

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 …

Tests Without Borders: A Global Approach To Measuring Visualization Literacy, Olivia A. Guess

McKelvey School of Engineering Graduate Student Theses & Dissertations

Visualization literacy assessments shape how we understand people's ability to interpret data, yet most existing instruments embed Western datasets and assumptions that limit their relevance for global audiences. This thesis argues that because data is personal, assessments must also be culturally grounded. We introduce a unified framework for adapting the Mini-VLAT into 22 regionally responsive short-form assessments, each retaining the structure of the original test while incorporating datasets and scenarios tailored to specific regions around the world. To demonstrate how such adaptations can be customized and validated, we present a detailed case study of a Ghana-adapted Mini-VLAT, developed in collaboration …

Is Ai Replacing Human Mental Health Professionals?, Michiko Ueda

Population Health Research Brief Series

An increasing number of people are turning to generative artificial intelligence (AI) tools and AI-assisted chatbots to manage mental health concerns. This data slice presents findings from a national survey of U.S. adults aged 18-49 (N = 1,805) conducted in October 2025. Among respondents, 35.2% reported using AI tools more than once a week for mental health support. Among those who had ever seen a human mental health professional, 28.4% reported visiting human providers less often since beginning to use AI for the same purpose. The findings suggest that a subset of users may be using AI to replace, rather …

Advancing Cybersecurity Practice: Explainable Machine Learning For Network Intrusion Detection, Adam Grabowski, Shengjie Xu

Journal of Cybersecurity Education, Research and Practice

This research investigates explainable artificial intelligence (XAI) integration within machine learning (ML)-based intrusion detection systems (IDS), focusing on distinguishing malicious from benign network activities. We employed Random Forest and XGBoost models evaluated on widely recognized datasets, including NSL-KDD and UNSW-NB15, using both binary and multi-class classification tasks. The objective was to enhance cybersecurity operations through improved model transparency and interpretability. By integrating SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-Agnostic Explanations), the study offers comprehensive global and local insights into model decision-making processes. Results demonstrate SHAP's effectiveness in providing a broad, dataset-wide understanding of feature interactions and importance, while …

Cybercamp: An Experience Report On The Transformations Of An Intensive Cybersecurity Summer Camp For High School Students, Jose R. Ortiz Ubarri, Kariluz Dávila Diaz Ph.D., Rafael A. Arce Nazario

Journal of Cybersecurity Education, Research and Practice

The Cybercamp is a Cybersecurity summer camp for high school students that has been held for the last nine years at a Hispanic Serving Institution. Since its inception in 2016 the Cybercamp has undergone several transformations in response to budget reductions and the COVID pandemic, to finally become its current version: a rich, hands-on learning experience that we believe is easily replicable even in resource-challenged environments.

In this paper, we document the transformations of the Cybercamp and discuss the developed curriculum and materials in hopes that others will reuse, adapt, and improve upon them. In the Cybercamp, we apply active …

Stability Analysis Of Thermohaline Convection With A Time-Varying Shear Flow Using The Lyapunov Method, Kalin Kochnev

Honors Scholar Theses

This work applies the Lyapunov method to identify instabilities and compute the growth rate of a linear time-varying system. The linear system studied describes cold fresh water on top of hot salty water with a periodically time-varying background shear flow. A time-dependent weighting matrix is employed to construct a Lyapunov function candidate. The resulting linear matrix inequalities are discretized in time using the forward Euler method. As the number of temporal discretization points increases, the growth rate predicted by the Lyapunov method or Floquet theory, used for comparison, will converge to the same value obtained from numerical simulations. Furthermore, the …

Achieving More Accurate And Interpretable Fraud Detection With Double Machine Learning, Jeremy Andrew Berry

Theses and Dissertations

Fraud detection remains a critical challenge across industries such as insurance, healthcare, finance, and government. Global losses from fraud and financial crime are estimated in the trillions annually, including billions in healthcare and insurance fraud alone. While effective for prediction, traditional machine learning methods often lack causal interpretability and struggle to adapt to evolving fraud tactics. This dissertation investigates the application of Double Machine Learning (DML), an emerging causal inference technique, to enhance both the accuracy and interpretability of fraud analytics. The research compares DML against established causal inference approaches, leveraging a meta-learning framework to evaluate model performance on accuracy, …

Patterns Of Llm Weaponization: A Comparative Analysis Of Exploitation Incidents Across Commercial Ai Systems, George Antoniou

Faculty and Staff Publications & Presentations

This comparative study examines patterns of Large Language Model (LLM) weaponization through systematic analysis of four major exploitation incidents spanning 2023-2025. While existing research focuses on isolated incidents or theoretical vulnerabilities, this study provides the first comprehensive comparative framework analyzing exploitation patterns across state-sponsored cyber-espionage (Anthropic Claude incident), academic security research (GPT-4 autonomous privilege escalation), social engineering platforms (SpearBot phishing framework), and underground criminal commoditization (WormGPT/FraudGPT ecosystem). Through comparative analysis across eight dimensions—adversary sophistication, target selection, exploitation techniques, autonomy levels, detection evasion, attribution challenges, defensive gaps, and capability democratization—this research identifies critical cross-case patterns informing defensive prioritization. Findings reveal three …