Computer Sciences Commons^™

The Effects Of Ai Tutors On Beginner Programmers*, Karan Swansi

Campus Research Month

Generative AI’s ability to solve coding problems has raised concerns about Computer Science (CS) education. However, recent research has shown promise in its ability to tutor students. Specifically, The literature does not tend to adequately preserve desirable difficulties, such as active recall or higher-order thinking. And when they do, they use self-reporting instead of experiments to measure the effectiveness of the AI tutor.

Our research will address this significant research gap by using a no-code AI tutor to preserve desirable difficulties, and a randomized control experiment followed by a post-test to obtain strong evidence that AI can be an effective …

Looking Good: The Math Behind Computer Vision*, Corbin Weiss

Campus Research Month

Exploring the mathematical foundations of a Multilayer Perceptron (MLP), a foundational approach to computer vision. Then expanding this understanding to create a visualization of the representation of reality in the MLP.

The Fear Of Replacement: How Ai Panic In Journalism Mirrors Existential Crisis In Industry, James Hutson

Faculty Scholarship

This study systematically examines the portrayal of artificial intelligence (AI) errors, such as hallucinations and deepfakes, in journalistic contexts, evaluating whether these narratives reflect a broader existential anxiety about AI's role in reshaping journalism. Using a systematic literature review combined with a qualitative content analysis of recent AI-focused news reports, this study identifies recurring themes in media coverage to assess the accuracy and context of reported AI errors relative to actual technological limitations and affordances. Findings suggest that while AI errors are comparatively rare, they receive amplified coverage, often fueling public mistrust in AI technologies. Nevertheless, a balanced examination reveals …

Dictating The Divine: Revisiting Authorship, Intention, And Authority From Sacred Texts To Generative Ai, James Hutson, W. Travis Mcmaken

Faculty Scholarship

This article interrogates the historical practice of mediated authorship in religious texts to draw critical parallels with contemporary debates surrounding generative artificial intelligence (AI), specifically large language models (LLMs). By juxtaposing the mediated authorship of sacred texts, such as the Hebrew Bible and New Testament—where figures like the Apostle Paul dictated theological concepts to scribes who infused these directives with their interpretive insights—with the generative processes of LLMs, this research underscores the shared dynamics of co-constructed authorship across historical and technological contexts. Employing interdisciplinary methodologies from art history, textual studies, and reception theory, as well as theological and biblical studies, …

Learning Parent Strategies: A Trajectory-Based Approach To Analyzing Parent Child Interactions With Llms, Chelsea Joe

Computer Science Senior Theses

Recent advancements in large language models (LLMs) have demonstrated their ability to leverage its immense world knowledge to excel in traditional reinforcement learning tasks. Building on these capabilities, we introduce a framework that uses LLMs to learn from human behavior video data and generate insights that serve as guidelines for predicting how individuals are likely to act. Our framework focuses on parent- child dialogic reading, with an emphasis on understanding each parent’s unique parenting strategies. The system identifies meaningful interaction episodes within analyzed video data. The learning component of the framework utilizes a long-term memory system, which stores and retrieves …

Ai Foundations And Applications: Summary Of A Panel Discussion At Loyola University Chicago, George K. Thiruvathukal, Dmitry Dligach, Shilpika, Michael B. Burns, Joseph Vukov, Fraser Turner, Mary Usher

Computer Science: Faculty Publications and Other Works

This document summarizes the panel discussion titled "AI Foundations and Applications," held at Loyola University Chicago as part of the "Forum on Global Affairs: Artificial Intelligence in a Globalized World" series. The panel brought together interdisciplinary experts to discuss the foundational aspects of artificial intelligence (AI), its applications, ethical considerations, and implications for education and society.

Bringing Different Disciplines And Competitions In Your Classroom, Eric Chan-Tin, Mohammed Abuhamad

Computer Science: Faculty Publications and Other Works

It is well-known that cybersecurity does not belong only to computer science/engineering. Other disciplines such as Psychology, Criminal Justice, Sociology, and Political Science can have a great impact in cybersecurity research and education. Students taking only courses are at a disadvantage and should be encouraged to participate in cybersecurity competitions to obtain real-world skills. This lightning talk will look at incorporating two aspects in an interdisciplinary cybersecurity program/curriculum: 1) different disciplines and majors such as Psychology, Criminal Justice, Political Science, Sociology into the cybersecurity program; and 2) including cybersecurity competitions as an integral part of the cybersecurity classroom and curriculum. …

48 - Improving Worship Experience: A Secure Application For Generating Worship Questions Using Ai, Hind Aldabagh, Rhys Ferris

Undergraduate Research Symposium

Improving worship Experience: A Secure application for generating worship questions using AI

Rhys Ferris

Under the direction of Hind Aldabagh, School of Cybersecurity

Generating discussion questions for family worship time during the week based on sermon notes presents an innovative and helpful tool to assist pastors in developing worship questions. Instead of using ChatGPT, hosting a small AI model with Mistral provides an alternative solution that better suits our project.

Using prompt engineering, a custom prompt was created within the statement of faith to guide the AI in reading the text file of the sermon notes. The front end consists …

47 - Enhancing Patient Experience: A Secure Self-Service Kiosk For Prescription Status In Pharmacies, Raneem Alarian

Undergraduate Research Symposium

Creating secure and dependable pharmacy kiosk systems is essential for improving both patient satisfaction and the overall efficiency of pharmacy operations. Patients often experience frustration due to long wait times at the pharmacy counter, especially when prescriptions are not ready. As a licensed pharmacy technician, I have witnessed this issue firsthand, which led me to develop a software solution developed to improve pharmacy workflow. This project focuses on the design and execution of a client-server application for a self-service pharmacy kiosk, enabling patients to securely check the status of their prescriptions before they reach the counter. Developed using Visual Studio …

Ai In Academia: Supportive Ally Or Cheating Accomplice?, Ian Offner

INSPIRE Student Research and Engagement Conference

• The purpose of this study was to investigate student attitudes toward the use of AI for college class work in a variety of domains.
• For some situations, the use of the AI was collaborative. The students would have to utilize their own abilities in conjunction with the AI as a co-intelligence. For some situations, the AI was a dominant agent, requiring little input from the students.

Ai Isn’T What We Should Be Worried About – It’S The Humans Controlling It, Billy J. Stratton

English and Literary Arts: Faculty Scholarship

Stratton examines depictions of AI in popular media and literature, drawing comparisons to real-world AI and humanity's capacity to harness technology for good or ill.

Evaluating Wrist Placement And Signal Processing Techniques For Real-World Hrv Monitoring Using Ppg, Andrew Murphy

College of Computing and Digital Media Dissertations

This thesis investigates trade-offs between signal quality and data coverage in photoplethysmographic (PPG) heart rate variability (HRV) monitoring using wrist-worn devices. The goal was to evaluate whether wrist placement and signal processing techniques can improve measurement reliability in real-world conditions. Data was collected from healthy participants wearing smartwatches on both wrists during rest and a structured math task introducing natural wrist movement. Three distinct processing methodologies were compared, including a proposed Rolling-Standardized Derivative (RSD) approach. Results showed that while HRV signals from both wrists were highly correlated at rest, motion caused a measurable drop in signal quality and inter-wrist agreement, …

Simplifying 3d Printing Using Natural Language Processing, Jared E. Rosenberger

Undergraduate Theses

3D printing is a crucial technology with many applications in different fields. To be able to use this technology to its full extent, expertise in computer aided design (CAD) technology and 3D modeling is required. Many people interested in 3D printing do not have this expertise and thus cannot build custom models, and are consequently forced to buy them instead. Natural language processing (NLP) is one tool that can vastly simplify 3D modeling for those lacking CAD experience. Using NLP, someone can simply dictate what they want to be able to print, and a computer can then build a 3D …

From Adversarial Attacks To Robust Classifiers - A Study In Social Media Spam Detection - Black Box & White Box, Jonathan Jose Penaloza Rumie

Undergraduate Theses

Adversarial attacks pose a significant threat to the reliability of machine learning-based spam detection systems in social media. This undergraduate thesis, "From Adversarial Attacks to Robust Classifiers: A Study in Social Media Spam Detection – Black Box & White Box," systematically examines the impact of both black-box and white-box adversarial attacks on a range of spam classifiers, including Logistic Regression, Decision Trees, Random Forests, K-Nearest Neighbors, Bagging, Gradient Boosting, and Support Vector Machines. Leveraging a novel dataset derived from Twitter spam messages and enhanced with adversarial perturbations such as synonym replacement and character-level modifications, this study evaluates classifier performance under …

Closing Remarks, Jay Yang

Value and Responsibility in AI Technologies

Closing remarks from director of Gonzaga's Institute for Informatics and Applied Technology, Dr. Jay Yang, with a reception to follow.

36 - Investigation Of The Digital Footprint Of Scientific Research In Social Media – Preliminary Findings, Lee Logan, Dominik Soos, Sean Baker, Jian Wu

Undergraduate Research Symposium

Title: Investigation of The Digital Footprint of Scientific Research in Social Media – Preliminary Findings

Authors: Lee Logan, Sean Baker, Dominik Soos, Jian Wu

The spread of scientific information and research beyond the confines of academic institutions plays a central role in how the public understands and trusts modern sciences. Social media has become an essential means of dissemination for scholarly news, papers, and other forms of engagement. This research aims to explore how scientific research is disseminated over social media to understand its role as a bridge between peer-reviewed research and the public's overall understanding. To support the research …

32 - Nested Two Level Decomposition For Quantum Computing, Andrew Maciejunes, John Stenger, Dan Gunlycke, Nikos Chrisochoides

Undergraduate Research Symposium

Abstract—We present a two-level decomposition strategy for solving the Vehicle Routing Problem (VRP) using the Quantum Approximate Optimization Algorithm (QAOA). A Problem-Level Decomposition (PLD) partitions a 9-node (72-qubit) VRP into smaller Traveling Salesman Problem (TSP) instances. Each TSP is then further simplified via Circuit-Level Decomposition (CLD), enabling execution on near-term quantum devices. Our approach achieves up to 90% reductions in circuit depth and qubit count. These results demonstrate the feasibility of solving VRPs previously too complex for quantum simulators and provide early evidence of potential quantum utility.

Highly Regenerable Magnetic Sulfonated Chitosan Crosslinked With Glutaraldehyde Composite Beads (Iron Sand/Naso3-Chi-G) For Aqueous Mercury Removal, Fathurrahmi Fathurrahmi, Rahmi Rahmi, Lelifajri Lelifajri, Anggun Sixthia Wulan Ayu, Muhammad Iqhrammullah

Karbala International Journal of Modern Science

We developed a novel adsorbent from sulfonated, glutaraldehyde-crosslinked chitosan embedded with magnetic iron sand. The adsorbent was synthesized through a two-step process: (1) sulfonation with N(SO₃Na)₃ to introduce sulfonate groups, and (2) crosslinking with glutaraldehyde to enhance structural stability. The optimal formulation, containing 43.5% iron sand and crosslinked with 0.17 M glutaraldehyde, exhibited the highest Hg²⁺ adsorption capacity (30.74 mg/g) at pH 3. The adsorbents were characterized using Scanning Electron Microscopy (SEM), Fourier transform infra-red spectroscopic (FT-IR), and X-ray diffraction (XRD) techniques. Adsorption equilibrium was achieved within 60 minutes, and isotherm modeling showed that the process followed the Freundlich model …

Neutrosophic Automata And Its Algebraic Properties, Anil Kr. Ram, Anupam K. Singh

Neutrosophic Systems with Applications

This research endeavors to elucidate the interrelationships among various classes of operators, including neutrosophic successor/neutrosophic source/neutrosophic core operators of neutrosophic automata based on neutrosophic resituated lattices. Furthermore, it delves into the characterization of algebraic properties such as neutrosophic subsystem, neutrosophic connectivity, and neutrosophic separability of a neutrosophic automaton using these operators. Finally, we study the concepts of neutrosophic primaries of the given neutrosophic automata using neutrosophic core operators.

An Approach For Hybridizing N-Subalgebra With Quantified Neutrosophic Set Using G-Algebra, Neha Andaleeb Khalid, Muhammad Saeed

Neutrosophic Systems with Applications

Neutrosophic sets are a generalized form of fuzzy sets as well as intuitionistic fuzzy sets, as they address the uncertainty factor as an independent component along with truthfulness and falsity. However, traditional neutrosophic approaches often struggle with effectively managing and quantifying indeterminate elements in complex algebraic structures. To address this limitation, this paper employs an expanded version of the neutrosophic set, incorporating a subalgebra. The proposed research is multifaceted: firstly, the new concept of N-Subalgebra (NSU) is proposed. This is the modified setting in the family of subalgebras whose proposed name is the representation of the author's initial name. Secondly, …

A Neutrosophic Micro Vague Correlation Measure: Application To Multi-Criteria Decision Making Problems, Vargees Vahini T, Trinita Pricilla M

Neutrosophic Systems with Applications

Statistical methods called correlation measures are employed to express the degree of association or relationship between two variables. The correlation coefficient which may be computed in a variety of ways is the most often used kind of correlation measure in many disciplines including biology, psychology, economics, and finance. Knowing the correlations between variables is essential for analysis and decision-making. This paper aims to commence a novel type of correlation measure called Neutrosophic Micro vague Correlation Measure and Neutrosophic Micro Vague Weighted Correlation Measure. Further demonstrates the implementation of the Neutrosophic Micro Vague correlation measure in the MCDM Problem. By adopting …

Improved Estimator For Population Mean Utilizing Known Medians Of Two Auxiliary Variables Under Neutrosophic Framework, Rajesh Singh, Shobh Nath Tiwari

Neutrosophic Systems with Applications

In the context of classical statistics, the estimation of the population mean is done with determinate, precise, and crisp data when auxiliary information is available. However, there are instances where dealing with uncertain, indeterminate, and imprecise data in interval form is required. To overcome this issue, Florentin Smarandache introduced neutrosophic statistics as a novel approach. This paper introduces a neutrosophic modified ratio-cum-product log-type estimator for the estimation of the population mean using known medians of two auxiliary variables in the neutrosophic context. The bias and mean squared error (MSE) for the proposed estimators are computed to the first-order approximation. The …

Enhancing Smart City Management With Ai: Analyzing Key Criteria And Their Interrelationships Using Dematel Under Neutrosophic Numbers And Mabac For Optimal Development, Asmaa Elsayed, Mai Mohamed

Neutrosophic Systems with Applications

Purpose: This paper explores the transformative role of AI across various domains of smart cities, including urban mobility, energy management, public safety, healthcare, environmental monitoring, economic development, and data management. It aims to develop a novel decision-making framework that integrates AI technologies with a hybrid approach to analyze the interrelationships among smart city components.

Methodology: This paper employs a hybrid decision-making framework that combines the Decision-Making Trial and Evaluation Laboratory (DEMATEL) method with single-valued trapezoidal neutrosophic numbers (STrNN). This approach is used to analyze the complex relationships among criteria and sub-criteria in smart city contexts, addressing uncertainty and incomplete information …

A Reconsideration Of Advanced Concepts In Neutrosophic Graphs: Smart, Zero Divisor, Layered, Weak, Semi, And Chemical Graphs, Takaaki Fujita, Florentin Smarandache

Neutrosophic Systems with Applications

One of the most powerful tools in graph theory is the classification of graphs into distinct classes based on shared properties or structural features. Over time, many graph classes have been introduced, each aimed at capturing specific behaviors or characteristics of a graph. Neutrosophic Set Theory, a method for handling uncertainty, extends fuzzy logic by incorporating degrees of truth, indeterminacy, and falsity. Building on this framework, Neutrosophic Graphs [9, 84, 135] have emerged as significant generalizations of fuzzy graphs. In this paper, we extend several classes of fuzzy graphs to Neutrosophic graphs and analyze their properties.

Mbj-Neutrosophic Structure Applied To Bp-Algebras: Bp-Subalgebras And Α-Ideals, Bavanari Satyanarayana, Shake Baji, Anjaneyulu Naik K.

Neutrosophic Systems with Applications

In this article, we introduce the concepts of MBJ-neutrosophic BP-subalgebras and MBJ-neutrosophic α-ideals in BP-algebra by applying MBJ-neutrosophic logic to algebraic structure BP-algebra. We prove that the intersection of two MBJ-neutrosophic α-ideals and the inverse image of an MBJ-neutrosophic α-ideal are also MBJ-neutrosophic α-ideals. Furthermore, we prove an MBJ-neutrosophic set is an MBJ-neutrosophic BP-subalgebra if and only if its level sets are BP-subalgebras.

Einstein Aggregate Operators Under Q-Rung Orthopair Fuzzy Hypersoft Sets With Machine Learning, Muhammad Gulistan, Muhammad Abid

Neutrosophic Systems with Applications

Thailand with its impressive 15.5% global share of renewable energy production, has a small 1% share of bitcoin mining. At the same time, the country is dealing with the severe effects of climate change, which emphasizes the necessity of taking proactive steps to solve environmental issues. This research integrates machine learning techniques and Einstein Aggregate Operators under q-rung orthopair fuzzy hypersoft set (q-ROFHS)-based multi-criteria decision-making technique to present a new method for analyzing CO₂ impacts and mitigation solutions in Thailand. We evaluate the environmental impacts of bitcoin mining and the incorporation of renewable energy sources using an interdisciplinary framework, …

Some Graph Parameters For Superhypertree-Width And Neutrosophictree-Width, Takaaki Fujita, Florentin Smarandache

Neutrosophic Systems with Applications

Graph characteristics are often studied through various parameters, with ongoing research dedicated to exploring these aspects. Among these, graph width parameters—such as treewidth—are particularly important due to their practical applications in algorithms and real-world problems. A hypergraph generalizes traditional graph theory by abstracting and extending its concepts [77]. More recently, the concept of a SuperHyperGraph has been introduced as a further generalization of the hypergraph. Neutrosophic logic [133], a mathematical framework, extends classical and fuzzy logic by allowing the simultaneous consideration of truth, indeterminacy, and falsity within an interval. In this paper, we explore Superhypertree-width, Neutrosophic treewidth, and t-Neutrosophic tree-width.

Solving N-Players Continuous Differential Games Under Neutrosophic Environment, M. G. Brikaa

Neutrosophic Systems with Applications

Uncertainty plays a crucial role in decision-making problems, particularly in game theory. Various forms of uncertainty have been explored in the literature, including fuzzy, soft, rough, and interval-based approaches. Game theory has been extensively studied under these uncertainty models, with researchers addressing vagueness, and imprecision from multiple perspectives. More recently, neutrosophic sets have emerged as an alternative framework for handling uncertainty. Neutrosophic numbers effectively incorporate indeterminacy in decision-making by considering factors such as intuition, assumptions, judgment, behavior, evaluation, and preferences of decision-makers. This paper presents a novel approach to solving a new class of n-player continuous differential games within a …

Enhancing State-Of-The-Art Motor Imagery Classification With Reinforcement Learning, Anton Shepelev

USF Tampa Graduate Theses and Dissertations

One of the key obstacles to the rapid adoption of non-invasive Brain-Computer Interfaces (BCIs) for Motor Imagery (MI) is the low signal-to-noise ratio, and the substantial data requirements which can be mentally taxing for users. EEGNet, a compact Convolutional Neural Network (CNN), has long been considered the state-of-the-art (SOTA) for MI classification, demonstrating strong performance even with limited data. However, recent studies advocate for integrating Deep Reinforcement Learning (RL) to further enhance classification accuracy by dynamically optimizing feature extraction and decision-making processes. Despite this potential, practical implementations remain scarce due to challenges in stabilizing RL training and adapting it to …

A Neutrosophic Micro Vague Correlation Measure: Application To Multi-Criteria Decision Making Problems, Vargees Vahini T, Trinita Pricilla M

Neutrosophic Systems with Applications

Statistical methods called correlation measures are employed to express the degree of association or relationship between two variables. The correlation coefficient which may be computed in a variety of ways is the most often used kind of correlation measure in many disciplines including biology, psychology, economics, and finance. Knowing the correlations between variables is essential for analysis and decision-making. This paper aims to commence a novel type of correlation measure called Neutrosophic Micro vague Correlation Measure and Neutrosophic Micro Vague Weighted Correlation Measure. Further demonstrates the implementation of the Neutrosophic Micro Vague correlation measure in the MCDM Problem. By adopting …