Digital Commons Network^™

Generating More Equitable Fair Use, Jacqueline Kessel

Pepperdine Law Review

From advancing healthcare and education to threatening democratic systems, generative artificial intelligence (AI) has demonstrated a capacity to positively and negatively impact society. And these benefits and consequences are not shared equitably. Copyright law, however, stands as a powerful mechanism in monitoring AI system development. Several complaints have charged generative AI system developers with copyright infringement, alleging that (1) ingesting copyrighted works as training data infringes the copyright owner’s exclusive right to reproduce works in copies and (2) generating AI outputs infringes the exclusive right to prepare derivative works because the outputs are based upon the works on which the …

Meet Atu Intro, Caleb Urbani, Darlene Matamoros, Dena Paw, Jean Caballero

ATU Scholars Symposium

Meet ATU is our app designed to improve a student’s network and campus experience. Specifically made for students at Arkansas Tech University, Meet ATU allows students to connect and engage with their classmates easily. Students can add classes to their profiles using a course reference number. Students can also personalize their profiles to help them find other students to connect with within their enrolled classes. Meet ATU encourages students to communicate and collaborate with others through the messaging page. This would help students grow their network. The app will also include a leaderboard page that tracks points earned through various …

Self-Supervised Learning And Its Applications In Medical Image Analysis, Siladittya Manna

Doctoral Theses

Self-supervised learning (SSL) enables learning robust representations from unlabeled data and it consists of two stages: pretext and downstream. The representations learnt in the pretext task are transferred to the downstream task. Self-supervised learning has appli- cations in various domains, such as computer vision tasks, natural language processing, speech and audio processing, etc. In transfer learning scenarios, due to differences in the data distribution of the source and the target data, the hierarchical co-adaptation of the representations is destroyed, and hence proper fine-tuning is required to achieve satisfactory performance. With self-supervised pre-training, it is possible to learn repre- sentations aligned …

Analysis And Monitoring Of A Robotics Curriculum: Are Simnow Modules Valuable?, Jacob Applegarth, Ibrahim Baida, Anthony Iacco, Ngan Nguyen, Nathan Novotny

Posters

No abstract provided.

One Size Doesn’T Fit All: Towards Design And Evaluation Of Developmentally Appropriate Parental Control Tool, Prakriti Dumaru, Mahdi Nasrullah Al-Ameen

Computer Science Student Research

As children progress through developmental stages, they undergo substantial biological, cognitive, and social changes, creating unique needs for online safety across different age groups (e.g., young children, tweens, teens). The existing parental control tools fail to account for these differences, leaving a notable gap in the literature on parental mediation. To this end, we conducted 10 focus group sessions with a total of 20 parents to understand their preferences for age-appropriate design components that promote self-regulation and open communication, followed by an ideation workshop with four UX design experts to translate these preferences into customized features. We then evaluated these …

Exploring The Impacts Of An Adaptive Haptic Heartbeat Within A Socially Assistive Robot, Jade Thompson

Honors Theses

This research investigates the therapeutic effects of an adaptive haptic heartbeat within Therabot, a stuffed robotic dog. A simulated haptic heartbeat that adjusts its own speed based on user heart rate was developed for integration within Therabot. A user study evaluated the effects of various heartbeat behaviors on user experiences with Therabot, with respect to improvements in self-reported state anxiety, physiological improvements, and perceptions of the robot. A relationship was found between improvements in self-reported state anxiety and positive opinions of Therabot, regardless of condition. Additionally, differences were found between conditions with respect to improved aspects of state anxiety, with …

Autonomous Intelligence In Fashion: A Comprehensive Analysis Of Agentic Ai Across The Fashion Ecosystem, Andrew Burnstine

Faculty and Staff Publications & Presentations

The fashion industry is undergoing a paradigm shift with the emergence of agentic artificial intelligence (AI), a sophisticated class of intelligent systems exhibiting autonomous decision-making, continuous learning, and adaptive action with minimal human intervention. Moving beyond traditional AI applications in fashion focused on predictive analytics, generative tools, and supervised automation, agentic AI introduces a transformative paradigm wherein intelligent agents proactively navigate the complexities inherent in design, manufacturing, supply chain optimization, and consumer personalization. This paper presents a comprehensive exploration of the evolving role of agentic AI across the multifaceted fashion ecosystem, offering an in-depth analysis of its technological underpinnings, operational …

Fact-Based Counter Narrative Generation To Combat Hate Speech, Brian Wilk, Homaira Huda Shomee, Suman Kalyan Maity, Sourav Medya

Computer Science Faculty Research & Creative Works

Online hatred has become an increasingly pervasive issue, affecting individuals and communities across various digital platforms. To combat hate speech in such platforms, counter narratives (CNs) are regarded as an effective method. In recent years, there has been growing interest in using generative AI tools to construct CNs. However, most of the generative models produce generic responses to hate speech and can hallucinate, reducing their effectiveness. To address the above limitations, we propose a counter narrative generation method that enhances CNs by providing non-aggressive, fact-based narratives with relevant background knowledge from two distinct sources, including a web search module. Furthermore, …

The Attitudes And Perspectives Of Laboratory Professionals On The Use Of Machine Learning Combined With Maldi For Viral Identification: A Qualitative Study, Grace Johnson

Honors Projects

The use of matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) with machine learning (ML) has been proposed by numerous studies as a novel approach for viral identification. However, the development and implementation of this instrumentation is still in its early stages, and laboratory professionals' perspectives on its feasibility, accuracy, implementation, and effect on current laboratory operating procedures remain underexplored.

This study aimed to investigate laboratory professionals’ attitudes and opinions regarding the use of MALDI-TOF-MS coupled with machine learning for viral identification, focusing on perceived benefits, barriers, and factors that would affect participants’ opinions on implementation.

A qualitative descriptive research …

Cascading Effects: Analyzing Project Failure Impact In The Maven Central Ecosystem, Mina Shehata

SPARK Symposium Presentations

Abstract—This study examines failure propagation patterns within the Maven Central ecosystem, a critical software de- pendency repository, through comprehensive analysis of dependency networks using the Goblin framework. Our dual-sampling methodology, investigating both top dependencies and random libraries, revealed two distinct failure propagation patterns that pose significant risks to ecosystem stability. Core infrastructure failures, particularly evident in cases like the AWS SDK family with 429,800 total dependencies, create immediate and widespread disruption, affecting an average of 20,402 dependent projects and propagating through dependency chains averaging 90.80 levels deep.

Our analysis of peripheral projects reveals their significant cascading effects, with higher average …

Real-Time Active-Learning Method For Audio-Based Anomalous Event Identification And Rare Events Classification For Audio Events Detection, Farkhund Iqbal, Ahmed Abbasi, Ahmad Almadhor, Shtwai Alsubai, Michal Gregus

All Works

Introduction: Audio event detection, the application of scientific methods to analyze audio recordings, can be helpful in examining and analyzing audio recordings to preserve, analyze, and interpret sound evidence. Furthermore, it can be helpful in safety and compliance, security, surveillance, maintenance, and predictive analysis. Audio event detection aims to recover meaningful information from audio recordings, such as determining the authenticity of the recording, identifying the speakers, and reconstructing conversations. However, filtering out noise for better accuracy in audio event detection is a major challenge. A greater sense of public security can be achieved by developing automated event detection systems that …

Cyber Safety: Protecting Yourself Online, Laxima Niure Kandel, Kayla D. Taylor, Bhawana Poudel, Helen Hernandez

Graduate Student Works

The IEEE Women in Engineering (WIE) Affinity Group of Daytona hosted a cybersecurity awareness event on Saturday, April 26, 2025, at the Port Orange Regional Library. The session was designed specifically to help seniors in Volusia County learn how to protect themselves online, avoid scams, create strong passwords, and safely navigate the digital world.

Systemization Of Knowledge (Sok): Goals, Coverage, And Evaluation In Cybersecurity And Privacy Games, Yue Huang, Marthie Grobler, Lauren S. Ferro, Georgia Psaroulis, Sanchari Das, Jing Wei, Helge Janicke

Research outputs 2022 to 2026

This paper systematized existing knowledge on cybersecurity and privacy game-based approaches, exploring their goals, scope, and evaluation methods. Our review of 93 academic papers revealed that these approaches serve multiple purposes and target diverse player types. We identified 11 key aspects of cybersecurity and privacy that these approaches addressed, such as threats, defensive strategies, and data privacy. Additionally, we analyzed the effectiveness evaluation methods of these approaches, emphasizing the connections between evaluation techniques, types of data used, and their alignment with the approaches' goals. We also summarized the aspects of user experience evaluated in the literature and the types of …

Autoradai: A Versatile Artificial Intelligence Framework Validated For Detecting Extracapsular Extension In Prostate Cancer, Pegah Khosravi, Shady Saikali, Abolfazl Alipour, Saber Mohammadi, Maxwell Boger, Dalanda M. Diallo, Christopher J. Smith, Marcio C. Moschovas, Iman Hajirasouliha, Andrew J. Hung, Srirama S. Venkataraman, Vipul Patel

Publications and Research

Preoperative identification of extracapsular extension (ECE) in prostate cancer (PCa) is crucial for effective treatment planning, as ECE presence significantly increases the risk of positive surgical margins and early biochemical recurrence following radical prostatectomy. AutoRadAI, an innovative artificial intelligence (AI) framework, was developed to address this clinical challenge while demonstrating broader potential for diverse medical imaging applications. The framework integrates T2-weighted MRI data with histopathology annotations, leveraging a dual convolutional neural network (multi-CNN) architecture. AutoRadAI comprises two key components: ProSliceFinder, which isolates prostate-relevant MRI slices, and ExCapNet, which evaluates ECE likelihood at the patient level. The system was trained and …

The Role Of Ai In Risk Management: Benefits, Challenges, And Adoption Strategies, Lukas Ludwig

Honors Projects in Information Systems and Analytics

This study explores the role of artificial intelligence (AI) in risk management, focusing on its integration within business operations. The primary objective of this research is to examine both the potential benefits and associated risks of adopting AI technologies, with a specific emphasis on data security, ethical concerns, and governance. A mixed methodology was employed, combining a comprehensive literature review on AI's applications and limitations with qualitative interviews conducted with professionals from various industries, including risk management, higher education, and IT development. The findings highlight key challenges in AI adoption, such as data privacy issues, bias in AI algorithms, and …

"Exploring The Training Data Landscape For Ai Based Threathunting For Protecting Intellectual Property", Manzi Siibo, Christopher Kreider

Cybersecurity Undergraduate Research Showcase

This study provides a comprehensive evaluation of the effectiveness that would result in the integration of AI into traditional threat hunting systems. To do so, 10-15 scholarly articles and data sets were evaluated to see the results of AI and machine learning threat hunting versus traditional systems. With so many proven benefits of this integration, this paper also explores how it impacts the protection of Intellectual property which is some of the most important forms of information that threat hunting systems aim to protect.

Fictional Failures And Real-World Lessons: Ethical Speculation Through Design Fiction On Emotional Support Conversational Ai, Fayle Kollig, Jessica Pater, Fayika Farhat Nova, Casey Fiesler

Health Services and Informatics Research

Conversational artificial intelligence (CAI), which replicates human-to-human interaction as human-to-machine, is increasingly developed to address insufficient access to healthcare. In this paper, we use design fiction methods to speculate on ethical consequences of CAI that offers emotional support to complement or replace mental healthcare. Through a near-future news article about a fictional, failed CAI, we explore safety and privacy concerns associated with mismatches between what an emotional support CAI is advertised to do, what it technically can do, and how it is likely to be used. We pose the following questions to researchers, regulators, and developers: How might we jointly …

The Role Of Natural Language Processing In Abstract Dataset To Improve Virtual Assistant Devices, Reem Alshahoomi, Salma Alameri, Sanaa Alfalasi, Feras Al-Obeidat

All Works

Natural Language Processing (NLP) has transformed human-computer interaction, especially in the realm of virtual assistants. NLP enables machines to understand, interpret, and generate human language, driving innovations in applications ranging from virtual assistants to customer service chatbots. This paper delves into the intersection of NLP and virtual assistants, examining advanced models like BERT and RoBERTa, which enhance contextual understanding and user intent recognition. Through a comprehensive evaluation using the dataset of research abstracts to explore new methods and improve response for virtual assistant devices, it explores methods to improve model efficiency, precision, and scalability. By leveraging machine learning techniques and …

Navigating Ethical Dimensions In The Metaverse: Challenges, Frameworks, And Solutions, Mousa Al-Kfairy, Saed Alrabaee, Omar Alfandi, Amr Taha Mohamed, Souheil Khaddaj

All Works

The Metaverse is rapidly evolving into a transformative digital ecosystem, bringing with it unprecedented opportunities and a complex array of ethical challenges. This narrative review, based on an in-depth analysis of 105 full publications, explores the key ethical themes associated with the Metaverse, including privacy and data security, identity and behavior, digital inclusivity, mental and physical health, ethical AI, content moderation, intellectual property, governance, environmental sustainability, harassment, cultural representation, and economic implications. Proposed solutions for these challenges encompass privacy-by-design frameworks, robust identity verification systems, equitable access initiatives, explainable AI, and blockchain-based intellectual property protections. Additionally, the review examines governance and …

Using Keystroke Dynamics Behavioral Biometrics To Identify Users, Bradley F. Budach

Research & Creative Achievement Day

This study explores the use of keystroke dynamics as a behavioral biometric for user identification. Unlike physiological biometrics, such as fingerprints or facial recognition, keystroke dynamics leverages the unique typing patterns of individuals to create a distinctive signature. This research was to develop a machine learning-based system that utilizes keystroke dynamics for continuous and unobtrusive user authentication. By collecting and analyzing keystroke data from multiple users, relevant features were extracted and used to train a machine learning model to identify user keystroke signatures with an equal error rate of 0.11. This model allows for reliable and scalable authentication that can …

Plasma Profiling Reveals Proteins Specific To Primary Disease Origin Of Retroperitoneal Fibrosis, Thomas J. Pelowitz, Benjamin Hurr, Matthew Koster, Jaeyun Sung

Research & Creative Achievement Day

Retroperitoneal fibrosis (RPF) is a rare inflammatory disease characterized by the formation of scar-like tissue in the retroperitoneum, which can lead to life-threatening obstructive nephropathy. RPF is typically a secondary disease, arising from various underlying conditions. Currently, no objective and highly accurate diagnostic methods exist. Identifying blood protein biomarkers specific to RPF could facilitate the development of objective minimally invasive diagnostic tests.

In this study, blood plasma samples were collected from 45 participants spanning 5 different primary causes of RPF, including idiopathic cases where no underlying condition was identified. Six participants without significant diseases at the time of sample collection …

Impact Of Containerization On The Performance Web Applications With Docker, Amin Elkhalifa

Research & Creative Achievement Day

This study aims to evaluate the performance impact of running a web application as a Docker container compared to running it natively. As Docker gains popularity in industry, it becomes increasingly important to understand the performance impact of containerization. This study aims to provide data that contributes to the decision-making process of building performance-sensitive applications. Gathering data consisted of building a web application, exposing an API endpoint, running tests and measuring the relevant performance metrics – CPU utilization and network response time – both in a native environment and within a Docker container. These findings confirm the introduction of overhead …

Using Multilayer Perceptron (Mlp) To Predict Crop Yields, Thomas M. Donnelly

Research & Creative Achievement Day

This study aimed to develop a Multilayer Perceptron (MLP) that accurately predicts crop yields within 10% of ground truth in 80% of cases using weather data, region, soil type, temperature, fertilizer, irrigation, days taken to harvest, and rail fall. The dataset has 1 million unique data points and 10 columns. In order to process the data, all Boolean data had to be converted to integers, Numerical data standardized, while Categorical data was checked for non-null values. The model will be trained using a random selection of 90% of the data for training and 10% for testing. The effectiveness of the …

An Implementation And Comparison Of Nat64 Using Ebpf And The Jool Kernel Module., Arvinder S. Dhanoa

Research & Creative Achievement Day

IPv4 exhaustion has been a prevalent problem for years, as organizations and service providers have fought against the scarcity of IPv4 address space on the internet. NAT64 is increasingly deployed as a solution to this problem. As a result, it becomes increasingly important that the deployment of NAT64 technologies is easy and performant. Numerous implementations of NAT64 technologies already exist, and some new implementations use eBPF as well. In this research, we implemented a CLAT with an eBPF TC classifier and compared its performance to Jool, a widely used kernel module. We did this using a series of virtual machines …

Cryptology With Bitcoin And Blockchain Applications, Seth D. Bergmann

OER Textbooks

This book is intended to be used for a first course in cryptography for computer science students. It assumes that the student has had at least one programming course and a discrete structures or discrete math course. This book places an emphasis on algorithms and the internals of cryptographic systems.

The book begins with some classical cryptographic algorithms used for confidentiality. Then it exposes modern cryptographic algorithms for confidentiality, integrity, and authenticity. Both private key (symmetric) and public key (asymmetric) algorithms are covered. This book also describes the workings of the most common cryptocurrency, Bitcoin, as well as blockchain technology. …

Romance Scam Victimization: A Survey-Based Examination Of Financial, Psychological, And Reporting Factors, Ld Herrera

Research & Publications

Romance scams are a growing type of cybercrime in which perpetrators develop and exploit fraudulent romantic relationships with victims to obtain financial resources. These schemes cause substantial economic and psychological damage, yet they are significantly underreported. Official 2022 reports indicate only \$1.3 billion lost to romance scams in the US, but the true financial toll is likely much higher.

Using survey data from 366 victims, this study examines the financial and psychological toll of romance scams, reporting patterns, obstacles to seeking help, and victims' perceptions of received help. Most of the victims (60.9\%) did not seek help from any source, …

A Hybrid Deep Learning-Based Approach For Visual Field Test Forecasting, Ashkan Abbasi, Sowjanya Gowrisankaran, Wei-Chun Lin, Xubo Song, Bhavna Josephine Antony, Gadi Wollstein, Joel Schuman, Hiroshi Ishikawa

Wills Eye Hospital Papers

OBJECTIVE: Longitudinal assessment of visual field (VF) testing is essential in glaucoma management. Conventional VF forecasting methods require numerous prior tests, while deep learning techniques have shown promising results with fewer tests. This study introduces a hybrid deep learning framework to enhance flexibility and accuracy in VF test forecasting.

DESIGN: A retrospective longitudinal study using deep learning-based VF forecasting models.

SUBJECTS AND CONTROLS: A total of 1750 subjects (healthy and glaucoma patients) with 19 437 Humphrey VF (24-2 Swedish Interactive Threshold Algorithm) tests collected from longitudinal glaucoma cohorts at the University of Pittsburgh and New York University.

METHODS: Three deep …

2025 Acssc Program, Acssc Planning Committee

Annual Celebration for Student Scholarship and Creativity

No abstract provided.

Designing A Statistical Plan For Measuring Self-Efficacy Using A 2k Factorial Design​, Rachel A. Hart, Eugene H. Thompson

Mathematics, Computer Science & Statistics Presentations

This study focuses on designing a statistical plan that measures the effects of self-efficacy using a 2k factorial design. Specifically, we simulated data on physical, mental, spiritual, and social health, so we could focus on their interaction with self-efficacy. By using ANOVA to see the main and interaction effects, we can see the impact of individual autonomy on health. Our findings show the need for experimental data on the demographic of interest, peri-and post-menopausal women.

Analyzing The Sentiment Of Feminist And Non-Feminist Works, Jasmine Borie, Megan G. Falschlehner

Mathematics, Computer Science & Statistics Presentations

This presentation focuses on a group of texts that advocate for a change in the current belief system. These texts are the Feminist Manifesto, Sojourner Truth: Ain’t I a Woman?, and Civilization and Its Discontents. These first two texts advocate for women’s rights, while Freud’s book is focused on civilization’s decline and how our understanding of community can affect this. Through our presentation, we want to examine the differences in sentiment and language between the feminist texts and Freud’s texts to pinpoint whether or not sentiment changes when advocating for different beliefs.