Digital Commons Network^™

Demystifying Hardware Formal Verification For Undergraduate Education: A Risc-V Processor Case Study With Coursework Implementation, Riley A. Peters

Master's Theses

Hardware verification engineers apply formal methods to prove that a digital device always behaves according to its specification. This differs from traditional functional verification, in which engineers establish correctness by repeatedly sending test inputs to the device and comparing the outputs against a reference model. With the growing complexity of integrated circuits, the demand for digital verification engineers with formal methods experience has continued to increase. However, California Polytechnic State University: San Luis Obispo's current curriculum lacks dedicated material to prepare students for these roles.

This thesis seeks to address the lack of formal methods material through two efforts. First, …

Designing For Trust In Chat-Based Question Answering Systems: An Exchange-Based Retrieval Approach, Nathan Mccutchen

Master's Theses

Community chat platforms such as Discord and Slack support spontaneous, collaborative communication but make it difficult to retrieve previously discussed information. As conversations accumulate, valuable exchanges become buried, leading to repeated questions and sustained burden on experienced community members.

This work contributes a set of design requirements for question-answering systems operating over unstructured chat data, a Discord bot prototype implementing those requirements named Echo, and an empirical evaluation of how such a system affects user trust. Rather than encoding discrete question-answer pairs or generating synthetic responses with a language model, Echo indexes conversation topics for semantic retrieval and presents results …

Using Ensemble Disagreement To Stabilize Conformal Prediction Under Distribution Shift, Patrick D. Murphy

Master's Theses

Semantic segmentation of eelgrass from drone imagery is crucial for coastal habitat monitoring, restoration, and management, as these habitats continue to see rapid changes due to climate change and human influence. However, the reliability of generalizing a deployed classification model relies on both high-accuracy segmentation as well as robust uncertainty quantification that holds up when conditions change over years or locations. Conformal prediction (CP) is a method that converts a classifier's output into prediction sets with a guaranteed average coverage level for in-distribution data. However, the “vanilla” conformal score can often under-cover in hard or out-of-distribution (OOD) regions under drift. …

Neurosymbolic Counterpoint Generation, Paul D. Jarski

Master's Theses

Recent advancements in generative artificial intelligence have revolutionized music generation, yet research has predominantly focused on raw audio synthesis over music in symbolic form, i.e. a score. This thesis presents the first neurosymbolic model designed to generate imitative Renaissance counterpoint in symbolic (MIDI) format. By leveraging an autoregressive Transformer architecture, this research explores the capacity of deep learning models to manage independent voices and strict stylistic constraints.

We compare multiple data representation strategies with distinct tokenization methods. The proposed model incorporates a symbolic component that enforces fundamental contrapuntal rules. Additionally, this thesis contributes a preprocessed dataset of Renaissance polyphony, in …

Argument-Based Consistency In Toxicity Explanations Of Llms, Ramaravind K. Mothilal, Joanna Roy, Syed Ishtiaque Ahmed, Shion Guha

Health Services and Informatics Research

The discourse around toxicity and LLMs in NLP largely revolves around detection tasks. This work shifts the focus to evaluating LLMs’ reasoning about toxicity—from their explanations that justify a stance—to enhance their trustworthiness in downstream tasks. Despite extensive research on explainability, it is not straightforward to adopt existing methods to evaluate free-form toxicity explanation due to their over-reliance on input text perturbations, among other challenges. To account for these, we propose a novel, theoretically-grounded multi-dimensional criterion, Argument-based Consistency (ArC), that measures the extent to which LLMs’ free-form toxicity explanations reflect an ideal and logical argumentation process. Based on uncertainty quantification, …

An Odd Protocol For An Agent-Based Model Of Hepatitis C Virus Transmission In A Two-Group Structural Heterogeneous Syringe-Sharing Network (M2), Seun Ale, Que Nguyen Dr., John D. Kelleher Prof., Elizabeth Hunter Dr.

Reports

The model described in this ODD is an agent-based model of hepatitis C virus (HCV) transmission among people who inject drugs (PWID). The model extended a baseline homogeneous model by incorporating structural heterogeneity via a two-group interaction framework. The syringe-sharing population in the model is divided into inner and outer circle groups representing individuals with differing levels of syringe-sharing interaction intensity. While all agents share the same syringe-sharing probability and epidemiological processes remain identical across agents, the number of daily interaction opportunities differs between the two groups. Interactions in the model are generated dynamically using proximity-based sampling at each timestep …

An Odd Protocol For An Agent-Based Model Of Hepatitis C Virus Transmission In A Three-Group Structural Heterogeneous Syringe-Sharing Network (M3), Seun Ale, Que Nguyen Dr., John D. Kelleher Prof., Elizabeth Hunter Dr.

Reports

The model described in this ODD is an agent-based model of hepatitis C virus (HCV) transmission among people who inject drugs (PWID). The model incorporates structural heterogeneity through a three-group interaction framework. The syringe-sharing population in the model is divided into core, inner, and outer circle groups representing individuals with high, moderate, and low levels of syringe-sharing interaction intensity, respectively. While the syringe-sharing rate and all epidemiological processes remain identical across agents, the number of daily interaction opportunities differs by agent grouping, capturing variation in structural position within the syringe-sharing network. Interactions are generated dynamically using proximity-based sampling at each …

The Illusion Of Causality In Llms: A Developmentally Grounded Analysis Of Semantic Scaffolding And Benchmark–Capability Mismatches, Daisuke Akiba

Publications and Research

Recent benchmarks increasingly report that large language models (LLMs) exhibit human-like causal reasoning abilities, including counterfactual inference and intervention planning. However, many such evaluations rely on domains that are heavily represented in training data and embed strong semantic cues, raising the possibility that apparent causal competence may reflect semantic pattern recombination rather than structure-sensitive causal reasoning. Drawing on human developmental theories of causal induction, this perspective argues that genuine causal understanding requires robustness to novelty and reliance on conditional structure rather than semantic familiarity. To illustrate the testability of this claim, the paper includes a pilot demonstration using synthetic causal …

Deep Learning Approaches For Anti-Money Laundering On Mobile Transactions: Review, Framework, And Directions, Jiani Fan, Lwin Khin Shar, Ruichen Zhang, Ziyao Liu, Wenzhuo Yang, Dusit Niyato, Kwok-Yan Lam

Research Collection School Of Computing and Information Systems

Money laundering is a financial crime that obscures the origin of illicit funds, necessitating the development and enforcement of anti-money laundering (AML) policies by governments and organizations. The proliferation of mobile payment platforms and smart IoT devices has significantly complicated AML investigations. As payment networks become more interconnected, there is an increasing need for efficient real-time detection to process large volumes of transaction data on heterogeneous payment systems by different operators such as digital currencies, cryptocurrencies, and account-based payments. Most of these mobile payment networks are supported by connected devices, many of which are considered loT devices in the FinTech …

Cylindformer: Image-To-Point Cloud Registration With Cylindrical Transformer, Jingtao Wang, Hao Tang, Yanpeng Sun, Shengfeng He, Zechao Li

Research Collection School Of Computing and Information Systems

Accurate correspondence extraction between distinctive pixel-wise and point-wise features is critical for image-to-point cloud (I2P) registration. Recent efforts leveraging Transformers for I2P feature representation have demonstrated potential, primarily by first capturing intra-modality global contextual dependencies via self-attention, and then learning cross-modality correlations via cross-attention. The strength of vanilla Transformers lies in modeling cross-modality global feature correlations. However, such mechanisms often struggle with the structural disparity between dense image pixels and sparse 3D points, hindering the establishment of fine-grained correspondences. Moreover, global attention may introduce ambiguity, as interactions with many inconsistent regions of intra-modality may degrade feature distinctiveness. To address these …

Private Set Intersection: A Systematic Review, Yunbo Yang, Defan Zhu, Jianting Ning, Qi Feng, Xiaoguo Li, Yuejia Cheng, Guomin Yang, Kui Ren

Research Collection School Of Computing and Information Systems

Various services, such as search engines, are increasingly deployed in cloud-based and distributed systems. However, data are typically managed by trusted servers, making user privacy and data security critical concerns. Private set intersection (PSI) is a powerful cryptographic primitive that enables multiple parties to compute the intersection of their datasets without revealing private inputs. It has been extensively studied over the past two decades, leading to significant gains in computational and communication efficiency. Yet, in many real-world scenarios, revealing the raw intersection may still leak sensitive information. To address this, numerous PSI variants have been developed to meet different application …

Improving Public Transport Through Machine Learning Influence Flow Analysis (Mifa): Southern England Bus Case Study, Benjamin Lee, Wolfgang Garn, Masoud Fakhimi, Nick F. Ryman-Tubb

Research Collection School Of Accountancy

Public transport (PT) is crucial for enhancing the quality of life and enabling sustainable urban development. As part of the UK Transport Investment Strategy, increasing PT usage is critical to achieving efficient and sustainable mobility. This paper introduces Machine Learning Influence Flow Analysis (MIFA), a novel framework for identifying the key influencers of PT usage. Using survey data from bus passengers in Southern England, we evaluate machine learning models. Subsequently, MIFA uncovers that easy payments, e-ticketing, and mobile applications can substantially improve the PT service. MIFA’s implementation demonstrates that strength and importance lead to specific insights into how service characteristics …

Navigating Ethical Considerations And Implications Of Ai Chatbots In Higher Education: A Systematic Review, Ons Al-Shamaileh, Ramy Hammady, Mahmoud Abdelrahman, Omar Mubin

All Works

This systematic review explores the ethical challenges associated with the use of AI-based chatbots in higher education, focusing on their implications for students, educators, institutions, and administrative stakeholders. Following PRISMA guidelines, peer-reviewed literature published between 2014 and 2024 was systematically identified across eight major academic databases, yielding a total of 109 eligible studies. A thematic analysis of the included literature indicates that concerns related to academic integrity are most frequently discussed, alongside recurring issues involving data privacy and security, algorithmic bias, overreliance on automated systems, and the risk of inaccurate or misleading outputs. The findings further demonstrate considerable variation in …

Law Library Blog (March 2026): Legal Beagle's Blog Archive, Roger Williams University School Of Law

Law Library Newsletters/Blog

No abstract provided.

Video Generation Techniques For Novel View Synthesis With Flow-Matching Transformers, Xiuyuan Qiu

Master's Theses

Novel view synthesis (NVS) aims to generate images of a scene from unseen camera viewpoints. Recent work, such as Stable Virtual Camera, shows that large-scale image diffusion models like Stable Diffusion can be adapted for pose-conditioned view synthesis by incorporating video-generation techniques with camera conditioning. In this thesis, we introduce MVFlow, a new NVS model that extends this approach to a different image generation architecture: a flow-matching diffusion transformer, specifically FLUX.1, which has demonstrated strong performance in image synthesis. We evaluate MVFlow under varying input view counts and pose distance settings. Our results show that this architectural transfer is feasible; …

Optimizing And Fortifying Ai Software Through The Lens Of Artifact Synthesis, Jieke Shi

Dissertations and Theses Collection (Open Access)

Artificial Intelligence (AI) has transformed the software landscape, ushering in a new era of intelligent systems that increasingly shape our daily lives. This transformation is evident in various domains, including Software Engineering (SE), where Large Language Models (LLMs) support many development tools, and control systems, where self-driving cars and autonomous drones rely on deep learning models for real-time decision-making. These AI systems are collectively referred to as AI software, with the former categorized as AI4SE software (AI for Software Engineering) and the latter as AI4Control software (AI for Control). As AI software becomes central to modern computing infrastructure, its reliability …

Student Mental Health: Screening For Stress, Anxiety And Depression Using Fitbit Data, Rebecca Lopez, Avantika Shrestha, Ml Tlachac, Kevin Hickey, Xingting Guo, Shichao Liu, Elke Rundensteiner

Information Systems and Analytics Department Faculty Conference Proceedings

College students experience many stressors, resulting in high levels of anxiety and depression. Wearable technology provides unobtrusive sensor data that can be used for the early detection of mental illness. However, current research is limited concerning the variety of psychological instruments administered, physiological modalities, and time series parameters. In this research, we collect the Student Mental and Environmental Health (StudentMEH) Fitbit dataset from students at our institution during the pandemic. We assess the ability of predictive machine learning models to screen for depression, anxiety, and stress using different Fitbit modalities. Our findings indicate potential in physiological modalities such as heart …

How Agile Became The Design Philosophy Of Ai Fishbowl Under Real-World Constraints, Jad Saad

University Honors Theses

This capstone review examines the development of AI Fishbowl, a public-facing, interactive artificial intelligence system, as a case study in how Agile methods evolve from a project management tool into a design philosophy under real-world constraints. Although the project adopted an Agile workflow early on through a Kanban-style task management approach, the initial system design and architecture were still shaped by a largely plan-first mindset. This created a mismatch between flexible process and rigid design assumptions, which became increasingly apparent as the team moved from high-level architecture into implementation.

A critical turning point occurred when early architectural plans proved difficult …

Codeultrafeedback: An Llm-As-A-Judge Dataset For Aligning Large Language Models To Coding Preferences, Martin Weyssow, Aton Kamanda, Xin Zhou, Houari Sahraoui

Research Collection School Of Computing and Information Systems

Evaluating the alignment of large language models (LLMs) with user-defined coding preferences is a challenging endeavor that requires a deep assessment of LLMs' outputs. Existing methods and benchmarks rely primarily on automated metrics and static analysis tools, which often fail to capture the nuances of user instructions and LLM outputs. To address this gap, we introduce the LLM-as-a-Judge evaluation framework and present CodeUltraFeedback, a comprehensive dataset for assessing and improving LLM alignment with coding preferences. CodeUltraFeedback consists of 10,000 coding instructions, each annotated with four responses generated from a diverse pool of 14 LLMs. These responses are annotated using GPT-3.5 …

Detecting Bitstream-Level Fpga Trojans With An Snn, Kylie Arnett

Shelby Hall Graduate Research Forum Presentations

Limited research has been conducted on SNNs for FPGA Trojan detection. FPGA design is often handled by manufacturers outside the U.S. FPGA manufactures outsource production to third-party foundries. This multi-step process introduces security vulnerabilities and increases risk of Hardware Trojan insertion.

Key Questions: To what extent can an FPGA be manipulated at the bitstream level to enable or disable encryption algorithms?

Can SNNs accurately detect the presence of Trojans within an FPGA?

A Scalable Iteration Of The Horizon Simulation Framework Using Multithreading Techniques, Jason E. Beals

Master's Theses

The Horizon Simulation Framework (HSF) occupies a unique space in the modern aerospace modeling landscape, enabling flexible, modular modeling of mission-level agent behavior through an object-oriented, hierarchical design. HSF's hallmark breadth-first search scheduling algorithm explores a "multiverse" of possible mission execution pathways, enabling exhaustive evaluation of schedule combinations against user-defined heuristics.

As aerospace systems become increasingly complex, HSF faces critical challenges in establishing verifiable, deterministic behavior. The framework's core scheduling algorithm had not undergone systematic validation, leaving questions about temporal consistency, state management correctness, and reproducibility across different program executions. Furthermore, the exponential growth of schedule combinations creates computational bottlenecks …

Stock Market Price Prediction Using Big Data Models Comparison Analysis, Vibhor Pal

Shelby Hall Graduate Research Forum Posters

The stock market consists of complex financial datasets, and achieving stock price real time prediction needs an efficient big data framework for processing. This paper compares big data distributed data processing frameworks for forecasting stock prices using Graph Neural Networks (GNNs) - Apache Flink and Apache Spark. We analyze 70 publicly traded companies’ monthly data for the last 5 years from Yahoo Finance, ranked by Price-to-Earnings (P/E). In the companies’ datasets, there may be a connection or similarity between companies, and this can lead to similar stocks’ price behavior. These interfirm relationships are maintained by GNNs models, and their output …

Evaluating Software-Based Hardware Abstraction As A Fault Injection Countermeasure, Tristan Clark, J. Todd Mcdonald

Shelby Hall Graduate Research Forum Posters

Despite how theoretically secure a system may be, it can be compromised if an adversary has physical access to the device. This can be done by injecting hardware corruptions directly into the physical system, which is called a fault injection (FI) attack. To combat this, there is a need for robust fault-tolerant countermeasures. One such countermeasure is obfuscating the program to introduce redundancy and complexity, particularly through software-based hardware abstraction (SBHA).

This research proposes using SBHA as a countermeasure to fault injection attacks. By transforming point-function password programs, the proposed countermeasure aims to increase the difficulty of conducting successful FI …

Explainable Deep Reinforcement Learning For Real-Time Network Intrusion Detection, Sebastian Bustamante

Shelby Hall Graduate Research Forum Posters

This research aims to enhance current Deep Reinforcement Learning (DRL)-based Intrusion Detection System (IDS) models by adding transparency using Explainable Artificial Intelligence (XAI). This study proposes a DRL-based IDS architecture that incorporates explainability to provide interpretable reasons for IDS decisions. A Deep Q-Network (DQN) agent will be trained in a simulated network using well-known datasets to learn traffic behavior. XAI methods will be applied to extract feature importance and allow users to understand why alerts were generated. The outcomes of this research will contribute to improving network security by providing more insight on how XAI could be adopted into modern …

Text Corpus Combined Method And Tools For Music Textual Analysis, Yuwei Lu

Shelby Hall Graduate Research Forum Posters

While there has been a great deal of research conducted on how to search images and video using text, there has been less focus on how to retrieve music using multiple facets such as mood and lyrical content. or its features This is due in part to the historical lack of available musical corpuses. A musical corpus is a specialized text corpus specifically designed to capture information about music. Recently, several musical corpora for music information retrieval have been built and made available. However, these corpora and the tools designed to exploit them are typically designed to facilitate only one …

Integrating Nonlinear Phase Space Analysis And Image-Based Representation For Network Intrusion Detection, Chakriya Suon

Shelby Hall Graduate Research Forum Posters

With the rise of cyber threats, cybersecurity continues to play a critical role in the ever-changing landscape of technology by protecting and defending against threat agents. Our research applies novel machine learning (ML)techniques to detect network intrusions effectively. Our primary focus is to extend prior research, which has used network flows that are processed by a nonlinear phase space algorithm (NLPSA). The NLSPA approach has proven extremely effective in detecting anomalous or malicious traffic patterns on representative data but requires extensive training time.

Our contribution integrates deep learning into the anomaly detection approach by creating image-based representations of the adjacency …

Evaluating The Effects Of Anti-Forensic Activities In Additive Manufacturing Devices, Daniel B. Miller

Shelby Hall Graduate Research Forum Posters

Additive Manufacturing (AM) is a newer famlily of production tecchologies that constructs objects by fusing layers of material into the desired shape. Methods for achieving this as described in Gibson et al. [1] are varied and include Fused Filament Deposition, Selective Laser Sintering, Stereolithography (SLA), and Powder Bed Fusion. Computers are integral to the processes being responsible for creating and decoding design instructions, collecting and processing sensor data, and, ultimately, directing the activity of the machines which implement the process. Additionally, the AM industry is rapidly expanding, worth an estimated $23 billion in 2023 and projected to reach $88 billion …

Cellebrite Reliability In Digital Forensics, Christina Huynh

Shelby Hall Graduate Research Forum Posters

Forensic tools like Cellebrite are commonly used in court to gather and interpret raw data for evidence. Cellebrite does not only collect data but creates and interprets the artifacts of data to create a scene of the process it has been through. With this, evidence can be influenced by software designs and not just the data on the mobile device. Courts and police use Cellebrite to gather evidence and reconstruct it to create an easily readable dataset. These tools lack reproducibility, transparency, integrity, and chain of evidence command. Cellebrite is often used in court and by police without further vetting …

Deconstructing Digital Disinformation: Social Media Data Preparation And Analysis For Healthcare Research, Russell W. Cantrell, Matt Campbell

Shelby Hall Graduate Research Forum Posters

The spread of medical misinformation poses significant threats to public health, healthcare system stability, and the quality of patient care. Our research examines misinformation targeting the U.S. healthcare system. It uses a mixed-methods approach that includes social media data analysis, surveys of practicing nurses, and agent-based simulation. This poster focuses on the initial phase, which attempts to detect potential misinformation and disinformation by analyzing patterns in social media posts and user account behaviors. A detailed account of the data preparation process lays the groundwork for examining how disinformation operates online. This phase draws on the Pushshift repository, which offers historical …

Detecting Sensor Data Manipulation, Ricky Green, Michael Black

Shelby Hall Graduate Research Forum Posters

The integration of Information Technology (IT) and Operational Technology (OT) have made OT devices vulnerable to threats that have been successfully exploited with devastating results. Many modern techniques for hardening and securing enterprise IT systems are either incompatible with OT components in an Industrial Control System (ICS), reduce the efficiency of processes, or are prohibitively expensive to implement. Research in the area of ICS security focuses on a top-down approach, such as intrusion prevention by securing the perimeter of the network at layers 3 – 5 of the Purdue model by hardening IT systems. This approach is useful in Enterprise …