Digital Commons Network^™

Phoneme Recognition For Pronunciation Improvement, Matthew Heywood

Theses/Capstones/Creative Projects

This project aims to improve English pronunciation by investigating speech errors and developing a tool to provide precise feedback. The study focuses on creating a new pronunciation tool that offers localized feedback, identifies specific errors, and suggests corrective measures. By addressing the shortcomings of current methods, this research seeks to enhance pronunciation refinement.

Utilizing cutting-edge technology, the tool leverages speech-to-phoneme AI models and modified lazy string matching algorithms to compare the user's spoken input with the intended pronunciation. This allows for a detailed analysis of discrepancies, providing users actionable insights into their phonetic errors. The speech-to-phoneme AI models mark a …

Analyzing Sleep Staging And Cognitive Transitions Using Fmrl Time Series Analysis, Qingwen Zeng

Arts & Sciences Graduate Student Theses and Dissertations

Understanding sleep stages and their underlying cognitive transitions is essential for advancing our knowledge of brain function. While sleep staging has traditionally relied on electroencephalogram (EEG), this study explores the feasibility of classifying sleep stages using only functional Magnetic Resonance Imaging (fMRI) data. We investigate the use of Hidden Markov Models (HMM) and Hierarchical Dirichlet Process Hidden Markov Models (HDP-HMM) to capture temporal brain-state dynamics from task-free fMRI recordings. A series of pipelines—including sliding window, two-stage majority filtering, and prototype-based mapping via the Hungarian algorithm—were implemented to align model-inferred states with EEG-defined sleep stages. Among the twelve tested pipelines, the …

Biomimetic Design Of Mechanochromic Single-Chain Nanoparticle Polymer Networks, Samuel Robinson

Honors Theses

Hydrogels are a class of polymer networks that show promise in many biomedical applications but are typically limited in use due to their brittle nature. Synthesizing hydrogel networks that are comparable to biological materials has long been an area of interest. In this study, we are working to create a polymer network inspired by the muscular protein, titin. Titin can unfold under mechanical tension, releasing stored length, making the muscle material extensible and durable. To mimic this behavior, we propose creating a polymer network with similar stored length using single chain nanoparticles (SCNPs) cross-linked with phenolphthalein (PP) and β-cyclodextrin (β-CD). …

Describing Functionality In Natural Language May Improve Decomposition Behaviors, Matthew R. Burns

All Graduate Theses and Dissertations, Fall 2023 to Present

Problem decomposition—the ability to break complex problems into simpler parts—is a critical skill for computer programming that many beginning students struggle to develop. This research examines how using natural language to describe program functionality can help students develop better problem-solving approaches.

We created a tool called ”Natural Language Functions” (NLFs) that allows students to write descriptions of what they want their code to do in plain English, which then generates working Python functions. We studied how students used this tool compared to students who solved programming problems in traditional ways.

Our findings show that students who used the NLFs tool …

Rotation-Adaptive Point Cloud Domain Generalization Via Intricate Orientation Learning, Bangzhen Liu, Chenxi Zheng, Xuemiao Xu, Cheng Xu, Huaidong Zhang, Shengfeng He

Research Collection School Of Computing and Information Systems

The vulnerability of 3D point cloud analysis to unpredictable rotations poses an open yet challenging problem: orientation-aware 3D domain generalization. Cross-domain robustness and adaptability of 3D representations are crucial but not easily achieved through rotation augmentation. Motivated by the inherent advantages of intricate orientations in enhancing generalizability, we propose an innovative rotation-adaptive domain generalization framework for 3D point cloud analysis. Our approach aims to alleviate orientational shifts by leveraging intricate samples in an iterative learning process. Specifically, we identify the most challenging rotation for each point cloud and construct an intricate orientation set by optimizing intricate orientations. Subsequently, we employ …

Worldcuisines: A Massive-Scale Benchmark For Multilingual And Multicultural Visual Question Answering On Global Cuisines, Genta Indra Winata, Et. Al

Research Collection School Of Computing and Information Systems

Vision Language Models (VLMs) often struggle with culture-specific knowledge, particularly in languages other than English and in underrepresented cultural contexts. To evaluate their understanding of such knowledge, we introduce WorldCuisines, a massive-scale benchmark for multilingual and multicultural, visually grounded language understanding. This benchmark includes a visual question answering (VQA) dataset with text-image pairs across 30 languages and dialects, spanning 9 language families and featuring over 1 million data points, making it the largest multicultural VQA benchmark to date. It includes tasks for identifying dish names and their origins. We provide evaluation datasets in two sizes (12k and 60k instances) alongside …

Hdwsa2: A Secure Hierarchical Deterministic Wallet Supporting Stealth Address And Signature Aggregation, Xin Yin, Zhen Liu, Guomin Yang, Guoxing Chen, Haojin Zhu

Research Collection School Of Computing and Information Systems

Hierarchical Deterministic Wallet (HDW) and Stealth Address (SA) are widely used in cryptocurrency communities due to their functionality and security. In the preliminary version of this work (ESORICS 2022), we formally define the syntax and security models of Hierarchical Deterministic Wallet supporting Stealth Address (HDWSA), capturing the functionality and security requirements imposed by the practice in cryptocurrency. We propose a concrete HDWSA construction and prove its security in the random oracle model. Note that when applied in blockchain, in practice, signature aggregation could reduce the cost of computation, storage, and communication dramatically. In this full version, we develop HDWSA definition …

Enriching Automatic Test Case Generation By Extracting Relevant Test Inputs From Bug Reports, Wendkuuni C. Ouedraogo, Laura Plein, Kader Kabore, Andrew Habib, Jacques Klein, David Lo, Tegawende F. Bissyande

Research Collection School Of Computing and Information Systems

The quality of software is closely tied to the effectiveness of the tests it undergoes. Manual test writing, though crucial for bug detection, is time-consuming, which has driven significant research into automated test case generation. However, current methods often struggle to generate relevant inputs, limiting the effectiveness of the tests produced. To address this, we introduce BRMiner, a novel approach that leverages Large Language Models (LLMs) in combination with traditional techniques to extract relevant inputs from bug reports, thereby enhancing automated test generation tools. In this study, we evaluate BRMiner using the Defects4J benchmark and test generation tools such as …

Reverse Modeling In Large Language Models, Sicheng Yu, Yuanchen Xu, Cunxiao Du, Yanying Zhou, Minghui Qiu, Qianru Sun, Hao Zhang, Jiawei Wu

Research Collection School Of Computing and Information Systems

Humans are accustomed to reading and writing in a forward manner, and this natural bias extends to text understanding in auto-regressive large language models (LLMs). This paper investigates whether LLMs, like humans, struggle with reverse modeling, specifically with reversed text inputs. We found that publicly available pre-trained LLMs cannot understand such inputs. However, LLMs trained from scratch with both forward and reverse texts can understand them equally well during inference. Our case study shows that different-content texts result in different losses if input (to LLMs) in different directions---some get lower losses for forward while some for reverse. This leads us …

Disambiguart: A Neural-Based Inference Model For Knowledge Graph Disambiguation, Budhitama Subagdja, D. Shanthoshigaa, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

One main challenge in constructing a knowledge graph (KG) is to deal with ambiguity. Specifically, an entity in the graph can be assigned with multiple meanings while two or more entities considered to have different meanings may actually be the same. Assigning an entity with the correct meaning may involve re-evaluation of its relevant contexts. This costly operation typically involves searching for other similar entities within the KG such that the context can be determined. In this paper, a new model called DisambiguART is proposed leveraging multi-channel matching and inference in a self-organizing neural network for sense disambiguation in knowledge …

Enhancing Deliberativeness: Evaluating The Impact Of Multimodal Reflection Nudges, Shun Yi Yeo, Zhuoqun Jiang, Anthony Tang, Simon Tangi Perrault

Research Collection School Of Computing and Information Systems

Nudging participants with text-based reflective nudges enhances deliberation quality on online deliberation platforms. The effectiveness of multimodal reflective nudges, however, remains largely unexplored. Given the multi-sensory nature of human perception, incorporating diverse modalities into self-reflection mechanisms has the potential to better support various reflective styles. This paper explores how presenting reflective nudges of different types (direct: persona and indirect: storytelling) in different modalities (text, image, video and audio) affects deliberation quality. We conducted two user studies with 20 and 200 participants respectively. The first study identifies the preferred modality for each type of reflective nudges, revealing that text is most …

Decictor: Towards Evaluating The Robustness Of Decision-Making In Autonomous Driving Systems, Mingfei Cheng, Xiaofei Xie, Yuan Zhou, Junjie Wang, Guozhu Meng, Kairui Yang

Research Collection School Of Computing and Information Systems

Autonomous Driving System (ADS) testing is crucial in ADS development, with the current primary focus being on safety. However, the evaluation of non-safety-critical performance, particularly the ADS's ability to make optimal decisions and produce optimal paths for autonomous vehicles (AVs), is also vital to ensure the intelligence and reduce risks of AVs. Currently, there is little work dedicated to assessing the robustness of ADSs' path-planning decisions (PPDs), i.e., whether an ADS can maintain the optimal PPD after an insignificant change in the environment. The key challenges include the lack of clear oracles for assessing PPD optimality and the difficulty in …

Oscar: Object Status And Contextual Awareness For Recipes To Support Non-Visual Cooking, Franklin Mingzhe Li, Kaitlyn Ng, Bin Zhu, Patrick Carrington

Research Collection School Of Computing and Information Systems

Following recipes while cooking is an important but difficult task for visually impaired individuals. We developed OSCAR (Object Status Context Awareness for Recipes), a novel approach that provides recipe progress tracking and context-aware feedback on the completion of cooking tasks through tracking object statuses. OSCAR leverages both Large-Language Models (LLMs) and Vision-Language Models (VLMs) to manipulate recipe steps, extract object status information, align visual frames with object status, and provide cooking progress tracking log. We evaluated OSCAR’s recipe following functionality using 173 YouTube cooking videos and 12 real-world non-visual cooking videos to demonstrate OSCAR’s capability to track cooking steps and …

Query Understanding In Llm-Based Conversational Information Seeking, Yifei Yuan, Zahra Abbasiantaeb, Yang Deng, Mohammad Aliannejadi

Research Collection School Of Computing and Information Systems

Query understanding in Conversational Information Seeking (CIS) involves accurately interpreting user intent through context-aware interactions. This includes resolving ambiguities, refining queries, and adapting to evolving information needs. Large Language Models (LLMs) enhance this process by interpreting nuanced language and adapting dynamically, improving the relevance and precision of search results in real-time. In this tutorial, we explore advanced techniques to enhance query understanding in LLM-based CIS systems. We delve into LLM-driven methods for developing robust evaluation metrics to assess query understanding quality in multiturn interactions, strategies for building more interactive systems, and applications like proactive query management and query reformulation. We …

A Pure Rotational Spectroscopic Study Of Two Nearly-Equivalent Structures Of Hexafluoroacetone Imine, (Cf3)C=Nh, Daniel A. Obenchain, Beppo Hartwig, Daniel J. Frohman, Garry S. Grubbs, B. E. Long, Wallace C. Pringle, Stewart E. Novick, S. A. Cooke

Chemistry Faculty Research & Creative Works

Rotational spectra for hexafluoroacetone imine, the singly substituted 13C isotopologues, and the 15N isotopologue, have been recorded using both cavity and chirped pulse Fourier transform microwave spectrometers. The spectra observed present as being doubled with separations between each pair of transitions being on the order of a few tens of kilohertz which is consistent with a large amplitude motion producing two torsional substates. The observed splitting is most likely due to the combined motions of the CF₃ groups, for which the calculated barrier is small. However, no transitions between states could be observed and, similarly, no Coriolis coupling parameters …

Multiobjective Linear Ensembles For Robust And Sparse Training Of Few-Bit Neural Networks, Ambrogio Maria Bernardelli, Stefano Gualandi, Simone Milanesi, Hoong Chuin Lau, Neil Yorke-Smith

Research Collection School Of Computing and Information Systems

Training neural networks (NNs) using combinatorial optimization solvers has gained attention in recent years. In low-data settings, the use of state-of-the-art mixed integer linear programming solvers, for instance, has the potential to exactly train an NN while avoiding computing-intensive training and hyperparameter tuning and simultaneously training and sparsifying the network. We study the case of few-bit discrete-valued neural networks, both binarized neural networks (BNNs) whose values are restricted to ±1 and integer-valued neural networks (INNs) whose values lie in the range {−P,…,P}. Few-bit NNs receive increasing recognition because of their lightweight architecture and ability to run on low-power devices: for …

Towards Supporting Children's Metacomprehension During Web Search, Christine Dianne Pinney

Boise State University Theses and Dissertations

As children interact online with search engine result pages (SERPs), children’s comprehension monitoring skills are put to work. Children are known to struggle with utilizing online information as the text content can be misaligned with their reading abilities. Comprehension monitoring skills allow people to assess the comprehensibility of text and is measured by how well comprehension predictions align with performance on comprehension tests. Previous research has shown that augmenting standard SERPs with readability visual cues can be helpful for children searching online. While comprehension predictions are traditionally collected after reading, SERP information provides the opportunity to measure children's perceived comprehensibility …

Jwst Reveals The Diversity Of Nuclear Obscuring Dust In Nearby Agn: Nuclear Isolation Of Miri/Mrs Data Cubes And Continuum Spectral Fitting, Omaira González-Martín, Daniel J. Díaz-González, Mariela Martínez-Paredes, Almudena Alonso-Herrero, Enrique López-Rodríguez, Begoña García-Lorenzo, Cristina Ramos Almeida, Ismael García-Bernete, Donaji Esparza-Arredondo, Sebastian F. Hoenig, Santiago García-Burillo, Chris Packham, Nancy A. Levenson, Alvaro Labiano, Miguel Pereira-Santaella, Francoise Combes, Anelise Audibert, Erin K.S. Hicks, Lulu Zhang, Enrica Bellocchi, Richard I. Davies, Laura Hermosa Muñoz, Masatoshi Imanishi, Claudio Ricci, Marko Stalevski

Faculty Publications

We investigate the capabilities of the mid-infrared instrument (MIRI) of JWST to advance our knowledge of active galactic nucleus (AGN) dust using the spectral fitting technique on an AGN collection of 21 nearby (z < 0.05) AGN (7 type-1 and 14 type-2) observations obtained with the medium resolution spectroscopy (MRS) mode. This collection includes publicly available AGN and data from the collaboration of Galactic Activity, Torus, and Outflow Survey (GATOS). We developed a tool named MRSPSFisol that decomposes MRS cubes into point-like and extended contributions. We found statistically good fits for 12 targets with current AGN dust models. The model that provides good fits (χ²/dof< 2) for these 12 targets assumes a combination of clumpy and smooth distribution of dust in a flare-disc geometry where the dust grain size is a free parameter. Still, two and one AGN statistically prefer the disc + wind and the classical clumpy torus model, respectively. However, the currently available models fail to reproduce 40 per cent of the targets, likely due to the extreme silicate features not well reproduced by the models and signatures of water-ice and aliphatic hydrocarbon absorption features in most targets. New models exploring, for instance, new chemistry, are needed to explain the complexity of AGN dust continuum emission observed by JWST.

Towards Reliable Ml: Data Attribution And Adversarial Robustness, Xiaosen Zheng

Dissertations and Theses Collection (Open Access)

Modern machine learning (ML) models achieve remarkable success, but face critical reliability challenges. This thesis advances two pillars of reliable ML systems: interpretability through data attribution and robustness against adversarial threats.

In the first part, we develop novel data attribution methods to elucidate the data-model relationship. We establish the critical role of memorization in model generalization through token-level influence analysis, extend sample-level attribution to diffusion models with effective approximation techniques, and introduce REGMIX, a group-level approach that predicts data mixture performance using small-scale experiments. These contributions provide practitioners with scalable tools to audit training data impacts across modalities.

The second …

The Influence Of Complex Terrain On The Turin, New York Tornado Of 2023, Alex D. Kramer

Atmospheric and Environmental Sciences Honors Program

Although uncommon as compared to other regions of the United States, the Northeast does experience significant tornados; those rated F/EF3 and above, of which some have had profound impacts on the region. Due to the diverse topography of the region, including its many northsouth oriented river valleys, most of these significant tornados traversed considerable changes in elevation throughout their lifetime. This study seeks to better understand the impacts of local topography on the intensity and overall progression of a significant tornadic event through using the most recent Northeast EF3: the Turin, NY tornado. With the consideration of previous studies involving …

Explainable Ai (Xai) For A Machine Learning Heart Disease Prediction Model, Sai Abhishek Sanchula

Electronic Theses, Projects, and Dissertations

Cardiovascular diseases (CVDs) remain the leading cause of mortality worldwide, necessitating the development of accurate and interpretable machine learning (ML) models for early diagnosis and risk assessment (World Health Organization, 2021). While ML algorithms such as logistic regression, decision trees, support vector machines (SVM) (Cortes & Vapnik, 1995), and deep learning models (LeCun et al., 2015) have demonstrated high predictive accuracy, their adoption in clinical practice is hindered by their black-box nature (Rudin, 2019). Explainable AI (XAI) techniques, including SHapley Additive Explanations (SHAP) (Lundberg & Lee, 2017), Local Interpretable Model-agnostic Explanations (LIME) (Ribeiro et al., 2016), and feature importance analysis …

Exploring The Biasing Effects Of Gender On Personality Disorder Diagnoses Formulated By Artificial Intelligence, Zoe Colclough

Student Theses

Gender bias is prevalent in personality disorder assessments, and while artificial intelligence has been posited as a solution to improve diagnostic objectivity and accuracy, the potential for such technologies to propagate human gender bias in mental health contexts remains underexplored. This study investigated the influences of gender bias on the diagnostic performance of ChatGPT-4o for personality disorders using three factorial research designs, which involved experimentally manipulating patient gender in a combined sample of 360 vignettes and case studies. Vignettes were synthesized through a novel artificial intelligence-assisted methodology established for this research, and case studies were identified from the literature. Significant …

Climate Change And The Field Of Farm Labor In The Lower Rio Grande Valley, Texas, Cody Richard Mortell

Theses and Dissertations

Farm workers in the United States are often vulnerable to adverse impacts of climate change, particularly extreme heat. This study explores farm workers’ climate change perceptions (CCP) as a mediating force in climate adaptation. Using latent class analysis, in-person survey data (n=404) from Lower Rio Grande Valley, TX (2024) and NOAA data were analyzed. Results were interpreted using Bourdieu’s field analysis framework and his notions of capital and symbolic power. Findings include: a social hierarchy with three latent classes of workers based on economic, cultural, social, and symbolic capital, which statistically significantly affected CCP. Workers in higher structural positions were …

Supporting Novice Programmers With Scaffolded And Open-Ended Generative Ai Interfaces: Insights From A Design-Based Research Study, Justin Olmanson, Azadeh Hassani, Gretchen K. Larsen

Department of Teaching, Learning, and Teacher Education: Faculty Publications

In this study, we explore student experiences in coding and learning programming with scaffolded and unscaffolded generative AI interfaces. Specifically, we supported higher education students in using ChatGPT, an open ended interface for interacting with generative AI; and Giuseppe, a specialized interface with an OpenAI backend service that offers personalized supports specifically for helping students overcome early-stage challenges in learning to code, and working on education technology prototyping projects. This study contributes to the field by offering design insights for scaffolding initial learning interactions between generative AI interfaces and novice programmers. Our findings suggest that those new to coding welcome …

Learning Educational Technology Prototyping With Generative Ai, Justin Olmanson, Azadeh Hassani, Gretchen K. Larsen

Department of Teaching, Learning, and Teacher Education: Faculty Publications

In this study, we use ethnographic methods, grounded theory, and an iterative analytical approach to explore participant experiences and strategies for engaging generative AI in support of both learning how to prototype educational technologies and learning to code. We examine how ChatGPT and Giuseppe (a scaffolded co-coding interface of our own design) influence students’ approaches to prototyping and programming. This study contributes to the field by: identifying specific challenges and affordances of generative AI in prototyping and educational technology development contexts; and offering insights into how educators, students, and learning technology developers can integrate generative AI in formative educational technology …

From Text To Utility: Distance-Aware Contrastive Learning For Detection-Ready And Shareable Malware Descriptions, Ivan Alejandro Montoya Sanchez

Open Access Theses & Dissertations

The rapid rise of sophisticated malware variants poses significant challenges for cybersecurity analysts, particularly due to the scarcity of data on newly emerging threats. Due to privacy, legal, and operational constraints, malware samples are often not shareable; instead, organizations publish cyber threat intelligence (CTI) in natural language. However, these reports are typically unstructured and inconsistent, limiting their utility in machine learning (ML) models. This thesis explores whether high-fidelity, shareable threat intelligence can be automatically generated from structured malware behaviors to supplement ML models when direct access to malware samples is limited. Two central questions are addressed:(i) How can descriptions be …

Automation Of Vulnerability And Patch Management: Information Extraction, Association, And Optimization, Kylie Mcclanahan

Graduate Theses and Dissertations

Vulnerability and patch management is an integral part of a robust cybersecurity program, yet it grows increasingly complex due to the sheer amount of data that must be analyzed. Particularly in Operational Technology (OT) environments, analysis must be done manually because of the lack of automated solutions. Additionally, there are many steps in this process, from the initial discovery of the vulnerability to the implementation of its remediation, and each step in the process requires different data in order to be performed effectively. In this work, we provide approaches and strategies to assist operators in industrial or OT environments throughout …

Application Of Deep Learning On Gage R&R For Anomaly Detection, Oluwatope Richard Ojo

Electronic Theses and Dissertations

This thesis explores the application of deep learning techniques, specifically autoencoder based models, to enhance anomaly detection within Gage Repeatability and Reproducibility (Gage R&R) studies—an essential component of Measurement System Analysis (MSA) in quality engineering. Traditional Gage R&R methodologies, while effective for linear and low-dimensional data, exhibit limitations in detecting subtle, nonlinear variations in complex measurement systems. To address this challenge, an unsupervised autoencoder was developed and trained on a synthetically generated dataset comprising 2,500 voltage measurements (5V and 33V) derived using Generative Adversarial Networks (GANs) based on real-world manufacturing data measurements.

The proposed autoencoder model achieved a 95th percentile-based …

Car Price Prediction Using Machine Learning: Analyzing The Dvm-Car Dataset, Yaman Abu Ghareebaih

Electronic Theses and Dissertations

The objective of this study is to predict car prices using machine learning models and the DVM-CAR dataset, which includes over 1.4 million images and car specifi- cations from 899 car models. Key factors such as mileage, engine power, and year of registration were analyzed for their correlation with car prices. Extensive data cleaning was performed, including filling missing values, identifying outliers, and normalizing numerical variables. Discrete variables like car make and body type were encoded using one-hot encoding. Linear relationships were analyzed with Multiple Logistic Regression, and Random Forest models were used for nonlinear patterns. Model performance was evaluated …

A Kinetic Analysis On Hydrolysis And Hydrothermal Conversion Of Cellulose To Dodecane, Joel Nyangoka Onyancha

Electronic Theses and Dissertations

Cellulose, the most abundant biomass on Earth, offers a promising pathway for alternative energy through conversion into alkane hydrocarbons. Traditional methods rely on high temperatures and high-pressure hydrogen, often derived from petroleum. In this study, we investigated the conversion of Microcrystalline Cellulose using hydrogen metal oxides (bronzes) under milder conditions. Following ASTM E3417-24 hydrolysis protocols, we employed hydrogen bronzes with toluene for product extraction. This approach enabled conversion at lower temperatures without pressurized hydrogen. Products were analyzed using Gas Chromatography Mass Spectrometer for identification and Gas Chromatography Flame Ionization Detector for quantification. Our findings revealed the formation of a possible …