Digital Commons Network^™

Navajo Speech Recognition Using Low-Resource Language Models, Emery M. Sutherland

Electrical and Computer Engineering ETDs

This thesis describes the development of a speech recognition system to classify Navajo (Dine) words using Low Resource Language (LRL) datasets. Presently there are no recognized high-quality open-sourced datasets for the Dine language needed to train models for speech recognition. A small balanced dataset was designed to train several models. To overcome the scarcity of the LRL dataset, the audio recordings were augmented to account for time-stretching, amplitude variations, time shifts, small amounts of white Gaussian noise, and SpecAugmentation. The models included a Recurrent Neural Network (RNN), a Convolutional Neural Network (CNN), and a Long Short-Term Memory (LSTM) model with …

Enhancing Organizational Resilience Through Fatality Prevention At Vulcan Materials Company, Ross Boeker

ASEM Capstones

2025 ASEM 620 Capstone Project

Robust Inner Knuckle Print Recognition System Using Densenet201 And Inceptionv3 Models, Haitham Salman Chyad, Tarek Abbes

Iraqi Journal for Computer Science and Mathematics

Texture features and stability have generated significant interest in biometric recognition. The inner knuckle print is distinctive and difficult to fake, making it extensively used in individual identification, criminal investigation, and various other domains. In recent years, the rapid progress of deep learning technology has created new prospects for internal knuckle recognition. This paper proposes a robust inner-knuckle-print recognition system (RIKP-RS) depending on two deep learning (DL) models. This paper focuses on the key components of the inner surface of the hand namely the little finger, ring finger, middle finger, index finger, and thumb finger that are used for human …

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 …

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 …

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 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 …

Privacy At Scale: A Study Of Mobile App Privacy Practices, Katherine Perez

LSU Master's Theses

What is privacy in a world where people are more connected than ever? Due to the Internet and its rapid advancement, the way information is shared and accessed has fundamentally changed. Millions of people interact with social networks, websites, and applications daily—and with each interaction, some data is collected from the user. In many cases, users cannot access a website or application without first accepting the service’s Privacy Policy. However, these policies often obscure the details of how a consumer’s data is handled, burying important information under dense legal language. In response to growing concerns about transparency, some platforms have …

2025- The Twenty-Ninth Annual Symposium Of Student Scholars

Symposium of Student Scholars Program Books

The full program book from the 29th Annual Symposium of Student Scholars, held on April 16-18, 2025. Includes abstracts from the presentations and posters.

Pajaro River Levee Remedial Design For Climate Resiliency, Anna Krebs, Karina Martin, Olivia Leonardis

Civil, Environmental and Sustainable Engineering Senior Theses

With climate change causing extreme weather events, low-income, underrepresented residents living in Pajaro, California need a more resilient flood mitigation solution because existing infrastructure– the Pajaro River Levee– has recently failed. A hydraulic analysis and overtopping analysis was performed to evaluate potential levee cross sections for a 1.7 mile stretch along the Pajaro River in California. These cross-sections were assessed based on both their material costs and ability to provide sufficient evacuation time.

Aimr-Brainstorm: Ai-Enhanced Interactive Mixed Reality For Collaborative Ideation, Yuchuan Ma

Dartmouth College Master’s Theses

This study investigates the potential of an AI-enhanced Mixed Reality (MR) brainstorming system, named AIMR-Brainstorm, in comparison to traditional sticky notes for creative ideation. By integrating real-time idea extraction through ChatGPT with immersive, physics-based visualizations, the system aims to transform analog brainstorming workflows into dynamic, interactive digital experiences. Using a within-subject experimental design, 30 participants engaged in paired brainstorming sessions with both AIMR and sticky notes. Quantitative measures of efficiency, engagement, creativity, and user satisfaction were collected through between-session and post-study surveys, while qualitative feedback provided additional insights into user experiences. Conclusively, while traditional sticky notes were generally preferred for …

Silenttalk Final Report, Yihui Wu , '25

Senior Theses, Projects, and Awards

SilentTalk is a noninvasive communication system that uses ultrasound technology to detect and interpret silent speech by analyzing lip and facial movements. This E90 project presents the design, construction, and experimental evaluation of a speaker–microphone device capable of emitting and capturing ultrasonic waves in the 20–55 kHz range. Data wereadS collected under five distinct conditions, including various static mouth gestures, and analyzed using Root Mean Square (RMS) smoothing and Fast Fourier Transform (FFT) techniques. The results show that the distinct features in the time and frequency domains correspond to different mouth shapes, supporting the feasibility of silent gesture classification. A …

On The Provenance Of Software Systems: Automating Software Traceability With Knowledge Graph And Large Language Model Synergy, Tyler Procko

Doctoral Dissertations and Master's Theses

The present dissertation delineates a system that enables those engaged in software development to automatically generate and maintain project life cycle provenance. All projects are implemented and made manifest with the development of artifacts, e.g., papers, code files, etc. Tools exist to accelerate artifact creation, but little focus is paid to the processes that produce them. In terms of Ontology, or, from Ancient Greek, the study of being, the two most basic entities in reality are Continuant and Occurrent, or, roughly, “Artifact” and “Process”. This dissertation posits that for any created artifact, its process of creation, i.e., its life …

Llm-Enhanced Multiple Instance Learning For Joint Rumor And Stance Detection With Social Context Information, Ruichao Yang, Jing Ma, Wei Gao, Hongzhan Lin

Research Collection School Of Computing and Information Systems

The proliferation of misinformation, such as rumors on social media, has drawn significant attention, prompting various expressions of stance among users. Although rumor detection and stance detection are distinct tasks, they can complement each other. Rumors can be identified by cross-referencing stances in related posts, and stances are influenced by the nature of the rumor. However, existing stance detection methods often require post-level stance annotations, which are costly to obtain. We propose a novel LLM-enhanced Multiple Instance Learning (MIL) approach to jointly predict post stance and claim class labels, supervised solely by claim labels, using an undirected microblog propagation model. …

Automated Data Analysis For Concussion Patient Records: A Flutter-Based Desktop Application, Fhaheem Tadamarry

USF Tampa Graduate Theses and Dissertations

Concussions are a prevalent and complex medical condition requiring careful clinical assessment and data-driven insights for effective management. This thesis presents the development of an automated data analysis system for concussion patient records, integrating Flutter-based desktop application development with SQL-driven data processing. The system provides a streamlined, interactive interface for clincians and researchers to upload, visualize, and analyze patient data efficiently.

The proposed solution automates data cleaning, preprocessing, and statistical analysis, ensuring robust and reliable insights into demographic, clinical, and recovery-related factors. Key analyses include sex-based differences injury mechanisms, prior head injury impact, mood disorder correlations, and time-to-treatment variations. The …

War Strategy Algorithm- Based Hybrid Optimization For Accurate And Rapid Speech Recognition, Shahad Thamear Abd Al-Latief, Salman Yussof, Azhana Ahmad, Saif Mohanad Khadim, Ahmed Alkhayyat

Iraqi Journal for Computer Science and Mathematics

Speech recognition-based applications increased and developed as a result of artificial intelligence's rapid growth, particularly Machine Learning, which play a crucial role in many aspects of daily life, such as applications related to human-computer interaction, and natural language processing. The complexity and diversity of speech signals provides challenges in maximizing the rate of accuracy and efficiency of speech recognition systems. Hyperparameter tuning is a crucial step in machine learning that has a significant role in optimizing the performance and generalization by determining the optimal values for the model's hyperparameters. This paper employed the recently developed WAR Strategy optimization algorithm for …

Developing Students' Sociotechnical Thinking In The Humanities-Engineering Classroom: A Treatment Versus Control Study Using A Scenario-Based Assessment, Lori Czerwionka, Siddhant S. Joshi, Gabriel O. Rios-Rojas, Kirsten A. Davis

School of Engineering Education Faculty Publications

Background

Engineering problems are open-ended and complex, involving technical and social aspects, yet engineering education focuses on technical training and closed-ended problems. To prepare engineering students, curricula should foster sociotechnical thinking—the ability to consider the interplay of technical and social factors during problem solving. Although educational interventions in this area show promise, further insight into the benefits of interdisciplinary interventions is warranted, particularly with treatment and control group designs.

Purpose

We examine the effect of a Humanities-Informed Engineering Projects (HIEP) course on students' sociotechnical thinking development.

Method

We compared the sociotechnical thinking development of engineering students who took the HIEP …

Fuzzy-Virtual Inertia Control To Improve The Frequency Response Of Multi-Area Power Systems, Nourelhouda Djaraf, Yacine Daili, Abderrahim Zemmit, Abdelghani Harrag

Turkish Journal of Electrical Engineering and Computer Sciences

Virtual inertia control (VIC) is essential for power systems dominated by electronic devices to compensate for the lack of inertia and ensure frequency regulation. However, most existing VICs often focus solely on optimizing the virtual inertia parameter to adapt to the high penetration of renewable energy sources (RESs) without considering the damping factor. This oversight can lead to significant fluctuations and power mismatches, especially in interconnected systems where the coordination between MGs is sensitive and essential, and there is a risk of propagation of deviations between MGs, which makes the control more complex. To address these issues, this paper presents …

Conversational Open-Domain Question Answering For Resource-Constrained Languages, Emrah Budur, Tunga Güngör

Turkish Journal of Electrical Engineering and Computer Sciences

The growing interest in Conversational AI has led to the development of Conversational OpenQA systems as a crucial step for meeting users' information needs in real world scenarios. Conversational OpenQA systems enhance standard OpenQA performance by leveraging conversation history of the users. However, building effective Conversational OpenQA systems requires large-scale Conversational OpenQA datasets, often limited to the English language, hindering progress in low-resource languages. We present a robust Conversational OpenQA system enhanced by conversational context, designed for languages with limited resources and exemplified in our case study for Turkish. To address data limitations in a cost-effective way, we repurpose existing …

Beyond Cultural Responsiveness: Elevating African American Stem Education Through African-Centered Models, Deanna Bailey, Charnee Bowens, Tamara Altman

Journal of Pre-College Engineering Education Research (J-PEER)

Researchers posit that the way science, technology, engineering, and mathematics (STEM) are taught to African Americans contributes to their underrepresentation in the STEM fields. STEM educators are increasingly utilizing culturally relevant pedagogy, culturally responsive teaching strategies, and culturally sustaining pedagogy to engage the African American STEM learner. However, these techniques are limited in addressing the holistic development, healing, and needs of African people.^[1] This essay advocates for the use and study of a new educational model titled African-centered STEM education (ACSE). The authors contend that this model is effective for African American STEM learners and African people and benefits …

Three-Way Decision Clustering Algorithm Fusion Of Mutant Fireflies Algorithm, Zhaobin Li, Jun Ye, Haoyan Zhou, Yixin Wang, Yuzhen Han

Journal of System Simulation

Abstract: To address problems such as the premature phenomenon in the three-way clustering algorithm caused by the random selection of initial cluster centers and the need for repeated experiments to determine the value of q in the q-nearest neighbor concept, a three-way clustering algorithm optimized by a variant of the firefly algorithm is proposed. The firefly algorithm is employed to solve the problem of sensitivity to initial cluster centers. The target function value is taken as the brightness intensity of firefly to search the clustering center point, and the optimal solution is taken as the clustering center of the algorithm …

Neurosymbolic Knowledge-Grounded Planning And Reasoning In Ai Systems, Amit Sheth, Vedant Khandelwal, Kaushik Roy, Vishal Pallagani, Megha Chakraborty

Faculty Publications

To build AI systems capable of decision-support assistance, such as AI-assisted healthcare, it is essential to develop user-centric decision-making processes that are robust, interpretable, and capable of effectively processing and acting on natural language interactions. Instruction-based prompting of large language models has demonstrated considerable success in supporting humans with information assistance tasks, including creative writing and content generation. However, recent studies reveal that language models exhibit limitations in performing complex reasoning and planning tasks, such as constructing compositional or hierarchical plans involving multiple reasoning steps. To address these challenges, we propose a neurosymbolic framework that integrates large language models with …

Feature Manifold Transformer For Detection Of Differential Item Functioning: Visual Detection Of Categorical Feature Nonconformity Through Attention-Based Analysis, Derrick A. Cox, Tanvi Banerjee, William L. Romine

Computer Science and Engineering Faculty Publications

Methods for interpreting complex feature interactions in educational assessment data remain a critical challenge, with traditional statistical approaches often creating barriers to accessibility and interpretability. We introduce the Feature Manifold Transformer (FMT), a novel machine learning approach that leverages dimensionality reduction, representation learning, and transformer architectures to visualize and interpret feature relationships in categorical data. Using the Concept Inventory of Natural Selection (CINS) and Concept Assessment of Natural Selection (CANS) datasets as testbeds, we demonstrate the FMT’s ability to capture subtle relationships between student demographics and response patterns. Our methodology enables both global and local pattern analysis, providing interpretable visualizations …

Conversational Voice User Interfaces Supporting Individuals With Down Syndrome: A Literature Review, Franceli L. Cibrian, Concepción Valdez, Lauren Min, Vivian Genaro Motti

Engineering Faculty Articles and Research

Conversational Voice User Interfaces (CVUIs) are widely used in commercial applications such as personal assistants. CVUIs are beneficial for most users as they enable interaction through speech and natural language. However, recent studies indicate that underrepresented user groups, such as individuals with speech impairments and specifically those with Down syndrome, face challenges in using voice commands to control CVUIs. The anatomical and physiological differences affecting the voice, speech, fluency, and prosody of users with Down syndrome hinder their experience with CVUIs. This article presents the results of 43 papers related to the use of voice user interfaces supporting individuals with …

Sustainable Viscosity Prediction Of Hybrid Alumina- Copper Oxide Nanofluid For Green Heat Transfer Applications Using Adaptive Neuro-Fuzzy Inference System (Anfis), Mohammad Reza Chalak Qazani, Ganesan Kadirgama, Navid Aslfattahi, Devarajan Ramasamy, Lingenthiran Samylingam, Kumaran Kadirgama, Chee Kuang Kok, Mohd Fairusham Ghazali

The Nexus of Sustainability and Energy Technology Journal

Developing more energy-efficient, environmentally friendly heat transfer solutions is necessary. As a result, the application of nanofluids has attracted an increasing amount of attention. This paper shows a new method for predicting the viscosity of hybrid alumina-copper oxide nanofluid. The Adaptive Neuro-Fuzzy Inference System (ANFIS) was used to predict the abovementioned physical property of the fluid dispersed in Therminol 55; a medium-temperature medium. The concentration of nanoparticles, temperature, and shear rate were found to be the major input factors. In comparison to Decision Trees (DT) and Support Vector Regression (SVR), the ANFIS method model was more effective, yielding a Root …

Cognitive Warfare In The South China Sea: Analyzing Media Influence And Public Opinion In Taiwan, Wyatt F. Blatti

Theses and Dissertations

In a time where conflict extends beyond traditional battlefields, cognitive warfare emerges as a powerful tool to influence perceptions and gain strategic advantages. This study investigates China’s cognitive warfare strategies against Taiwan through trend analysis, topic modeling, and sentiment analysis of news media articles from March 2013 to August 2024 to uncover evolving techniques and mitigation efforts. The findings highlight the potential for tracking cognitive campaigns overtime but will require more than news media alone and suggests future research to better understand indicators of cognitive warfare.

Are Emojis The New Words? A Sentiment Analysis Of Social Media Brand Conversations, Yashodhan Karulkar, Dev T. Vora, Siddharth Vaddepalli, Yash Thakur

Journal of International Technology and Information Management

Emojis have become an increasingly important aspect of consumer-brand interactions in the Indian subcontinent. However, the impact of emoji use on brand image and mental health remains underexplored, particularly in emerging economies like India, where structured research on this topic is limited. To address this gap, the present study analyzes over 4,600 consumer tweets related to 19 prominent brands across eleven industries. Using VADER sentiment analysis, the research develops a metric to assess consumer sentiment and brand engagement in relation to emoji usage. The findings indicate that effective integration of emojis contributes to positive consumer sentiment and enhanced brand engagement. …

Cal Poly Construction Spanish Class, Josue E. Basilio

Construction Management

This project develops a Construction Spanish & Communication course for Cal Poly’s Construction Management program to address the growing need for bilingual communication on job sites. The course equips students with essential Spanish language skills for safety meetings, work instructions, and team coordination, improving job site efficiency and inclusivity. Deliverables include a detailed course outline in preparation for the semester conversion, curriculum, course catalog entry, and a first-day lecture presentation. The course blends lecture-based instruction with hands-on activities like role-playing, translation exercises, and real-world simulations. Assessments include scenario-based quizzes, a reflection essay, participation grading, and a final exam to ensure …

Quantum Finite Automaton Using Ternary Rotation Quantum Gates And Chrestenson Family Quantum Gates, Yuchen Huang, Marek Perkowski, Xiaoyu Song, John M. Acken

Electrical and Computer Engineering Faculty Publications and Presentations

Quantum automata can solve certain problems with a smaller state space than classical automata. We developed a quantum finite automaton using ternary rotation quantum gates and the Chrestenson family of ternary quantum gates. The main idea of this paper is to show how to combine rotation ternary quantum circuit-based QuantumFinite Automaton and quantum reversible circuit-based Deterministic Finite Automaton to build a more powerful machine. The combined machine can enable more complex language and pattern recognition. The developed quantum finite automaton and resulting combined machine can be used for robotics applications such as language, gesture, and motion recognition.

Understanding Avionics Maintenance Training Student Outcomes In A Student-Centered Active Learning Environment, Scott M. Wyman

Theses and Dissertations

This study examines the effects of active learning compared to didactic methodologies on two soft skills, namely teamwork and self-efficacy using regression analyses and connected letter reports. Learning styles and personality traits were used as predictors. Findings indicate significant interaction effects between methodology, aural learning style, and personality traits on self-efficacy and teamwork ability. The findings highlight the nuanced role of learner traits in shaping teamwork outcomes across instructional methods. While active learning supports soft skills, individual differences must be considered in instructional design to optimize teamwork in technical education settings.