Digital Commons Network^™

Efficient Deep Neural Networks For Autonomous Perception, Reeshad Khan

Graduate Theses and Dissertations

Autonomous perception systems must operate reliably under uncertainty arising from noisy observations, incomplete supervision, and hardware constraints. This dissertation investigates the design of efficient deep neural networks for autonomous perception through a unified perspective that treats uncertainty, efficiency, and sensing as interconnected challenges. The first contribution develops adaptive extensions of unbiased risk estimators, including eSURE and ePURE, enabling unsupervised training of deep neural networks for magnetic resonance image denoising under Gaussian and Poisson noise. However, these methods rely on known noise assumptions, which motivates the second contribution: a unified diffusion and Bayesian risk framework that estimates and adapts to unknown …

Grazed Pasture Effects On Greenhouse Gas Emissions In The Ozark Highlands, Tyler Buchanan

Graduate Theses and Dissertations

In the United States (US), grazinglands serve as the main foundation for the livestock industry, and, in Arkansas specifically, pastures are essential for rotational grazing and dairy operations. Climate change is increasingly becoming a concern in the agriculture industry, largely caused by anthropogenic activities increasing greenhouse gas (GHG) concentrations in the atmosphere, at least partly due to the nutrient recycling that occurs from animal manure additions in grazinglands. Therefore, quantifying GHG emissions from pastures is essential to better understanding the impacts of grazing on the environment. The objective of this study was to quantify and evaluate the potential effects of …

Collective Dissipative Charging And Energy Extraction In Quantum Batteries, Sagar Pokhrel

Graduate Theses and Dissertations

In this dissertation, we investigate the charging and discharging dynamics of a quantum battery composed of a collectively driven ensemble of $N$ identical two level systems coupled to a structured electromagnetic environment. The system is described using collective angular momentum operators in the Dicke basis, which provides a compact and physically transparent framework for analyzing collective light-matter interactions. Rather than treating dissipation as an unwanted source of loss, we explicitly use it as a mechanism for energy storage and work extraction. Starting from a coherently driven ensemble coupled to common reservoirs, we derive a master equation in Lindblad form under …

From Phenology To Yield Zones: Functional Clustering Of Satellite Time Series For Crop Growth Monitoring, Ikram Morso

Graduate Theses and Dissertations

Remote sensing and land surface phenology provide a strong basis for characterizing crop development, but their usefulness for within-field yield-zone delineation depends on whether crop development is analyzed as a phenological trajectory and whether the resulting zones are evaluated with spatially defensible statistics. These questions are especially relevant in soybean production because soybean is one of the most important row crops in the United States and the country’s dominant oilseed crop. This relevance is strong in Arkansas, where soybean is a major component of agricultural production. In soybean production, within-field yield variability reflects the combined influence of soil properties, stand …

Conservation Agriculture Effects On Greenhouse Gas Emissions From Cotton, Soybean, And Corn In Southeast Arkansas, Jonathan Benjamin Brye

Graduate Theses and Dissertations

The slow degradation of natural resources has resulted in the focus of agriculture shifting towards conservation practices, such as reduced/no-tillage, cover crops (CC), and organic amendments (i.e., biochar), that conserve and improve natural resource quality. The objectives of this thesis were to i) quantify the impacts of biochar rate (i.e., 0, 2000, and 4000 kg ha-1) and ii) the combination of CC and tillage practice on carbon dioxide (CO¬2), methane (CH4), and nitrous oxide (N2O) fluxes, growing-season-long emissions, global warming potential (GWP), soil properties, and plant response from a minimally tilled cotton (Gossypium hirsutum)-corn (Zea mays) rotation and a soybean …

Geospatial Analysis Of The Influence Of Wastewater Disposal On The Induced Seismicity In Oklahoma, Usa, Kristine Nagy

Graduate Theses and Dissertations

Seismic records over the past decade and a half have indicated a significant increase of earthquakes in the state of Oklahoma and the evidence has strongly suggested the rise is likely caused by substantial wastewater disposal operations, a subsequent process of oil and natural gas extraction. This study investigated the relationship between wastewater disposal via injection wells, and its influence on inducing earthquakes in Oklahoma by employing Geographic Information System (GIS) tools for geospatial data integration and spatial analysis using United States Geological Survey (USGS) earthquake data and Underground Injection Control (UIC) Class II well data sourced from the Oklahoma …

Toward Causal Generative Modeling: From Representation Learning To Controllable Generation, Aneesh Komanduri

Graduate Theses and Dissertations

The hallmark of human intelligence is causal reasoning, the ability to infer relationships between causes and effects through observation and intervention. While modern deep learning has excelled at identifying statistical patterns, current generative models often struggle to capture the underlying structural causal mechanisms of the data-generating process, leaving them vulnerable to shortcut learning and spurious associations. To achieve true generalizability and interpretability, artificial intelligence must transition from simple association to higher-level causal reasoning to be capable of scheduling and planning in the real world. This dissertation develops fundamental methodologies for causal generative modeling by integrating Pearl’s Structural Causal Model (SCM) …

Sevoauth: Secure Voiceprint Authentication With Hash-Based Feature Transformation, Rui Zhang, Zheng Yan, Robert H. Deng

Research Collection School Of Computing and Information Systems

While voiceprint authentication offers convenient user authentication and access control through voice feature recognition, a critical research gap remains: existing voiceprint authentication systems fail to simultaneously achieve sound security against replay, spoofing, and adversarial attacks, preserve voice privacy leakage, and satisfy usability demand. Previous efforts have struggled to balance these issues comprehensively. To bridge this gap, we present SeVoAuth, a cloud-based Voiceprint Authentication as a Service (VAaaS) system designed to provide privacy preservation, robust security, and enhanced usability. SeVoAuth stores a synthesized voiceprint of a user in the cloud during user registration, thereby safeguarding the privacy of the real voiceprint …

Mease: Multi-Agent Episodic Action Sequence Explanation, Phyo Wai Khaing, Minghong Geng, Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Multi-agent reinforcement learning (MARL) achieves remarkable performance in complex coordination tasks, yet interpreting the emergent behaviors of trained agents remains a fundamental challenge. Most current explainability methods focus on individual agent decisions, overlooking the critical interplay of joint strategiesand temporal coordination patterns that define successful multi-agent policies. We present MEASE (Multi-agent Episodic Action Sequence Explanation), a novel explainable MARL (XMARL) framework that explains trained MARL policies as human-interpretable emergent cooperative joint behaviors. MEASE employs a cognition-inspired episodic memory model to learn spatio-temporal multi-agent interaction patterns, coupled with abstraction algorithms that identify significant cooperative agent behaviors. We evaluate MEASE on diverse …

Synthesis And Evaluation Of Long-Term History-Aware Medical Dialogue, Hebin Hu, Renke Dai, Ah-Hwee Tan, Yilin Kang

Research Collection School Of Computing and Information Systems

An effective healthcare agent must be able to recall and reason over a patient’s longitudinal medical history. However, the absence of datasets with realistic long-term dialogue timelines limits systematic evaluation. Real clinical text is constrained by privacy and ethics, while existing benchmarks focus on isolated interactions, failing to capture cross-session reasoning. We introduce a framework for synthesizing high-quality, long-term medical dialogues with LLMs. Our approach entails a knowledge-guided decomposition into three stages: constructing synthetic patient profiles with diverse disease and complication trajectories, generating multiturn dialogues per encounter, and integrating them into a coherent longitudinal history dataset, MediLongChat. We establish three …

Collaborative Practices And Tool Utilization In Software Development Projects: A Student Perspective, Yi Meng Lau, Muhammad Syahmi Bin Abbas, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Software development is a collaborative activity that depends on effective teamwork, shared understanding, and coordinated use of development practices and tools. While these aspects are well studied in professional environments, they are less frequently examined within software engineering education. This study investigates how students collaborate in group projects, focusing on collaborative practices, tool usage, and their perceptions of software quality. We conducted a quantitative post-project survey with 143 second-year undergraduate students enrolled in a software development course. The results show that students actively share information and often establish team norms to support coordination and collaboration. However, students face challenges in …

Causality-Driven Test Case Minimisation For Cyber-Physical Systems, Michael Foster, Christopher M. Poskitt, Nicholas R. Latimer, Neil Walkinshaw, Richard Somers, Robert M. Hierons

Research Collection School Of Computing and Information Systems

Cyber-physical systems allow digital control systems to interact with the physical world using sensors and actuators. They are increasingly being used to automate critical infrastructure, where software faults can have dire consequences. Due to the complex nature and unpredictability of these systems, their resilience is often tested using a technique called fuzzing, which generates quasi-random sequences of sensor and actuator manipulations with the goal of forcing a system into unsafe states. However, there is currently no way of determining which manipulations of a test case cause a failure without systematically removing each one and re-running the test, which can be …

Market Reactions To Deceptive Language In Fake News: Implications From Language Expectancy Theory And Transfer Learning, Ka Chung Ng, Ping Fan Ke, Ping Fan, Mike So, Tam, Kar Yan

Research Collection School Of Computing and Information Systems

The advent of generative artificial intelligence (AI) has heightened the proliferation of fake news. A key challenge is the limited real-world data to investigate the societal impact of fake news produced by generative AI. In this paper, we examine stock market reactions to financial news articles that exhibit stylometric similarity to human-crafted and AI-crafted fake financial news. Grounded in language expectancy theory, we employ a style-based transfer learning model, pre-trained to recognizing deceptive language employed in various types of fake news intricacies. We then apply this model to a comprehensive dataset of financial news, assigning a “veracity style score” to …

Open Source Software Development Tool Installation: Challenges And Strategies For Novice Developers, Larissa Salerno, Christoph Treude, Patanamon Thongtanunam

Research Collection School Of Computing and Information Systems

As the world of technology advances, so do the tools that software developers use to create new programs. In recent years, software development tools have become more popular, allowing developers to work more efficiently and produce higher-quality software. Still, installing such tools can be challenging for novice developers at the early stage of their careers, as they may face issues such as compatibility problems (e.g., with operating systems) and unclear instructions. Therefore, this work aims to investigate the challenges novice developers face when installing software development tools and the strategies they employ to overcome them. To investigate these, we conducted …

Generation Of Elaborated, Targeted And Effective Feedback For Novice Programmers Using Llm, Hua Leong Fwa

Research Collection School Of Computing and Information Systems

Programming errors and misconceptions are pervasive in novice programmers which causes difficulty in the learning of computer programming. Large Language Models (LLMs), with their ability to comprehend and generate programming codes have shown promising results in the automatic identification of errors. This can potentially benefit student programmers by providing them with timely formative feedback at efficiencies and scale that were not attainable previously. In this study, we leveraged an LLM - OpenAI o4-mini for the generation of elaborated, targeted feedback for novice programmers across PHP and JavaScript exercises. We contend that the feedback needs to be effective and targeted other …

Natural Adversaries: Fuzzing Autonomous Vehicles With Realistic Roadside Object Placements, Yang Sun, Haoyu Wang, Christopher M. Poskitt, Jun Sun

Research Collection School Of Computing and Information Systems

The emergence of Autonomous Vehicles (AVs) has spurred research into testing the resilience of their perception systems, i.e., ensuring that they are not susceptible to critical misjudgements. It is important that these systems are tested not only with respect to other vehicles on the road, but also with respect to objects placed on the roadside. Trash bins, billboards, and greenery are examples of such objects, typically positioned according to guidelines developed for the human visual system, which may not align perfectly with the needs of AVs. Existing tests, however, usually focus on adversarial objects with conspicuous shapes or patches, which …

Func: Reducing The Impact Of Android Framework Evolution On Malware Detection, Hailong Yu, Tiantian Wang, Lwin Khin Shar, Hanmeng Li, David Lo

Research Collection School Of Computing and Information Systems

Android malware detection approaches commonly use APIs and permissions as features for classifying malware. However, since the release of the first Android operating system in 2008, the Android framework has undergone numerous version updates. The evolution of the Android framework over time has led to changes in APIs and permissions, including deprecations and replacements. These changes can result in inaccurate characterization of Android malware, thereby affecting performance of malware detectors. There is a lack of methods to mitigate the impact of Android framework evolution on malware detection. To fill this gap, we conduct a systematic study of the impact of …

Fighting Against Recruitment Scams: Theory-Driven Supervised Learning And Empirical Analysis For Digital Fraudulent Recruitment Posting Behavior, Tom (Tianteng) Wang, David (Jingjun) Xu, Keng Siau, Zhongju (John) Zhang

Research Collection School Of Computing and Information Systems

The number of recruitment postings on digital recruitment hiring platforms has increased since the COVID-19 pandemic. However, the weak surveillance and operations of these platforms, combined with the fact that most job seekers have relatively low vigilance and a strong desire for recruitment offers, enable scammers to easily deceive job seekers for their money and confidential information. In this work, we combine prevailing text mining techniques (i.e., ChatGPT with prompting engineering and supervised machine learning) with interpersonal deception theory (IDT) from social science to design an interpretable IT system to predict fraudulent recruitment postings on digital recruitment-hiring platforms. We compare …

Enhancing Action And Ingredient Modeling For Semantically Grounded Recipe Generation, Guoshan Liu, Bin Zhu, Yian Li, Jingjing Chen, Chong-Wah Ngo, Yu-Gang Jiang

Research Collection School Of Computing and Information Systems

Recent advances in Multimodal Large Language Models (MLMMs) have enabled recipe generation from food images, yet outputs often contain semantically incorrect actions or ingredients despite high lexical scores (e.g., BLEU, ROUGE). To address this gap, we propose a semantically grounded framework that predicts and validates actions and ingredients as internal context for instruction generation. Our two-stage pipeline combines supervised fine-tuning (SFT) with reinforcement fine-tuning (RFT): SFT builds foundational accuracy using an Action-Reasoning dataset and ingredient corpus, while RFT employs frequency-aware rewards to improve long-tail action prediction and ingredient generalization. A Semantic Confidence Scoring and Rectification (SCSR) module further filters and …

Selective Concolic Testing, Guofeng Zhang, Zhenbang Chen, Ziqi Shuai, Jun Sun, Weijiang Hong, Yufeng Zhang, Ji Wang, Yang Liu

Research Collection School Of Computing and Information Systems

The principled combination of symbolic execution and random testing lacks a formal foundation, especially in deciding which inputs to symbolize. We propose selective concolic testing, a cost-aware framework that formulates this choice as an optimized policy problem of a MDP (Markov Decision Process). We model program exploration over a finite control-flow graph, where MDP states represent covered statements, actions partition path constraints into symbolic and random fragments, rewards reflect coverage gain, and costs account for SMT solving effort and sampling inefficiency. Our framework yields the first formal characterization of selective symbolization as policy synthesis in a probabilistic system. We prove …

Detecting Doubt In Reflective Learning: A Learning Analytics Study With Large And Small Language Models, Eng Lieh Ouh, Kar Way Tan, Siaw Ling Lo, Yuhao Zhang

Research Collection School Of Computing and Information Systems

Reflective learning enhances understanding, especially when instructors promptly address difficulties raised in student reflections. Automated doubt detection can reduce time for instructors, yet existing classification approaches take substantial time for manual annotation and model training. This paper investigates whether large and small language models (LLMs, SLMs) can automate doubt detection without time-consuming training. Using a dataset of anonymized student reflections, we evaluate zeroshot, few-shot prompting, and multi-step reasoning against prior supervised classification baselines. We show that LLMs (GPT-4o, Claude-4, Gemini-2.5) surpass earlier F1 scores without prompting, while prompting further improves their performance. However, using proprietary LLMs can raise cost and …

Gencode: A Generic Data Augmentation Framework For Boosting Deep Learning-Based Code Understanding, Zeming Dong, Qiang Hu, Xiaofei Xie, Maxime Cordy, Mike Papadakis, Yves Le Traon, Jianjun Zhao

Research Collection School Of Computing and Information Systems

Pre-trained code models lead the era of code intelligence, with multiple models designed with impressive performance. However, one important problem, data augmentation for code data that automatically helps developers prepare training data lacks study in this field. In this paper, we introduce a generic data augmentation framework, GenCode, to enhance the training of code understanding models. Simply speaking, GenCode follows a generation-and-selection paradigm to prepare useful training code data. Specifically, it employs code augmentation techniques to generate new code candidates first and then identifies important ones as the training data by influence scores. To evaluate the effectiveness of GenCode, we …

High Throughput Phenomics Pipeline For Pulse Crop Nutritional Breeding, Amod Udayanga Madurapperumage

All Dissertations

Dry pea (Pisum sativum L.), lentil (Lens culinaris Medik.), and chickpea (Cicer arietinum L.) are major pulse crops valued for their high nutritional composition and importance to global food systems. Pulses are rich in carbohydrates, protein, and essential minerals, making them ideal whole foods and critical contributors to food and nutrition security. Due to these advantages, pulse breeding programs are increasingly focusing on enhancing nutritional traits, such as protein quality, amino acid balance, and micronutrient density, through the process of biofortification. However, improvement of agronomic traits remains equally essential. Characteristics such as plant height, standability, stress tolerance, …

Generalizable Adaptation For Vision-Language Models, Niloufar Alipour Talemi

All Dissertations

Vision-Language Models (VLMs) and Multimodal Large Language Models (MLLMs) have recently emerged as powerful frameworks for learning joint representations across visual and textual modalities. These models enable a wide range of applications, including visual recognition, multimodal reasoning, and visual question answering. However, adapting large pre-trained VLMs to downstream tasks while preserving their strong generalization ability remains a significant challenge, particularly under domain shifts or limited supervision. This dissertation focuses on developing methods for generalizable adaptation of VLMs, aiming to improve robustness, efficiency, and applicability across diverse tasks and environments.

First, this work introduces novel prompt learning strategies for adapting CLIP-style …

Learning Global Context For Sparse Activity Recognition In Lengthy Recordings With Limited Dataset Size, Zeyu Tang

All Dissertations

This dissertation describes methods to analyze lengthy recordings of data in order to detect sparsely occurring activities. The narrative below describes the progression of research that led to the development of these methods and their generalization into a unified framework. My research started with designing models for dietary monitoring, including detecting meals from day-long recordings and detecting intake gestures from meal-length recordings. Both tasks share some common characteristics: (a) the target event takes only a small portion of data recordings, and (b) there is global context within full-length data recordings that can help a model make better decisions. After finishing …

Towards Generalizable Representation Learning Across Domains, Hossein Kashiani

All Dissertations

Despite remarkable progress in deep learning, a major challenge remains: machine learning models often struggle to generalize to unseen domains under distribution shift. In real-world settings, data often differ from training conditions due to changes in lighting, sensor type, image resolution, and style. These differences can significantly degrade performance, highlighting the need for representations that are both robust and generalizable. This thesis addresses this challenge by developing a set of frameworks for generalization across domains in anomaly detection, deepfake detection, and vision-language image recognition. For anomaly detection, this thesis introduces ROADS, a robust prompt-driven framework for multi-class unified anomaly detection. …

Decision Making For Large-Scale Problems Under Uncertainty And Conflict, Benjamin J. Hamlin

All Dissertations

Large-scale decision-making problems appear in many areas including long-range forecasting such as energy generation forecasting. Many such problems are subject to conflicting objectives and uncertain data, and can be modeled as linear optimization problems. We study novel theoretical results and algorithms for large-scale linear decision problems under conflict and uncertainty. First, we propose a parametric Benders decomposition algorithm for solving large-scale linear optimization problems with multiple objectives or deterministically uncertain objectives. Second, we extend the parametric Benders decomposition to a multi-stage setting, developing a parametric stochastic dual dynamic programming algorithm, which enables decision-making when conflicts and uncertainty have planning impacts …

Parameterized Polynomial Systems: Monodromy, Sparse Polynomials, And Solutions, Julianne Barnhart

All Dissertations

The lift of a loop in the base space of a branched cover to the cover induces a permutation of points in a fibre. The monodromy group of the branched cover is the permutation group generated by all such permutations. When loops are restricted to a particular subset of the base space, the corresponding permutation group induced by these loops is the restricted monodromy group. Monodromy groups encode structure and symmetries of many enumerative problems. We describe the relationship between the restricted monodromy group and the monodromy group of the original branched cover. Our main result is a local-to-global property: …

Galois Action And Arithmetic In Algebraic Number Fields, Jared Kettinger

All Dissertations

This dissertation explores the arithmetic of numerous algebraic objects living within an algebraic number field from submonoids of the integers up to localizations of the ring of integers. We begin with a study of factorization in proper orders using an element-theoretic approach. In Chapter 2, by defining a natural generalization of the Davenport constant, we are able to determine the elasticity of certain orders whose integral closure is a unique factorization domain. In Chapter 3, using ideal-theoretic analogues, we are able to significantly broaden the scope of our results and the literature on factorization in orders. In particular, we give …

Integrating Incentive Design And Spatial Prioritization For Climate-Smart Forestry Adoption In South Carolina, United States, Miah Maye Pormon

All Dissertations

Forests provide essential ecosystem services, including carbon sequestration, water regulation, timber production, and habitat provision. However, increasing development pressures and land-use changes threaten forest persistence and long-run ecosystem service provision. Climate-smart forestry (CSF) practices, such as improved forest management and extended rotation, offer opportunities to enhance carbon storage, forest resilience, and economic livelihoods. The effectiveness of these practices depends on forest owners’ participation and the strategic allocation of financial resources or incentives. This dissertation develops an integrated framework that combines behavioral economic analysis and mapping to improve the design of current incentive programs. The first chapter employs the Contingent Valuation …