Digital Commons Network^™

Automatic Generation Of Introductory Programming Exercises With Large Language Models, Nguyen Binh Duong Ta, Hua Gia Phuc Nguyen, Gottipati Swapna

Research Collection School Of Computing and Information Systems

Despite recent advances in code generation made possible by large language models (LLMs), programming is still an essential skill that computing students need to master now and in the foreseeable future. In learning programming, frequent practices with exercises set at an appropriate difficulty and knowledge level is of crucial importance for students. However, it’s not a trivial task for instructors to create many good quality exercises customized for each student. Programming problems found on Internet sources such as LeetCode are mostly too challenging for novice programmers with no prior coding knowledge. Recent work in AI-enabled education has been leveraging LLMs …

Choice-Based Crowdshipping For Next-Day Delivery Services: A Dynamic Task Display Problem, Alp Arslan, Firat Kilci, Shih-Fen Cheng, Archan Misra

Research Collection School Of Computing and Information Systems

This paper studies integrating the crowd workforce into next-day home delivery services. In this setting, both crowd drivers and contract drivers collaborate in making deliveries. Crowd drivers have limited capacity and can choose not to deliver if the presented tasks do not align with their preferences. The central question addressed is: How can the platform minimize the total task fulfilment cost, which includes payouts to crowd drivers and additional payouts to contract drivers for delivering the unselected tasks by customizing task displays to crowd drivers? To tackle this problem, we formulate it as a finite-horizon Stochastic Decision Problem, capturing crowd …

Can We Read Ai’S Mind? A Quest For Transparency, Santhosh Kumar Ravindran, Estera Kot, Fiona Fui-Hoon Nah

Research Collection School Of Computing and Information Systems

Although Artificial Intelligence (AI) systems are playing an increasing role in critical domains such as healthcare, finance, and autonomous systems, their decision-making processes remain largely opaque. This paper examines the challenges of AI transparency, addressing the “black box” problem using Explainable AI (XAI) techniques such as SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME). It also examines the ethical, regulatory, and societal implications of AI opacity and proposes a Comprehensive AI Observability (CAO) Framework that integrates deep explainability, provenance tracking, and real-time monitoring to enhance AI accountability. By bridging technical solutions with governance structures, this research emphasizes the …

Actor-Critic For Continuous Action Chunks: A Reinforcement Learning Framework For Long-Horizon Robotic Manipulation With Sparse Reward, Jiarui Yang, Bin Zhu, Jingjing Chen, Yu-Gang Jiang

Research Collection School Of Computing and Information Systems

Existing reinforcement learning (RL) methods struggle with long-horizon robotic manipulation tasks, particularly those involving sparse rewards. While action chunking is a promising paradigm for robotic manipulation, using RL to directly learn continuous action chunks in a stable and data-efficient manner remains a critical challenge. This paper introduces AC3 (Actor-Critic for Continuous Chunks), a novel RL framework that learns to generate high-dimensional, continuous action sequences. To make this learning process stable and dataefficient, AC3 incorporates targeted stabilization mechanisms for both the actor and the critic. First, to ensure reliable policy improvement, the actor is trained with an asymmetric update rule, learning …

Leveraging Large Language Models For Career Mobility Analysis: A Study Of Gender, Race, And Job Change Using Us Online Resume Profiles, Palakorn Achananuparp, Ye Xu, Yao Lu, Xavier Jayaraj Siddarth Ashok, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

We present a large-scale analysis of career mobility of college-educated U.S. workers using online resume profiles to investigate how gender, race, and job change options are associated with upward mobility. This study addresses key research questions of how the job changes affect their upward career mobility, and how the outcomes of upward career mobility differ by gender and race. We address data challenges – such as missing demographic attributes, missing wage data, and noisy occupation labels – through various data processing and Artificial Intelligence (AI) methods. In particular, we develop a large language models (LLMs) based occupation classification method known …

Dual-Lora And Quality-Enhanced Pseudo Replay For Multimodal Continual Food Learning, Xinlan Wu, Bin Zhu, Feng Han, Pengkun Jiao, Jingling Chen

Research Collection School Of Computing and Information Systems

Food analysis has become increasingly critical for health-related tasks such as personalized nutrition and chronic disease prevention. However, existing large multimodal models (LMMs) in food analysis suffer from catastrophic forgetting when learning new tasks, requiring costly retraining from scratch. To address this, we propose a novel continual learning framework for multimodal food learning, integrating a Dual-LoRA architecture with Quality-Enhanced Pseudo Replay. We introduce two complementary low-rank adapters for each task: a specialized LoRA that learns task-specific knowledge with orthogonal constraints to previous tasks’ subspaces, and a cooperative LoRA that consolidates shared knowledge across tasks via pseudo replay. To improve the …

Design Principles For Customer-Engaging Digital Service Systems: An Action Research Study, Keng Leng Siau, Xiaofeng Chen, Xin Tan

Research Collection School Of Computing and Information Systems

Digital services represent a business approach employed by organizations to operate in the digital environment. However, systematic development guidelines for developing quality digital service systems are lacking in the literature. The authors identified four general challenges for developing and implementing customer-engaging digital service systems (CEDSS). By employing the method of canonical action research in a digital service system project, they derived 10 design principles for developing high-quality CEDSS. They empirically evaluated the design principles in the development project and through follow-up focus group sessions. The design principles provide applicable and actionable guidelines for the development of CEDSS.

Towards Secure Program Partitioning For Smart Contracts With Llm’S In-Context Learning, Ye Liu, Yuqing Niu, Chengyan Ma, Ruidong Han, Wei Ma, Yi Li, Debin Gao, David Lo

Research Collection School Of Computing and Information Systems

Smart contracts are highly susceptible to manipulation attacks due to the leakage of sensitive information. Addressing manipulation vulnerabilities is particularly challenging because they stem from inherent data confidentiality issues rather than straightforward implementation bugs. To tackle this by preventing sensitive information leakage, we present PARTITIONGPT, the first LLM-driven approach that combines static analysis with the in-context learning capabilities of large language models (LLMs) to partition smart contracts into critical (privileged) and normal codebases, guided by a few annotated sensitive data variables. We evaluated PARTITIONGPT on 18 annotated smart contracts containing 99 sensitive functions. The results demonstrate that PARTITIONGPT successfully generates …

Editorial: Special Section On Challenges And Opportunities In Retrieval-Augmented Generation For Llms: Techniques, Trends, And Applications, Philip S. Yu, Haofen Wang, Feida Zhu

Research Collection School Of Computing and Information Systems

Retrieval-Augmented Generation (RAG) represents a transformative advancement for Large Language Models (LLMs) by integrating external knowledge to substantially improve accuracy and mitigate hallucinations. As a pivotal technology in the contemporary generative Artificial Intelligence (AI) landscape, RAG addresses fundamental challenges in knowledge-intensive tasks. This special issue serves as a dedicated platform to showcase these cutting-edge advancements. It features six rigorously peer-reviewed papers that present state-of-the-art research and applications in the rapidly evolving field of RAG.

Qualitative Study For Llm-Assisted Design Study Process: Strategies, Challenges, And Roles, Shaolun Ruan, Rui Sheng, Xiaolin Wen, Jiachen Wang, Tianyi Zhang, Yong Wang, Tim Dwyer, Jiannan Li

Research Collection School Of Computing and Information Systems

Design studies aim to develop visualization solutions for real-world problems across various application domains. Recently, the emergence of large language models (LLMs) has introduced new opportunities to enhance the design study process, providing capabilities such as creative problem-solving, data handling, and insightful analysis. However, despite their growing popularity, there remains a lack of systematic understanding of how LLMs can effectively assist researchers in visualization-specific design studies. In this paper, we conducted a rnulti-stage qualitative study to fill this gap, which involved 30 design study researchers from diverse backgrounds and expertise levels. Through in-depth interviews and carefully-designed questionnaires, we investigated strategies …

Artem: Enhancing Large Language Model Agents With Spatial-Temporal Episodic Memory, Cassandra Hui Ming Tan, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Current large language models (LLMs) exhibit significant deficiencies in episodic memory tasks including encoding, storing, and retrieving specific information from temporally dependent events over a long period of time. Recent approaches to handle memory tasks in LLMs, such as in-context learning, retrieval-augmented generation (RAG), and fine-tuning, may resolve the long-term retention issues, but are still inadequate to handle tasks requiring chronological awareness of the stored information. We introduce Agentic Retrieval with Temporal-Episodic Memory (ARTEM), a hybrid LLM-based agent architecture integrating LLMs with a self-organizing neural network named Spatial-Temporal Episodic Memory (STEM), designed to handle episodic memory tasks. Our approach employs …

Dystop: Dynamic Staleness Control And Topology Construction For Asynchronous Decentralized Federated Learning, Yizhou Shi, Qianpiao Ma, Yan Xu, Junlong Zhou, Ming Hu, Yunming Liao

Research Collection School Of Computing and Information Systems

Federated Learning (FL) has emerged as a potential distributed learning paradigm that enables model training on edge devices (i.e., workers) while preserving data privacy. However, its reliance on a centralized server leads to limited scalability. Decentralized federated learning (DFL) eliminates the dependency on a centralized server by enabling peer-to-peer model exchange. Existing DFL mechanisms mainly employ synchronous communication, which may result in training inefficiencies under heterogeneous and dynamic edge environments. Although a few recent asynchronous DFL (ADFL) mechanisms have been proposed to address these issues, they typically yield stale model aggregation and frequent model transmission, leading to degraded training performance …

Llamoco: Instruction Tuning Of Large Language Models For Optimization Code Generation, Zeyuan Ma, Yue-Jiao Gong, Hongshu Guo, Jiacheng Chen, Yining Ma, Zhiguang Cao

Research Collection School Of Computing and Information Systems

Recently, combining the strength of large language models (LLMs) and Evolutionary Computation (EC) has shown promising results for addressing optimization problems. It typically involves either iterative next-step solution seeking or directly prompting LLMs to generate critical optimization codes. However, these methods often suffer from low computational efficiency, high sensitivity to prompt design, and a lack of domain-specific knowledge. We introduce LLaMoCo, the first instruction-tuning framework designed to adapt LLMs for solving optimization problems in a code-to-code manner. LLaMoCo features a comprehensive instruction set that includes code-style problem descriptions as input prompts and robust optimization codes from expert EC optimizers as …

Flood-Season Surface Water-Groundwater Interactions Across Distinct Geomorphic Units In A Yellow River Great Bend Tributary Basin, Yinlong Wang, Ruizhong Gao, Debin Jia, Xixi Wang, Tingxi Liu, Xiaomin Liu, Shiming Bai

Civil & Environmental Engineering Faculty Publications

Surface water-groundwater interactions are complex in the Great Bend region of the Yellow River. Clarifying water exchange and source differences among geomorphic units is important for understanding regional hydrological processes and improving water resources management. In this study, the Wulanmulun River Basin, a typical tributary of the Yellow River, was selected as the study area. A total of 90 water samples were collected, including 25 river water samples, 43 groundwater samples, and 22 precipitation samples. Gibbs diagrams, multivariate statistical analysis, PMF, and MixSIAR models were used to investigate the hydrochemical and isotopic characteristics, source contributions, and transformation relationships of surface …

The Journey Of High School Teachers Evolving Into Career Educators, Diane B. Ried

UNF Graduate Theses and Dissertations

Abstract

Teacher attrition has been a major challenge in the United States for decades, but more so after covid. This case study explored and expanded the understanding of the different levels of environmental impact on high school teacher retention in a Florida high school as they evolved into career educators. The present study used Bronfenbrenner’s (1979) Ecological Systems Theory to examine the teacher’s retention in a county in northcentral Florida. In order to better understand the experience of career development, this study used Savickas’ Career Construction Theory (2019). This case study investigated strategies, supports, and diversity related initiatives impacting a …

Ridit-Based Adaptive Allocation In Two-Stage Clinical Trials With Binary Outcomes, Dewan Fahim

UNF Graduate Theses and Dissertations

This study explores better ways to assign patients to treatments in clinical trials with binary outcomes, such as success or failure. Adaptive methods are used to learn from early results and adjust treatment assignments during the trial, helping more patients receive better performing treatments while maintaining reliable conclusions. We focus on trials comparing multiple treatments using a two-stage design. In the first stage, several treatments are tested to identify the most promising one; in the second stage, that treatment is compared with a control. Unlike traditional equal assignment, we use adaptive allocation in the second stage to make better use …

Energy-Efficient Security For Narrowband Iot Using Blockchain And Ep-Cumac, Hafizullah Kakar

UNF Graduate Theses and Dissertations

The Narrowband Internet of Things (NB-IoT) continues to expand but faces challenges such as cryptographic overhead and energy consumption. Security frameworks such as blockchain and Energy-Performance Cumulative Message Authentication Codes (EP-CuMAC) rely heavily on SHA-256, which is not optimized for energy-limited devices.

This work unifies two complementary approaches, a hybrid blockchain-based NB-IoT framework and an EP-CuMAC-based framework, by engineering their cryptographic core with an Energy Complexity Model-optimized SHA-256 (ECM-SHA256). ECM applies parallel memory-bank mapping and block-level access optimization to reduce redundant power usage while preserving algorithmic integrity.

Experimental evaluation on identical Intel DDR3 systems using pyRAPL shows energy savings of …

Growth And Dielectric Characterization Of Epitaxial Sr1-Xmgxtio3 Thin Films, Richard Badu

UNF Graduate Theses and Dissertations

Complex oxide materials with ferroelectric ground states remain promising candi dates for next-generation high-capacitance and nonlinear microelectronic applica tions. One of those materials is SrTiO3 (STO). However, STO is an incipient fer roelectric with anomalously high dielectric permittivity at low temperatures. STO crystals possess a highly polarizable lattice that is sensitive to even small amounts of impurities. Substituting Mg into the STO matrix is predicted to induce a corre lation between ferroelectric and relaxor behavior. In this thesis, we demonstrated the growth of a series of epitaxial STO and Sr1-xMgxTiO3 thin films using molec ular beam epitaxy. The surface evolution …

Entropic Foundation Of Finance And Physics: Securities Price Dynamics And Quantum Theory, Mohammad Abedi

Electronic Theses & Dissertations (2024 - present)

In many scientific and financial contexts, we must reason and make predictions under conditions of incomplete information. This dissertation develops Entropic Dynamics (ED) as a unified framework for deriving dynamical laws directly from principles of inference. Within this approach, probability distributions represent states of knowledge, and their evolution is determined through entropy maximization subject to relevant constraints. This leads to a novel concept of entropic time and a formulation of dynamics as an inferential process. In this talk, I will present how ED provides a common foundation across multiple domains. In physics, quantum dynamics for particles and scalar fields in …

A Predator-Prey Biological Model Of Multiple Species With Linear Growth Rates, Joon Hyuk Kang

Faculty Publications

No abstract provided.

Artificial Intelligence, Fundamental Motives, And Evolutionary Mismatch, Amy J. Lim, Jose. C. Yong, Edison Sora Tan

Research Collection School of Social Sciences

In recent years, the intersection of artificial intelligence (AI) and psychology has garnered unprecedented attention, particularly following the advent of generative AI tools in 2022. These tools, capable of producing human-like text, images, and even deepening our understanding of cognitive processes, have not only captured the public imagination but also sparked new concerns and debates within the psychological community. While AI has been a subject of research for decades, the emergence of its generative capabilities has truly thrust AI into the spotlight. This article explores how these advancements are reshaping our understanding of human cognition and behavior, as well as …

Ultrafast Vibrational Dynamics In Important Wide-Bandgap Semiconductors, Dielectrics And Energetic Materials, Dinusha Madushanka Senarathna

Open Access Dissertations

This dissertation applies time-resolved coherent anti-Stokes Raman scattering (tr-CARS), to measure ultrafast vibrational dynamics in technologically important solid-state and van der Waals molecular systems. The central goal is to use time-domain Raman methods to resolve mode-specific phonon and vibrational dephasing processes with high temporal precision, high spectral selectivity, and sufficient experimental flexibility to probe materials ranging from wide-bandgap semiconductors and oxide crystals to energetic molecular crystals. Across the work, I show that carefully designed tr-CARS measurements can access vibrational lifetimes from hundreds of femtoseconds to several picoseconds, enabling direct observation of decay pathways, relaxation mechanisms, and dispersion effects that shape …

Challenges And Best Practices For The Development Of Coastal Hazard Decision Support Tools, Noah Hallisey

Open Access Dissertations

There is growing interest in developing Decision Support Tools (DSTs) supporting emergency managers and other decision-makers during coastal storm events. Yet many tools fail to inform decision-making due to challenges associated with their development and transition into operational tools for real-time decision-making. This dissertation investigates these challenges and offers best practices for their development and implementation for real-world decision-making through a literature review, interviews with subject matter experts in the United States, and a real-world case study.

Manuscript 1 reviews existing published literature to understand whether and how tool developers are incorporating emergency managers in the development of DSTs and …

Volatiles In Mantle Sources At Mid-Ocean Ridge And Intraplate Settings, Rebecca Lippitt

Open Access Dissertations

Volatiles play an integral role in upper mantle processes and the eruptive styles of volcanoes. Although we know the importance of volatiles to volcanic systems, processes like melting, crystallization, and degassing alter the volatile abundances of mantle melts, making it difficult to quantify mantle source compositions and the extent to which volatiles influence melting processes. Additionally, volatile content may be a key factor in setting the oxidation conditions of mantle source rocks and subsequently changing those conditions in a body of magma as it ascends through the crust and is erupted at the Earth’s surface. Recent work, however, has identified …

Latent Classification Of Time-Dependent Transition Rates In Longitudinal Binary Outcome Data, Joonha Chang, Wenyaw Chan

Faculty, Staff and Student Publications

Continuous-time Markov chain (CTMC) models and latent classification methods are commonly used to analyze longitudinal categorical outcomes in medical research. While CTMC models are popular for their simplicity and effectiveness, their assumption of constant transition rates presents limitations in capturing dynamic behaviors. To address this, non-homogeneous continuous-time Markov chains (NH-CTMCs) have been developed, incorporating time-varying transition rates to enhance model flexibility. In this study, we leverage closed-form transition probabilities for a fully ergodic two-state NH-CTMC model and propose a latent class clustering approach to identify heterogeneous transition rate patterns within the population. We emphasize the potential advantages of these models …

Aqueous Synthesis Of Luminescent Semiconductors For Opto-Electronic Applications, Saurabh Singh

Theses and Dissertations--Chemical and Materials Engineering

The advancement of opto-electronic and scintillation technologies relies heavily on developing low-temperature, eco-friendly, and scalable synthesis routes for high performance luminescent halide-based semiconductor materials. However, traditional synthesis methods for halide-based semiconductors, including hot-injection, solvothermal, solid-state reactions, Ligand-Assisted Reprecipitation (LARP), microwave-assisted synthesis, and thin film deposition techniques (spin coating, physical vapor deposition (PVD), chemical vapor deposition (CVD), etc.), often demand toxic organic/inorganic solvents, elevated processing temperatures, and high vacuum/inert environments. Such constraints limit their scalability, raise environmental concerns, and impede their commercial-level device integration. This research overcomes these long-standing challenges by employing water as a powerful crystallization-directing, and environmentally benign medium …

Measuring The Efficiency Of The Arts And Culture Sector Relative To Gdp: A State-Level Analysis Of The United States, Ameerkhan Jaffar Khan Khader Khan

Selected Full-Text Master Theses 2021-

Arts and cultural production contributed $1.17 trillion to United States gross domestic product in 2023, 4.2% of the national total, but that contribution is spread very unevenly across states, and the official statistics describe how large the sector is rather than how efficiently it operates (Bureau of Economic Analysis, 2024). This study asks how efficiently each state convert growth in arts and culture employment into growth in value added, how many inputs the efficiency model can carry before it stops distinguishing 51 observations, and whether observable state characteristics explain the differences found. The analysis uses 2023 state-level data for all …

Better Practices In Feedback, Sarah Wackerbarth, Madeline Aulisio Miller

Pedagogicon Conference Proceedings

Feedback is an essential part of the learning process. This paper examines various types of feedback, identifies barriers, and presents practices for enhancing classroom feedback. A case study of quick polling in an online course demonstrates how to collect timely student feedback to improve teaching.

A Study Of The Impacts Of Infusing Data Analysis And Research In An Interdisciplinary Environmental Economics Course, Sean P. Macdonald

Publications and Research

This paper explores the impacts of introducing quantitative literacy skills in an interdisciplinary Environmental Economics course typically taught as an issues and policy course without a quantitative component. The study examines the effects of infusing an engaging, student-selected data collection and analysis assignment on students' quantitative reasoning skills, as well as their interest in and attitudes about data analysis and quantitative information. Using data gathered from a set of pre- and post-assessment questions designed to measure changes in quantitative reasoning skills and attitudes, the findings point to significant attitudinal impacts, gains, but smaller, insignificant gains in quantitative reasoning skills.

Detection Of Financial And Political Fake News As A Measure To Prevent Instability In Financial Markets, Konstantyn Malyshenko

DLSU Business & Economics Review

This article explores the role of social networks as a catalyst for instability in financial markets. Its purpose is to present strategies for mitigating the media’s influence on adverse outcomes, primarily by analyzing the information cascades and related transactions in stock markets. The innovative aspect of this research lies in the development of methods for analyzing specific types of information, particularly media reports, to identify indicators of fake that distort public perception. The focus of this study is on fake news and the analysis of its potential linguistic features for identification purposes. A significant outcome of this research is the …