Physical Sciences and Mathematics Commons^™

Evaluating Chatgpt To Answer Multi-Modal Exercises In Computer Science Education, Eng Lieh Ouh, Kar Way Tan, Siaw Ling Lo, Benjamin Gan

Research Collection School Of Computing and Information Systems

This study investigates ChatGPT-4o's ability to answer multi-modal assessment exercises in computer science (CS) courses. While the use of large language models (LLMs) to answer text-based exercises are extensively researched, their ability to answer exercises involving artifacts of other modalities remains underexplored. To close this gap, we evaluate ChatGPT-4o's answers to 120 multi-modal CS exercises in programming, software design, human-computer interaction, statistical analysis, process analysis, and simulation. The multi-modal artifacts in these exercises include class diagrams, sequence diagrams, user interface images, analytical charts, workflow diagrams and object-flow diagrams. Our comparisons to the expected answers of these exercises show that ChatGPT-4o …

An On-The-Fly Synthesis Framework For Ltl Over Finite Traces, Shengping Xiao, Yongkang Li, Shufang Zhu, Jun Sun, Jianwen Li, Geguang Pu, Moshe Vardi

Research Collection School Of Computing and Information Systems

We present an on-the-fly synthesis framework for Linear Temporal Logic over finite traces (LTLf) based on top-down deterministic automata construction. Existing approaches rely on constructing a complete Deterministic Finite Automaton (DFA) corresponding to the LTLf specification, a process with doubly exponential complexity relative to formula size in the worst case. In this case, the synthesis cannot be conducted until the entire DFA is constructed. This inefficiency is the main bottleneck of existing approaches. To address this challenge, we first present a method for converting LTLf into Transition-based DFA (TDFA) by directly leveraging LTLf semantics, incorporating intermediate results as direct components …

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

Research Collection School Of Computing and Information Systems

Query understanding in CIS involves accurately interpreting user intent through context-aware interactions. This includes resolving ambiguities, refining queries, and adapting to evolving information needs. LLM 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 multi-turn interactions, strategies for building more interactive systems, and applications like proactive query management and query reformulation. We also discuss key challenges in integrating …

An Evening With Mobile Hyflex, Peter Alexander

Case studies: Digital Education

Network Security is a 10-credit module taught on the part-time Bachelor of Science in Computing in Digital Forensics & Cyber Security course in TU Dublin. While the overall course is mainly delivered online, there are some topics in this particular module which benefit from having a hands-on interactive element. The challenge though with facilitating learners to have that interactive experience is that the ones who cannot travel to campus should not be excluded. The mobile Hyflex project helped address this challenge by giving students both on campus and online a comparable interactive experience. Changes made to practice (100-150 words).

Application Of Hyflex In The Application Security Module, Vanessa Ayala-Rivera

Case studies: Digital Education

No abstract provided.

Enhancing Phenotyping Accuracy For Selection Of Urochloa Spp. Tolerant Genotypes To Red Spider Mite (Oligonychus Trichardti), Paula Espitia-Buitrago, José Miguel Cotes Torres, Luis Miguel Hernández, Juan Andres Cardoso, Frank Chidawanyika, Rosa N. Jauregui

All Peer-Reviewed Publications

The red spider mites are a major biotic limitation to productivity for Brachiaria (Urochloa spp.) grasses in tropical Eastern Africa, causing severe economic losses mainly in the dry seasons. However, due to the lack of reports of integrated pest management strategies, genetic resistance can play a crucial role in Brachiaria-based livestock systems, minimising the impact of this pest. The objective of this study was to develop and validate a methodology for accurately categorising resistance responses in Urochloa genotypes to identify potential sources of resistance to the Western Kenya red spider mite Oligonychus trichardti (Meyer 1974). Accordingly, 25 genotypes of Urochloa …

Customizing Ai Strategies Across Multiple Generations, Matthew Harrer

Theses

This project investigates how artificial intelligence can help brands and marketers connect more effectively with Generation X, Millennials, and Generation Z. The literature review lays the groundwork that focuses on consumer behaviors and the integration of AI into digital marketing practices for each generation. The second part of the project involves a secondary data analysis of 21 recent marketing surveys and reports that explores topics related to trust, personalization, and social media. By integrating the findings into an insightful guidebook, marketers will be able to maximize these insights into clear actionable strategies.

Literature Review Of Reverse Electrodialysis Technoeconomic And Environmental Analysis, Kevin Allen Wear

Water Resources Science and Technology Theses and Graduate Research Reports (Archived)

This thesis presents a theoretical analysis of Reverse Electrodialysis (RED) for electricity generation using produced water—a high-salinity byproduct from oil and gas extraction. Drawing from over seventy peer-reviewed studies, this research explores the potential of RED as a sustainable energy solution for industrial wastewater streams. Chapter 1 outlines the environmental and economic implications of produced water. Chapter 2 reviews ion transport theories and membrane technologies. Chapter 3 evaluates past implementations of RED and related membrane systems. Chapter 4 delivers a comprehensive synthesis of current literature, modeling RED performance under realworld salinity gradients, ion compositions, and membrane constraints. Chapter 5 discusses …

Sequential Data Modeling Of Influenza A Via Traditional, Dwt-Gpr Hybrid, And Deep Learning Architectures, Edmund Fosu Agyemang

Theses and Dissertations

Influenza A is responsible for 290,000 to 650,000 respiratory deaths a year, though this estimate is an improvement from years past due to improved sanitation, healthcare practices, and vaccination programs. In this study, we perform a comparative analysis of traditional, deep-learning and discrete wavelet (DWT)-Gaussian Process (GP) hybrid models to predict Influenza A outbreaks. Using historical data from January 2009 to December 2023, we compared the performance of traditional ARIMA and ETS models, four variants of DWT-GPR models and six distinct deep learning architectures: Simple RNN, LSTM, GRU, BiLSTM, BiGRU and Transformer. The results reveal a clear superiority of all …

A Modular Paradigm For The Directly Efficient Representation Of Kinetic Laser-Driven Plasmas, Roland D. Hesse

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

A natural inefficiency in conventional treatment of the plasma distribution arises from indiscriminate consideration of the contributions to field structure that are dynamically sourced from kinetic activity in disparate sectors of phase space. We introduce a range of techniques for model design to maximize representation efficiency without breaking key physical invariants indicative of physical reliability. An overview of varied adaptation to stable time-advance methods is given. Low-dimensional representation of a laser-driven plasma requires some creativity in differential structural modification, while direct efficiency is uncovered through the compression and rarefaction of a nonuniform momentum grid. These numerical models introduce embedded gains …

Exploring And Characterizing Organic Chemistry Students’ Meaningful Engagement In Science Practices, John Zhou

Dissertations and Doctoral Documents, University of Nebraska-Lincoln, 2023–

Undergraduate organic chemistry frequently engages students in key science practices such as analyzing and interpreting spectroscopic data and constructing explanations through reaction mechanisms. However, these activities are often framed as procedural tasks rather than as tools for constructing knowledge. As a result, students may develop incomplete understanding of these practices, making it harder for them to see how scientific knowledge is generated and to use them meaningfully as tools for sensemaking. To better understand how students take up these practices as epistemic tools, three qualitative studies were conducted in this dissertation to investigate how undergraduate organic chemistry students reason with …

Enhancing Proof-Of-Learning Security Against Spoofing Attacks Using Model Watermarking, Ozgur Ural

Doctoral Dissertations and Master's Theses

With the rapid expansion of machine learning (ML) technologies across diverse domains such as healthcare, finance, and autonomous systems, ensuring secure and trustworthy training methodologies has become more critical than ever. Proof-of-Learning (PoL) has recently emerged as a foundational mechanism for verifying the computational effort invested in training ML models, thereby certifying the authenticity and reproducibility of the training process. Yet PoL, when deployed in isolation, remains vulnerable to sophisticated spoofing attacks that manipulate its subset-verification pathways and tolerance parameters. In parallel, model watermarking has become indispensable for safeguarding intellectual property and detecting unauthorized model usage. Motivated by these complementary …

Investing Hysteresis In Floodplain Dynamics Of Lakes In The Middle St. Johns River Using Sentinel-1 Sar Imagery, Keenan Hubbard

Doctoral Dissertations and Master's Theses

Floodplain dynamics are often complex, with hysteresis potentially affecting the temporal relationship between flood stage and flood extent during subsequent inundation phases. This study leverages Sentinel-1 synthetic aperture radar (SAR) imagery to map flood extent in the Middle St. Johns River Lake floodplains and examine the presence of hysteresis during flood events. SAR scenes corresponding to river gauge readings were analyzed from the rising and falling limbs of a flood hydrograph. By comparing these flood maps, we assess differences in inundated areas at equivalent water levels during each stage of the flood event. The findings aim to enhance flood monitoring …

Experimental Analysis Of Satellite Operator Training Using Game-Based Virtual Reality Simulation, Lana Laskey

Doctoral Dissertations and Master's Theses

Satellite data plays a vital role in modern global infrastructure by enabling communications, navigation, and weather forecasting. As demand for satellite technology grows, so does the need for highly trained satellite ground operators. Traditional training regimens for satellite operators employ simulation using two-dimensional computer console displays paired with the varied ability of trainees to generate abstract mental imagery of the scenario. However, this development of mental imagery imposes a considerable learning curve and cognitive workload on the trainee, which may negatively impact the user experience and knowledge gained during the training scenario.

This experimental study investigated the effects of game-based …

Sepsis: I Can Catch Your Lies – A New Paradigm For Deception Detection, Anku Rani, Dwip Dalal, Shreya Gautam, Pankaj Gupta, Vinija Jain, Aman Chadha, Amitava Das, Amit P. Sheth

Publications

Deception is the intentional practice of twisting information. It is a nuanced societal practice deeply intertwined with human societal evolution, characterized by a multitude of facets. This research explores the problem of deception through the lens of psychology, employing a framework that categorizes deception into three forms: lies of omission, lies of commission, and lies of influence. The primary focus of this study is specifically on investigating only lies of omission. We propose a novel framework for deception detection leveraging NLP techniques. We curated an annotated dataset of 876,784 samples by amalgamating a popular large-scale fake news dataset and scraped …

Graduate School Blog - July 2025 Volume 1, Cynthia Haynes

UofM Grad School Blog

The July 2025 UofM Graduate School Blog – Volume 1 continues the Cost of Graduate School Guide with a deep dive into hidden and variable expenses such as residency-based tuition differences, program-specific fees, and differential tuition. The blog provides practical tips for prospective students on how to ask the right financial questions when comparing programs. It also features a student spotlight on Billy Brooks, a dual MHA/MBA candidate motivated to transform healthcare access and equity. Upcoming events include a Virtual Fall 2025 Open House with Financial Aid and USBS, a Dissertation Writers Retreat, and both in-person and virtual Graduate Student …

Political Ecologies Of Storage For The 21st Century, Sayd Randle, Matthew Archer

Research Collection College of Integrative Studies

New resource storage arrangements are proliferating rapidly both in terms of physical infrastructures-for the storage of things like "clean" energy, nuclear waste, carbon dioxide, fresh water, and data-and as part of a set of discursive moves that reinforce a vision of a near future world in which problems of climate change mitigation and adaptation in particular (but also issues like energy security, water security, industry growth, etc.) are solved through eco-modernist techno-fixes. This Symposium sketches the contours of a framework we term political ecologies of storage. In doing so, we treat storage as both a potent imaginary and a concrete …

Sensor Lag Adjustments On A Mobile Meteorological Cart In Tropical Environments: A Case Study From An Urban Park In Singapore, Moshe Eliezer Mandelmilch, Sin Kang Yik, Beatrice H. Ho, Graces N. Y. Ching, Peter J. Crank, Winston T. L. Chow

Research Collection College of Integrative Studies

This study adds to the growing literature on mobile platforms by examining the performance of the Singapore MaRTy (SMaRTy) in conducting mobile micrometeorological measurements along a designated route in an urban park in Singapore, reflecting a pedestrian walking experience. The main objective of the study was to calculate the sensor lag for the mobile climate measurements: Air Temperature (TA), and Relative Humidity (RH) of SMaRTy along a designated route in an urban park in Singapore based on data from fixed stations (HOBO sensors) in two significant synoptic meteorological periods during the Northeast and Southwest monsoons. Statistically significant regression models were …

Investigating The Thixotropy Of Fresh Struvite Cement-Based Composite: Insights On Mechanisms Of The Pastes’ Thixotropic Behavior, Ugochukwu Ewuzie, Abdulkareem O. Yusuf, Damilola Daramola, Monday Uchenna Okoronkwo

Chemical and Biochemical Engineering Faculty Research & Creative Works

Struvite (ST) recovered during wastewater treatment has been sparsely applied in cement-based composites. This study systematically evaluated the thixotropic behavior of cement-struvite (CST) pastes, a mix of 5–20 % ST by mass of cement, and proposed the interaction mechanisms leading to the pastes' thixotropy. The hysteresis loop area was used to establish the pastes' thixotropy and investigate its relationship with increased ST content, temperature, and yield stress. In the thixotropic behavior model used, the equilibrium shear stress was employed to examine the CST pastes' irreversible change; the characteristic time of deflocculation was used to study the flocs destruction process; and …

An Incentive Mechanism For Privacy Preserved Data Trading With Verifiable Data Disturbance, Man Zhang, Xinghua Li, Bin Luo, Yanbing Ren, Yinbin Miao, Ximeng Liu, Robert H. Deng

Research Collection School Of Computing and Information Systems

To motivate data owners’ (DOs’) trading willingness, the existing incentive mechanisms allow DOs to independently disturb data following data consumer's (DC’s) availability requirement. However, they cannot motivate DOs’ honest disturbance, which is attributed to DOs’ independent disturbance without any supervision. Thus, we implement an incentive mechanism for privacy preserved data trading with verifiable data disturbance where an honest-but-curious disturbance generator (DG) is additionally introduced to supervise DOs’ local disturbance and assist disturbance verification between DOs and DC. Specifically, DG generates the disturbance strategies and secretly distributes to DOs following private information retrieval, guaranteeing DOs's local disturbance's privacy and verifiability with …

Research On The Capacity Development Of National Science And Technology Intelligence System, Hui Li, Shu Chen, Xiao Tan

Journal of Scientific Information Research

[Purpose/significance] The unique form and systematic characteristics of great power competition, such as system-establishment and whole of society confrontation, multi-domain and multi-depth high-tech containment and counter-containment, and multi-means and multi-element mixed deterrence, determine that national scientific and technological intelligence must have considerable systemic capabilities to match and follow up.

[Method/process] This article focuses on scientific and technological intelligence institutions within the traditional system, defines the connotation of national scientific and technological intelligence system capabilities, constructs a six-dimensional capability cognition model of ""institutional improvement capability-system coordination capability-resource guarantee capability-technological innovation capability-intelligence shaping capability-safe operation capability"", and expounds its main contents.

[Result/conclusion] …

Thematic Hotspots And Strategy Analysis Of International Ai Regulatory Texts Based On Lda Models, Taitian Mao, Yihe Peng

Journal of Scientific Information Research

[Purpose/significance]This article conducts an in-depth exploration of international artificial intelligence (AI) regulatory policies and gains insights into the regulatory focuses and trends of various countries, with the aim of providing valuable references for global AI governance strategies.

[Method/process] This paper applies the LDA topic clustering analysis method to conduct an in-depth study of twenty-seven international policy documents. The aim is to accurately identify the topics, analyze the key theme words, and further reveal the regulatory hotspots in the field of artificial intelligence.

[Results/conclusion] The study reveals six core regulatory themes: systemic risk assessment, ethical and legal regulation, social impact governance, …

Culture Bears The Way, While Technology Facilitates Action: Research Of The Adoption Willingness Of Aigc In Academic Writing Among Young Scholars, Jiangfeng Liu, Zihui Wang, Zhiwei Hu, Lei Pei

Journal of Scientific Information Research

[Purpose/significance] Clarifying the influencing factors of young scholars' willingness to use AIGC and its path of action,then making effective enhancement strategies,would help to further expand the application of AIGC in academic writing.

[Method/process] This paper combs through the studies on AIGC information behavior, and identifies TOE(Technology-Organization-Envifonment，TOE) theory and research life cycle theory as the base theory. Semi-structured interviews were conducted for procedural grounded theory coding. Then, a questionnaire survey and qualitative comparative analysis using fuzzy sets were conducted to obtain the influencing factors grouping path.

[Result/conclusion] Five factors, induding content quality, system quality, perceived risk, expectation confirmation, and group norms, …

Toward A Simplified Framework For Sequential Character Recognition, Nicholas Howe

Computer Science: Faculty Publications

This paper proposes a novel approach to handwritten charac- ter recognition using convolutional non-recurrent deep neural networks. Such a network can run in parallel at every point of a document, offer- ing potential advantages in speed over recurrent approaches. The net- work’s output feeds into a beam search optimization for final decoding. Preliminary quantitative results show that the framework can achieve bootstrap training from labeled word images. It provides an alternative to sequential models that rely on connectionist temporal classification for alignment.

Analysis Of Vision Transformers And Domain Adaptation In Long-Range Facial Recognition, Zachary Michael Swanson

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

Atmospheric turbulence presents a significant barrier to long-range facial recognition, introducing severe geometric distortions and blur that degrade image quality. This thesis investigates deep learning approaches for mitigating these effects, with a focus on transformer based architectures and domain adaptation strategies.

An in-depth benchmarking study was performed using convolutional neural networks (CNNs) and vision transformers (ViTs) on the Husker BRIAR Research Collection from up to 500m (HBRC-500) face dataset. The results demonstrated that vision transformers, particularly hierarchical vision transformers like the shifted-window (Swin) transformer, outperform CNN-based models at long distances due to their ability to model global spatial relationships and …

An Exponential Cone Integer Programming And Piece-Wise Linear Approximation Approach For 0-1 Fractional Programming, Hoang Giang Pham, Thuy Anh Ta, Tien Mai

Research Collection School Of Computing and Information Systems

We study a class of binary fractional programs commonly encountered in important application domains such as assortment optimization and facility location. These problems are known to be NP-hard to approximate within any constant factor, and existing solution approaches typically rely on mixed-integer linear programming or second-order cone programming reformulations. These methods often utilize linearization techniques (e.g., big-M or McCormick inequalities), which can result in weak continuous relaxations. In this work, we propose a novel approach based on an exponential cone reformulation combined with piecewise linear approximation. This allows the problem to be solved efficiently using standard cutting-plane or branch-and-cut procedures. …

Crow: Eliminating Backdoors From Large Language Models Via Internal Consistency Regularization, Nay Myat Min, Long H. Pham, Yige Li, Jun Sun

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) are vulnerable to backdoor attacks that manipulate outputs via hidden triggers. Existing defense methods—designed for vision/text classification tasks—fail for text generation. We propose Internal Consistency Regularization (CROW), a defense leveraging the observation that backdoored models exhibit unstable layer-wise hidden representations when triggered, while clean models show smooth transitions. CROW enforces consistency across layers via adversarial perturbations and regularization during finetuning, neutralizing backdoors without requiring clean reference models or trigger knowledge—only a small clean dataset. Experiments across Llama-2 (7B, 13B), CodeLlama (7B, 13B), and Mistral-7B demonstrate CROW’s effectiveness: it achieves significant reductions in attack success rates across …

Position: Trustworthy Ai Agents Require The Integration Of Large Language Models And Formal Methods, Yedi Zhang, Yufan Cai, Xinyue Zuo, Xiaokun Luan, Kailong Wang, Zhe Hou, Yifan Zhang, Zhiyuan Wei, Meng Sun, Jun Sun, Jing Sun, Jin Song Dong

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have emerged as a transformative AI paradigm, profoundly influencing broad aspects of daily life. Despite their remarkable performance, LLMs exhibit a fundamental limitation: hallucination—the tendency to produce misleading outputs that appear plausible. This inherent unreliability poses significant risks, particularly in high-stakes domains where trustworthiness is essential. On the other hand, Formal Methods (FMs), which share foundations with symbolic AI, provide mathematically rigorous techniques for modeling, specifying, reasoning, and verifying the correctness of systems. These methods have been widely employed in mission-critical domains such as aerospace, defense, and cybersecurity. However, the broader adoption of FMs remains constrained …

Llmscan: Causal Scan For Llm Misbehavior Detection, Mengdi Zhang, Kai Kiat Goh, Peixin Zhang, Jun Sun, Lin Xin Rose, Hongyu Zhang

Research Collection School Of Computing and Information Systems

Despite the success of Large Language Models (LLMs) across various fields, their potential to generate untruthful and harmful responses poses significant risks, particularly in critical applications. This highlights the urgent need for systematic methods to detect and prevent such misbehavior. While existing approaches target specific issues such as harmful responses, this work introduces LLMSCAN, an innovative LLM monitoring technique based on causality analysis, offering a comprehensive solution. LLMSCAN systematically monitors the inner workings of an LLM through the lens of causal inference, operating on the premise that the LLM’s ‘brain’ behaves differently when generating harmful or untruthful responses. By analyzing …

Hps: Hard Preference Sampling For Human Preference Alignment, Xiandong Zou, Wanyu Lin, Yuchen Li, Pan Zhou

Research Collection School Of Computing and Information Systems

Aligning Large Language Model (LLM) responses with human preferences is vital for building safe and controllable AI systems. While preference optimization methods based on PlackettLuce (PL) and Bradley-Terry (BT) models have shown promise, they face challenges such as poor handling of harmful content, inefficient use of dispreferred responses, and, specifically for PL, high computational costs. To address these issues, we propose Hard Preference Sampling (HPS), a novel framework for robust and efficient human preference alignment. HPS introduces a training loss that prioritizes the most preferred response while rejecting all dispreferred and harmful ones. It emphasizes “hard” dispreferred responses — those …