Physical Sciences and Mathematics Commons^™

Towards Multimodal Emotional Support Conversation Systems, Yuqi Chu, Lizi Liao, Zhiyuan Zhou, Chong-Wah Ngo, Richang Hong

Research Collection School Of Computing and Information Systems

The integration of conversational artificial intelligence (AI) into mental health care promises a new horizon for therapist-client interactions, aiming to closely emulate the depth and nuance of human conversations. Despite the potential, the current landscape of conversational AI is markedly limited by its reliance on single-modal data, constraining the systems’ ability to empathize and provide effective emotional support. This limitation stems from a paucity of resources that encapsulate the multimodal nature of human communication essential for therapeutic counseling. To address this gap, we introduce the Multimodal Emotional Support Conversation (MESC) dataset, a first-of-its-kind resource enriched with comprehensive annotations across text, …

Conv4rec: A 1‑By‑1 Convolutional Autoencoder For User Profiling Through Joint Analysis Of Implicit And Explicit Feedbacks, Antoine Ledent, Petr Kasalický, Rodrigo Alves, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

We introduce a new convolutional autoencoder architecture for user modeling and recommendation tasks with several improvements over the state of the art. First, our model has the flexibility to learn a set of associations and combinations between different interaction types in a way that carries over to each user and item. Second, our model is able to learn jointly from both the explicit ratings and the implicit information in the sampling pattern (which we refer to as ”implicit feedback”). It can also make separate predictions for the probability of consuming content and the likelihood of granting it a high rating …

Rethinking Cognitive Complexity For Unit Tests: Toward A Readability-Aware Metric Grounded In Developer Perception, Wendkûuni C. Ouédraogo, Yinghua Li, Xueqi Dang, Xin Zhou, Anil Koyuncu, Jacques Klein, David Lo, Tegawendé F. Bissyandé

Research Collection School Of Computing and Information Systems

Automatically generated unit tests-from searchbased tools like EvoSuite or LLMs-vary significantly in structure and readability. Yet most evaluations rely on metrics like Cyclomatic Complexity and Cognitive Complexity, designed for functional code rather than test code. Recent studies have shown that SonarSource's Cognitive Complexity metric assigns nearzero scores to LLM-generated tests, yet its behavior on EvoSuitegenerated tests and its applicability to test-specific code structures remain unexplored. We introduce CCTR, a Test-Aware Cognitive Complexity metric tailored for unit tests. CCTR integrates structural and semantic features like assertion density, annotation roles, and test composition patterns-dimensions ignored by traditional complexity models but critical for …

Flow, Immersion, And Presence: Creating Virtual Reality And Engagement In The Era Of Ubiquitous And Intelligent Technologies, Yi Maggie Guo, Fiona Fui-Hoon Nah, Nannan Xi, Marshall Scott Poole

Research Collection School Of Computing and Information Systems

Researchers use the concepts of flow, immersion, and presence to explain the usage of and engagement (e.g., cognitive absorption) with information technology. In this special issue, we showcase four papers on empirical investigations of flow and immersion, their antecedents, and their outcomes. These papers address research questions that range from investigating the antecedents and consequences of immersion in head-mounted displays of virtual reality, designing for the flow experience in extended reality, studying factors influencing user engagement in the metaverse, and identifying adverse effects of work-related flow. We also provide directions and suggestions for future research.

Vibemus: Proactive Agentic System For Music Personalization, Zhiliang Guo, Teng Tu, Yunshan Ma, Xun Yang

Research Collection School Of Computing and Information Systems

Large language models (LLMs) enable diverse forms of AI-assisted creation, yet they often struggle to bridge the preference-articulation gap: users may provide incomplete or vague intentions or lack the vocabulary to specify what they want, yielding outputs misaligned with true preferences. To address this gap and facilitate music creation in a vibe-centric environment, we introduce VibeMus, a proactive agentic system built on open-source components. The system engages in multi-turn dialogue to progressively determine the music’s emotion, genre, lyrics, and other aspects before generation. Simulated evaluations show that proactive clarification improves alignment with users’ intended nuances. Our approach is training-free, leveraging …

Improving Co-Decoding Based Security Hardening Of Code Llms Leveraging Knowledge Distillation, Dong Li, Shanfu Shu, Meng Yan, Zhongxin Liu, Chao Liu, Xiaohong Zhang, David Lo

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have been widely adopted by developers in software development. However, the massive pretraining code data is not rigorously filtered, allowing LLMs to learn unsafe coding patterns. Several prior studies have demonstrated that code LLMs tend to generate code with potential vulnerabilities. The widespread adoption of intelligent programming assistants poses a significant threat to the software development process. Existing approaches to mitigating this risk primarily involve constructing secure data that are free of vulnerabilities and then retraining or fine-tuning the models. However, such an effort is resource intensive and requires significant manual supervision. When the model parameters …

Finding Safety Violations Of Ai-Enabled Control Systems Through The Lens Of Synthesized Proxy Programs, Jieke Shi, Zhou Yang, Junda He, Bowen Xu, Dongsun Kim, Donggyun Han, David Lo

Research Collection School Of Computing and Information Systems

Given the increasing adoption of modern AI-enabled control systems, ensuring their safety and reliability has become a critical task in software testing. One prevalent approach to testing control systems is falsification, which aims to find an input signal that causes the control system to violate a formal safety specification using optimization algorithms. However, applying falsification to AI-enabled control systems poses two significant challenges: (1) it requires the system to execute numerous candidate test inputs, which can be time-consuming, particularly for systems with AI models that have many parameters, and (2) multiple safety requirements are typically defined as a conjunctive specification, …

Exploring Parameter-Efficient Fine-Tuning Techniques For Code Generation With Large Language Models, Martin Weyssow, Xin Zhou, Kisub Kim, David Lo, Houari A. Sahraoui

Research Collection School Of Computing and Information Systems

Large language models (LLMs) demonstrate impressive capabilities to generate accurate code snippets given natural language intents in a zero-shot manner, i.e., without the need for specific fine-tuning. While prior studies have highlighted the advantages of fine-tuning LLMs, this process incurs high computational costs, making it impractical in resource-scarce environments, particularly for models with billions of parameters. To address these challenges, previous research explored in-context learning (ICL) and retrieval-augmented generation (RAG) as strategies to guide the LLM generative process with task-specific prompt examples. However, ICL and RAG introduce inconveniences, such as the need for designing contextually relevant prompts and the absence …

Ponzilens+: Visualizing Bytecode Actions For Smart Ponzi Scheme Identification, Xiaolin Wen, Tai D. Nguyen, Shaolun Ruan, Qiaomu Shen, Jun Sun, Feida Zhu, Yong Wang

Research Collection School Of Computing and Information Systems

With the prevalence of smart contracts, smart Ponzi schemes have become a common fraud on blockchain and have caused significant financial loss to cryptocurrency investors in the past few years. Despite the critical importance of detecting smart Ponzi schemes, a reliable and transparent identification approach adaptive to various smart Ponzi schemes is still missing. To fill the research gap, we first extract semantic-meaningful actions to represent the execution behaviors specified in smart contract bytecodes, which are derived from a literature review and in-depth interviews with domain experts. We then propose PonziLens+, a novel visual analytic approach that provides an intuitive …

Managing Rumors On Electronic Interaction Platforms: How Management Responses Affect Investor Reaction, Runyu Wang, Zili Zhang, Keng Siau, Ziqiong Zhang

Research Collection School Of Computing and Information Systems

This study investigates how listed firms respond to investors’ rumor-related inquiries and examines the impact of these responses on investor reactions, as indicated by subsequent daily abnormal stock returns (ARs). Using a unique dataset of question-and-answer (Q&A) interactions from China’s major e-interaction platforms, established by the stock exchanges, our study provides insights into regulated firm-investor communications in a structured Q&A setting. Unlike informal social media channels, these platforms enable official responses from firm representatives, typically board secretaries, under direct regulatory oversight. By analyzing rumor-related Q&A pairs with regression models and several robustness checks, we find that firms can benefit from …

Shortcuts Everywhere And Nowhere: Exploring Multi-Trigger Backdoor Attacks, Yige Li, Jiabo He, Hanxun Huang, Jun Sun, Xingjun Ma, Yu-Gang Jiang

Research Collection School Of Computing and Information Systems

Backdoor attacks have become a significant threat to the pre-training and deployment of deep neural networks (DNNs). Although numerous methods for detecting and mitigating backdoor attacks have been proposed, most rely on identifying and eliminating the “shortcut” created by the backdoor, which links a specific source class to a target class. However, these approaches can be easily circumvented by designing multiple backdoor triggers that create shortcuts everywhere and therefore nowhere specific. In this study, we explore the concept of Multi-Trigger Backdoor Attacks (MTBAs), where multiple adversaries leverage different types of triggers to poison the same dataset. By proposing and investigating …

Robface: A Test Suite For Efficient Robustness Evaluation Of Face Recognition Systems, Ruihan Zhang, Jun Sun

Research Collection School Of Computing and Information Systems

Face recognition is a widely used authentication technology in practice, where robustness is required. It is thus essential to have an efficient and easy-to-use method for evaluating the robustness of (possibly third-party) trained face recognition systems. Existing approaches to evaluating the robustness of face recognition systems are either based on empirical evaluation (e.g., measuring attacking success rate using state-of-the-art attacking methods) or formal analysis (e.g., measuring the Lipschitz constant). While the former demands significant user efforts and expertise, the latter is extremely time-consuming. In pursuit of a comprehensive, efficient, easy-to-use, and scalable estimation of the robustness of face recognition systems, …

Implementing Slack-Free Custom Penalty Function For Qubo On Gate-Based Quantum Computers, Xin Wei Lee, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

Solving NP-hard constrained combinatorial optimization problems using quantum algorithms remains a challenging yet promising avenue toward quantum advantage. Variational Quantum Algorithms (VQAs), such as the Variational Quantum Eigensolver (VQE), typically require constrained problems to be reformulated as unconstrained ones using penalty methods. A common approach introduces slack variables and quadratic penalties in the QUBO formulation to handle inequality constraints. However, this leads to increased qubit requirements and often distorts the optimization landscape, making it harder to find high-quality feasible solutions. To address these issues, we explore a slack-free formulation that directly encodes inequality constraints using custom penalty functions, specifically the …

Optimizing Fire Detection In Remote Sensing Imagery For Edge Devices: A Quantization-Enhanced Hybrid Deep Learning Model, Syed Muhammad Salman Bukhari, Nadia Dahmani, Sujan Gyawali, Muhammad Hamza Zafar, Filippo Sanfilippo, Kiran Raja

All Works

Wildfires are increasing in frequency and severity, presenting critical challenges for timely detection and response, particularly in remote or resource-limited environments. This study introduces the Inception-ResNet Transformer with Quantization (IRTQ), a novel hybrid deep learning (DL) framework that integrates multi-scale feature extraction with global attention and advanced quantization. The proposed model is specifically optimized for edge deployment on platforms such as unmanned aerial vehicles (UAVs), offering a unique combination of high accuracy, low latency, and compact memory footprint. The IRTQ model achieves 98.9% accuracy across diverse datasets and shows strong generalization through cross-dataset validation. Quantization significantly reduces the parameter count …

Applying Artificial Intelligence And Chatbots To Enhance Collection Development In Health Sciences Libraries, Ivan Portillo, David Carson

Library Presentations, Posters, and Audiovisual Materials

The continuous advancement of artificial intelligence (AI) and large language models (LLMs) has presented several opportunities for librarians to reduce their workload and become more efficient. This session will explore the potential of generative AI chatbots in assisting health sciences librarians with collection development. Two methods that will be discussed include the potential of AI to help discover new titles and how AI can evaluate your library collection for any potential gaps based on a college program’s curriculum.

Scientific Multimodal Summarization : Integrating Knowledge Across Textual, Visual And Auditory Content, Zusheng Tan

Lingnan Theses (MPhil & PhD)

As scientific publications increasingly incorporate multimodal content, ranging from textual descriptions to figures, tables, presentation videos, and audio, there is a growing need for summarization systems that can effectively process and integrate information across these diverse modalities.

This work presents a comprehensive exploration of Scientific Multimodal Summarization, introducing a series of novel architectures and datasets aimed at advancing this emerging field. 1): We begin by introducing CMT-Sum, which integrates multimodal scientific source content (i.e., primarily paper text and figures) to generate high-quality textual summaries and identify representative graphical abstracts. We refer to this task as Scientific Multimodal Summarization with …

Fisheries Science Update - Pilbara Demersal Scalefish Resource - September 2025, Department Of Primary Industries And Regional Development, Western Australia

Fisheries Science Updates

The Department of Primary Industries and Regional Development (DPIRD) monitors the status of Western Australia’s demersal scalefish resources by undertaking periodic stock assessments on key indicator species.

This summary provides key outcomes of the 2024 assessment of the Pilbara Demersal Scalefish Resource (Fisheries Research Report No. 338).

Advancing U.S. Competitiveness In Agentic Gen Ai: A Strategic Framework For Interoperability And Governance, Satyadhar Joshi

Harrisburg University Other Works

Abstract : The rapid evolution of artificial intelligence has given rise to agentic AI systems—autonomous entities capable of perceiving their environment, making decisions, and executing actions with minimal human intervention. This work provides a systematic analysis of agentic AI frameworks, governance models, and implementation strategies. Drawing on a comprehensive review of the literature, we examine the current state of agentic AI technologies, highlight key challenges in governance, security, and ethical oversight, and compare architectural frameworks for responsible deployment. Our results, illustrated through detailed framework comparisons and governance analyses, demonstrate that while agentic AI holds transformative potential across multiple sectors, notable …

Resource Assessment Report No. 02: West Coast Demersal Scalefish Resource 2025 Assessment, Emily A. Fisher, David V. Fairclough, Elaine Lek, Jeremy Briggs, Sybrand Alex Hesp, Ainslie Denham

Resource Assessment Reports

The West Coast Demersal Scalefish Resource (WCDSR) comprises over 100 species inhabiting inshore (20-250 m deep) and offshore ( > 250 m deep) waters of the West Coast Bioregion (WCB; north of Kalbarri to east of Augusta). The WCDSR is primarily targeted by commercial, charter and recreational boat-based line fishers, including the commercial West Coast Demersal Scalefish (Interim) Managed Fishery (WCDSIMF). Indicator species selected for monitoring and assessing the status of the inshore suite of the WCDSR include Snapper, WA Dhufish and Baldchin Groper, while indicators for the offshore suite include Hapuku, Bass Groper and Blue-eye Trevalla.

The WCDSR is more …

Exploring The Cooling Effects Of Urban Forests In Summer, Xiaoyue Li

Tennessee State University Alumni Theses and Dissertations

As a nature-based solution to combat urban heat islands, urban forests can provide cooling and other co-benefits. However, little is known about the cooling benefits of urban forests in parking lots and under different land covers, especially with field observations. To address this gap, we measured air temperature (AT) and relative humidity (RH) and calculated heat index (HI) in three urban settings in Nashville, TN, in summer 2024. The research sites included: 1) Two different parking lots: parking lots with and without trees; 2) Three different distances from trees within the parking lot with trees: under trees, near trees, and …

Regioselective C-Allylation Of Indole With Potassium Allyltrifluoroborate In The Presence Of Pd-Catalyst, Milton Kumar Kundu

Tennessee State University Alumni Theses and Dissertations

Indole is a versatile heterocyclic scaffold renowned for its wide range of pharmacological activities and strong potential as a successful drug candidate. These attributes continue to inspire researchers to explore indole derivatives as promising leads in drug development. In this project, we report the development of a cross-coupling reaction of indoles and potassium allyltrifluoroborate to the corresponding 3-allylindoles in the presence of PdCl2(dtbpf) and PdCl2(dppf)CH2Cl2 catalyst under microwave heating, offering a rapid, regioselective, and high-yielding synthetic route. This methodology provides a valuable platform for generating structurally diverse indole-based compounds, which could serve as promising leads for further pharmacological evaluation and …

Effects Of Tillage On Wheat Canopy, Stephanie Adanna Anyanwu

Tennessee State University Alumni Theses and Dissertations

Abstract Wheat canopy cover and greenness are useful crop performance indicators that provide significant insight into the performance of wheat crops. Understanding the effects of no-till and conventional tillage practices on winter wheat canopy cover and greenness will help inform agronomic decision making in wheat production. Therefore, the aim of this study was to assess the effects of no-till and conventional tillage practices on wheat canopy cover and greenness using drones. Wheat canopy cover mapping was carried out using deep learning supervised classification. The normalized difference vegetation index (NDVI), green normalized difference vegetation index (GNDVI) and optimized soil adjusted vegetation …

Distribution And Occurrence Of Cyanohabs, Nutrients, And Water-Quality Data In The Tennessee State University Wetland, Kristi Hill

Tennessee State University Alumni Theses and Dissertations

Toxic algal blooms are an expanding issue for aquatic ecosystems because they are hazardous to human and environmental health. Algal blooms naturally occur from the combination of warm temperatures, sunlight, and abundant nutrients in water, but what triggers them to become harmful algal blooms (HABs) and begin synthesizing toxin is not well understood, and their threat to freshwater sources was not heavily researched until recently. Microcystin (MC), a freshwater algal toxin, is a HABs toxin which targets the liver and causes sickness and death in humans and animals (pets, livestock, and wildlife). Urban freshwater wetlands are among the most HAB …

Evaluating Early Successional Habitat Selection By Herpetofauna And Pygmy Rattlesnakes In Tennessee, Carlin Frost

Tennessee State University Alumni Theses and Dissertations

Coupled with climate change, global biodiversity declines are exacerbated by increasing anthropogenic pressures and ecosystem destruction. Amphibians and reptiles are particularly vulnerable due to their specific and narrow habitat requirements. In Tennessee, the Western Pygmy Rattlesnake (Sistrurus miliarius streckeri) is classified as Threatened and is primarily associated with floodplains adjacent to early successional habitats (ESH) in the western Interior Plateau ecoregion. These ESH support unique flora and fauna but have declined in recent decades, largely due to urban encroachment and disturbance suppression. Studying snakes is challenging because of their limited activity periods, small home ranges, and low detectability from cryptic …

Lipid And Cholesterol Peroxidation Leads To Α-Crystallin Membrane Aggregation And Cataract Formation, Nawal K. Khadka, Preston Hazen, Oluwaseyi Akinola, Xinzhu Pu, Laxman Mainali

Boise State University Publications and Presentations

Purpose: The significant lens chaperone protein α-crystallin (αABc), comprised of αA-crystallin (αAc) and αB-crystallin (αBc) subunits, is found to form membrane-bound aggregates with age and cataract formation. However, the molecular basis for such aggregate formation is still unclear. Our research primarily aims to elucidate the effect of lipids (phospholipids and sphingolipids) and cholesterol (Chol) peroxidation on the aggregation of αAc, αBc, and αABc to bovine lens nuclear membrane (NM).

Methods: Lipid and Chol peroxidation was induced by a photosensitized peroxidation reaction, and topographical images of NM and oxidized-NM (Ox-NM) with and without αAc, αBc, or αABc were obtained using atomic …

Procedures For Rangeland Condition Assessment In The Kimberley 2025, Department Of Primary Industries And Regional Development, Western Australia

Natural resources published reports

This report defines the procedures used in 2025 by DPIRD to complete rangeland condition assessment (RCA) in the Kimberley region which has grass-based pastures. For the rest of the pastoral estate, DPIRD uses the Procedures for RCA in the Pilbara and southern rangelands which have predominantly shrub pastures.

RCA is the process DPIRD uses to make systematic, station-level assessment of rangeland. Rangeland condition considers both the condition of pastures (as defined in the 'Pasture condition guide for the Kimberley') and soils as determined by erosion, using the erosion assessment method on pastoral lands in Western Australia. The methods have evolved …

The God Prompt And Deus Ex Machina: Techno-Theological Tropes And Operational Metaphors In Generative Media, James Hutson

Faculty Scholarship

This study reframes two durable tropes—the ―God Prompt‖ and the deus ex machina—as analytic lenses for understanding how contemporary generative systems stage beginnings and endings of cultural production. The ―God Prompt‖ denotes command-driven synthesis in which minimal textual instructions instantiate content on demand, crystallizing a production loop of input, model execution, and post hoc evaluation that orients anticipation toward instantaneous yield and controllable variation. The deus ex machina names an externally imposed resolution that interrupts causal development—historically a crane-borne god, functionally an algorithmic override—thereby concentrating attention on closure mechanics rather than world-building continuity. Read together, the pair offers a compact …

Exact And Approximate Conformal Inference For Multi-Output Regression, Chancellor Johnstone, Eugene Ndiaye

Faculty Publications

It is common in machine learning to estimate a response y given covariate information x . However, these predictions alone do not quantify any uncertainty associated with said predictions. One way to overcome this deficiency is with conformal inference methods, which construct a set containing the unobserved response with a prescribed probability. Unfortunately, even with a one-dimensional response, conformal inference is computationally expensive despite recent encouraging advances. In this paper, we explore multi-output regression, delivering exact derivations of conformal inference p-values when the predictive model can be described as a linear function of y . Additionally, we introduce a multivariate …

The Global Phase Space Of The Three-Vortex Interaction System And Its Application To Vortex-Dipole Scattering, Atul Anurag

Dissertations

This dissertation presents a global reduction of the classical three-vortex problem that is free from coordinate singularities, enabling a comprehensive analysis of the system's dynamics across all circulation regimes.

To achieve this, a two-step symplectic reduction procedure is developed. The first step introduces Jacobi coordinates adapted to the symplectic structure of the vortex system, and the second applies a Lie-Poisson reduction to the resulting system. This formulation eliminates the non-physical singularities associated with collinear vortex configurations and facilitates a global phase space analysis, including a detailed and novel investigation of bifurcations.

Within this reduced framework, all relative fixed points are …

Robust Ai Solutions For Financial Markets Through Generative Modeling, Dynamic Graph Learning, And Reinforcement-Based Portfolio Optimization, Jingyi Gu

Dissertations

Financial markets are inherently uncertain and dynamic, driven by complex factors such as macroeconomic signals, investor sentiment, and evolving inter-asset relationships. While machine learning has advanced financial modeling, existing approaches often fall short in addressing the real-world intricacies of finance. This dissertation confronts two critical challenges, human-driven stochasticity and risk-intensive decision-making under real-world trading constraints, while seizing a pivotal opportunity, the structural dynamics of evolving financial systems. These elements are foundational to advancing robust and practical financial intelligence.

To this end, this dissertation develops a unified framework for robust financial modeling and decision-making. The framework is architected as a progressive, …