Digital Commons Network^™

A Novel Hierarchical Multi-Agent System For Payments Using Llms, Donghao Huang, Joon Kiat Chua, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

Large language model (LLM) agents, such as OpenAI’s Operator and Claude’s Computer Use, can automate workflows but unable to handle payment tasks. Existing agentic solutions have gained significant attention; however, even the latest approaches face challenges in implementing end-to-end agentic payment workflows. To address this gap, this research proposes the Hierarchical Multi-Agent System for Payments (HMASP), which provides an end-to-end agentic method for completing payment workflows. The proposed HMASP leverages either open-weight or proprietary LLMs and employs a modular architecture consisting of the Conversational Payment Agent (CPA - first agent level), Supervisor agents (second agent level), Routing agents (third agent …

“Alexa, Do Not Say That In Front Of My Boss!” A Cross-Cultural Comparison Of User And Ai Preferences For Privacy-Aware Smart Speaker Interactions Across Contexts, Lynne Warin, Emily Aurelia, Anthony Tang, Emily Aurelia, Delphine Reinhardt

Research Collection School Of Computing and Information Systems

Due to their limited ability to reason about the social context in which they are used, smart speakers pose significant privacy risks by responding in ways that may violate people's implicit social boundaries. We conducted a cross-cultural vignette study (N = 944) in Germany and Singapore to investigate how situational factors—specifically social context (bystander relationships and closeness), physical context (location), and interaction context (topic and deceptive intent)—regulate user preferences for smart speaker responses. Our results demonstrate that these factors are superior predictors of response preferences than dispositional user traits (i.e., intrinsic personal traits). We identify two distinct social dynamics: a …

Potential Recyclable Materials In Buildings: A Framework For Greenhouse Gas Emissions Assessment Of Residential Buildings In Singapore, Pradeep Alva, Riccardo Talami, Wanyu Pei, Goran Sibenik, Martin Mosteiro-Romero, Clayton Miller, Rudi Stouffs

Research Collection College of Integrative Studies

As countries aim to reduce resource consumption and greenhouse gas (GHG) emissions, Whole Life Carbon Assessment (WLCA) has become a vital method for quantifying embodied and operational GHG emissions. However, few studies have conducted WLCA on an urban scale, often addressing operational or embodied GHG emissions in isolation without considering their cumulative impact. This study introduces a city-wide WLCA framework to assess the potential recyclable materials of urban building stock, using Singapore as a case study with 5915 public residential buildings. Upfront GHG emissions are calculated from material intensity and building information, while operational emissions are based on energy use …

Scaling Up Multi-Agent Reinforcement Learning For Large Agent Teams And Long-Horizon Tasks: A Survey, Minghong Geng, Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Multi-agent reinforcement learning (MARL) empowers multiple autonomous agents to acquire effective policies for collaborative problem-solving. Over the last decade, MARL has seen significant advancements, with numerous algorithms achieving impressive performance across various benchmarks and real-world applications. Nevertheless, the scalability of multi-agent systems, in terms of the number of agents and the length of the task horizon, remains a critical consideration for applying MARL methods to complex problem-solving. Given that a dedicated review of the existing approaches and challenges in scaling up multi-agent systems remains largely absent, this survey aims to bridge this gap by delivering a comprehensive review of MARL …

Evaluating Species At Risk In Data-Limited Fisheries: A Productivity–Susceptibility Analysis For Marine Aquarium Fish, Gabrielle A. Baillargeon, Alice A. Wynn, Jemelyn Grace P. Baldisimo, Michael F. Tlusty, Andrew L. Rhyne

Arts & Sciences Faculty Publications

The marine aquarium trade (MAT) is a significant global industry harvesting millions of wild-caught, live coral reef fishes for public and private aquaria markets in the United States and Europe annually, while supporting fisher livelihoods in the Indo-Pacific. This diverse and species-rich trade is considered data-limited, creating barriers to quantifying the current and future socio-ecological sustainability of the fishery. We present a revised and expanded productivity–susceptibility analysis (PSA) that serves as a holistic risk assessment to estimate the vulnerability of marine aquarium fish to overfishing. Our global analysis includes 306 species that are actively in trade. Improvements to the PSA …

Geometric Characterization Of Ideals In Bipolar Semigroups, Kittipong Laipaporn, Rasimate Maungchang, David M. Cook, Prathomjit Khachorncharoenkul

Research outputs 2022 to 2026

This paper develops a geometric framework for analyzing the ideal structure of the bipolar semigroup ��={(−��,��)∣��,��∈ℝ+0} under coordinate-wise addition. Subsets of B are interpreted as planar regions, allowing ideals to be described in terms of boundary behavior. In particular, we prove that the complement of a simply connected region is an ideal of the commutative additive semigroup (��,+) if and only if its boundary contains no strictly decreasing segment. This provides a direct and visually verifiable criterion for ideality, linking algebraic structure to geometric shape. Each ideal can be written as a union of translates of the form ��+��, with …

Georoad-Upernet: Geo-1-Based Weakly Supervised Multispectral Road Extraction Via Role-Aware Context Fusion And Semantic Regularization, Shaoqian Chen, Yunliang Chen, Jianxin Li, Ao Yang

Research outputs 2022 to 2026

Extracting roads accurately from remote sensing images is important for map updates, traffic analysis, and infrastructure monitoring. Medium-resolution multispectral images can provide useful surface and background information, but when used alone, the spatial details are limited for retaining narrow roads, intersection structures, and fine road topologies. To address this problem, this paper proposes GeoRoad-UPerNet, a Geo-1-centered weakly supervised multispectral framework for road extraction. In this framework, Geo-1 serves as the primary 16-band multispectral source, Sentinel-2 Level-2A imagery serves as auxiliary contextual support, and OpenStreetMap (OSM) road information is converted into proxy supervision rather than dense manual ground truth. GeoRoad-UPerNet contains …

Numerical Evaluation Of A Zero Poisson’S Ratio Structure In Μ-3d-Printed Self-Expanding Nitinol Stents, Farhana Yasmin, Ana Vafadar, Majid Tolouei-Rad

Research outputs 2022 to 2026

Stenting is a minimally invasive treatment used in managing peripheral artery disease (PAD). However, clinical challenges persist, including in-stent thrombosis and restenosis, primarily driven by axial foreshortening or elongation and suboptimal balance between radial stiffness and flexibility inherent to conventional stent designs. This study proposes an innovative arrow-shaped geometry exhibiting zero Poisson’s ratio (ZPR) behaviour for 3D-printed self-expanding Nitinol stents. The complete stent deployment process was modelled using finite element analysis (FEA), including radial crimping and subsequent expansion to enable systematic parametric investigation while accounting for µ-3D printing constraints. Response surface methodology (RSM) rigorously evaluated mechanical performance, defining peak stress, …

Spatiotemporal Pah Patterns In Size-Fractionated Particles (Pm>10-Pm0.1) From Northern Thailand Biomass Burning Via Sentinel-2, Phakphum Paluang, Watinee Thavorntam, Sarawut Sangkham, Phuchiwan Suriyawong, Hisam Samae, Thaneeya Chetiyanukornkul, Masami Furuuchi, Worradorn Phairuang

Research outputs 2022 to 2026

Biomass burning, particularly from forest fires and crop residue burning during the dry season, is a major source of particulate pollution across many Asian countries. However, accurately identifying these emissions remains challenging due to uncertainties in burned area estimation and the limited availability of country-specific emission factors. This study quantified the spatiotemporal distribution of emissions from biomass burning using satellite imagery. Burned areas were classified using a random forest (RF) algorithm implemented on the Google Colaboratory (Colab) platform. The RF model showed strong performance, with a kappa coefficient of 0.85 and an average accuracy of 0.81. Emission estimates for the …

Fostering Innovation At The Intersection Of Maker Education And Extended Reality (Xr), Jewoong Moon, Yong Ju Jung, Soo Hyeon Kim, Younggon Bae, Bertrand Schneider

School of Mathematical & Statistical Sciences Faculty Publications

No abstract provided.

Hyper-Bishops, Hyper-Rooks, And Hyper-Queens: Percentage Of Safe Squares On Higher Dimensional Chess Boards, Caroline Cashman, Joseph Cooper, Raul Marquez, Steven J. Miller, Jenna Shuffelton

School of Mathematical & Statistical Sciences Faculty Publications

Chess has inspired an abundance of mathematical problems, especially in combinatorics and probability. One such problem, initially studied by Miller, Sheng, and Turek, considers the proportion of safe spaces when randomly placing n rooks on an 𝑛×𝑛 chess board. They show that as n approaches infinity, the proportion of safe spaces converges to 1/𝑒2. We first generalize their results to bishops and queens. This problem is significantly more interesting and difficult; while a rook attacks the same number of spaces regardless of its position, this is not so for bishops and queens. We prove that the proportion of safe spaces …

Use Of Intraoperative Vancomycin Powder And Its Effects On The Incidence Of Surgical Site Infection In Orthopaedic Trauma: A Systematic Review With Meta-Analysis, Troy B. Puga, Mckenna Box, Alan Lam, Claire Ferguson, Mason Poffenbarger, Cornelis J. Potgieter, Kisan Parikh, John T. Riehl

Student Publications

Introduction: Surgical site infection (SSI) in orthopaedic trauma can have devastating consequences. The use of intraoperative powdered vancomycin is one strategy used in orthopaedic trauma surgery to reduce SSI; however, evidence and guidelines remain unclear. The aim of this systematic review is to evaluate the evidence for the use of powdered vancomycin in orthopaedic trauma surgery for the prevention of SSI.

Methods: A search was conducted across PubMed/Medline, Cochrane, and Embase databases to evaluate the use of powdered vancomycin in orthopaedic trauma surgery for the prevention of SSIs. The search used a combination of keywords and MeSH terms. Titles and …

Optimizing Fpga And Wafer Test Coverage With Spatial Sampling And Machine Learning: Analysis Of Local Spatial Consistency, Weiquan Wang, K. M.Shahriar Alam Adib, Foisal Ahmed, Riaz Ul Haque Mian

Research outputs 2022 to 2026

Wafer and FPGA testing remains costly in semiconductor manufacturing. This paper studies random sampling, stratified sampling, and k-means sampling under a partial-measurement setting with Gaussian Process Regression (GPR), and introduces Short Distance Elimination (SDE), a spatial screening rule that spreads selected training points over the layout. Combining value-based sampling with SDE yields two hybrid methods: S-SDE, which applies SDE within stratified subsets, and K-SDE, which applies SDE within k-means clusters. A calibration-based protocol fixes the value-group labels and SDE thresholds before target-file prediction. The SDE thresholds are selected from (Formula presented.) configurations in (Formula presented.), excluding (Formula presented.), using local …

Robotic Assessment Of Human Motor Control: Contextual Learning, Aging, And The Balancing Of Unstable Systems, Laura Alvarez Hidalgo

School of Engineering, Computing and Mathematics Theses

This thesis investigates human sensorimotor control using three complementary sets of experiments. These examine contextual motor learning, aging-related motor performance, and human balance.First, a series of experiments examined how different sensory modalities influence motor memory formation during dynamic learning. Using a robotic manipulandum to implement an interference task, we assessed how the contextual effect of visual and passive lead-in movements decays over time, specifically as a function of dwell time between the movement cue and the required action onset. Results revealed a modality-dependent pattern of decay: while both cue types enabled dual adaptation to opposing force fields, passive cues preserved …

Exploiting Underground Mine Topology For Resilient Concurrent Lora Mesh Emergency Communications: Architecture, Protocol Design, And Performance Analysis, Hilary Kelechi Anabi, Samuel Frimpong, Muhammad Azeem Raza

Mining Engineering Faculty Research & Creative Works

Underground mine emergencies compromise fixed communication infrastructure exactly when situational awareness is most critical for effective rescue operations. Existing LoRa mesh protocols fail in underground mines because they ignore the structured topology of tunnel networks, specifically the waveguide effect along straight galleries, severe signal discontinuity at junctions, and the dead-end geometry of working faces. This paper presents the Topology-Aware Concurrent LoRa (TACL) mesh protocol, in which each node autonomously infers its structural role from local RF observations and packet header information, without GPS, pre-loaded mine maps, or central coordination. Role classification resolves the contender estimation problem (Formula presented.) left open …

Golden And Silver Dark Sirens For Precise H0 Measurement With Hetdex, Yixuan Dang, Ish Gupta, Robin Ciardullo, Erin Mentuch Cooper, Shiksha Pandey, Dustin Davis, Surhud More, Rachel Gray, Hsin Yu Chen, Daniel J. Farrow, Caryl Gronwall, Donghui Jeong, Shun Saito, Donald P. Schneider

Physics Faculty Research & Creative Works

Gravitational waves (GWs) from compact binary coalescences are standard sirens that provide a direct measure of the source's luminosity distance, enabling an independent measurement of the Hubble constant (H0). While a bright siren—a GW event with an identified electromagnetic (EM) counterpart—provided the first such constraint, most detections, currently dominated by black hole mergers, lack EM signatures. A measurement of H0 is still possible with these dark sirens by statistically associating GW events with galaxies in existing catalogs based on the sky localization. In this work, we explore the potential of two subsets of dark sirens categorized by their localization precision: …

Pso-Style Social Influence In An Ant Colony Algorithm For Continuous-Domain Optimization, Ashraf M. Abdelbar, Donald C. Wunsch

Electrical and Computer Engineering Faculty Research & Creative Works

ACOR is a well-established Ant Colony Optimization (ACO) algorithm for continuous-domain optimization. In this paper, we propose an extension (which we call ACOR∗) in which several fundamental modifications are made to ACOR's solution construction process, including the incorporation of a social influence mechanism borrowed from Particle Swarm Optimization (PSO). Our modifications to the ACOR algorithm are intended to promote search diversity and combat premature convergence. We experimentally evaluate our proposal in the context of training feedforward neural networks for classification using 65 widely used datasets from the University of California Irvine (UCI) repository, as well as the optimization of several …

Multiplexed Fabry-Pérot High-Temperature Sensing Based On Dispersive Microwave-Photonic Frequency-Time Domain Analysis, Ruimin Jie, Chen Zhu, Bohong Zhang, Koustav Dey, Jie Huang

Electrical and Computer Engineering Faculty Research & Creative Works

We propose and experimentally demonstrate a multiplexed high-temperature Fabry-Pérot (FP) fiber sensing system interrogated by dispersive microwave-photonic frequency-time domain analysis (DM-FTDA). In the proposed architecture, incoherent broadband probing light is modulated by radio-frequency (RF) signals and then reflected by a parallel network of hollow-core photonic crystal fiber FP (HCPCF-FP) sensors. A chirped fiber Bragg grating provides strong dispersion to map the composite FP spectral response into a well-defined microwave transfer function. Unlike conventional optical Fourier-domain multiplexing that requires deliberate cavity-length allocation, the proposed approach achieves multiplexing via delay-dominated discrimination. Distinct delay fibers are assigned to each sensor branch, and an …

Rode: Linear Rectified Mixture Of Diverse Experts For Food Large Multi-Modal Models, Pengkun Jiao, Xinlan Wu, Bin Zhu, Jingjing Chen, Chong-Wah Ngo, Yu-Gang

Research Collection School Of Computing and Information Systems

Large Multi-modal Models (LMMs) have significantly advanced a variety of vision-language tasks. The scalability and availability of high-quality training data play a pivotal role in the success of LMMs. In the realm of food, while comprehensive food datasets such as Recipe1M offer an abundance of ingredient and recipe information, they often fall short of providing ample data for nutritional analysis. The Recipe1M+ dataset, despite offering a subset for nutritional evaluation, is limited in the scale and accuracy of nutrition information. To bridge this gap, we introduce Uni-Food, a unified food dataset that comprises over 100,000 images with various food labels, …

Benchmarking Gaslighting Negation Attacks Against Multimodal Large Language Models, Bin Zhu, Yinxuan Gui, Huiyan Qi, Jingjing Chen, Chong-Wah Ngo, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Multimodal Large Language Models (MLLMs) have exhibited remarkable advancements in integrating different modalities, excelling in complex understanding and generation tasks. Despite their success, MLLMs remain vulnerable to conversational adversarial inputs. In this paper, we systematically study gaslighting negation attacks—a phenomenon where models, despite initially providing correct answers, are persuaded by user-provided negations to reverse their outputs, often fabricating justifications. We conduct extensive evaluations of state-of-the-art MLLMs across diverse benchmarks and observe substantial performance drops when negation is introduced. Notably, we introduce the first benchmark GaslightingBench, specifically designed to evaluate the vulnerability of MLLMs to negation arguments. GaslightingBench consists of multiple-choice …

Not Too Early, Not All At Once: Design Tensions In Ai-Mediated Self-Disclosure In Online Dating, Pei-Hua Tsai, Tianyi Zhang, Emran Bin Elias Poh, Anthony Tang, Yung-Ju Chang

Research Collection School Of Computing and Information Systems

Online dating relies on self-disclosure, yet initial conversations are fragile: users must navigate uncertainty around timing, boundaries, and reciprocity with little shared context. While advances in AI raise the possibility of mediating disclosure, how such support might reshape the experience of early-stage relational disclosure remains underexplored. We conducted 29 semi-structured interviews to examine how daters envision AI-mediated self-disclosure in online dating. Our findings surface recurring design tensions rather than simple opportunities or risks. Participants welcomed guidance that could pace disclosure, support reflection, and reduce social awkwardness, but stressed preserving agency and authorship. They valued interpretive assistance for sense-making of ambiguous …

Language Embeddings Meet Shallow Autoencoders, Rodrigo Alves, Vojtěch Vančura, Pavel Kordík, Antoine Ledent

Research Collection School Of Computing and Information Systems

Shallow autoencoders are appealing recommenders due to their simplicity, scalability, and competitive retrieval quality, but they struggle in strict cold-start settings where new items have no interactions. We propose an inductive shallow autoencoder that leverages item side information (language embeddings) by fixing the decoder to item features and learning only an encoder in the same semantic space. To prevent trivial self-reconstruction without enforcing a hard zero diagonal, we introduce diagonal gating: a leave-one-item-out objective that blocks the self-copy shortcut only for the item being updated while retaining context from the rest of the user history. An alternating-style optimization trains the …

Sok: Understanding Zkvm: From Research To Practice, Guomin Yang, Yunbo Yang, Yuejia Cheng, Haibo Tang, Bingsheng Zhang, Kui Ren

Research Collection School Of Computing and Information Systems

Zero-knowledge virtual machine (zkVM) is a powerful infrastructure for proving the correctness of a program execution with a succinct proof, attracting significant interest from researchers, developers, and users. It has been widely used in applications such as blockchain rollups, privacy-preserving machine learning, and off-chain computation. As the field grows, a wide range of zkVMs have been proposed. However, they adopt different choices in instruction formats, trace layouts, and proving backends, which results in a highly heterogeneous design landscape and makes it difficult to understand the relations among these systems.To bridge this gap, we provide a comprehensive study of zkVMs that …

Anatomical Domain Shifts: Test-Time Heterogeneous Adaptation For 3d Human Pose Prediction, Qiongjie Cui, Pan Zhou, Jingjing Chen, Na Zhao

Research Collection School Of Computing and Information Systems

The research frontier in human pose prediction (HPP) is advancing toward continual test-time adaptation (TTA), where models must self-adapt to dynamic test distributions. To date, the homeostatic continual TTA remains the sole viable solution, which isolates the model parameters and update domain-sensitive ones. Despite mitigating full-body domain gaps, human anatomical heterogeneity (domain shifts often localize to specific regions) is ignored. This anatomical-agnostic approach forces uniform parameter adaptation across kinematically distinct segments, causing: over-adaptation of stable regions and under-adaptation of shift-prone articulations. To address it, we introduce TT-HA, a novel Test-Time Heterogeneous Adaptation that implicitly estimates domain changes for anatomical segments, …

Enhancing Pointing Gestures Of Non-Hmd Users In Asymmetric Collocated Mixed Reality Collaboration, Nam-Dang Vo, Van-Vinh Thai, Anthony Tang, Khanh-Duy Le

Research Collection School Of Computing and Information Systems

A common collocated group setting in mixed-reality (MR) collaboration is a person wearing a MR headset (HMD user) and presenting MR contents to audiences who are not provided with such specialized devices (Non-HMD users). In this setting, while Non-HMD users can view the MR environment shown on a large physical display, it still remains challenging for the HMD user to interpret their pointing gesture when they spatially refer to objects in the MR environment. To address this, we designed and evaluated two pointing techniques—SCREEN and SCREEN+SPACE—that support Non-HMD users in referring to MR content. Screen pointing allows users to refer …

Happycal: Designing Text And Image-Based Supports For Savouring Positive Work Experiences, Molly Stewart, Minghao Cai, Anthony Tang, Sam Liu, Chris Mosunic, Sowmya Somanath

Research Collection School Of Computing and Information Systems

Savouring positive work experiences can promote positive affect and well-being at work, yet there is limited guidance on how digital applications can support workers to engage in savouring. We developed HappyCal, a work-focused savouring application offering two forms of savouring support: text-based, a common modality in workplace reflection tools, and images, a largely unexplored approach in work-related savouring. We conducted an exploratory qualitative study where participants (N=36) used HappyCal over five days and engaged in savouring through either a text-only modality (n=17) or text input paired with image output (n=19). We found that (1) participants in both groups reported heightened …

How Do Machine Learning Models Change?, Joel Castaño, Rafael Cabañas, Antonio Salmerón, David Lo, Silverio Martínez-Fernández

Research Collection School Of Computing and Information Systems

The proliferation of Machine Learning (ML) models and their open source implementations has transformed AI research and applications. Platforms like Hugging Face (HF) enable this evolving ecosystem, yet a large-scale longitudinal study of how these models change is lacking. This study addresses this gap by analyzing over 680,000 commits from 100,000 models and 2,251 releases from 202 of these models on HF using repository mining and longitudinal methods. We apply an extended ML change taxonomy to classify commits and use Bayesian networks to model temporal patterns in commit and release activities. Our findings show that commit activities align with established …

Analytical And Numerical Methods For Solving Fractional Integro-Differential Equations Using The Modified Operational Matrix Method, Nour Alzoubi

Theses

Fractional calculus has attracted considerable attention in recent years because of its wide applicability to model a variety of linear and nonlinear physical phenomena across different scientific disciplines. In particular, fractional diferential equation systems have proven to be effective in describing processes with memory and hereditary properties. However, the solvability and analysis of such systems strongly depend on the type of fractional operator employed, especially in the presence of nonlocal fractional derivatives with singular kernels, which remain an open and challenging area of research.

The main objective of this thesis is to develop efficient analytical and numerical techniques for solving …

A Fiftieth Year Retrospective On The 1976 Mw 7.5 Motagua Earthquake In Guatemala, Grant Clark, Trenton Mcenaney, Jeremy Maurer, Andreas Eckert, Stephen S. Gao, Omar G. Flores, Robin Yani, Tina Niemi, Christoph Grützner, Francisco Gomez, Jonathan Obrist-Farner

Geosciences and Geological and Petroleum Engineering Faculty Research & Creative Works

On 4 February 1976, an Mw > 7:5 earthquake ruptured ∼240 km of the Motagua fault in Guatemala, causing ∼23,000 fatalities. This event provided evidence for the fault's role as a major transform boundary between the North American and Caribbean plates. Field observations, seismological analyses, and postseismic studies helped constrain fundamental aspects of the 1976 earthquake mechanics and the spatial complexity of the rupture. This event opened a window for studies documenting past deformation along this plate boundary across multiple spatial and temporal scales. Five decades of research have established this earthquake as an important event for understanding strike-slip ruptures along …

Advanced Mathematical Modeling And Data-Driven Techniques For The Diagnosis Of Diabetes Using Continuous Glucose Monitoring (Cgm) Data, Farah Morsi

Theses

Diabetes mellitus is a major and growing health challenge, particularly in the Middle East and North Africa (MENA) region. Continuous Glucose Monitoring (CGM) provides high-resolution time-series data that capture detailed glucose fluctuations over time. However, conventional CGM summary measures, such as mean glucose, standard deviation, and time-in-range, may not fully describe the nonlinear temporal structure of glucose dynamics.

This thesis investigates nonlinear dynamical approaches for analyzing CGM time series, with a focus on recurrence-based analysis and ordinal-network analysis. Recurrence-based methods, including recurrence quantification analysis (RQA), are used to characterize geometric and temporal patterns in reconstructed phase space, while ordinal networks …