Computer Sciences Commons^™

Hide-And-Sweep: Detecting Concealed Cameras Via Led Illumination Sweeps, Jonghyuk Yun, Jaeyoung Moon, Yunseo Park, Sean Rui Xiang Tan, Byunghyun Kim, Rajesh Krishna Balan, Jun Han

Research Collection School Of Computing and Information Systems

Hidden cameras have increasingly infiltrated hotel and Airbnb rooms, posing serious privacy risks. Detecting such cameras is challenging because they are visually inconspicuous and often embedded inside everyday objects. Even worse, existing handheld detectors are manual and also rely on single-angle illumination and hence suffer from high false-positive rates. We present SweepLED (pronounced "sweepled")1, a practical hidden camera detection system that operates on a commodity smartphone augmented with an unobtrusive LED-embedded case. SweepLED performs LED sweeping - a controlled sequence of multi-angle illumination - while the user simply holds the phone still by hand, enabling the camera to capture how …

Saag: Structured Agent Assessment And Grounding, Ritvik Garimella, Vedant Khandelwal, Anvi Kohli, Amit Sheth

Publications

Exact-match evaluation of agent-calling obscures qualitatively different failure modes: a model may select the right function yet hallucinate argument values, or satisfy a schema while choosing a agent for the wrong reason. Existing benchmarks collapse these distinctions into a single binary score, leaving practitioners unable to diagnose where agent calls fail. We propose SAAG a cascaded diagnostic framework that decomposes agent-calling evaluation into three sequential stages: registry conformance, structural completeness, and argument grounding, each producing interpretable stage-specific diagnostics. These diagnostics additionally enable iterative self-repair: on prediction failure, the stage-specific signal guides targeted correction without leaking ground-truth values. We evaluate this …

Ai In Healthcare: Regulatory Guidelines And Judge-Made Negligence Principles For Ai Implementers, Gary K. Y. Chan

Research Collection Yong Pung How School Of Law

The use of artificial intelligence (AI) in healthcare may, notwithstanding its potential benefits, result in harm to patients from allegedly negligent acts or omissions by hospitals and medical doctors. In such circumstances, how should the principles in the tort of negligence (duty of care, breach, causation, remoteness of damage, and defences) respond to AI innovations in healthcare? In particular, how may the standard of care expected of hospitals and medical doctors be informed by regulatory guidelines? We refer to case law precedents and regulatory guidelines on the roles and responsibilities of doctors and hospitals as AI implementers. Importantly, they prompt …

A Machine Learning Framework For Residential District Cooling: Forecasting Consumption, Explaining Drivers, And Evaluating Decarbonization Pathways, Kadhim Hayawi, Husna Maliakkal, Neethu Venugopal, Thanveer Musthafa Hussain, Gomathi Bhavani Rajagopalan

All Works

District Cooling Systems (DCS) in the Middle East, while energy-efficient, are significant contributors to carbon emissions. This study introduces a novel framework to decarbonize DCS operations by integrating predictive machine learning, explainable AI (XAI), and renewable energy planning, all grounded in extensive real-world data. Leveraging a unique dataset from 59 residential buildings in the UAE—including energy consumption, climate variables, and building features—we developed a high-fidelity cooling load forecasting model. Following a rigorous chronological validation methodology, the Random Forest model was identified as the most robust, achieving a strong performance (R² = 0.8256, RMSE = 11,668.31). Outdoor temperature was confirmed …

From Ethical Principles To Executable Governance: A Policy-As-Code Framework For Trustworthy Ai In Higher Education, Edmund Evangelista, Syed M. Salman Bukhari

All Works

Artificial intelligence holds great potential to transform higher education, but a persistent gap remains between ethical aspirations and their practical, auditable enforcement. This study addresses that gap by developing and validating an end-to-end executable governance framework grounded in a policy-as-code (PaC) paradigm. Using student dropout prediction as a high-stakes example, the framework operationalizes governance through an automated gatekeeper, a multi-strategy fairness mitigation toolbox, and a tamper-evident audit chain for full reproducibility. The governance compliance was tested across sixteen fixed model configurations evaluated under five policy tiers (strict, medium, lenient, and two deployment-realistic variants). None were approved, as fairness violations, dominated …

Patchfuzz: Patch Fuzzing For Javascript Engines, Junjie Wang, Zhihua Xie, Xiaofei Xie, Xiaoning Du, Xiangwei Zhang

Research Collection School Of Computing and Information Systems

Context: Patch fuzzing is a technique aimed at identifying vulnerabilities that arise from newly patched code. While researchers have made efforts to apply patch fuzzing to testing JavaScript (JS) engines with considerable success, these efforts have been limited to using ordinary test cases or publicly available vulnerability PoCs (Proof of Concepts) as seeds, and the sustainability of these approaches is hindered by the challenges associated with automating the PoC collection. Objective: To address these limitations, we propose an end-to-end sustainable approach for JS engine patch fuzzing, named PatchFuzz. Method: It automates the collection of PoCs of a broader range of …

A Pruning-Based Question-Answering For Interactive Video Search: A Simple Baseline, Yu Tong Cheng, Phuong Anh Nguyen, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

There are various factors affecting the performance of video search. An imprecise query will enlarge search space and reduce the discriminative power of ranking functions. This problem is further exacerbated by the presence of numerous visually or semantically similar videos in large datasets. Consequently, users need to painstakingly browse through many highly similar candidates to locate the search target, leading to increased cognitive load and inefficient searching. Ideally, engaging users through interactive questioning to resolve uncertainties in the search process is an effective strategy for progressively narrowing down the search space. However, despite rapid advances in deep learning, generating informative …

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 …

Sam3-Litetext: An Anatomical Study Of The Sam3 Text Encoder For Efficient Vision-Language Segmentation, Chengxi Zeng, Yuxuan Jiang, Ge Gao, Shuai Wang, Duolikun Danier, Bin Zhu, Stevan Rudinac, David Bull, Fan Zhang

Research Collection School Of Computing and Information Systems

Vision-language segmentation models such as SAM3 enable flexible, prompt-driven visual grounding, but inherit large, general-purpose text encoders originally designed for open-ended language understanding. In practice, segmentation prompts are short, structured, and semantically constrained, leading to substantial over-provisioning in text encoder capacity and persistent computational and memory overhead. In this paper, we perform a large-scale anatomical analysis of text prompting in vision–language segmentation, covering 404,796 real prompts across multiple benchmarks. Our analysis reveals severe redundancy: most context windows are underutilized, vocabulary usage is highly sparse, and text embeddings lie on a low-dimensional manifold despite high-dimensional representations. Motivated by these findings, we …

Group Conversational Agents: A Review Of Designs That Support And Shape Group Interaction, Shunyi Yeo, Tianyi Zhang, Scott Bateman, Gary Hsieh, Young-Ho Kim, Simon Tangi Perrault, Jiannan Li, Anthony Tang

Research Collection School Of Computing and Information Systems

Conversational agents that participate in or mediate group interaction introduce challenges that extend beyond supporting individual users, raising new questions about how agents participate in and influence groups. To characterise this emerging design space, we present a systematic review of 53 peer-reviewed studies on group conversational agents (GCAs). We analyse how GCAs intervene in group-level processes, including participation regulation, conflict mediation, task alignment, and execution support. Using concepts from group research as an analytic lens, we organise prior GCA work around recurring group interactional challenges (orientation, conflict, alignment, and execution), and examine the roles agents are designed to play in …

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 …

Ppg-Sport: A Dataset For Reliable Heart Rate Monitoring From Wrist Ppg Under Dynamic Sports Conditions, Changshuo Hu, Hung Manh Pham, Yiming Zhang, Guanru Yan, Xiao Ma, Yuezhong Wu, Thivya Kandappu, Archan Misra, Dong Ma

Research Collection School Of Computing and Information Systems

Photoplethysmography (PPG) has become a cornerstone of physiological sensing in wearable devices, enabling non-invasive monitoring of heart rate and related biomarkers. However, its reliability deteriorates sharply under dynamic, high-intensity, or non-periodic motions such as those in sports, where existing datasets fail to capture realistic wrist dynamics. To address this gap, we introduce PPG-Sport, the first large-scale dataset designed for heart rate monitoring from wrist-worn PPG under real sports conditions. The PPG-Sport dataset includes synchronized PPG, inertial measurement unit (IMU), and electrocardiography (ECG) recordings from both wrists of 30 participants across six representative activities: stationary, walking, running, badminton, table tennis, and …

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, …

History To Future: Evolving Agent With Experience And Thought For Zero-Shot Vision-And-Language Navigation, Guangzhao Dai, Shuo Wang, Zihan Wang, Guo-Sen Xie, Yang Yang, Jinshan Pan, Qianru Sun, Xiangbo Shu

Research Collection School Of Computing and Information Systems

Vision-and-Language Navigation in Continuous Environment (VLN-CE) requires an agent to follow language instructions to navigate the target destination. With the advancement of large language models (LLMs), recent efforts have explored adapting them for zero-shot VLN-CE, offering a promising solution in addressing the drawbacks of poor generalization in the training-based paradigm. However, existing LLM-based works primarily perform naive reasoning for decision-making and lack feedback, e.g., reviewing historical errors and predicting future potentials. Consequently, it may suffer from continuous failure for those initial error tasks. In this paper, we rethink LLM-based zero-shot VLN-CE and propose a new paradigm, named EvoNav, to improve …

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 …

Modeling Generative Ai Adoption In Higher Education: An Integrated Tam–Tpb–Sdt Framework With Sem Validation, Dina Tbaishat, Omar Alfandi, Faten Hamad, Syed Muhammad Salman Bukhari, Suha Al Muhaissen

All Works

This study investigates the determinants of university students' adoption of generative artificial intelligence (GAI) tools in higher education. Integrating the Technology Acceptance Model (TAM), the Theory of Planned Behavior (TPB), and Self-Determination Theory (SDT), it develops and tests a complete model that captures cognitive, social, and motivational influences on adoption. A cross-sectional survey was conducted among 517 undergraduate and postgraduate students at Jordanian universities. The data were analyzed using structural equation modeling (SEM) with a two-step approach: confirmatory factor analysis (CFA) to validate the measurement model, followed by SEM to test the hypothesized structural relationships. Reliability, validity, measurement invariance across …

A Hybrid Approach To Phishing Email Detection: Leveraging Machine Learning And Large Language Models, Hessa Shamal Biri

Theses

Phishing attacks have reached a new level of sophistication through the deployment of large language models by attackers. The current AI-generated threats defeat existing detection systems which base their operation on past data. The thesis presents a hybrid system for phishing email detection which combines real email data with synthetic LLM-created samples to enhance traditional machine learning classifiers performance. The study created a hybrid dataset of 20,627 emails by combining 18,631 real messages from the Kaggle Email Classification Dataset with 1,996 synthetic emails. The synthetic emails were generated using four large language models LLaMA-3, Falcon, LLaVA, and Mistral to capture …

Computational Insights Into Nucleosome Dynamics In Epigenetics Using Molecular Dynamics Simulations, Rutika Patel

Dissertations, Theses, and Capstone Projects

Nucleosome core particles (NCP) are the building blocks that form a highly organized and compact chromatin structure. Nucleosomes package DNA in the nucleus of eukaryotic cells. The NCP consists of about 147 base pairs of DNA wrapped around the histone octamer, with 1.65 superhelical turns in a left-handed manner. The histone octamer is composed of two copies of H3, H4, H2A, and H2B. Together with histone H1 and linker DNA, they further assemble into a higher-order chromatin structure. The nucleosome complex is stabilized by electrostatic interactions between positively charged histone residues and the negatively charged DNA backbone. To effectively access …

Ai-Powered Student Support And Development Platform, Wadha Rashed Alyammahi

Theses

Over the past few years, academic stress and student mental well-being have become critical concerns in educational settings, significantly affecting academic performance and overall quality of life. Students increasingly rely on digital platforms for academic support; however, many existing solutions lack the ability to adapt to users’ emotional states or provide personalized, context-aware assistance. In response to this challenge, this study presents the design and development of an intelligent, stress-aware conversational support system for students based on advanced natural language processing techniques and large language models.

The main goal of this study is to explore the effectiveness of an LLM-based …

Malicious Quic Traffic Detection Using Malicious Quic Traffic Detection Using Malicious Quic Traffic Detection Using Malicious Quic Traffic Detection Using, Choudhary Muhammad Zia

Theses

The enhanced QUIC protocol's encryption capabilities not only encrypt the traffic payload but also encrypt the packet headers that network security tools rely on for packet inspection. This enhanced encryption capability introduces challenges for network operators in monitoring and analyzing network traffic by creating blind spots in firewalls, intrusion detection systems, and deep packet inspection devices. Earlier research has demonstrated that training machine learning classifiers on individual QUIC packets across different classifiers has failed to detect any malicious traffic due to encrypted packet headers.

This thesis demonstrates that shifting to network flow analysis resolves this problem. Rather than analyzing individual …

To Wait Or To Transfer? A Three-Level Optimization Framework For Intermodal Transfer Coordination In First Train Timetabling And Bus Bridging Services Management, Hao Li, Liujiang Kang, Norman Weik, Huijun Sun, Qingying Lai, Zhiguang Cao

Research Collection School Of Computing and Information Systems

This study addresses the integrated optimization of the first train timetabling and bus bridging service design (FTT-BBSD) for morning transfer challenges, two critical but interdependent passenger services in the public transit system. In contrast to most existing studies and conventional approaches, this study explicitly models the influence of passenger path choices and transfer mode selections on FTT-BBSD. Through a novel dual-level network representation that integrates subway and bus systems, we formulate the FTT-BBSD problem as a mixed-integer nonlinear programming model. The model simultaneously determines subway and bus timetables and bridging line deployment to minimize total travel time for all first …

Extensive And Intensive Margin Labor Supply On Ride-Sourcing Platforms, Hao Sun, Hai Wang, Zhixi Wan

Research Collection School Of Computing and Information Systems

The rapid expansion of ride-sourcing platforms has enabled freelance drivers to flexibly determine both their participation and working hours. Understanding this flexible labor supply behavior is essential for managing platform capacity and evaluating the impacts of pricing and incentive policies on driver welfare. This study develops a labor supply model in which drivers optimally choose whether to participate (extensive margin) and how long to work (intensive margin) to maximize their utility from consumption and leisure. The model incorporates heterogeneity in drivers’ other income, idle time, and participation costs, allowing us to analytically characterize equilibrium labor supply decisions. The results show …

When Politics Meets Digital Assets: Gender Identity Salience And Nft Pricing After Roe V. Wade, Xiang Liu, Yao Zhao, Ping Fan Ke

Research Collection School Of Computing and Information Systems

Major sociopolitical events can reshape public attention toward identity-related issues, potentially influencing valuation patterns in digital markets where identity-related characteristics are embedded in digital assets. Using the overturning of Roe v. Wade as an exogenous policy shock, this paper examines how gender attributes represented in non-fungible token (NFT) avatars affect market outcomes. Using transaction data from six major avatar-based NFT collections traded on Etherscan in 2022, we apply a quasi-experimental design combining propensity score matching and a difference-in-differences model. The results indicate that the policy shock significantly increased the resale prices of NFTs representing female avatars. These findings suggest that …

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, …

Frozen Lvlms For Micro-Video Recommendation: A Systematic Study Of Feature Extraction And Fusion, Huatuan Sun, Yunshan Ma, Changguang Wu, Yanxin Zhang, Pengfei Wang, Xiaoyu Du

Research Collection School Of Computing and Information Systems

Frozen Large Video Language Models (LVLMs) are increasingly employed in micro-video recommendation (MVR) due to their strong multimodal understanding. However, existing apporches typically deploy LVLMs as fixed black-box feature extractors without systematically comparing alternative representation strategies. To address this gap, we present the first systematic empirical study on various feature extraction paradigms and integration strategies, along with hierarchical representations from frozen LVLMs for MVR. Extensive experiments on representative LVLMs reveal that hidden states from multiple decoder layers provide richer and more effective representations for MVR. Guided by this insight, we propose the Dual Feature Fusion (DFF) Framework, a lightweight approach …

Co-Designing With Autistic Livestreamers: Care, Constraints, And Trade-Offs In Livestreaming, Terrance Mok, Anthony Tang, Lora Oehlberg

Research Collection School Of Computing and Information Systems

Autistic livestreamers use platforms like Twitch for social connection, self-expression, and community, but these spaces also impose ongoing social and emotional demands. Prior work has documented these experiences, but less is known about what autistic creators themselves envision for the tools and platforms they use. We address this gap through a Research through Design (RtD) co-design study with three autistic Twitch streamers, using speculative artefacts as discussion prompts to explore how participants reasoned about potential livestreaming technologies. Across three co-design activities, we identify three overarching tensions shaping autistic streaming practice: Expression versus Misinterpretation and Harm; Public Participation versus Control and …

Adaptive Outlier Detection Over Data Stream, Rui Zhu, Mingyuan Jiang, Xiaochun Yang, Baihua Zheng, Bin Wang, Tao Qiu

Research Collection School Of Computing and Information Systems

Continuous distance-based outlier detection in streaming data poses significant challenges and has a wide range of practical applications. Traditional threshold-based methods perform well under stable streaming conditions, where fixed parameters remain effective. However, they often struggle with dynamic data distributions and high stream speeds, leading to suboptimal performance, limited control over the number of returned outliers, and failure to meet real-time detection requirements. To address these issues, this paper introduces a novel Recall and Proportion-Aware Outlier Detection (RPA-OD) query. In RPA-OD, ρ defines a distance relaxation that enables real-time outlier detection. Specifically, objects with fewer than k neighbors within the …

Task Complexity Matters: An Empirical Study Of Reasoning In Llms For Sentiment Analysis, Donghao Huang, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

Large language models (LLMs) with reasoning capabilities have fueled a compelling narrative that reasoning universally improves performance across language tasks. We test this claim through a comprehensive evaluation of 504 configurations across seven model families—including adaptive, conditional, and reinforcement learning-based reasoning architectures—on sentiment analysis datasets of varying granularity (binary, five-class, and 27-class emotion). Our findings reveal that reasoning effectiveness is strongly task-dependent, challenging prevailing assumptions: (1) Reasoning shows task-complexity dependence—binary classification degrades up to -19.9 F1% points (pp), while 27-class emotion recognition gains up to  +16.0 pp; (2) Distilled reasoning variants underperform base models by 3–18 pp on simpler tasks, …

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 …

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 …