Physical Sciences and Mathematics Commons^™

Grokformer: Graph Fourier Kolmogorov‑Arnold Transformers, Guoguo Ai, Guansong Pang, Hezhe Qiao, Yuan Gao, Hui Yan

Research Collection School Of Computing and Information Systems

Graph Transformers (GTs) have demonstrated remarkable performance in graph representation learning over popular graph neural networks (GNNs). However, self-attention, the core module of GTs, preserves only low-frequency signals in graph features, leading to ineffectiveness in capturing other important signals like high-frequency ones. Some recent GT models help alleviate this issue, but their flexibility and expressiveness are still limited since the filters they learn are fixed on predefined graph spectrum or spectral order. To tackle this challenge, we propose a Graph Fourier Kolmogorov-Arnold Transformer (GrokFormer), a novel GT model that learns highly expressive spectral filters with adaptive graph spectrum and spectral …

What Are Anomalies In A Network?, Kai Ming Ting, Zhong Zhuang, Guansong Pang, Zongyou Liu, Tianrun Liang, Qiuran Zhao

Research Collection School Of Computing and Information Systems

This article examines a collection of assumptions used in the current literature on node anomaly detection in a network. The examination raises the question: What are anomalies in a network? Our attempt to answer this question has provided some interesting findings and led to some open questions. This is the first article which formally defines anomalies in a network and introduces the concept of self-verifiability of a detector without ground-truths in a network. They enable existing detectors to be categorized into two types along the line whether they are self-verifiable or not. We suggest a method to evaluate self-verifiable detectors …

Explaining Explanations: An Empirical Study Of Explanations In Code Reviews, Ratnadira Widyasari, Ting Zhang, Abir Bouraffa, Walid Maalej, David Lo

Research Collection School Of Computing and Information Systems

Code reviews are central for software quality assurance. Ideally, reviewers should explain their feedback to enable authors of code changes to understand the feedback and act accordingly. Different developers might need different explanations in different contexts. Therefore, assisting this process first requires understanding the types of explanations reviewers usually provide. The goal of this article is to study the types of explanations used in code reviews and explore the potential of Large Language Models (LLMs), specifically ChatGPT, in generating these specific types. We extracted 793 code review comments from Gerrit and manually labeled them based on whether they contained a …

How Are We Detecting Inconsistent Method Names? An Empirical Study From Code Review Perspective, Kisub Kim, Xin Zhou, Dongsun Kim, Julia Lawall, Kui Liu, Tegawendé F. Bissyandé, Jacques Klein, Jaekwon Lee, David Lo

Research Collection School Of Computing and Information Systems

Proper naming of methods can make program code easier to understand, and thus enhance software maintainability. Yet, developers may use inconsistent names due to poor communication or a lack of familiarity with conventions within the software development lifecycle. To address this issue, much research effort has been invested into building automatic tools that can check for method name inconsistency and recommend consistent names. However, existing datasets generally do not provide precise details about why a method name was deemed improper and required to be changed. Such information can give useful hints on how to improve the recommendation of adequate method …

Understanding The Bad Development Practices Of Android Custom Permissions In The Wild, Xiaohan Zhang, Zhiyuan Yu, Xinghua Li, Cen Zhang, Cong Sun, Ning Zhang, Robert H. Deng

Research Collection School Of Computing and Information Systems

Android system provides application developers with the ability to define custom permissions, which serve to moderate the sharing of resources and interactions with other applications. However, poor development practices of developers can render the permission mechanism ineffective, weakening the system protection. This paper presents a comprehensive examination of the problematic practices surrounding custom permissions employed by developers, referred to as Bad Practices of Custom Permissions (BPCP issues). To accomplish this, we conducted an empirical study and identified nine common BPCP issue patterns that can lead to various adverse consequences, such as installation failures, crashes, or even component hijacking. To automatically …

Unambiguous Granularity Distillation For Asymmetric Image Retrieval, Hongrui Zhang, Yi Xie, Haoquan Zhang, Cheng Xu, Xuandi Luo, Donglei Chen, Xuemiao Xu, Huaidong Zhang, Pheng Ann Heng, Shengfeng He

Research Collection School Of Computing and Information Systems

Previous asymmetric image retrieval methods based on knowledge distillation have primarily focused on aligning the global features of two networks to transfer global semantic information from the gallery network to the query network. However, these methods often fail to effectively transfer local semantic information, limiting the fine-grained alignment of feature representation spaces between the two networks. To overcome this limitation, we propose a novel approach called Layered-Granularity Localized Distillation (GranDist). GranDist constructs layered feature representations that balance the richness of contextual information with the granularity of local features. As we progress through the layers, the contextual information becomes more detailed, …

Leakage-Resilient Easily Deployable And Efficiently Searchable Encryption (Edese), Jiaming Yuan, Yingjiu Li, Jun Li, Daoyuan Wu, Jianting Ning, Yangguang Tian, Robert H. Deng

Research Collection School Of Computing and Information Systems

Easily Deployable and Efficiently Searchable Encryption (EDESE) is a cryptographic primitive designed for practical searchable applications, offering efficient search and easy deployment. However, it remains vulnerable to Leakage-Abuse attacks, allowing adversaries to exploit keyword-matching processes to extract sensitive information. To address these vulnerabilities, we introduce Leakage-Resilient EDESE (LR-EDESE) with k-indistinguishability and controlled leakage functions. We then propose Volume Leakage-Resilient EDESE (VLR-EDESE), a new scheme to protect against both query and document volume leakage. Our experimental results demonstrate that at k = 5000 (maximum security setting), VLR-EDESE incurs an overhead of 63× compared to the baseline EDESE without leakage protection, outperforming …

Llm-Based Multi-Agent Systems For Software Engineering: Literature Review, Vision And The Road Ahead, Junda He, Christoph Treude, David Lo

Research Collection School Of Computing and Information Systems

Integrating Large Language Models (LLMs) into autonomous agents marks a significant shift in the research landscape by offering cognitive abilities that are competitive with human planning and reasoning. This paper explores the transformative potential of integrating Large Language Models into Multi-Agent (LMA) systems for addressing complex challenges in software engineering (SE). By leveraging the collaborative and specialized abilities of multiple agents, LMA systems enable autonomous problem-solving, improve robustness, and provide scalable solutions for managing the complexity of real-world software projects. In this paper, we conduct a systematic review of recent primary studies to map the current landscape of LMA applications …

Autoregressive Modeling Of Dna Molecule Shapes Accompanied By An Empirical Assessment Of The Ljung-Box Test, David William Custer

Theses and Dissertations

The assumption of independence rarely holds in real-world data. Correlated observations are ubiquitous, especially in sequential contexts where time series models are essential for capturing temporal dependence. This study analyzed six groups of damaged and undamaged DNA sequences, where an "F" in the middle of a sequence indicates damage. One biological aim is to understand how DNA regenerates with the assistance of proteins that recognize damaged regions. Motivated by empirical support for AR(2) modeling, we fit autoregressive models to the first three principal component scores of each DNA group, capturing the dominant structure in the data. We conducted model diagnostics, …

First Detrital Zircon Provenance Data From Oligocene-Pleistocene Sediment In The Beaufort-Mackenzie Basin, Arctic Ocean, Joseph Martina

Theses and Dissertations

Sediment, runoff, and nutrient input to the Arctic Ocean plays a critical role in both physical and biological processes that impact regional and global systems. The Beaufort-Mackenzie Basin, situated in the Arctic Ocean offshore northwestern Canada, contains more than 14 km of clastic strata and provides a record of erosion and sediment transport from the Cretaceous to present. Pliocene sedimentation rates within the basin jump nearly 2000% relative to underlying units, but the cause of this shift remains unknown. We used cuttings from the N. Issungnak L-86 well, focusing on the Oligocene-lower Miocene Kugmallit and Mackenzie Bay sequences and the …

Process-Grounded Knowledge-Infused Learning And Decision Making, Kaushik Roy

Theses and Dissertations

This dissertation introduces process-grounded knowledge-infused learning and reasoning, a novel framework for integrating domain-expertise-based process knowledge into the learning and reasoning mechanisms of artificial intelligence systems. This approach is designed to produce controlled, transparent, and reliable predictions in critical tasks such as medical diagnosis and recommendation. By focusing on the case study of mental illness diagnosis and recommendation—where decision-making must be grounded in processes such as disorder-specific diagnostic criteria—this work demonstrates methods to embed structured decision-making directly into the system architecture during both training and inference. This integration facilitates end-to-end training and reasoning while ensuring that outputs strictly adhere to …

Spatio-Temporal Modeling & Goodness Of Fit Testing For Ecological Fire Data, Jedidiah Olof Lindborg

Theses and Dissertations

An analysis of fire data sets resulting from controlled burns was performed. Spatio-temporal models were applied to the data sets to determine which covariates are significant in predicting fire temperature. The data sets were censored and only contain temperatures above 300C, due to a limitation in the measuring device. To handle the censoring, an extrapolation was used to reconstruct the temperatures below 300C. Models were created and run for a data set with the extrapolated temperatures and a data set with all censored temperatures removed. Several aspects of the model were evaluated, such as the chosen hyperparameters, the spatial covariance …

Quantifying Biomass Burning Impacts On Soil Nox Emissions And Reactive Nitrogen Cycling, Olivia Rae Steinbeck

Theses and Dissertations

Nitrogen oxides (NOx = NO + NO₂) are trace gases that play a critical role in the atmosphere by influencing air quality, oxidation chemistry, and the deposition of fixed nitrogen. Historically, NOx emissions have been primarily linked to anthropogenic sources such as fossil fuel combustion, industrial activities, and agriculture. However, as successful legislation has significantly reduced these emissions, the relative importance of natural NOx sources has become an increasing concern. Soil NOx emissions are of particular interest due to their strong temperature dependence and their connection to global climate change. Rising global temperatures are expected to accelerate soil NOx emissions …

Explainable Process Recommendation Through Multi-Contextual Grounding Of Dynamic Multimodal Process Knowledge Graphs, Revathy Venkataramanan

Theses and Dissertations

Can I eat this food or not? Is this food suitable for diabetes and why? Which AI pipeline is best suited for a given task and dataset? How should an end-to-end pipeline be constructed? These questions differ from factual question-answering tasks. Recipes and AI pipelines are processes consisting of several entities interacting with each other. A recipe consists of ingredients, cooking methods, and their interactions, while an AI pipeline includes datasets, preprocessing techniques, models, hyperparameters, tasks, and results. Each entity must be analyzed individually, and collective inferencing is performed to derive the final decision. This decision-making process, known as compositional …

Functional Data Analysis On Life Expectancy And Healthcare Expenditure, Hagen Sanchez

Theses and Dissertations

This study analyzes the life expectancy for 237 countries from 1950-2023 and the healthcare expenditure for 50 countries from 1970-2022, and how life expectancy and healthcare expenditure relate to each other. Functional Principal Components Analysis was used to analyze the life expectancy and healthcare expenditure for each of the countries. Additionally, the regions of the countries were analyzed to identify any regional trends for the life expectancy data. Due to missing data and the structure of the healthcare data, multiple imputation methods and Principal Component Analysis techniques were explored for the healthcare data. Furthermore, a simulation study was conducted to …

Approaches To Enhancing Multiple Hypothesis Testing Methods With Side-Information, Siyu Zheng

Theses and Dissertations

Lesion-symptom mapping (LSM) studies offer insight into the brain areas involved in various aspects of cognition. This is commonly done via behavioral testing in patients with a naturally occurring brain injury or lesions (e.g., strokes or brain tumors). This results in high-dimensional observational data where lesion status (present/absent) is non-uniformly distributed, with some voxels having lesions in very few (or no) subjects. In this situation, mass univariate hypothesis tests have severe power heterogeneity where many tests are known a priori to have little to no power. Additionally, high-dimensional observational data can be grouped according to brain anatomical structure.

In this …

Functional Time Transformation Model With Applications To Digital Health, Rahul Ghosal Ph.D., Marcos Matabuena, Sujit K. Ghosh

Faculty Publications

The advent of wearable and sensor technologies now leads to functional predictors which are intrinsically infinite dimensional. While the existing approaches for functional data and survival outcomes lean on the well-established Cox model, the proportional hazard (PH) assumption might not always be suitable in real-world applications. Motivated by physiological signals encountered in digital medicine, we develop a more general and flexible functional time-transformation model for estimating the conditional survival function with both functional and scalar covariates. A partially functional regression model is used to directly model the survival time on the covariates through an unknown monotone transformation and …

Full-Stack Web Applications: Infrastructure, Development Pipelines & Devsecops, Yassine Chahid, Patrick Slattery

Publications and Research

This research explores emerging development methodologies and technologies which facilitate the deployment and maintenance of software applications. It evaluates architectural styles for the development of software such as monolithic (legacy) and microservice models, with a focus on their key differences such as scalability or project structure through to the development of an application. By examining methodologies such as Agile and continuous integration/continuous development pipelines along with the deployment tools Docker and Git for version/release control, the study analyzes how these innovations speed up development, improve existing practices, and serve as the foundation for development operations. Cloud solutions for tasks such …

Eeg Based Real Time Classification Of Consecutive Two Eye Blinks For Brain Computer Interface Applications, Masud Rabbani, Nafi Us Sabbir Sabith, Anubhav Parida, Iysa Iqbal, Sayed Mashroor Mamun, Rumi Ahmed Khan, Farhad Ahmed, Sheikh Iqbal Ahamed

Computer Science Faculty Research and Publications

Human eye blinks are considered a significant contaminant or artifact in electroencephalogram (EEG), which impacts EEG-based medical or scientific applications. However, eye blink detection can instead be transformed into a potential application of brain–computer interfaces (BCI). This study introduces a novel real-time EEG-based framework for classifying three blink states: no blink, single blink, and two consecutive blinks in one model. EEG data were collected from ten healthy participants using an 8-channel wearable headset under controlled blinking conditions. The data were preprocessed and analyzed using four feature extraction techniques: basic statistical, time-domain, amplitude-driven, and frequency-domain methods. The most significant features were …

Bicomplex Hardy Classes Of Solutions To Beltrami Equations And The Schwarz Boundary Value Problem, William L. Blair

Math Faculty Publications and Presentations

We define Hardy classes of bicomplex-valued functions on the complex unit disk which solve bicomplex versions of the Beltrami and related equations. Using representations in terms of their complex-valued counterparts, we show these bicomplex-valued functions recover the boundary behavior associated with the classic holomorphic Hardy spaces. This work generalizes known results for complex-valued functions and continues recent work in the setting of bicomplex analogues of Hardy spaces of both holomorphic and generalized analytic functions. Also, we show Schwarz and Dirichlet boundary value problems associated with the bicomplex Beltrami equation are solvable and provide solution formulas.

Performance Comparison Of Quantum And Classical Machine Learning Models For Chronic Kidney Disease Prediction, Parama Sridevi, Paramita Basak Upama, Masud Rabbani, Sheikh Iqbal Ahamed

Computer Science Faculty Research and Publications

In this study, we develop and compare quantum and classical machine learning-based chronic kidney disease prediction models. We used the "Chronic_Kidney_Disease Data Set" of the UCI Machine Learning Repository. We performed data preprocessing and applied feature engineering techniques to select the best features. We developed two quantum machine learning-based models and two classical machine learning-based models. We used a hybrid classical-quantum environment for building quantum machine learning models. Finally, we compared the performances of all four models. We found that the Quantum Support Vector Machine performs best among the quantum models. The model’s accuracy was 95% with a k-fold cross-validation …

Hdifftg: A Lightweight Hybrid Diffusion-Transformer-Gcn Architecture For 3d Human Pose Estimation, Yajie Fu, Chaorui Huang, Junwei Li, Hui Kong, Yibin Tian, Huakang Li, Zhiyuan Zhang

Research Collection School Of Computing and Information Systems

We propose HDiffTG, a novel 3D Human Pose Estimation (3DHPE) method that integrates Transformer, Graph Convolutional Network (GCN), and diffusion model into a unified framework. HDiffTG leverages the strengths of these techniques to significantly improve pose estimation accuracy and robustness while maintaining a lightweight design. The Transformer captures global spatiotemporal dependencies, the GCN models local skeletal structures, and the diffusion model provides step-by-step optimization for fine-tuning, achieving a complementary balance between global and local features. This integration enhances the model’s ability to handle pose estimation under occlusions and in complex scenarios. Furthermore, we introduce lightweight optimizations to the integrated model …

Non-Traditional Socio-Environmental And Geospatial Determinants Of Alzheimer's Disease-Related Dementia Mortality, Skanda Moorthy, Jean-Eudes Dazard, Zhuo Chen, Ruby Charak, Shruthika Palanivel, Salil Deo, Sadeer G. Al-Kindi, Sanjay Rajagopalan

Psychological Science Faculty Publications

Importance

Design

Modeling Multiple Tasks In Recommendation Systems, Dinh Hieu Do

Dissertations and Theses Collection (Open Access)

Traditional research in recommendation systems has largely centered on the static offline supervised learning setting. In this paradigm, all available user-item interaction data is collected and partitioned into fixed training, validation, and test sets. Models are developed and evaluated in this controlled environment, where the underlying data distribution is assumed to remain unchanged. This approach offers clear advantages: it simplifies experimentation, enables reproducible benchmarking, and allows for straightforward comparisons between algorithms.

However, this static offline setting does not reflect the realities faced by modern recommendation systems. In real-world applications, data is dynamic and ever-evolving, where new users and items are …

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 …

Efficient Prompt Tuning For Hierarchical Ingredient Recognition, Yinxuan Gui, Bin Zhu, Jingjing Chen, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Fine-grained ingredient recognition presents a significant challenge due to the diverse appearances of ingredients, resulting from different cutting and cooking methods. While existing approaches have shown promising results, they still require extensive training costs and focus solely on fine-grained ingredient recognition. In this paper, we address these limitations by introducing an efficient prompt-tuning framework that adapts pretrained visual-language models (VLMs), such as CLIP, to the ingredient recognition task without requiring full model finetuning. Additionally, we introduce three-level ingredient hierarchies to enhance both training performance and evaluation robustness. Specifically, we propose a hierarchical ingredient recognition task, designed to evaluate model performance …

Unveiling Knowledge Boundary Of Large Language Models For Trustworthy Information Access, Yang Deng, Moxin Li, Liang Pang, Wenxuan Zhang, Wai Lam

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have emerged as powerful tools for generating content and facilitating information seeking across diverse domains. While their integration into conversational systems opens new avenues for interactive information-seeking experiences, their effectiveness is constrained by their knowledge boundaries—the limits of what they know and their ability to provide reliable, truthful, and contextually appropriate information. Understanding these boundaries is essential for maximizing the utility of LLMs for real-time information seeking while ensuring their reliability and trustworthiness. In this tutorial, we will explore the taxonomy of knowledge boundary in LLMs, addressing their handling of uncertainty, response calibration, and mitigation of …

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 …

Repairing Adversarial Texts Through Perturbation, Guoliang Dong, Jingyi Wang, Jun Sun, Sudipta Chattopadhyay, Xinyu Wang, Ting Dai, Jie Shi, Jin Song Dong

Research Collection School Of Computing and Information Systems

It is known that neural networks are subject to attacks through adversarial perturbations. Worse yet, such attacks are impossible to eliminate, i.e., the adversarial perturbation is still possible after applying mitigation methods such as adversarial training. Multiple approaches have been developed to detect and reject such adversarial inputs. Rejecting suspicious inputs however may not be always feasible or ideal. First, normal inputs may be rejected due to false alarms generated by the detection algorithm. Second, denial-of-service attacks may be conducted by feeding such systems with adversarial inputs. To address this, in this work, we focus on the text domain and …

Sanitizable Cross-Domain Access Control With Policy-Driven Dynamic Authorization, Jianfei Sun, Guowen Xu, Hongwei Li, Tianwei Zhang, Cong Wu, Xuehuan Yang, Robert H. Deng

Research Collection School Of Computing and Information Systems

The increasing demand for secure and efficient data sharing has underscored the importance of developing robust cryptographic schemes. However, many existing endeavors have overlooked the following critical issues: (1) unauthorized access resulting from malicious information leakage by senders; (2) absence of constraints on write and read permissions for participants; (3) and inflexibility of strategies to dynamically designate ciphertexts to multiple recipients. In this paper, we present SCPA, a cross-domain access control scheme imbued with sanitization features and propelled by policy-driven dynamic authorization, tailored for cloud-based data sharing. This scheme not only facilitates access controls, including regulations for no-read and no-write …