Digital Commons Network^™

Lsfdnet: A Single-Stage Fusion And Detection Network For Ships Using Swir And Lwir, Yanyin Guo, Runxuan An, Junwei Li, Zhiyuan Zhang

Research Collection School Of Computing and Information Systems

Traditional ship detection methods primarily rely on single-modal approaches, such as visible or infrared images, which limit their application in complex scenarios involving varying lighting conditions and heavy fog. To address this issue, we explore the advantages of short-wave infrared (SWIR) and long-wave infrared (LWIR) in ship detection and propose a novel single-stage image fusion detection algorithm called LSFDNet. This algorithm leverages feature interaction between the image fusion and object detection subtask networks, achieving remarkable detection performance and generating visually impressive fused images. To further improve the saliency of objects in the fused images and improve the performance of the …

Parameter-Efficient Variational Autoencoder For Multimodal Multi-Interest Recommendation, Nhu Thuat Tran, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Learning user preferences in recommendation systems is enriched by multimodal features, such as textual and visual content, and amplified by multi-interest modeling with Variational AutoEncoders (VAEs). However, prior efforts are limited by single modality focus and cumbersome, parameter-heavy architecture designs. To address these limitations, we introduce an innovative solution that blends the semantic richness of multimodal data with the representational power of multi-representation VAEs. Drawing inspiration from Mixture of Experts (MoE), we cast each VAE as an expert tailored to a specific modality, then fuse them via a novel parameter-merging function into a lean, unified model. This approach efficiently captures …

Search Trajectory Network-Enhanced Multi-Objective Dynamic Algorithm Configuration, Robbert Reijnen, Zaharah Bukhsh, Hoong Chuin Lau, Yaoxin Wu, Yingqian Zhang

Research Collection School Of Computing and Information Systems

Deep reinforcement learning (DRL) has emerged as an effective technique for dynamic algorithm configuration, particularly in evolutionary computation, enabling adaptive parameter updates during algorithmic execution. DRL-based methods have shown broad applicability across different problem domains and are designed to configure algorithms without problem-specific information, making them highly transferable across problem variants and scalable to different problem sizes. This paper proposes a novel graph neural network-based approach that learns representations of Search Trajectory Networks (STNs) to track the convergence behavior of multiple objectives and dynamically reconfigures multiobjective evolutionary algorithms during execution. By capturing how solutions evolve and interact over time, the …

Mitigating Cross-Modal Representation Bias For Multicultural Image-To-Recipe Retrieval, Qing Wang, Chong-Wah Ngo, Yu Cao, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Existing approaches for image-to-recipe retrieval have the implicit assumption that a food image can fully capture the details textually documented in its recipe. However, a food image only reflects the visual outcome of a cooked dish and not the underlying cooking process. Consequently, learning cross-modal representations to bridge the modality gap between images and recipes tends to ignore subtle, recipe-specific details that are not visually apparent but are crucial for recipe retrieval. Specifically, the representations are biased to capture the dominant visual elements, resulting in difficulty in ranking similar recipes with subtle differences in use of ingredients and cooking methods. …

Language-Driven 3d Human Pose Estimation In Multi-Person Scenarios: A New Dataset And Approach, Tingrui Shen, Bangzhen Liu, Zhirun Fan, Shiting Zhang, Weifeng Pan, Sun Fan, Dan Cao, Shengfeng He

Research Collection School Of Computing and Information Systems

In an NBA game scenario, consider the challenge of locating and analyzing the 3D poses of players performing a user-specified action, such as attempting a shot. Traditional 3D human pose estimation (3DHPE) methods often fall short in such complex, multi-person scenes due to their lack of semantic integration and reliance on isolated pose data. To address these limitations, we introduce Language-Driven 3D Human Pose Estimation (L3DHPE), a novel approach that extends 3DHPE to general multi-person contexts by incorporating detailed language descriptions. We present Panoptic-L3D, the first dataset designed for L3DHPE, featuring 3,838 linguistic annotations for 1,476 individuals across 588 videos, …

Diffusionmat: Alpha Matting As Deterministic Sequential Refinement Learning, Yangyang Xu, Shengfeng He, Wenqi Shao, Yong Du, Kwan-Yee K. Wong, Yu Qiao, Jun Yu, Ping Luo

Research Collection School Of Computing and Information Systems

In this paper, we introduce DiffusionMat, a novel image matting framework that employs a diffusion model for the transition from coarse to refined alpha mattes. Diverging from conventional methods that utilize trimaps merely as loose guidance for alpha matte prediction, our approach treats image matting as a deterministic sequential refinement learning process. This process begins with the addition of noise to trimaps and iteratively denoises them using a pre-trained diffusion model, which incrementally guides the prediction towards a clean alpha matte. The key innovation of our framework is a correction module that adjusts the output at each denoising step, ensuring …

Lightweight Population-Based Policy Optimization For Pickup And Delivery Problems, Yizhou Liu, Li Li, Yixin Xu, Tang Liu, Rong Cheng, Die Wu, Jilin Yang, Jingwen Li

Research Collection School Of Computing and Information Systems

In recent years, applying deep models to automatically learn construction heuristics for vehicle routing problems has achieved remarkable advancements. However, they are less effective in searching solutions due to two primary limitations: relying on deterministic probability distributions and overlooking the strategic advantage of prioritizing nearby unvisited nodes during the route construction process, resulting in suboptimal policies In this paper, we propose a novel lightweight population-based policy optimization (LPPO) framework that learns a diverse population of solution strategies through the utilization of innovative perturbation factors, in order to facilitate search exploration. Moreover, we design a localized attention synthesis (LAS) network to …

Laboratory Investigation Of High-Temperature Preformed Particle Gels For Fluid Control In Granite Cores For Geothermal Applications, K. Caleb Darko, Yanbo Liu, Thomas P. Schuman, Mingzhen Wei, Baojun Bai

Chemistry Faculty Research & Creative Works

To understand the applicability of high-temperature preformed particle gel (HT-PPG) for control of short-circuiting in enhanced geothermal systems (EGSs), core flooding experiments were conducted on fractured granite cores under varying fracture widths, gel particle sizes and swelling ratios. Key parameters such as injection pressure, water breakthrough pressure, and residual resistance factor were measured to evaluate HT-PPG performance. The gel exhibited strong injectability, entering granite fractures at pressure gradients as low as 0.656 MPa/m; HT-PPG yields a superior sealing performance by significantly reducing the permeability; and dehydration occurs during HT-PPG propagation, with a dehydration ratio ranging from 4.71% to 11.36%. This …

Contrastrepair: Enhancing Conversation-Based Automated Program Repair Via Contrastive Test Case Pairs, Jiaolong Kong, Xiaofei Xie, Mingfei Cheng, Shangqing Liu, Xiaoning Du, Qi Guo

Research Collection School Of Computing and Information Systems

Automated Program Repair (APR) aims to automatically generate patches for rectifying software bugs. Recentstrides in Large Language Models (LLM), such as ChatGPT, have yielded encouraging outcomes in APR,especially within the conversation-driven APR framework. Nevertheless, the efficacy of conversation-drivenAPR is contingent on the quality of the feedback information. In this article, we propose ContrastRepair, anovel conversation-based APR approach that augments conversation-driven APR by providing LLMs withcontrastive test pairs. A test pair consists of a failing test and a passing test, which offer contrastive feedback tothe LLM. Our key insight is to minimize the difference between the generated passing test and the …

Morphology-Aware Hrv Estimation From Wrist Ppg In Sedentary Scenarios, Changshuo Hu, Hung Manh Pham, Dong Ma

Research Collection School Of Computing and Information Systems

Photoplethysmography (PPG) is widely used in wearable devices for non-invasive heart rate variability (HRV) monitoring. While most prior work focuses on mitigating motion artifacts, recent studies highlight that even subtle contact pressure variations can distort waveform morphology and lead to inaccurate HRV estimates. In this work, we propose a morphology-aware deep learning framework that conditions HRV estimation on beat-level waveform types. Our model jointly encodes the raw PPG waveform and a sequence of pressure-induced morphology labels using parallel encoders, integrates them via cross-attention, and predicts normal-to-normal (NN) intervals and beat count to support downstream HRV computation. Evaluated on the public …

Polyqent: A Polynomial Quantified Entailment Solver, Krishnendu Chatterjee, Amir Kafshdar Goharshady, Ehsan Kafshdar Goharshady, Mehrdad Karrabi, Milad Saadat, Maximilian Seeliger, Dorde Zikelic

Research Collection School Of Computing and Information Systems

Polynomial quantified entailments with existentially and universally quantified variables arise in many problems of verification and program analysis. We present PolyQEnt which is a tool for solving polynomial quantified entailments in which variables on both sides of the implication are real valued or unbounded integers. Our tool provides a unified framework for polynomial quantified entailment problems that arise in several papers in the literature. Our experimental evaluation over a wide range of benchmarks shows the applicability of the tool as well as its benefits as opposed to simply using existing SMT solvers to solve such constraints.

A Data-Driven Framework For Optimal Retail Store Location, Ming Hui Tan

Dissertations and Theses Collection (Open Access)

This study develops a data-driven framework for optimal retail store location planning that integrates road network analysis, mobility data and optimization techniques. By addressing the limitations of traditional approaches that rely on outdated census data and manual site selection, this research offers a scalable and adaptable solution for retail expansion in diverse urban environments. Chapters 1 and 2 establish the foundational context and theoretical underpinnings of this research. Chapter 1 introduces the research problem and motivation, highlighting the limitations of existing approaches and defining three key research objectives: automating candidate site identification, improving footfall estimation, and developing a scalable multi-site …

Gravitational Perturbations And Quantum Field Interactions In Modified Spacetime Backgrounds, Abhishek Rout

Theses and Dissertations

This dissertation presents a study of gravitational perturbations and quantum field dynamics in modified spacetime backgrounds. The research is motivated by the quest to understand how quantum fields behave in curved spacetimes, particularly when extensions to general relativity, such as Chern--Simons modifications, are introduced.

The first part examines quantum field interactions with oscillating solitonic backgrounds, inspired by breather-type solutions of the sine--Gordon equation. Fermion bound states are shown to undergo destabilization due to the oscillatory background, leading to particle production and flux propagation to infinity. These results highlight the challenges of maintaining localized fermionic states in time-dependent topological backgrounds.

The …

Coefficients Of The Characteristic Polynomial Of A Hypergraph And Their Combinatorial Properties, Utku Okur

Theses and Dissertations

We investigate the combinatorial properties of the characteristic polynomial $\phi_\mathcal{H}\ev{t}$ of a hypergraph $\mathcal{H}$, in particular, its coefficients. Due to a classical result of Jacobi, the generating function of closed walks at a vertex $u$ in a graph $G$ is determined by the rational function $\phi_{G-u}(t) / \phi_G(t)$. The connection between closed walks of $G$ and its characteristic polynomial has a known elegant proof via an application of Viennot's Heaps of Pieces framework, where cycles are taken as pieces and the concurrence relation is sharing a vertex. Here, we prove a bijection between heaps with a unique maximal piece containing …

Thesis: Comparing Functional And Effective Brain Connectivity Metrics For Eeg, Diksha Srishyla

Theses and Dissertations

Background:Brain connectivity measures have been used to study communication between brain regions using electroencephalography (EEG). Functional and effective connectivity estimate the synchronization and the flow of information between regions, respectively. However, findings from studies using different measures to investigate similar connections do not converge. To guide the selection of functional and effective connectivity measures in future studies, we systematically compared a set of measures in the context of resting state EEG. We examined four functional connectivity metrics (coherence (Coh), the imaginary part of coherence (imCoh), the corrected imaginary part of phase lagged value (ciPLV), the debiased weighted phase-locking index (dwPLI)) …

Evaluation Of Towed Tem Potential For Rapid Characterization Of Levee Foundations, Kolawole Arowoogun, Katherine Grote, Jeremy Maurer

Geosciences and Geological and Petroleum Engineering Faculty Research & Creative Works

Assessing the geologic conditions of levee foundation soils is a challenging task owing to the extensive length of most levees and the heterogeneity of many alluvial deposits. Traditional investigation techniques (such as boring and cone penetrometer testing [CPT]) are expensive, invasive, and provide spatially-limited information. As a result, they are restricted to pre-identified problematic zones in the levee. To overcome these challenges, geophysical instruments capable of better spatial coverage are proposed for rapid geoelectrical characterization of levees. In this study, we presented a field-based application of the towed time-domain electromagnetic method (tTEM) system in characterizing the subsurface geology adjacent to …

Improved Extraction And Detection Of Disinfection Byproducts, Impacts Of Wildland-Urban Interface Wildfires On Drinking Water, And Change In Disinfection Byproducts Over Time In Chlorinated Vs. Chloraminated Distribution Systems, Patrick Thomas Justen

Theses and Dissertations

Drinking water disinfection is critical to prevent the occurrence of waterborne pathogens in drinking water. However, disinfection causes the unintended formation of disinfection byproducts (DBPs) through the reaction of disinfectants (e.g., chlorine, chloramine) with natural organic matter (NOM), algal matter, or anthropogenic pollutants present in source waters. Exposure to DBPs is associated with increased bladder cancer, colorectal cancer, miscarriage, and birth defects. The U.S. EPA currently regulates eleven DBPs in drinking water—four trihalomethanes, five haloacetic acids, bromate, and chlorite. However, research shows that DBP related toxicity in drinking water is driven mainly by other, non-regulated DBPs, particularly iodinated DBPs and …

Synthesis And Characterization Of Lanthanide Extended Structures And Their Novel Transuranic Analogues, Hunter Bernard Tisdale

Theses and Dissertations

The United States owns a substantial amount of radioactive waste as a result of decades of research, weapons manufacturing, and nuclear energy production. As nuclear energy and research continue to add to our stockpiles of waste, the issue of remediating this waste becomes more pressing. Many of the radioactive constituents of this waste, such as the transuranic (Z > 92) elements, will give off radioactivity at harmful levels for millennia. Thus, a robust method of storing this waste is paramount to ensuring public safety. Currently, nuclear waste is being processed by vitrifying it in borosilicate glass. However, this method has shortcomings …

Investigating The Influence Of Instructional Strategies On The Development Of Procedural And Conceptual Knowledge In Advanced Algebra Ii Students, Maura Frances Yinger

Theses and Dissertations

This mixed-methods action research study investigated the influence of instructional strategies shown to improve students’ procedural and conceptual understanding in a rational expressions and equations unit in Advanced Algebra II. The instructional strategies used in the study include comparing, self-explaining, and exploring before instruction. The students (N=27) completed a pre-test and a post-test, both of which were followed by questions asking students to justify their responses on two questions. All students also responded to six digital self-explanation journal prompts. Randomly selected students were placed into three homogenous groups to participate in performance task observations. Analysis of the data …

Application Of Machine Learning For Vascular System Analysis, Alireza Bagheri Rajeoni

Theses and Dissertations

The analysis of vascular structures is critical for diagnosing, monitoring, and treating vascular diseases such as aneurysms, stenosis, and vascular calcification. Traditional methods often rely on manual interpretation of imaging data, which is time-consuming, subjective, and not scalable. This work explores the application of advanced machine learning techniques to automate and enhance vascular system analysis. Our contributions include achieving state-of-the-art accuracy in vascular segmentation, developing a machine learning pipeline to automatically quantify vascular calcification in peripheral arterial disease, and designing a multi-stage machine learning system for abdominal aortic aneurysm analysis that identifies aneurysm boundaries and estimates aneurysm volume in a …

New Approaches On Source Coding For Quantum Stochastic Sources And Implementation Of Quantum Fanout Gate, Rabins Wosti

Theses and Dissertations

The accurate computation of advanced quantum algorithms like Shor’s integer factorization, quantum phase estimation (QPE), and the quantum Fourier transform (QFT) requires quantum circuits of considerable size and depth. It is difficult to achieve reliable computation with deep quantum circuits due to the limited coherence times of the current noisy quantum devices. The quantum fanout gate is known to be a powerful primitive for reducing the depth of many quantum circuits (Høyer and Špalek 2003; Gottesman and Chuang 1999). Shallow or constant-depth quantum circuits are desirable for both near-term and fault-tolerant quantum computations as they reduce noise and allow faster …

Implicit Neural Representation For Image Reconstruction, Canyu Zhang

Theses and Dissertations

Image reconstruction seeks to restore corrupted images and recover visual content that has been lost or degraded. Such degradation may result from low resolution, occlusion, masking, or shadow interference. This problem has become an increasingly significant research topic, as visual information plays a central role in almost every aspect of modern life. Neural network based approaches have recently emerged as highly effective solutions for this task. In particular, convolutional neural networks and transformer based architectures have demonstrated remarkable success in producing visually convincing reconstructions. However, these models remain constrained in several important ways, one of the most critical being that …

Computational Analogies In The Era Of Large Language Models, Amarakoon Mudiyanselage Thilini Wijesiriwardene

Theses and Dissertations

Analogical reasoning is an important part of human cognition requiring the integration of abstract reasoning, pattern recognition, and background knowledge. Despite significant advances in language modeling, the capacity of current methods to accurately identify, model, and evaluate analogies remains fundamentally underexplored.

Analogies enable individuals to perceive deep similarities between superficially different situations. Effective analogy-making requires integrating knowledge about the external world with abstract reasoning and pattern recognition capabilities. While current language models (LMs), trained on massive textual corpora using autoregressive or masked objectives, achieve impressive performance across Natural Language Processing (NLP) tasks such as text generation, summarization, and classification, their …

Multi-Perspective Feature Learning For Facial Expression Recognition In The Wild, Xiangyu Hu

Theses and Dissertations

With the rapid progress of deep learning, Facial Expression Recognition (FER) has seen substantial improvements in performance, particularly “in the wild” meaning real world conditions. Despite these advances, most existing methods extract features from facial images as the sole emotional cues, which limits the model’s ability to capture the full complexity of human emotional expressions.

In reality, facial expressions are composed of diverse and multi-perspective information, including appearance-based cues and geometric structural deformations due to activations of facial muscles. Depending exclusively on one type of representation may fail to exploit the complementary nature of these cues, an issue that becomes …

Ai-Enabled Multi-Layer Security Operations: A Combined Siem, Ids, And Threat Intelligence Model For Adaptive Cyber Defense, Mohamad Khayat

Dissertations

This dissertation presents a comprehensive framework for the evolution of Security Operation Centers (SOCs) through the integration of advanced artificial intelligence (AI), blockchain, and optimization techniques. Motivated by the increasing complexity of cyber threats and the limitations of traditional reactive SOC strategies, this work begins with a systematic literature review that identifies critical gaps in current SOC operations. Based on these insights, a reference architecture is proposed to guide the integration of intelligent components into SOC environments. To address the challenge of secure and trustworthy information sharing, a blockchain-based threat intelligence platform is developed, leveraging Byzantine Fault Tolerance and Zero-Knowledge …

“Toward A World Where Many Worlds Fit”: Thinking-Feeling Our Way In The Pluriverse, Michael Burns

Sustainability Research & Practice Seminar Presentations

Dr. Michael Burns, English, shares "Toward a 'World Where Many Worlds Fit': Thinking-Feeling Our Way into the Pluriverse" Recording shares the lecture portion. Following the lecture participants shared their thoughts with one another.

Harnessing Se Community Knowledge For Developer-Centric Code Intelligence, Chengran Yang

Dissertations and Theses Collection (Open Access)

The integration of Large Language Models (LLMs), particularly those tailored for programming tasks—referred to as code LLMs—has created novel opportunities to enhance developer productivity. These advanced models automate routine and repetitive coding tasks, such as code generation and debugging, and enable faster prototyping and more efficient problem-solving. Despite these remarkable advantages, the current generation of code LLMs exhibits notable limitations that impact their practical effectiveness in real-world software engineering scenarios. These models frequently produce code that is inefficient or suboptimal in runtime performance, demonstrate opaque reasoning processes, and struggle to adapt effectively to diverse developer contexts and specific requirements. Moreover, …

Competition Of Light-And Phonon-Dressing In Microwave-Dressed Bose Polarons, G. M. Koutentakis, S. I. Mistakidis, F. Grusdt, H. R. Sadeghpour, P. Schmelcher

Physics Faculty Research & Creative Works

We theoretically investigate the stationary properties of a spin-1/2 impurity immersed in a one-dimensional confined Bose gas. In particular, we consider coherently coupled spin states with an external field, where only one spin component interacts with the bath, enabling light dressing of the impurity and spin-dependent bath-impurity interactions. Through detailed comparisons with ab-initio many-body simulations, we demonstrate that the composite system is accurately described by a simplified effective Hamiltonian. The latter builds upon previously developed effective potential approaches in the absence of light dressing. It can be used to extract the impurity energy, residue, effective mass, and anharmonicity induced by …

Effective Two- And Three-Body Interactions Between Dressed Impurities In A Tilted Double-Well Potential, F. Theel, A. G. Volosniev, D. Diplaris, F. Brauneis, S. I. Mistakidis, P. Schmelcher

Physics Faculty Research & Creative Works

We explore the impact and scaling of effective interactions between two and three impurity atoms, induced by a bosonic medium, on their density distributions. To facilitate the detection of mediated interactions, we propose a setup where impurities are trapped in a tilted double-well potential, while the medium is confined to a ring. The tilt of the potential breaks the spatial inversion symmetry allowing us to exploit the population of the energetically elevated well as a probe of induced interactions. For two impurities, the interaction with the medium reduces the impurity population at the energetically elevated well, which we interpret as …

Bound Deuteron-Antideuteron System (Deuteronium): Leading Radiative And Internal-Structure Corrections To Bound-State Energies, Gregory S. Adkins, Ulrich D. Jentschura

Physics Faculty Research & Creative Works

We evaluate the energy levels of the deuteronium bound system, which consists of a deuteron and an antideuteron, with a special emphasis on states with nonvanishing orbital angular momenta. The excited atomic bound states of deuteronium constitute probes for the understanding of higher-order quantum electrodynamic corrections for spin-1 particles in a bound system where the typical field strength of the binding Coulomb field (at a distance of the generalized Bohr radius) exceeds Schwinger's critical field strength. For states with nonvanishing angular momenta, effects due to the internal structure of the deuteron and virtual annihilation contributions are highly suppressed. Relevant transitions …