Digital Commons Network^™

Rethinking Neural Multi-Objective Combinatorial Optimization Via Neat Weight Embedding, Jinbiao Chen, Zhiguang Cao, Jiahai Wang, Yaoxin Wu, Hanzhang Qin, Zizhen Zhang, Yue-Jiao Gong

Research Collection School Of Computing and Information Systems

Recent decomposition-based neural multi-objective combinatorial optimization (MOCO) methods struggle to achieve desirable performance. Even equipped with complex learning techniques, they often suffer from significant optimality gaps in weight-specific subproblems. To address this challenge, we propose a neat weight embedding method to learn weight-specific representations, which captures weight-instance interaction for the subproblems and was overlooked by most current methods. We demonstrate the potentials of our method in two instantiations. First, we introduce a succinct addition model to learn weight-specific node embeddings, which surpassed most existing neural methods. Second, we design an enhanced conditional attention model to simultaneously learn the weight embedding …

Learning-Guided Bi-Objective Evolutionary Optimization For Green Municipal Waste Collection Vehicle Routing, Shubing Liao, Yixin Xu, Yunyun Niu, Zhiguang Cao

Research Collection School Of Computing and Information Systems

Waste management has emerged as a critical issue in modern society, where vehicles are scheduled to visit multiple locations for waste collection and transport. This study focuses on a key problem in waste management: route optimization of waste collection vehicles, and formulate it as a bi-objective vehicle routing problem with stochastic demand (VRPSD), aiming to minimizing both total costs and carbon emissions. Although previous studies have significantly advanced our understanding of solving similar problems, the lack of real-world data and limited problem-solving capabilities still restrict the practical applicability of existing methods. To bridge this research gap, this study designed a …

Dps: Design Pattern Summarisation Using Code Features, Najam Nazar, Sameer Sikka, Christoph Treude

Research Collection School Of Computing and Information Systems

Automatic summarisation has been used efficiently in recent years to condense texts, conversations, audio, code, and various other artefacts. A range of methods, from simple template-based summaries to complex machine learning techniques -- and more recently, large language models -- have been employed to generate these summaries. Summarising software design patterns is important because it helps developers quickly understand and reuse complex design concepts, thereby improving software maintainability and development efficiency. However, the generation of summaries for software design patterns has not yet been explored.Our approach utilises code features and JavaParser to parse the code and create a JSON representation. …

Context-Aware Representation: Jointly Learning Item Features And Selection From Triplets, Rodrigo Alves, Antoine Ledent

Research Collection School Of Computing and Information Systems

In areas of machine learning such as cognitive modeling or recommendation, user feedback is usually context-dependent. For instance, a website might provide a user with a set of recommendations and observe which (if any) of the links were clicked by the user. Similarly, there is growing interest in the so-called “odd-one-out” learning setting, where human participants are provided with a basket of items and asked which is the most dissimilar to the others. In both of those cases, the presence of all the items in the basket can influence the final decision. In this article, we consider a classification task …

Alphaedit: Null-Space Constrained Knowledge Editing For Language Models, Junfeng Fang, Houcheng Jiang, Kun Wang, Yunshan Ma, Jie Shi, Xiang Wang, Xiangnan He, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

Large language models (LLMs) often exhibit hallucinations, producing incorrector outdated knowledge. Hence, model editing methods have emerged to enabletargeted knowledge updates. To achieve this, a prevailing paradigm is the locatingthen-editing approach, which first locates influential parameters and then edits themby introducing a perturbation. While effective, current studies have demonstrated that this perturbation inevitably disrupt the originally preserved knowledge within LLMs, especially in sequential editing scenarios. To address this, we introduce AlphaEdit, a novel solution that projects perturbation onto the null space of the preserved knowledge before applying it to the parameters. We theoretically prove that this projection ensures the output …

Predictive Modelling For Vessel Traffic Flow: A Comprehensive Survey From Statistics To Ai, Deshan. Chen, Chen. Huang, Tengze. Fan, Hoong Chuin Lau, Xinping. Yan

Research Collection School Of Computing and Information Systems

Recognizing the specific complexities of vessel traffic flow, this comprehensive survey exclusively addresses the predictive modelling in maritime transportation, tracing the evolution from conventional statistical approaches to modern artificial intelligence (AI) techniques. The survey examines a broad range of predictive targets, including vessel volume, trajectories, velocities, destinations and traffic patterns. Through bibliometric analysis utilizing Citespace, the central research themes and technological trends characterizing the vessel traffic flow prediction domain have been identified and discussed. Our analysis indicates a clear trend towards AI-based models, highlighting their increasing dominance in enhancing predictive accuracy and efficiency. Additionally, we highlight persistent challenges, such as …

Open-Set Graph Anomaly Detection Via Normal Structure Regularisation, Qizhou Wang, Guansong Pang, Mahsa Salehi, Xiaokun Xia, Christopher Leckie

Research Collection School Of Computing and Information Systems

This paper considers an important Graph Anomaly Detection (GAD) task, namely open-set GAD, which aims to train a detection model using a small number of normal and anomaly nodes (referred to as *seen anomalies*) to detect both seen anomalies and *unseen anomalies* (*i.e*., anomalies that cannot be illustrated the training anomalies). Those labelled training data provide crucial prior knowledge about abnormalities for GAD models, enabling substantially reduced detection errors. However, current supervised GAD methods tend to over-emphasise fitting the seen anomalies, leading to many errors of detecting the unseen anomalies as normal nodes. Further, existing open-set AD models were introduced …

A Functional Software Reference Architecture For Llm-Integrated Systems, Alessio Bucaioni, Martin Weyssow, Junda He, Yunbo Lyu, David Lo

Research Collection School Of Computing and Information Systems

The integration of large language models into software systems is transforming capabilities such as natural language understanding, decision-making, and autonomous task execution. However, the absence of a commonly accepted software reference architecture hinders systematic reasoning about their design and quality attributes. This gap makes it challenging to address critical concerns like privacy, security, modularity, and interoperability, which are increasingly important as these systems grow in complexity and societal impact. In this paper, we describe our emerging results for a preliminary functional reference architecture as a conceptual framework to address these challenges and guide the design, evaluation, and evolution of large …

Biogenic Modification Of Tidally Modified Substrates From The Micro- To Macroscopic Scale, Rogers Clark Caldwell Buntin Ii

OES Theses and Dissertations

Digital outcrop models generated by high-resolution photogrammetric imagery permit investigations into organism-substrate interactions at the centimeter to sub-millimeter scale. This dissertation uses this three-dimensional technology to study two sedimentary successions— the Archaean Dresser Formation and Cretaceous Dakota Sandstone— by capturing images via unmanned aircraft systems and single lens reflex cameras. The ~3.48 Ga Dresser Formation provides evidence for some of the earliest life on Earth in the form of stromatolites and microbially induced sedimentary structures. Aerial imagery of the 3.5 km2 Buick Geoheritage reserve capture the site’s geologic structures and close-range imagery documents stromatolites and several microbially induced sedimentary structures …

Low Dissolved Oxygen Operation Enhances Biological Phosphorus Removal In Wastewater Treatment, Haley Morgan

Civil & Environmental Engineering Theses & Dissertations

Biological phosphorus (bio-P) removal occurs when bacteria are exposed to anaerobic/aerobic conditions that stimulate polyphosphate-accumulating organisms (PAOs) to uptake phosphorus. In most treatment plants, dissolved oxygen (DO) concentrations in the aeration tanks are commonly at or above 2.0 mg O₂/L, which is often referred to as the most optimal aeration condition for bio-P. If bio-P can happen efficiently at lower DO (< 0.3 mg O₂/L), then the energy demand of aeration can be decreased appreciably. This research was conducted in a biological nutrient removal (BNR) pilot plant to assess the performance of bio-P at progressively lower DO operation. This …

Enhancing Iot Security Using Lightweight Machine Learning Algorithms: A Comprehensive Approach Using Ensemble Learning, Feature Selection, And Federated Transfer Learning, Khawlah Harahsheh

Electrical & Computer Engineering Theses & Dissertations

The rapid expansion of the Internet of Things (IoT) has introduced significant security vulnerabilities due to the resource-constrained nature of IoT devices and their exposure to cyber threats. Traditional security solutions are often infeasible due to the high computational and storage demands they impose. This dissertation presents a lightweight, AI-driven security framework that enhances IoT network resilience by integrating feature selection, ensemble learning, and federated transfer learning while maintaining data privacy and minimizing computational overhead.

The proposed framework consists of three primary components: Feature Selection for Intrusion Detection, which optimizes performance by reducing redundant data and improving detection accuracy with …

Synchrotron Radiation Interferometry At Cebaf, Sankalp Rajendra Shinde

Physics Theses & Dissertations

Synchrotron radiation interferometry is a method to measure transverse beam size in electron accelerators. By using synchrotron radiation interferometry at a dispersive location in CEBAF at Jefferson Lab, we measure the electron beam size and energy spread. This interferometry technique allows us to monitor the energy spread non-invasively, to measure precise electron beam rms energy spread for hypernuclear experiments, and verify that they meet experiment requirements in real time. This dissertation discusses the design, simulations, construction, and commissioning of this Synchrotron Radiation Interferometer (SRI) in the Hall C line at Jefferson Lab in 2024–2025.

The Structure Function Of The Free Neutron At High X-Bjorken, Madhusudhan Pokhrel

Physics Theses & Dissertations

Understanding the internal structure of nucleons is one of the primary goals of nuclear physicists. As protons and neutrons are only the bound state solution of the QCD lagrangian (at least inside atomic nuclei), studying protons and neutrons helps uncover nuclear structure. Due to its easy availability, many studies on protons have been done on a wide range of kinematics. However, free neutron targets are not readily achievable. So, any information on neutrons has to be extracted from neutron-rich nuclei, and some nuclear models have to be used to subtract the contributions from other nucleons to extract the information …

Ground-Arthropod Assemblage Response To Groundwater As A Metric Of Flooding In The Middle Rio Grande, Wesley J. Noe

Water Resources Professional Project Reports

Riparian zones are dynamic ecosystems, crucial for maintaining biodiversity and ecological balance, particularly in arid environments like the Middle Rio Grande (MRG). Ground arthropods, with their sensitivity to environmental changes, serve as bioindicators for assessing the impacts of water regime changes in the MRG, specifically flooding which was historically the main driver of the MRG ecosystem. This study investigated the responses of ground arthropod communities to fluctuations in groundwater and land management practices within MRG riparian habitats. Using a combination of pitfall trapping and habitat assessments, arthropod abundance was assessed in relation to depth to groundwater (DTG). Findings revealed shifts …

Ground-Arthropod Assemblage Response To Groundwater As A Metric Of Flooding In The Middle Rio Grande, Wesley Noe

Water Resources Professional Project Reports

Riparian zones are dynamic ecosystems, crucial for maintaining biodiversity and ecological balance, particularly in arid environments like the Middle Rio Grande (MRG). Ground arthropods, with their sensitivity to environmental changes, serve as bioindicators for assessing the impacts of water regime changes in the MRG, specifically flooding which was historically the main driver of the MRG ecosystem. This study investigated the responses of ground arthropod communities to fluctuations in groundwater and land management practices within MRG riparian habitats. Using a combination of pitfall trapping and habitat assessments, arthropod abundance was assessed in relation to depth to groundwater (DTG). Findings revealed shifts …

Spatial And Equity Analysis Of The Xeriscape Conversion Rebate Program In Albuquerque, Nm., Claire Jordy

Water Resources Professional Project Reports

With increasing water scarcity concerns threatening water supplies, many cities in the Western U.S. are focusing more effort on their water conservation programs to reduce consumptive water use. The Albuquerque Bernalillo County Water Utility Authority (Water Authority) in Bernalillo County, NM has had several water conservation programs in place since the 1990s, and still, they aim to further reduce water consumption. The Xeriscape Conversion Rebate Program is one of the primary tools to achieve this goal, encouraging customers to convert their high water-use turfgrass lawns to desert-friendly xeriscaping by providing a one-time rebate on their water bill. This rebate program …

High-Quality Development Evaluation Of Cultural And Tourism Integration Empowered By The Digital Economy Under Double Valued Neutrosophic Sets, Jun Wang, Xiong Hu

Neutrosophic Sets and Systems

This study proposed a decision-making approach to evaluate the cultural and tourism integration empowered by the digital economy. Two methods are used in this study, such as Entropy method to compute the criteria weights and the MABAC method to rank the alternatives. These methods are used under the neutrosophic sets. Neutrosophic sets (NSs) are used to represent ambiguous, inconsistent, and unpredictable data that arise in practical issues. Indeterminacy leaning toward truth membership and indeterminacy leaning toward falsity membership are two separate components of double-valued neutrosophic sets (DVNSs), a variant of NSs. Three experts have evaluated the criteria and alternatives. Ten …

Enhancing Medical X-Ray Image Classification With Neutrosophic Set Theory And Advanced Deep Learning Models, Walid Abdullah

Neutrosophic Sets and Systems

The classification of medical images presents significant challenges due to the presence of noise, uncertainty, and indeterminate information. Traditional deep learning models often struggle to manage this, leading to reduced diagnostic accuracy, especially when dealing with low-quality or ambiguous conditions. This paper proposes a hybrid approach that integrates Neutrosophic Set (NS) theory with deep learning models to enhance X-ray image classification under uncertain conditions. NS theory introduces three domains: True (T), Indeterminate (I), and False (F) to manage image uncertainty and noise, allowing deep learning models to better interpret complex, ambiguous visual information. To evaluate the approach, five state-of-the-art deep …

Enhancing Llm-Based Coding Tools Through Native Integration Of Ide-Derived Static Context, Yichen Li, Yun Peng, Yintong Huo, R. Michael Lyu

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) have achieved remarkable success in code completion, as evidenced by their essential roles in developing code assistant services such as Copilot. Being trained on in-file contexts, current LLMs are quite effective in completing code for single source files. However, it is challenging for them to conduct repository-level code completion for large software projects that require cross-file information. Existing research on LLM-based repository-level code completion identifies and integrates cross-file contexts, but it suffers from low accuracy and limited context length of LLMs. In this paper, we argue that Integrated Development Environments (IDEs) can provide direct, accurate and …

On Minimizing Adversarial Counterfactual Error In Adversarial Reinforcement Learning, Roman Belaire, Arunesh Sinha, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Deep Reinforcement Learning (DRL) policies are highly susceptible to adversarial noise in observations, which poses significant risks in safety-critical scenarios. The challenge inherent to adversarial perturbations is that by altering the information observed by the agent, the state becomes only partially observable. Existing approaches address this by either enforcing consistent actions across nearby states or maximizing the worst-case value within adversarially perturbed observations. However, the former suffers from performance degradation when attacks succeed, while the latter tends to be overly conservative, leading to suboptimal performance in benign settings. We hypothesize that these limitations stem from their failing to account for …

Women In Academic Leadership In The East And The West: Navigating Challenges To Attain Key Leadership Positions In Male-Dominated Societies, Ngoc Lan Thi Dang

Journal of Comparative & International Higher Education

No abstract provided.

Data Driven Multi-Objective Optimization Of The Scheduling For Towing A Floating Offshore Wind Turbine Between Assembly Port And Installation Location Throughout A Year, Frédéric Le Pivert, Adam Roberts, Adan Lopez-Santander, Matthew Craven, Saeid Kazemi

School of Engineering, Computing and Mathematics

High demand for the installation of floating offshore wind turbines over the coming years is likely to place significant pressure on ports and installation vessels. Optimization of the routes between ports and farms and the towing schedule when transporting equipment is therefore critical to reducing operation timescales and carbon emissions. This paper presents two series of multi-objective optimizations for minimizing the timescale and carbon emissions for the case of an IEA 15 MW turbine on a VolturnUS-S platform being wet towed through the English Channel to the Celtic Sea. The study makes use of the Maritime Simulation Laboratory (MSL) Ship …

Machine Learning For Reactor Power Monitoring With Limited Labeled Data, C. L. Stewart, B. L. Goldblum, R. G. Abbott, L. Appleby, Brett J. Borghetti, V. Hollingshead, J. H. Whetzel

Faculty Publications

Real-time reactor power monitoring is critical for a variety of nuclear applications, spanning safety, security, operations, and maintenance. While machine learning methods have shown promise in monitoring reactor power levels, there is limited research on their efficacy in label-starved environments. The goal of this work is to assess the feasibility of classifying nuclear reactor power level using multisource data in scenarios with limited labels. Data were collected using low-resolution multisensors at four nuclear reactor facilities: two large research reactors and two TRIGA reactors. Within each pair, one reactor dataset served as the source and the other as the target in …

The Effects Of Snow Cover On The Dynamic Pressure Of Nuclear Detonation Blast Waves, Adam Card, Andrew W. Decker

Faculty Publications

Blast pressure is the primary military targeting metric for nuclear weapons. Any local conditions that affect blast pressure have the potential for altering nuclear plans, both from defensive and offensive standpoints. Understanding the impact of snow to the blast wave, therefore, provides a benefit both to military planners and to warfighters on the ground, for any operation occurring in arctic environments. No existing data provides a quantitative description of how snow on the ground affects a nuclear detonation blast wave passing over it. Similar blast waves passing over dust have experimentally proven to enhance blast pressure in a localized region.1 …

Incorporating Technology And Engineering Literacy Into The 4th Through 8th Grade Educational Experience, Robert Beauchamp

School of Education and Leadership Student Capstone Projects

This capstone project addresses the lack of technology and engineering literacy education at the elementary and middle school levels. The purpose of this capstone project is to help educators at schools without a STEM focus improve the technology and engineering literacy of their 4th through 8th grade students. The project was designed to create a series of practical and engaging professional development sessions tailored to educators with limited time and resources. To achieve this the existing standards and research were reviewed with a concentration on the ITEEA Standards for Technological and Engineering Literacy (STEL), the impact of experiential learning in …

Incorporating Indigenous Knowledge Systems In Environmental Education: Creating Culturally Responsive Curriculum To Foster A More Inclusive And Holistic Approach To Science Learning, Emilie Potocki

School of Education and Leadership Student Capstone Projects

This project explores how elementary science curriculum can be adapted to become more culturally responsive (CR), with a particular focus on integrating Indigenous Knowledge Systems (IKS) into 4th-grade instruction. Grounded in the belief that many Indigenous cultures have long held deep ecological knowledge and sustainable practices, the curriculum seeks to challenge the dominant, Eurocentric framework of traditional science education. Research highlights that culturally responsive teaching not only affirms students’ identities but also improves engagement, academic achievement, and long-term retention of scientific concepts. However, few curricular models at the elementary level meaningfully incorporate Indigenous perspectives in ways that are respectful, authentic, …

Nature-Based Education In A Student-Led Environment: A Program Proposal, Cynthia Duus

School of Education and Leadership Student Capstone Projects

This abstract explores the development of documents to be used for the proposal of a nature-based education program for students in grades kindergarten through second grade. This program is grounded in the principles of student-led learning and the nature-human connection. There is a growing body of research that indicates that exposure to natural environments correlates with significant improvement in the physical, social-emotional, and cognitive development in children. By combining outdoor education experiences with student-led learning, the program fosters confidence, self-direction, and a lasting connection to the natural world. The program is structured around thematic, inquiry-driven units that can be designed …

Blacktail Creek Pdier, Hgl

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Draft Final 2022 Unreclaimed Sites Sampling: Ur-06 Site Evaluation Summary Report, Pioneer Technical Services, Inc.

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Draft Final 2022 Unreclaimed Sites Sampling: Ur-12 Site Evaluation Summary Report, Pioneer Technical Services, Inc.

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.