Digital Commons Network^™

Explaining The Association Between Kittlitz's Murrelets (Brachyramphus Brevirostris) And Tidewater Glaciers: Which Habitat Factors Influence Spatial Distribution?, Brendan Higgins

Marine Biology

The Kittlitz’s Murrelet (Brachyramphus brevirostris) is a rare and cryptic seabird species that inhabits Alaska and Eastern Siberia. Populations of Kittlitz’s Murrelets that occur in areas with tidewater glaciers are tightly associated with tidewater glaciers and are only found in close proximity to them. The Kittlitz’s Murrelet is a species of conservation concern, but specific habitat associations are poorly understood. I conducted a multidisciplinary investigation to better understand associations between Kittlitz’s Murrelets and tidewater fjord physical structure. I used remotely sensed spectral indices to model change in abundance of suitable nesting habitat, and a long-term oceanographic dataset to quantify changes …

Organic Matter Sources And The Seasonal And Spatial Trophic Dynamics In Arctic Lagoon Food Webs, Sydney Wilkinson

Marine Biology

The rapid loss of sea ice, warming waters, and increasing freshwater inputs are altering Arctic coastal lagoons, ecosystems that support diverse invertebrate communities, fishes, and subsistence harvests. To resolve how trophic interactions in these systems function under strong seasonal and spatial variability, I applied multiple biochemical tracers, specifically bulk δ13C and δ15N, compound-specific stable carbon isotopes of essential amino acids, and fatty acids to characterize organic matter sources and better understand the trophodynamics of benthic invertebrates and fishes in Beaufort Sea lagoons. I first established local biomarker baselines for terrestrial, microalgal, and macroalgal producers, showing that no single tracer could …

Health Outcomes Of Sarcopenia: A Consensus Report By The Outcome Working Group Of The Global Leadership Initiative In Sarcopenia (Glis), Charlotte Beaudart, Julian Alcazar, Ivan Aprahamian, John A. Batsis, Yosuke Yamada, Carla M. Prado, Jean Yves Reginster, Dolores Sanchez-Rodriguez, Wee Shiong Lim, Marc Sim, Stephan Von Haehling, Jean Woo, Gustavo Duque

Research outputs 2022 to 2026

The Global Leadership Initiative in Sarcopenia (GLIS) aims to standardize the definition and diagnostic criteria for sarcopenia into one unifying, common classification. Among other actions to achieve this objective, the GLIS has organized three different working groups (WGs), with the WG on outcomes of sarcopenia focusing on reporting its health outcomes to be measured in clinical practice once a diagnosis has been established. This includes sarcopenia definitions that better predict health outcomes, the preferred tools for measuring these outcomes, and the cutoffs defining normal and abnormal values. The present article synthesizes discussions and conclusions from this WG, composed of 13 …

State Of Stroke Rehabilitation In Australia: A Who Stars Assessment To Identify Strengths And Gaps Across Policy, Practice And Funding, Lauren J. Christie, Erin Godecke, Maddison Smith, Katharine Scrivener, Kelvin Hill, Joosup Kim, Maria Crotty, Dominique A. Cadilhac, Angela Dos Santos, Natasha A. Lannin

Research outputs 2022 to 2026

Purpose of Review: Rehabilitation following stroke is a complex series of assistive and catalytic interventions enabling a survivor to recover and adapt to their stroke. To achieve adaptation, rehabilitation should supplement healthcare across the continuum, however comprehensive evidence on the provision of stroke rehabilitation in Australia is lacking. The aim of this paper was to describe stroke rehabilitation provision, collecting data using the World Health Organisation (WHO) template for rehabilitation information collection (TRIC). Data were analysed descriptively to complete the Systematic Assessment of Rehabilitation Situation (STARS) assessment. Recent Findings: Challenges include inadequacies in reporting and poor data integration between state- …

Separating The Control Of Moving And Holding In Human Post-Stroke Arm Paresis, Alkis M. Hadjiosif, Kahori Kita, Scott T. Albert, Robert A. Scheidt, Reza Shadmehr, John W. Krakauer

Biomedical Engineering Faculty Research and Publications

Moving and holding-still (holding) have been posited to be separately controlled. The paretic arm after stroke exhibits different abnormalities during rest vs. movement, providing an opportunity to ask whether control of these behaviors is independently affected in stroke. We quantified resting postural abnormalities in human stroke patients by measuring their biases in force production as they held their hand still in various locations in a planar workspace and then assessed whether these resting force biases influenced reaching in the same workspace. Patients displayed marked resting force biases at each location, even when the arm was supported. However, these …

Effective Transfer Of Tumor Annotations From Hematoxylin And Eosin To Fluorescence Images Of Breast And Lung Tissues, Tianling Niu, Emi Ampo, Julie M. Jorns, Mollie Patton, Tongtong Lu, Dong Hye Ye, Tina Yen, Bing Yu

Biomedical Engineering Faculty Research and Publications

Significance: Accurate transfer of annotations from histological images to fluorescence images is essential in developing deep learning (DL)-based optical imaging systems for intraoperative assessment of tumor margins. Manual annotation is time-consuming, prone to interobserver variability, and impractical for large-scale datasets.

Aim: We present a semi-automated method that can effectively transfer tumor annotations from pathologist-annotated hematoxylin and eosin (H&E) images to fluorescence images captured using microscopy with ultraviolet surface excitation (MUSE). This method is not intended for intraoperative use but rather to facilitate the creation of annotated datasets for DL model development.

Approach: Our semi-automated method consists of nonrigid image registration, …

Otherwise Than Human: Responsibility In The Wake Of Disaster, An Eco-Deconstructive Response To Climate Catastrophe, James W. Harris

Masters Theses and Doctoral Dissertations

This thesis will, firstly, assume a line of eco-deconstructive reasoning, which takes as its point of departure from other approaches to the environment the basic premises of deconstruction, which aim to de-center the ontological and epistemological assumptions of Western thought about the subject and language, and apply it to the concept of the human as a distinct and, most importantly, privileged being as this privilege has operated within language and culture, thereby demonstrating how climate catastrophe constitutes a fundamental rupture in traditional ontology. Secondly, I will turn towards the ethics of Emmanuel Levinas, as in present in his God, Death, …

Optimizing Xylitol Production: A Molecular And Experimental Study Of Xylose Reductase In Candida Tropicalis, Zackery Neal

Masters Theses and Doctoral Dissertations

Xylitol, a naturally occurring sugar alcohol, is widely used in the food and pharmaceutical industries as both an artificial sweetener and an anticariogenic agent. Traditional xylitol production relies on harsh chemicals and energy-intensive processes, making microbial fermentation a more sustainable alternative. This study explores the ability of Candida tropicalis to convert D-xylose into xylitol through the enzyme xylose reductase, with a focus on optimizing pH conditions to enhance conversion efficiency. To achieve this, both experimental fermentation and computational molecular dynamics simulations using GROMACS and the pHbuilder tool are employed. By analyzing the enzyme’s stability and structural dynamics across different pH …

More Than Peyote: Trauma, Healing, And The Politics Of Indigenous Cultural Survival In The Age Of Psychedelic Colonialism, Christine Diindiisi Mccleave

Indigenous Studies

This dissertation examines the intersection of peyote religion, historical trauma, and the emergent psychedelic movement through a critical Indigenous lens. Centering peyote as both a sacred medicine and a symbolic flashpoint, the study highlights how contemporary psychedelic policy, practice, and commercialization perpetuate settler-colonial paradigms and threaten Indigenous cultural survival. While mainstream narratives frame psychedelics as tools for healing, this research emphasizes how such framing often obscures deeper histories of dispossession, cultural appropriation, and epistemic violence. Using a mixed-methods approach, including 50 anonymous survey responses, 13 qualitative interviews, and a 6-person focus group, this study amplifies the voices of tribal citizens …

Developing A LingíT Cultural Learning Theory, Eldri Waid Westmoreland

Indigenous Studies

This dissertation develops a Lingít cultural learning theory grounded in ancestral knowledge, cultural values, and intergenerational oral histories. Rooted in Indigenous methodologies and guided by Grounded Theory, the study explores how Lingít ways of knowing, centered on relationships, reciprocity, and respect can inform and transform educational practices for all learners and teachers. Through open-ended interviews and archival transcripts, participants recalled their earliest learning experiences using sensory memory and each identified emotional safety as a key factor for engagement in the learning process. These narratives revealed four foundational themes: processes, patterns, principles, and purposes of learning. The resulting theory honors the …

Trajectories Of Plant-Based Dietary Patterns And Their Sex-Specific Associations With Cardiometabolic Health Among Young Australian Adults, Laura E. Marchese, Sarah A. Mcnaughton, Gilly A. Hendrie, Priscila P. Machado, Therese A. O’Sullivan, Lawrence J. Beilin, Trevor A. Mori, Kacie M. Dickinson, Katherine M. Livingstone

Research outputs 2022 to 2026

Background: Plant-based diets are associated with favourable cardiovascular health markers. Although increasingly consumed among younger demographics, it is unclear how plant-based diet quality tracks from adolescence to young adulthood, and how this impacts cardiovascular health later in life. Thus, this study aimed to explore trajectories of plant-based dietary patterns from adolescence to young adulthood and investigate associations with cardiometabolic health markers in young Australian adults. Methods: Longitudinal data from 417 participants from the Raine Study were included. Semi-quantitative food frequency questionnaires conducted at 14, 20, and 27 years of were used to derive three plant-based diet quality index scores: an …

Feasibility Of A Co-Designed And Personalised Intervention To Improve Vegetable Intake In Rural-Dwelling Young Adults, Katherine Mary Livingstone, Jonathan C. Rawstorn, Stephanie R. Partridge, Yuxin Zhang, Eric O, Stephanie L. Godrich, Sarah A. Mcnaughton, Gilly A. Hendrie, Kathleen M. Dullaghan, Gavin Abbott, Lauren C. Blekkenhorst, Ralph Maddison, Scott Barnett, John C. Mathers, Laura Alston

Research outputs 2022 to 2026

Background: This study determined the feasibility, acceptability, engagement and efficacy of a co-designed and personalised digital intervention to increase vegetable intake (Veg4Me) in young (18-to-35 years) rural-dwelling Australian adults. Methods: Participants living in rural Australia were recruited via local government networks and social media and randomised to receive 12-weeks’ access to personalised (intervention) or non-personalised (control) versions of the free Veg4Me web application. The intervention included: (1) personalised recipes, (2) geo-located food environment map, (3) healthy eating resources, (4) goal-setting portal, and (5) personalised e-newsletters. The primary outcome was feasibility (recruitment, participation, and retention rate). Secondary outcomes were user engagement, …

Optimization Of Size And Siting Of Distributed Generation In Unbalanced Distribution Systems: A Literature Review, Pema Dorji, Stefan Lachowicz, Octavian Bass

Research outputs 2022 to 2026

Renewable energy sources (RES) are essential for meeting the rising global electricity demand while reducing greenhouse gas emissions from conventional generation. As traditional systems approach capacity saturation, the integration of RES into power grids becomes increasingly vital. However, the intermittent and variable nature of RES introduces significant technical, economic, and operational challenges. This review focuses on the optimal planning and integration of distributed generation in unbalanced distribution systems, which more accurately reflect real-world power network conditions. Emphasis is placed on siting and sizing strategies aimed at enhancing voltage stability, minimizing power losses, and reducing system costs and emissions. The review …

Sediment Burial Negatively Impacts The Growth Of Seagrass Posidonia Sinuosa, Chanelle Webster, Nicole Said, Natasha Dunham, Simone Strydom, Kathryn Mcmahon

Research outputs 2022 to 2026

Burial disturbances affect foundation plant species in marine ecosystems. Deposition of dredge spoil can bury seagrass meadows yet we have limited threshold information to predict the trajectory of impact from burial or possible recovery. To investigate the response to burial by dredge spoil, established seagrass ramets of Posidonia sinuosa were collected from a population in Western Australia and exposed to cutter suction dredge spoil sediment. Plant responses were measured during a burial phase after 2, 4 and 8 weeks to assess the influence of duration to burial depths (0, 1, 4, 8 and 16 cm). Sediments were then removed, and …

Co-Design Of A Personalised Physical Activity Intervention For Stroke Survivors, Natalie A. Fini, Emily R. Ramage, Julie R. Bernhardt, Erin M. Bicknell, Chris C.M. Tzefronis, Paul M. Fink, Erin Godecke, Jill L. Francis, Rebecca Wood, Nicole Li, Brandon Lin, Coralie English, Catherine M. Said

Research outputs 2022 to 2026

Introduction/ aims: Incorporating the perspectives of knowledge-users such as stroke survivors into intervention development processes can enhance their relevance and feasibility. The aims of this study were: i) to use co-design to determine “active ingredients” and develop a personalised physical activity intervention for stroke survivors, and ii) to evaluate the co-design process. Methods: A four-stage integrated knowledge translation approach (involving planning and workshops) was applied to co-design a post-stroke physical activity intervention. Knowledge-user participants (stroke survivors (n = 10), carers (n = 3) and clinicians (n = 12)) were recruited. Knowledge-user participants (n = 25) and the research team (n …

Cognitive Frailty And Cardiometabolic Risk In Middle-Aged And Older Adults: Evidence From The Uk And China, Haiyang Yan, Jingjing Lang, Chengfeng Li, Samaneh Eftekhariranjbar, Guoyan Jiang, Jing Lei, Lixin Sun, Carlos J. Toro-Huamanchumo, Zhongyang Guan

Research outputs 2022 to 2026

Background: Cognitive frailty, a novel construct integrating cognitive and physical deficits, is increasingly recognized in aging research. Aims: This study aimed to examine the associations between cognitive frailty and cardiometabolic risk in two nationally representative cohorts from China and the United Kingdom. Methods: We analyzed data from 7,628 participants in the China Health and Retirement Longitudinal Study (CHARLS) and 4,703 participants from the English Longitudinal Study of Ageing (ELSA), all aged ≥ 50 years. Frailty was assessed using the frailty index (FI) in the main analysis. Cox proportional hazards models were applied to estimate hazard ratios (HRs) for incident cardiometabolic …

High-Dose Beta-Alanine Supplementation For Two Weeks Did Not Enhance Intermittent Endurance Or Sprint Performance In Trained Futsal Players, Hossein Miraftabi, Erfan Berjisian, Marzieh Nouri Dizicheh, Alireza Naderi, Masoud Bodaghi, Majid S. Koozehchian, Fatemeh Shabkhiz, Alvaro Lopez-Samanes

Research outputs 2022 to 2026

Background: This study aimed to investigate the effects of a high-dose beta-alanine (BA) supplementation on physical performance, blood lactate concentration, and ratings of perceived exertion (RPE) in trained futsal players. Methods: Sixteen trained futsal players participated in a randomized, parallel, double-blind experiment, completing a two-week supplementation period with either 12 g/day of BA (n = 8; age: 19 ± 2 years; height: 1.78 ± 0.03 m; body mass: 68.5 ± 5.4 kg) or a placebo (PLA) (n = 8; age: 18 ± 1 years; height: 1.74 ± 0.08 m; body mass: 65.6 ± 6.4 kg). Athletes completed the futsal intermittent …

Impact Of Exercise In Patients With Pancreatic Cancer Across Different Treatment Phases: A Systematic Review, Linda Toniolo, Anita Borsati, Cristina Crespo-Garcia, Diana Giannarelli, Christian Ciurnelli, Gloria Adamoli, Lorenzo Belluomini, Ilaria Trestini, Daniela Tregnago, Federico Schena, Robert U. Newton, Salvatore Paiella, Roberto Salvia, Michele Milella, Sara Pilotto, Alice Avancini

Research outputs 2022 to 2026

Background: With a dismal prognosis of 8–10 % 5-year survival since diagnosis, pancreatic cancer remains one of the most aggressive oncological diseases. This work aimed to evaluate the effects of exercise medicine on safety and feasibility, physical fitness, body composition, patient-reported outcomes, and clinical outcomes across different treatment phases in patients with pancreatic cancer. Method: PubMed, Cochrane, and Scopus databases were systematically screened to identify single-arm studies and randomized/non-randomized controlled trials investigating a physical exercise intervention in patients with pancreatic cancer. The RoB 2 and ROBINS-I tools were used to evaluate study quality for randomized and non-randomized studies, respectively. Qualitative …

Exploring The Experiences And Needs Of Chinese Older Adults And Their Family Caregivers, Yu Huang

Research outputs 2022 to 2026

This multi-generational research project represents an academic partnership between Edith Cowan University (ECU) and Chung Wah Community Care (CWCC), conducted from February to August 2025. Through CWCC's established community participation programs, this collaboration provided both a rich platform for community engagement and an accessible entry point for an ECU Research Internship to collect and analyse in-depth data on the "homing" experiences of Chinese elderly immigrants in Australia.

The study employed a mixed-methods design, engaging 162 survey participants and 15 interview participants across CWCC's two service locations (Balcatta Hub and Willetton Hub) and one well-aged group of name as Evergreen College. …

Exploring Fathers’ Child And Family Support During Aboriginal Mothers’ Incarceration, Bon Miu, Paul Leslie Simpson, Tony Butler, Mandy Wilson, Destiny Kynuna, Robert Shaw, Jocelyn Jones

Research outputs 2022 to 2026

Aboriginal women are one of the fastest-growing subgroups among the Australian incarcerated population. Their incarceration affects increasing numbers of children, families, and communities. Few studies have examined the role of fathers when mothers are incarcerated. Using 49 in-depth interviews with Aboriginal mothers in Western Australian prisons, we explore the types of child and family support fathers provide based on the incarcerated mother’s perspective. Four themes were identified: (1) diverse support and involvement by fathers; (2) absence of father’s support due to death or incarceration; (3) parental cooperation and communication; and (4) supports and challenges to maintaining family networks. Overall, fathers …

Island-Based Evolutionary Computation With Diverse Surrogates And Adaptive Knowledge Transfer For High-Dimensional Data-Driven Optimization, Xianrong Zhang, Yuejiao Gong, Zhiguang Cao, Jun Zhang

Research Collection School Of Computing and Information Systems

In recent years, there has been a growing interest in data-driven evolutionary algorithms (DDEAs) employing surrogate models to approximate the objective functions with limited data. However, current DDEAs are primarily designed for lower-dimensional problems and their performance drops significantly when applied to large-scale optimization problems (LSOPs). To address the challenge, this paper proposes an offline DDEA named DSKT-DDEA. DSKT-DDEA leverages multiple islands that utilize different data to establish diverse surrogate models, fostering diverse subpopulations and mitigating the risk of premature convergence. In the intra-island optimization phase, a semi-supervised learning method is devised to fine-tune the surrogates. It not only facilitates …

Digital Communications Between Firms And Investors: Impact Of Explanatory Responses On Investor Engagement In Online Financial Q&A, Runyu Wang, Zili Zhang, Keng Siau, Ziqiong Zhang

Research Collection School Of Computing and Information Systems

The emerging trend of digital communications between firms and investors through online question-and-answer (Q&A) platforms is recognized as a vital strategy for managing investor relations, contributing to enhanced market efficiency and information transparency through increased information exchange. Potential investors can seek responses from firm managers to address their information needs, thereby mitigating market uncertainties. To provide foundational insights, we conduct a survey of investors to assess their awareness, usage, and perceptions of firm-investor Q&A platforms. In the subsequent empirical study, we specifically focus on the substance of managers’ responses, which are primarily aimed at clarifying firm events or information. In …

Contx: Scene Context Prediction Via Context Bank And Layout Perception, Jingxin Liang, Yangyang Xu, Haorui Song, Yuan Lu, Yuhui Deng, Yiyi Long, Yan Huang, Shengxin Liu, Jianbo Jiao, Shengfeng He

Research Collection School Of Computing and Information Systems

Scene context prediction, which seeks to infer unknown contextual information from isolated object properties, currently faces limitations due to predominant reliance on pixel-wise supervision that overlooks real-world context priors. To address this, we present ContX, a context-prior-driven, coarse-to-fine model. ContX distinctively integrates explicit linguistic-contextual knowledge in two key ways. First, it proposes a linguistic guided context bank, leveraging linguistic-statistical contextual data to guide the rationality of segmentation shapes and foster meaningful inter-class contextual interactions. Second, ContX augments contextual comprehension by correlating layouts with linguistic descriptions, enhancing layout perception through a multi-modal strategy. Comprehensive experiments demonstrate ContX's superiority and versatility, outperforming …

Backdoorllm: A Comprehensive Benchmark For Backdoor Attacks And Defenses On Large Language Models, Yige Li, Hanxun Huang, Yunhan Zhao, Xingjun Ma, Jun Sun

Research Collection School Of Computing and Information Systems

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce adversaryspecified outputs. While prior research has predominantly focused on backdoor risks in vision and classification settings, the vulnerability of LLMs in open-ended text generation remains underexplored. To fill this gap, we introduce BackdoorLLM1 , the first comprehensive benchmark for systematically evaluating backdoor threats in text-generation LLMs. BackdoorLLM provides: (i) a unified repository of benchmarks with a standardized training and evaluation pipeline; (ii) a diverse suite of …

A Learning‑Augmented Dynamic Programming Approach For Orienteering Problem With Time Windows, Guansheng Peng, Lining Xing, Fuyan Song Ma, Aldy Gunawan, Aldy Gunawan

Research Collection School Of Computing and Information Systems

Recent years have witnessed a surge of interest in solving combinatorial optimization problems (COPs) using machine learning techniques. Motivated by this trend, we propose a learning-augmented exact approach for tackling an NP-hard COP, the Orienteering Problem with Time Windows, which aims to maximize the total score collected by visiting a subset of vertices in a graph within their time windows. Traditional exact algorithms rely heavily on domain expertise and meticulous design, making it hard to achieve further improvements. By leveraging deep learning models to learn effective relaxations of problem restrictions from data, our approach enables significant performance gains in an …

Sopo: Text-To-Motion Generation Using Semi-Online Preference Optimization, Xiaofeng Tan, Hongsong Wang, Xin Geng, Pan Zhou

Research Collection School Of Computing and Information Systems

Text-to-motion generation is essential for advancing the creative industry but often presents challenges in producing consistent, realistic motions. To address this, we focus on fine-tuning text-to-motion models to consistently favor highquality, human-preferred motions—a critical yet largely unexplored problem. In this work, we theoretically investigate the DPO under both online and offline settings, and reveal their respective limitation: overfitting in offline DPO, and biased sampling in online DPO. Building on our theoretical insights, we introduce Semi-online Preference Optimization (SoPo), a DPO-based method for training text-to-motion models using “semi-online” data pair, consisting of unpreferred motion from online distribution and preferred motion in …

Hybrid-Balance Gflownet For Solving Vehicle Routing Problems, Ni Zhang, Zhiguang Cao

Research Collection School Of Computing and Information Systems

Existing GFlowNet-based methods for vehicle routing problems (VRPs) typically employ Trajectory Balance (TB) to achieve global optimization but often neglect important aspects of local optimization. While Detailed Balance (DB) addresses local optimization more effectively, it alone falls short in solving VRPs, which inherently require holistic trajectory optimization. To address these limitations, we introduce the Hybrid-Balance GFlowNet (HBG) framework, which uniquely integrates TB and DB in a principled and adaptive manner by aligning their intrinsically complementary strengths. Additionally, we propose a specialized inference strategy for depot-centric scenarios like the Capacitated Vehicle Routing Problem (CVRP), leveraging the depot node's greater flexibility in …

Uniteformer: Unifying Node And Edge Modalities In Transformers For Vehicle Routing Problem, Dian Meng, Zhiguang Cao, Jie Gao, Yaoxin Wu, Yaqing Hou

Research Collection School Of Computing and Information Systems

Neural solvers for the Vehicle Routing Problem (VRP) have typically relied on either node or edge inputs, limiting their flexibility and generalization in real-world scenarios. We propose UniteFormer, a unified neural solver that supports node-only, edge-only, and hybrid input types through a single model trained via joint edge-node modalities. UniteFormer introduces: (1) a mixed encoder that integrates graph convolutional networks and attention mechanisms to collaboratively process node and edge features, capturing cross-modal interactions between them; and (2) a parallel decoder enhanced with query mapping and a feed-forward layer for improved representation. The model is trained with REINFORCE by randomly sampling …

Large Language Models As End-To-End Combinatorial Optimization Solvers, Xia Jiang, Yaoxin Wu, Minshuo Li, Zhiguang Cao, Yingqian Zhang

Research Collection School Of Computing and Information Systems

Combinatorial optimization (CO) problems, central to decision-making scenarios like logistics and manufacturing, are traditionally solved using problem-specific algorithms requiring significant domain expertise. While large language models (LLMs) have shown promise in automating CO problem solving, existing approaches rely on intermediate steps such as code generation or solver invocation, limiting their generality and accessibility. This paper introduces a novel framework that empowers LLMs to serve as end-to-end CO solvers by directly mapping natural language problem descriptions to solutions. We propose a two-stage training strategy: supervised fine-tuning (SFT) imparts LLMs with solution generation patterns from domain-specific solvers, while a feasibility-and-optimality-aware reinforcement learning …

Learning Memory-Enhanced Improvement Heuristics For Flexible Job Shop Scheduling, Jiaqi Wang, Zhiguang Cao, Peng Zhao, Rui Cao, Yubin Xiao, Yuan Jiang, You Zhou

Research Collection School Of Computing and Information Systems

The rise of smart manufacturing under Industry 4.0 introduces mass customization and dynamic production, demanding more advanced and flexible scheduling techniques. The flexible job-shop scheduling problem (FJSP) has attracted significant attention due to its complex constraints and strong alignment with real-world production scenarios. Current deep reinforcement learning (DRL)-based approaches to FJSP predominantly employ constructive methods. While effective, they often fall short of reaching (near-)optimal solutions. In contrast, improvement-based methods iteratively explore the neighborhood of initial solutions and are more effective in approaching optimality. However, the flexible machine allocation in FJSP poses significant challenges to the application of this framework, including …