Institution profile

Deakin University

Academic institutionaustralasia · au
Official website
Research library377linked papers
Opportunities0open roles
Selected work

Representative Papers

Energy-Efficient Prediction in Textile Manufacturing: Enhancing Accuracy and Data Efficiency With Ensemble Deep Transfer Learning

Jan 19, 2026IEEE Access

This study addresses the challenge of high energy consumption in traditional textile manufacturing and the limited applicability of deep neural networks (DNNs) in production output prediction due to data scarcity caused by the high cost of sensor deployment. To overcome this, the authors propose an Ensemble Deep Transfer Learning (EDTL) framework that uniquely integrates ensemble learning with transfer learning. EDTL leverages models pretrained on data-rich production lines and incorporates a feature alignment layer to enhance cross-line generalization, enabling effective knowledge transfer to data-scarce lines. Evaluated on a real-world textile factory dataset, EDTL achieves a 5.66% improvement in prediction accuracy and a 3.96% gain in robustness compared to conventional DNNs when only 20%–40% of training data is available, significantly enhancing both data efficiency and model performance.

2 citationsRead paper

BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents

Jan 08, 2026arXiv.org

This work addresses the lack of systematic understanding regarding the cross-stage propagation mechanisms of backdoor attacks within multi-stage workflows of large language model (LLM) agents. We propose the first agent-centric unified analysis framework that decomposes agent workflows into three phases: planning, memory, and tool use. By integrating phase-aware modeling, trigger injection, and tracking techniques, our framework systematically demonstrates that a backdoor implanted in a single stage can persistently activate across multiple steps and influence downstream outputs. Leveraging this framework, we establish standardized benchmarks for both language and multimodal settings, revealing that on GPT-family base models, trigger persistence rates reach 43.58%, 77.97%, and 60.28% in the planning, memory, and tool-use stages, respectively—highlighting the inherent vulnerability of agent workflows to backdoor threats.

1 citationsRead paper

Who is Responsible? The Data, Models, Users or Regulations? Responsible Generative AI for a Sustainable Future

Jan 15, 2025

This paper addresses the implementation gap in ethical governance of generative AI (Gen AI) in the post-ChatGPT era. Methodologically, it introduces the first end-to-end Responsible Gen AI (RAI) practice framework—spanning governance, technology, evaluation, and deployment—integrating philosophical responsibility theory, eXplainable AI (XAI), benchmark alignment, cross-sector application modeling, and KPI-based quantitative assessment. It pioneers an AI-readiness-oriented testbed evaluation methodology and establishes a comprehensive RAI Key Performance Indicator (KPI) system. Contributions include: (1) systematically bridging the chasm between normative ethical principles and engineering practice while redefining accountability structures; and (2) releasing an open-source resource repository—including standards, tools, and benchmark datasets—to provide researchers, policymakers, and industry practitioners with scalable, reusable, and trustworthy implementation guidance.

1 citationsRead paper

Enhancing stroke disease classification through machine learning models via a novel voting system by feature selection techniques

Jan 09, 2025PLoS ONE

To address the need for early and precise identification of cardiovascular and cerebrovascular diseases, this paper proposes an interpretable classification framework integrating feature selection and ensemble learning. Methodologically, it optimizes features via recursive feature elimination combined with correlation analysis, ensembles nine diverse models—including XGBoost, Random Forest, and SVM—and employs grid search with five-fold cross-validation for hyperparameter tuning; an adaptive weighted voting mechanism is further designed to enhance generalizability and robustness. The key contribution lies in the first-time deep integration of feature selection into the multi-model weight assignment process for voting, thereby jointly optimizing predictive performance and model interpretability. Experimental results demonstrate that the XGBoost submodel achieves 99% accuracy, 99% precision, 98% recall, 99% F1-score, and 100% ROC AUC; overall, the proposed framework significantly outperforms existing state-of-the-art methods.

1 citationsRead paper

Ethical Concerns of Generative AI and Mitigation Strategies: A Systematic Mapping Study

Jan 08, 2025arXiv.org

This study systematically examines the multidimensional ethical challenges and cross-domain governance dilemmas arising from real-world deployments of generative AI—particularly large language models (LLMs). Method: Through a systematic literature review (SLR) and thematic coding, we structurally map 39 empirical studies using an original five-dimensional ethical framework. Contribution/Results: Our analysis uncovers a fundamental tension between the dynamic evolution of ethical risks and the persistent lag in governance responses—a finding not previously documented. We demonstrate that existing mitigation strategies exhibit severe adaptive deficits in high-stakes domains such as healthcare and public administration, stemming from misalignment among technological development, ethical reasoning, and institutional evolution. To address this, we propose a tripartite co-evolutionary pathway integrating ethics, technology, and institutions, offering both theoretical grounding and an actionable framework for resilient governance of generative AI.

1 citationsRead paper
Recent publications

Latest Papers