Yuan Miao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yuan Miao has a total of 126 co-authors. Here are the top co-authors by number of shared publications:
- Chunyan Miao
School of Computer Science and Engineering, Nanyang Technological University, Singapore, Singapore
6 shared publications - Hua Wang
Victoria University
5 shared publications - Jiao Yin
Victoria University
5 shared publications - Jinli Cao
La Trobe University, Melbourne, Australia
5 shared publications - Khandakar Ahmed
College of Engineering and Science, Victoria University, Melbourne 3000, Australia
3 shared publications - Wei Hong
Victoria University
3 shared publications
Latest Publications
- Open Access
- 24 July 2026
- Published by Elsevier in SSRN Electronic Journal
Estimating Aboveground Biomass Density at 10m Resolution Using Multi-Product Consensus Samples and Optimized Machine Learning
Aboveground biomass density (AGBD) serves as a critical metric for characterizing terrestrial ecosystem carbon stocks. However, the limited comparability among existing AGBD products constrain their application. Focusing on these issues, we integrated five AGBD products through a multi-product consensus approach to construct reliable training samples. We combined these samples 124 multi-source features to evaluate machine learning models for AGBD mapping at 10m spatial resolution across Spain, France, and Italy. The results showed that: (1) Five products exhibited substantial numerical discrepancies at the pixel level, the reliable training samples can be constructed through multi-product consensus. Models trained on the 454,000 reliable training samples substantially outperformed those based on individual products. (2) XGBoost outperformed RF, LightGBM, and CNN in AGBD estimation. After reducing redundant features from 124 to 15, XGBoost maintained an R² of 0.86 and an RMSE of 32.80Mg ha⁻¹. (3) Total AGB across the study area was estimated at 6.34Pg. Urban areas had an average AGBD of 27.82Mg ha⁻¹, slightly higher than that of bare/sparse vegetation (25.17Mg ha⁻¹) and shrubland (25.38Mg ha⁻¹). The spatial upscaling analysis revealed that coarsening pixel size led to a sharp loss in urban AGBD representation. These findings demonstrate that reliable training samples can be constructed from discrepant products by explicitly exploiting their pixel-level consensus. urban vegetation as a non-negligible component of regional aboveground biomass stocks. Overall, the proposed framework provides a robust foundation for high-resolution vegetation biomass mapping and regional carbon stock assessment.
- 24 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessEstimating Aboveground Biomass Density at 10m Resolution Using Multi-Product Consensus Samples and Optimized Machine Learning
Aboveground biomass density (AGBD) serves as a critical metric for characterizing terrestrial ecosystem carbon stocks. However, the limited comparability among existing AGBD products constrain their application. Focusing on these issues, we integrated five AGBD products through a multi-product consensus approach to construct reliable training samples. We combined these samples 124 multi-source features to evaluate machine learning models for AGBD mapping at 10m spatial resolution across Spain, France, and Italy. The results showed that: (1) Five products exhibited substantial numerical discrepancies at the pixel level, the reliable training samples can be constructed through multi-product consensus. Models trained on the 454,000 reliable training samples substantially outperformed those based on individual products. (2) XGBoost outperformed RF, LightGBM, and CNN in AGBD estimation. After reducing redundant features from 124 to 15, XGBoost maintained an R² of 0.86 and an RMSE of 32.80Mg ha⁻¹. (3) Total AGB across the study area was estimated at 6.34Pg. Urban areas had an average AGBD of 27.82Mg ha⁻¹, slightly higher than that of bare/sparse vegetation (25.17Mg ha⁻¹) and shrubland (25.38Mg ha⁻¹). The spatial upscaling analysis revealed that coarsening pixel size led to a sharp loss in urban AGBD representation. These findings demonstrate that reliable training samples can be constructed from discrepant products by explicitly exploiting their pixel-level consensus. urban vegetation as a non-negligible component of regional aboveground biomass stocks. Overall, the proposed framework provides a robust foundation for high-resolution vegetation biomass mapping and regional carbon stock assessment.
- Open Access
- 16 March 2026
- Published by European Alliance for Innovation n.o. in ICST Transactions on Scalable Information Systems
- Vol. 12 (8)
A Decentralised Coordination Framework for Demand-Side Solar-Storage and Its Electricity Market Participation
The rapid proliferation of rooftop photovoltaics and behind-the-meter battery storage is creating systemic risks in distribution networks. This includes local network constraint violations, insufficient outage resilience, and enlarged cybersecurity attack surfaces, leaving millions of demand-side distributed energy resources (DERs) to operate without coordinated oversight. Existing solutions (dynamic operating envelopes, virtual power plants, peer-to-peer trading, and single-household energy management systems) each address only partial aspects of this challenge. Based on multi-agent reinforcement learning, this paper proposes a Decentralised Coordination Framework (DCF) that organises the energy dispatch into a three-tier hierarchical architecture. Specifically, it has a user layer executing Proximal Policy Optimisation (PPO) for local dispatch, a feeder layer in which a dynamically elected L1 leader applies MADDPG to coordinate community flexibility via a Virtual Aggregation Unit (VAU); and a cross-feeder layer where an L2 leader manages inter-community balancing and market interfaces. It integrates a directed acyclic graph (DAG)-based verifiable execution ledger, Paillier homomorphic encryption, and LLM-based anomaly detection to enhance security. Potential market participation pathway and revenue distribution mechanism are proposed to align with the Australian National Electricity Market. The DCF provides a scalable, market-ready foundation for commercial demandside DER deployment under high renewable penetration.
- 16 March 2026
- Published by European Alliance for Innovation n.o. in ICST Transactions on Scalable Information Systems
- Vol. 12 (8)
Open AccessA Decentralised Coordination Framework for Demand-Side Solar-Storage and Its Electricity Market Participation
The rapid proliferation of rooftop photovoltaics and behind-the-meter battery storage is creating systemic risks in distribution networks. This includes local network constraint violations, insufficient outage resilience, and enlarged cybersecurity attack surfaces, leaving millions of demand-side distributed energy resources (DERs) to operate without coordinated oversight. Existing solutions (dynamic operating envelopes, virtual power plants, peer-to-peer trading, and single-household energy management systems) each address only partial aspects of this challenge. Based on multi-agent reinforcement learning, this paper proposes a Decentralised Coordination Framework (DCF) that organises the energy dispatch into a three-tier hierarchical architecture. Specifically, it has a user layer executing Proximal Policy Optimisation (PPO) for local dispatch, a feeder layer in which a dynamically elected L1 leader applies MADDPG to coordinate community flexibility via a Virtual Aggregation Unit (VAU); and a cross-feeder layer where an L2 leader manages inter-community balancing and market interfaces. It integrates a directed acyclic graph (DAG)-based verifiable execution ledger, Paillier homomorphic encryption, and LLM-based anomaly detection to enhance security. Potential market participation pathway and revenue distribution mechanism are proposed to align with the Australian National Electricity Market. The DCF provides a scalable, market-ready foundation for commercial demandside DER deployment under high renewable penetration.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 9100-9109
RSFomer: Time Series Transformer for Robust Sports Action Recognition
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 9100-9109
Open AccessRSFomer: Time Series Transformer for Robust Sports Action Recognition
- Open Access
- 11 October 2025
- Published by Elsevier in Results in Control and Optimization
- Vol. 21
Quadratic Diophantine fuzzy sentiment-based nonlinear decision-making for medical diagnostics through soft sets and cognitive maps
- 11 October 2025
- Published by Elsevier in Results in Control and Optimization
- Vol. 21
Open AccessQuadratic Diophantine fuzzy sentiment-based nonlinear decision-making for medical diagnostics through soft sets and cognitive maps
- 30 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. PP (21682194) , 1-14
MDP-GRL: Multi-disease Prediction by Graph-enabled Representation Learning
In recent years, automatic disease prediction based on electronic health records (EHRs) has emerged as a focal area of research in medical informatics. While successfully facilitating disease diagnosis, this technique still suffers from many limitations caused by the complexity of medical data, particularly the diverse relations and shared risk factors among multiple diseases. Besides, the data sparsity and imbalanced problem in EHR also undermines the effectiveness of existing approaches. Therefore, new approaches are urgently needed to accommodate the EHR features better and make effective predictions on individuals' potential diseases. To address the above challenges, this paper proposes MDP-GRL, a novel multi-label disease prediction model based on graph-enabled representation learning. Specifically, MDP-GRL constructs a medical knowledge graph (MKG) based on the patient and disease information in EHR and then employs a graph neural network (GNN) to realise the disease prediction. To address the data sparsity issue, it incorporates supplementary data for both patients and diseases, i.e., enriching patient nodes by personal basic information, examination indicators, and illness history, and supplementing disease information with comorbidity information, prevalent populations, common causes, and diagnostic basis. To mitigate the data complexity issue, MDP-GRL considers four different relation patterns in MKG, which optimizes the modelling capabilities. To address the data imbalance problem, it introduces an attention mechanism and self-adversarial negative sampling strategy, which further enhance MDP-GRL's ability to identify error-prone and minority samples. Comprehensive experiments and ablation studies are conducted based on the MIMIC-IV dataset. The results demonstrate MDP-GRL's superiority in multi-disease prediction compared with state-of-the-art approaches.
- 30 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. PP (21682194) , 1-14
MDP-GRL: Multi-disease Prediction by Graph-enabled Representation Learning
In recent years, automatic disease prediction based on electronic health records (EHRs) has emerged as a focal area of research in medical informatics. While successfully facilitating disease diagnosis, this technique still suffers from many limitations caused by the complexity of medical data, particularly the diverse relations and shared risk factors among multiple diseases. Besides, the data sparsity and imbalanced problem in EHR also undermines the effectiveness of existing approaches. Therefore, new approaches are urgently needed to accommodate the EHR features better and make effective predictions on individuals' potential diseases. To address the above challenges, this paper proposes MDP-GRL, a novel multi-label disease prediction model based on graph-enabled representation learning. Specifically, MDP-GRL constructs a medical knowledge graph (MKG) based on the patient and disease information in EHR and then employs a graph neural network (GNN) to realise the disease prediction. To address the data sparsity issue, it incorporates supplementary data for both patients and diseases, i.e., enriching patient nodes by personal basic information, examination indicators, and illness history, and supplementing disease information with comorbidity information, prevalent populations, common causes, and diagnostic basis. To mitigate the data complexity issue, MDP-GRL considers four different relation patterns in MKG, which optimizes the modelling capabilities. To address the data imbalance problem, it introduces an attention mechanism and self-adversarial negative sampling strategy, which further enhance MDP-GRL's ability to identify error-prone and minority samples. Comprehensive experiments and ablation studies are conducted based on the MIMIC-IV dataset. The results demonstrate MDP-GRL's superiority in multi-disease prediction compared with state-of-the-art approaches.
- Open Access
Distributed Retrieval-Augmented Generation
As large language models (LLMs) become increasingly adopted on edge devices, Retrieval-Augmented Generation (RAG) is gaining prominence as a solution to address factual deficiencies and hallucinations by integrating external knowledge. However, centralized RAG architectures face significant challenges in data privacy and scalability. For instance, smart healthcare services often rely on collecting sensitive patient data and building a centralized knowledge base to provide better diagnosis and treatment advice, while privacy concerns significantly impede this process. Besides, maintaining a comprehensive and continuously updated knowledge base is costly, particularly in response to regional epidemics and rapidly mutating viruses. To address these challenges, this paper introduces Distributed Retrieval-Augmented Generation (DRAG), a novel framework that improves data privacy by eliminating the need for a centralized knowledge base and restoring data control to owners. DRAG incorporates a Topic-Aware Random Walk (TARW) algorithm that leverages LLMs to extract query topics and facilitate targeted peer discovery within a peer-to-peer network, enabling efficient knowledge retrieval in decentralized environments. Extensive experiments across three diverse datasets and LLMs demonstrate that DRAG with TARW achieves near-centralized RAG performance by using half as many messages as flooding. The code is available at https://github.com/xuchenhao001/DRAG.
Open AccessDistributed Retrieval-Augmented Generation
As large language models (LLMs) become increasingly adopted on edge devices, Retrieval-Augmented Generation (RAG) is gaining prominence as a solution to address factual deficiencies and hallucinations by integrating external knowledge. However, centralized RAG architectures face significant challenges in data privacy and scalability. For instance, smart healthcare services often rely on collecting sensitive patient data and building a centralized knowledge base to provide better diagnosis and treatment advice, while privacy concerns significantly impede this process. Besides, maintaining a comprehensive and continuously updated knowledge base is costly, particularly in response to regional epidemics and rapidly mutating viruses. To address these challenges, this paper introduces Distributed Retrieval-Augmented Generation (DRAG), a novel framework that improves data privacy by eliminating the need for a centralized knowledge base and restoring data control to owners. DRAG incorporates a Topic-Aware Random Walk (TARW) algorithm that leverages LLMs to extract query topics and facilitate targeted peer discovery within a peer-to-peer network, enabling efficient knowledge retrieval in decentralized environments. Extensive experiments across three diverse datasets and LLMs demonstrate that DRAG with TARW achieves near-centralized RAG performance by using half as many messages as flooding. The code is available at https://github.com/xuchenhao001/DRAG.
- 29 November 2024
- Published by Springer Nature
- p. 102-113
From Data to Insights: Constructing and Evaluating a Hospitality Dataset for Quadruple Aspect-Based Sentiment Analysis
- 29 November 2024
- Published by Springer Nature
- p. 102-113
From Data to Insights: Constructing and Evaluating a Hospitality Dataset for Quadruple Aspect-Based Sentiment Analysis
- Open Access
- 31 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 18 (8) , 1-17
A Compact Vulnerability Knowledge Graph for Risk Assessment
Software vulnerabilities, also known as flaws, bugs or weaknesses, are common in modern information systems, putting critical data of organizations and individuals at cyber risk. Due to the scarcity of resources, initial risk assessment is becoming a necessary step to prioritize vulnerabilities and make better decisions on remediation, mitigation, and patching. Datasets containing historical vulnerability information are crucial digital assets to enable AI-based risk assessments. However, existing datasets focus on collecting information on individual vulnerabilities while simply storing them in relational databases, disregarding their structural connections. This article constructs a compact vulnerability knowledge graph, VulKG, containing over 276 K nodes and 1 M relationships to represent the connections between vulnerabilities, exploits, affected products, vendors, referred domain names, and more. We provide a detailed analysis of VulKG modeling and construction, demonstrating VulKG-based query and reasoning, and providing a use case of applying VulKG to a vulnerability risk assessment task, i.e., co-exploitation behavior discovery. Experimental results demonstrate the value of graph connections in vulnerability risk assessment tasks. VulKG offers exciting opportunities for more novel and significant research in areas related to vulnerability risk assessment. The data and codes of this article are available at https://github.com/happyResearcher/VulKG.git .
- 31 July 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 18 (8) , 1-17
Open AccessA Compact Vulnerability Knowledge Graph for Risk Assessment
Software vulnerabilities, also known as flaws, bugs or weaknesses, are common in modern information systems, putting critical data of organizations and individuals at cyber risk. Due to the scarcity of resources, initial risk assessment is becoming a necessary step to prioritize vulnerabilities and make better decisions on remediation, mitigation, and patching. Datasets containing historical vulnerability information are crucial digital assets to enable AI-based risk assessments. However, existing datasets focus on collecting information on individual vulnerabilities while simply storing them in relational databases, disregarding their structural connections. This article constructs a compact vulnerability knowledge graph, VulKG, containing over 276 K nodes and 1 M relationships to represent the connections between vulnerabilities, exploits, affected products, vendors, referred domain names, and more. We provide a detailed analysis of VulKG modeling and construction, demonstrating VulKG-based query and reasoning, and providing a use case of applying VulKG to a vulnerability risk assessment task, i.e., co-exploitation behavior discovery. Experimental results demonstrate the value of graph connections in vulnerability risk assessment tasks. VulKG offers exciting opportunities for more novel and significant research in areas related to vulnerability risk assessment. The data and codes of this article are available at https://github.com/happyResearcher/VulKG.git .
- Open Access
- 24 May 2024
- Published by Springer Nature in World Wide Web
- Vol. 27 (4) , 1-24
A heterogeneous graph-based semi-supervised learning framework for access control decision-making
For modern information systems, robust access control mechanisms are vital in safeguarding data integrity and ensuring the entire system’s security. This paper proposes a novel semi-supervised learning framework that leverages heterogeneous graph neural network-based embedding to encapsulate both the intricate relationships within the organizational structure and interactions between users and resources. Unlike existing methods focusing solely on individual user and resource attributes, our approach embeds organizational and operational interrelationships into the hidden layer node embeddings. These embeddings are learned from a self-supervised link prediction task based on a constructed access control heterogeneous graph via a heterogeneous graph neural network. Subsequently, the learned node embeddings, along with the original node features, serve as inputs for a supervised access control decision-making task, facilitating the construction of a machine-learning access control model. Experimental results on the open-sourced Amazon access control dataset demonstrate that our proposed framework outperforms models using original or manually extracted graph-based features from previous works. The prepossessed data and codes are available on GitHub,facilitating reproducibility and further research endeavors.
- 24 May 2024
- Published by Springer Nature in World Wide Web
- Vol. 27 (4) , 1-24
Open AccessA heterogeneous graph-based semi-supervised learning framework for access control decision-making
For modern information systems, robust access control mechanisms are vital in safeguarding data integrity and ensuring the entire system’s security. This paper proposes a novel semi-supervised learning framework that leverages heterogeneous graph neural network-based embedding to encapsulate both the intricate relationships within the organizational structure and interactions between users and resources. Unlike existing methods focusing solely on individual user and resource attributes, our approach embeds organizational and operational interrelationships into the hidden layer node embeddings. These embeddings are learned from a self-supervised link prediction task based on a constructed access control heterogeneous graph via a heterogeneous graph neural network. Subsequently, the learned node embeddings, along with the original node features, serve as inputs for a supervised access control decision-making task, facilitating the construction of a machine-learning access control model. Experimental results on the open-sourced Amazon access control dataset demonstrate that our proposed framework outperforms models using original or manually extracted graph-based features from previous works. The prepossessed data and codes are available on GitHub,facilitating reproducibility and further research endeavors.
- 24 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 50 (6) , 1620-1638
Neural Library Recommendation by Embedding Project-Library Knowledge Graph
The prosperity of software applications brings fierce market competition to developers. Employing third-party libraries (TPLs) to add new features to projects under development and to reduce the time to market has become a popular way in the community. However, given the tremendous TPLs ready for use, it is challenging for developers to effectively and efficiently identify the most suitable TPLs. To tackle this obstacle, we propose an innovative approach named PyRec to recommend potentially useful TPLs to developers for their projects. Taking Python project development as a use case, PyRec embeds Python projects, TPLs, contextual information, and relations between those entities into a knowledge graph. Then, it employs a graph neural network to capture useful information from the graph to make TPL recommendations. Different from existing approaches, PyRec can make full use of not only project-library interaction information but also contextual information to make more accurate TPL recommendations. Comprehensive evaluations are conducted based on 12,421 Python projects involving 963 TPLs, 9,675 extra entities, 121,474 library usage records, and 73,277 contextual records. Compared with five representative approaches, PyRec improves the recommendation performance significantly in all cases.
- 24 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Software Engineering
- Vol. 50 (6) , 1620-1638
Neural Library Recommendation by Embedding Project-Library Knowledge Graph
The prosperity of software applications brings fierce market competition to developers. Employing third-party libraries (TPLs) to add new features to projects under development and to reduce the time to market has become a popular way in the community. However, given the tremendous TPLs ready for use, it is challenging for developers to effectively and efficiently identify the most suitable TPLs. To tackle this obstacle, we propose an innovative approach named PyRec to recommend potentially useful TPLs to developers for their projects. Taking Python project development as a use case, PyRec embeds Python projects, TPLs, contextual information, and relations between those entities into a knowledge graph. Then, it employs a graph neural network to capture useful information from the graph to make TPL recommendations. Different from existing approaches, PyRec can make full use of not only project-library interaction information but also contextual information to make more accurate TPL recommendations. Comprehensive evaluations are conducted based on 12,421 Python projects involving 963 TPLs, 9,675 extra entities, 121,474 library usage records, and 73,277 contextual records. Compared with five representative approaches, PyRec improves the recommendation performance significantly in all cases.