Qilin Li

Qilin Li

Senior Lecturer & ARC DECRA Fellow — AI for intelligent infrastructure and structural health monitoring

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

portfolio

publications

Semisupervised learning on graphs with an alternating diffusion process

Published in IEEE Transactions on Neural Networks and Learning Systems, 2020

Semisupervised learning on graphs using an alternating diffusion process.

Recommended citation: Li, Qilin, Senjian An, Wanquan Liu, and Ling Li. "Semisupervised learning on graphs with an alternating diffusion process." IEEE Transactions on Neural Networks and Learning Systems 32, no. 7 (2021): 2862-2874.
Paper

Prediction of BLEVE blast loading using CFD and artificial neural network

Published in Process Safety and Environmental Protection, 2021

CFD and artificial neural networks for predicting BLEVE blast loading.

Recommended citation: Li, Jun, Qilin Li, Hong Hao, and Ling Li. "Prediction of BLEVE blast loading using CFD and artificial neural network." Process Safety and Environmental Protection 149 (2021): 711-723.
Paper

Multi-View Diffusion Process for Spectral Clustering and Image Retrieval

Published in IEEE Transactions on Image Processing, 2023

This paper is about image retrieval and clustering using a novel multi-view diffusion process.

Recommended citation: Li, Qilin, Senjian An, Ling Li, Wanquan Liu, and Yanda Shao. "Multi-View Diffusion Process for Spectral Clustering and Image Retrieval." IEEE Transactions on Image Processing 32 (2023): 4610-4620.
Paper | Code

A comparative study on the most effective machine learning model for blast loading prediction: From GBDT to Transformer

Published in Engineering Structures, 2023

This paper is a comparative study of commonly used machine learning approach for blast loading prediction.

Recommended citation: Li, Qilin, Yang Wang, Yanda Shao, Ling Li, and Hong Hao. "A comparative study on the most effective machine learning model for blast loading prediction: From GBDT to Transformer." Engineering Structures 276 (2023): 115310.
Paper

A novel transformer-based semantic segmentation framework for structural condition assessment

Published in Structural Health Monitoring, 2024

This paper is about structural component and structural damage identification via vision-based semantic segmentation with SOTA Transformer networks.

Recommended citation: Wang, Ruhua, Yanda Shao, Qilin Li, Ling Li, Jun Li, and Hong Hao. "A novel transformer-based semantic segmentation framework for structural condition assessment." Structural Health Monitoring 23, no. 2 (2024): 1170-1183.
Paper

Machine learning prediction of BLEVE loading with graph neural networks

Published in Reliability Engineering & System Safety, 2024

This paper is about data-driven simulation of BLEVE blast wave propagation

Recommended citation: Li, Qilin, Yang Wang, Wensu Chen, Ling Li, and Hong Hao. "Machine learning prediction of BLEVE loading with graph neural networks." Reliability Engineering & System Safety 241 (2024): 109639.
Paper | Code

Prediction and interpretability of accidental explosion loads from hydrogen-air mixtures using CFD and artificial neural network method

Published in International Journal of Hydrogen Energy, 2024

CFD and interpretable neural networks for predicting accidental hydrogen-air explosion loads.

Recommended citation: Hu, Qingchun, Xihong Zhang, Qilin Li, Hong Hao, Chris Coffey, and Fiona Mitchell-Corbett. "Prediction and interpretability of accidental explosion loads from hydrogen-air mixtures using CFD and artificial neural network method." International Journal of Hydrogen Energy 66 (2024): 135-147.
Paper

Structural damage identification by using physics-guided residual neural networks

Published in Engineering Structures, 2024

Physics-guided residual neural networks for structural damage identification.

Recommended citation: Wang, Ruhua, Jun Li, Ling Li, Senjian An, Bradley Ezard, Qilin Li, and Hong Hao. "Structural damage identification by using physics-guided residual neural networks." Engineering Structures 318 (2024): 118703.
Paper

EdgeConvFormer: An Unsupervised Anomaly Detection Method for Multivariate Time Series

Published in International Conference on Pattern Recognition (ICPR), 2024

An unsupervised anomaly detection method (EdgeConvFormer) for multivariate time series.

Recommended citation: Liu, Jie, Qilin Li, Senjian An, Bradley Ezard, and Ling Li. "EdgeConvFormer: An Unsupervised Anomaly Detection Method for Multivariate Time Series." In International Conference on Pattern Recognition, pp. 367-382. Springer, 2024.
Paper

A probability-based risk assessment of secondary fragments ejected from the reinforced concrete wall under close-in explosions

Published in Structural Safety, 2025

Probability-based risk assessment of secondary fragments from RC walls under close-in explosions.

Recommended citation: Wang, Zitong, Qilin Li, Wensu Chen, Hong Hao, and Ling Li. "A probability-based risk assessment of secondary fragments ejected from the reinforced concrete wall under close-in explosions." Structural Safety 114 (2025): 102565.
Paper

Diffusion process with structural changes for subspace clustering

Published in Pattern Recognition, 2025

A diffusion process incorporating structural changes for improved subspace clustering.

Recommended citation: Zhu, Yanjiao, Qilin Li, Wanquan Liu, and Chuancun Yin. "Diffusion process with structural changes for subspace clustering." Pattern Recognition 158 (2025): 111066.
Paper

Dynamic graph-based approach for prediction of spatiotemporal response of RC structure to impact loads

Published in Computers & Structures, 2025

This paper presents a dynamic graph-based approach for predicting the spatiotemporal response of reinforced concrete structures subjected to impact loads.

Recommended citation: Li, Qilin, Zhijie Huang, Yanda Shao, Ling Li, Wensu Chen, and Hong Hao. "Dynamic graph-based approach for prediction of spatiotemporal response of RC structure to impact loads." Computers & Structures 316 (2025): 107861.
Paper

Advancing crack detection with generative AI for structural health monitoring

Published in Structural Health Monitoring, 2025

This paper integrates a text-to-image generative model with large language models to synthesize realistic crack images, improving deep-learning-based crack detection for structural health monitoring.

Recommended citation: Shao, Yanda, Ling Li, Jun Li, Xiaofang Yao, Qilin Li, and Hong Hao. "Advancing crack detection with generative AI for structural health monitoring." Structural Health Monitoring (2025).
Paper

Unsupervised structural damage detection and severity assessment via U-GraphFormer

Published in Structural Health Monitoring, 2025

This paper presents U-GraphFormer, an unsupervised approach for detecting structural damage and assessing its severity.

Recommended citation: Liu, Jie, Qilin Li, Ling Li, and Senjian An. "Unsupervised structural damage detection and severity assessment via U-GraphFormer." Structural Health Monitoring (2025).
Paper

Data-Driven BLEVE Overpressure Prediction Using Explainable Machine Learning

Published in Engineering Applications of Neural Networks (EANN 2025), 2025

This paper develops explainable machine learning models for data-driven prediction of blast overpressure from boiling liquid expanding vapour explosions (BLEVEs).

Recommended citation: Shi, Zifan, Qilin Li, Ling Li, Yanda Shao, and Hong Hao. "Data-Driven BLEVE Overpressure Prediction Using Explainable Machine Learning." In Engineering Applications of Neural Networks, pp. 68-80. Cham: Springer Nature Switzerland, 2025.
Paper

Discovering interpretable blast loading equations from black-box machine learning models

Published in Advanced Engineering Informatics, 2026

This paper extracts interpretable equations for blast loading prediction from black-box machine learning models.

Recommended citation: Shi, Zifan, Qilin Li, Yanda Shao, Ling Li, and Hong Hao. "Discovering interpretable blast loading equations from black-box machine learning models." Advanced Engineering Informatics 71 (2026): 104244.
Paper

talks

teaching

Fundamental Concepts of Cryptography

Undergraduate course, Curtin University, Department of Computing, 2020

An introduction to basic concept of cryptography with an emphasis on coding theory, classical cryptosystems and public key cryptography. Principles of information theoretic security. Computational hardness and number theory (Euclid’s algorithm, Euler and Fermat’s theorems). Public and private-key encryption, message authentication and digital signatures. ISEC2000 – Fundamental Concepts of Cryptography in the Curtin handbook.

Foundations of Computer Science

Undergraduate course, Curtin University, Department of Computing, 2020

This unit introduces the mathematical theory that underlies the computing profession. It introduces proof and logic concepts central to computer science and programming methodology, including an introduction to set theory and mathematical relations, graph theory. Computational and mathematical recursion is also addressed, along with the paired concept of induction proofs. Finally, the analysis of software using discrete statistics is also addressed, including univariate statistics and confidence intervals. COMP1006 – Foundations of Computer Science in the Curtin handbook.

Explainable Approaches to Machine Learning

Postgraduate course, Curtin University, Department of Computing, 2022

The unit will focus on special machine learning approaches, named explainable artificial intelligence or XAI, that generate solutions that can be trusted and are easy to understand and particularly well suited to fields such as medicine, finance, security, legal, military, and where human-machine interaction is needed. It will provide students with XAI fundamentals such as interpretability, explainability, and visualisation as well as legal and ethical issues surrounding XAI. The unit will also cover different classes of techniques from model-agnostic, example-based, to neural network interpretation. Finally, common XAI applications and current trends in XAI will also be discussed. COMP6013 – Explainable Approaches to Machine Learning in the Curtin handbook.

Machine Learning

Undergraduate course, Curtin University, Department of Computing, 2024

This unit introduces the foundational concepts, algorithms, and applications of Machine Learning (ML). Students will gain hands-on experience with diverse data types including tabular, image, text, and time series, and will learn to develop ML models such as linear models, SVM, decision trees, and neural networks. Covering a broad spectrum of topics within supervised and unsupervised learning, self-supervised learning, and deep learning, the unit also focuses on practical applications in computer vision and natural language processing, equipping students with the skills to implement ML solutions and solve real-world problems effectively. COMP3010 – Machine Learning in the Curtin handbook.

Search and Logic Approaches in Machine Learning

Postgraduate course, Curtin University, Discipline of AI & Data Science, 2026

This unit covers the different aspects of search and logic in machine learning and artificial intelligence. It familiarises learners with the modelling of intelligent agents and the related artificial intelligence problems and approaches. Methods for programming agent behaviour as well as the basics of planning are introduced, along with the role of logic in machine learning for certain types of agents. COMP6009 – Search and Logic Approaches in Machine Learning in the Curtin handbook.