Xiaoyou Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiaoyou Wang has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Yong Xia
Department of Civil and Environmental Engineering, The Hong Kong Polytechnic University, Hong Kong, China
8 shared publications - Keyu Lai
The Hong Kong Polytechnic University
4 shared publications Wanglin Wu
The Hong Kong Polytechnic University
4 shared publications- Chong Li
Guangdong Provincial Key Laboratory of New Drug Screening, School of Pharmaceutical Sciences, Southern Medical University, Guangzhou, China
2 shared publications - Hong Guan
Griffith University
2 shared publications - Ling Yang
School of Electrical and Computer Engineering, University of Sydney, Street Address, Sydney, NSW 2006, Australia
2 shared publications
Latest Publications
- 17 August 2026
- Published by SAGE Publications in Advances in Structural Engineering
Multi-type data anomaly detection for structural health monitoring using interpretable machine learning methodology
Structural health monitoring (SHM) systems utilize multi-type monitoring data, particularly data collected under extreme events, to assess safety and serviceability during structures’ lifetime. However, sensor faults can compromise the reliability of structural analysis. This study proposes a novel interpretable data anomaly detection framework to identify both extreme events and sensor faults across various data types in SHM systems. Sensitive parameters and features are first defined based on the similarities and differences between normal pattern, data under extreme events, and sensor faults. Two machine learning methods, Kernel density estimation and support vector data description, are then used to help determine anomaly detection thresholds for these parameters and features. Based on the thresholds, sensor faults and extreme events in acceleration data can be simultaneously detected. Subsequently, the results of extreme event detection in acceleration data can assist in separating extreme events from sensor faults in wind speed and strain data. Two datasets from the SHM systems of a footbridge and Tsing Ma Bridge are used to validate the proposed method. Results demonstrate that the proposed anomaly detection framework can identify anomalies across multiple types of sensors in SHM systems with high efficiency and accuracy.
- 17 August 2026
- Published by SAGE Publications in Advances in Structural Engineering
Multi-type data anomaly detection for structural health monitoring using interpretable machine learning methodology
Structural health monitoring (SHM) systems utilize multi-type monitoring data, particularly data collected under extreme events, to assess safety and serviceability during structures’ lifetime. However, sensor faults can compromise the reliability of structural analysis. This study proposes a novel interpretable data anomaly detection framework to identify both extreme events and sensor faults across various data types in SHM systems. Sensitive parameters and features are first defined based on the similarities and differences between normal pattern, data under extreme events, and sensor faults. Two machine learning methods, Kernel density estimation and support vector data description, are then used to help determine anomaly detection thresholds for these parameters and features. Based on the thresholds, sensor faults and extreme events in acceleration data can be simultaneously detected. Subsequently, the results of extreme event detection in acceleration data can assist in separating extreme events from sensor faults in wind speed and strain data. Two datasets from the SHM systems of a footbridge and Tsing Ma Bridge are used to validate the proposed method. Results demonstrate that the proposed anomaly detection framework can identify anomalies across multiple types of sensors in SHM systems with high efficiency and accuracy.
- Open Access
- 26 May 2026
- Published by SAGE Publications in Structural Health Monitoring
Domain-adaptive nonlinear probabilistic latent variable model for vibration-based structural damage detection under climate change
A major challenge in vibration-based structural damage detection is differentiating actual damage from environmental and operational variations. Most existing studies are limited to short-term scenarios and do not consider long-term variations. With climate change driving more frequent and intense extreme weather events, long-term structural monitoring data exhibit covariate shift, for example, annual mean temperature increases over time. Such shifts pose fundamental challenges for machine learning models trained on historical datasets, as traditional algorithms often fail to extrapolate to these out-of-distribution environmental domains. This study develops a domain-adaptive nonlinear probabilistic latent variable model to advance long-term damage detection under climate change. First, Bayesian inference and kernel techniques are integrated to capture underlying nonlinear environmental effects without explicit environmental data. Second, domain adaptation is incorporated to enhance model adaptability to covariate shift scenarios due to climate change. The developed method is applied to a laboratory-tested slab and the practical Z24 bridge. Structural vibration properties are estimated under changing temperature and humidity conditions with consideration of four climate emission scenarios. The results demonstrate that the proposed method can distinguish damage-induced variations from climate-related environmental effects. It outperforms traditional methods that may result in false-positive and false-negative damage detections due to climate change and environmental nonlinear impacts.
- 26 May 2026
- Published by SAGE Publications in Structural Health Monitoring
Open AccessDomain-adaptive nonlinear probabilistic latent variable model for vibration-based structural damage detection under climate change
A major challenge in vibration-based structural damage detection is differentiating actual damage from environmental and operational variations. Most existing studies are limited to short-term scenarios and do not consider long-term variations. With climate change driving more frequent and intense extreme weather events, long-term structural monitoring data exhibit covariate shift, for example, annual mean temperature increases over time. Such shifts pose fundamental challenges for machine learning models trained on historical datasets, as traditional algorithms often fail to extrapolate to these out-of-distribution environmental domains. This study develops a domain-adaptive nonlinear probabilistic latent variable model to advance long-term damage detection under climate change. First, Bayesian inference and kernel techniques are integrated to capture underlying nonlinear environmental effects without explicit environmental data. Second, domain adaptation is incorporated to enhance model adaptability to covariate shift scenarios due to climate change. The developed method is applied to a laboratory-tested slab and the practical Z24 bridge. Structural vibration properties are estimated under changing temperature and humidity conditions with consideration of four climate emission scenarios. The results demonstrate that the proposed method can distinguish damage-induced variations from climate-related environmental effects. It outperforms traditional methods that may result in false-positive and false-negative damage detections due to climate change and environmental nonlinear impacts.
- 15 July 2025
- Published by Elsevier in Engineering Structures
- Vol. 342
GNN-LSTM-based full-field temperature prediction of bridges using sparse sensor data and heat-transfer analysis
- 15 July 2025
- Published by Elsevier in Engineering Structures
- Vol. 342
GNN-LSTM-based full-field temperature prediction of bridges using sparse sensor data and heat-transfer analysis
- 2 May 2025
- Published by SAGE Publications in Structural Health Monitoring
- Vol. 25 (5) , 3128-3146
Anomaly detection of sensor faults and extreme events by anomaly locating strategies and convolutional autoencoders
Deep learning has demonstrated advantages in the detection and classification of sensor faults. However, challenges exist in the domain of extreme event detection, including the scarcity of training data due to the rarity of extreme events and the difficulty of distinguishing between sensor anomalies and extreme events. This study proposes a novel two-stage anomaly detection method that can separately detect extreme events and sensor faults from the normal pattern without using any data related to extreme events in the training step. In the first stage, the potential segments are located using three defined indexes from raw normal acceleration data and then represented as peak and root mean-square envelopes. Then, these envelopes are normalized and grouped by the three indexes to train three convolutional autoencoders. The preprocessing strategies minimize the difference of the normalized sequence shapes between the normal pattern and extreme response. Hence, well-trained convolutional autoencoders can detect sensor fault patterns with different sequence shapes from the normal pattern. In the second stage, several thresholds are defined to separate the patterns sensitive only to absolute values from the normal pattern, including extreme events and partial Minor scenarios. A multilabel classification is followed to identify specific sensor fault patterns. Datasets from two real structural health monitoring systems are utilized to validate the proposed method. Results show that extreme events and sensor faults can be detected efficiently and accurately. Three extreme events, Typhoon Saola, Typhoon Higos, and a pedestrian test, are successfully detected using the developed method.
- 2 May 2025
- Published by SAGE Publications in Structural Health Monitoring
- Vol. 25 (5) , 3128-3146
Anomaly detection of sensor faults and extreme events by anomaly locating strategies and convolutional autoencoders
Deep learning has demonstrated advantages in the detection and classification of sensor faults. However, challenges exist in the domain of extreme event detection, including the scarcity of training data due to the rarity of extreme events and the difficulty of distinguishing between sensor anomalies and extreme events. This study proposes a novel two-stage anomaly detection method that can separately detect extreme events and sensor faults from the normal pattern without using any data related to extreme events in the training step. In the first stage, the potential segments are located using three defined indexes from raw normal acceleration data and then represented as peak and root mean-square envelopes. Then, these envelopes are normalized and grouped by the three indexes to train three convolutional autoencoders. The preprocessing strategies minimize the difference of the normalized sequence shapes between the normal pattern and extreme response. Hence, well-trained convolutional autoencoders can detect sensor fault patterns with different sequence shapes from the normal pattern. In the second stage, several thresholds are defined to separate the patterns sensitive only to absolute values from the normal pattern, including extreme events and partial Minor scenarios. A multilabel classification is followed to identify specific sensor fault patterns. Datasets from two real structural health monitoring systems are utilized to validate the proposed method. Results show that extreme events and sensor faults can be detected efficiently and accurately. Three extreme events, Typhoon Saola, Typhoon Higos, and a pedestrian test, are successfully detected using the developed method.
- Top Cited PapersOpen Access
- 10 March 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-16
Berberine-inspired ionizable lipid for self-structure stabilization and brain targeting delivery of nucleic acid therapeutics
Lipid nanoparticles have shown success in targeting major organs such as the liver, spleen, and lungs, but crossing the blood-brain barrier (BBB) remains a major challenge. Effective brain-targeted delivery systems are essential for advancing gene therapy for neurological diseases but remain limited by low transport efficiency and poor nucleic acid stability. Here, we report a library of ionizable lipids based on the tetrahydroisoquinoline structure of protoberberine alkaloids, designed to improve BBB penetration via dopamine D3 receptor-mediated endocytosis. These nanoparticles offer three key advantages: enhanced brain uptake, improved nucleic acid stability through poly(A) self-assembly, and minimal immunogenicity with inherent neuroprotective properties. In murine models, they demonstrate therapeutic potential in Alzheimer’s disease, glioma, and cryptococcal meningitis. This berberine-inspired delivery system integrates precise receptor targeting with nucleic acid stabilization, offering a promising platform for brain-targeted therapeutics.
- 10 March 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1-16
Top Cited PapersOpen AccessBerberine-inspired ionizable lipid for self-structure stabilization and brain targeting delivery of nucleic acid therapeutics
Lipid nanoparticles have shown success in targeting major organs such as the liver, spleen, and lungs, but crossing the blood-brain barrier (BBB) remains a major challenge. Effective brain-targeted delivery systems are essential for advancing gene therapy for neurological diseases but remain limited by low transport efficiency and poor nucleic acid stability. Here, we report a library of ionizable lipids based on the tetrahydroisoquinoline structure of protoberberine alkaloids, designed to improve BBB penetration via dopamine D3 receptor-mediated endocytosis. These nanoparticles offer three key advantages: enhanced brain uptake, improved nucleic acid stability through poly(A) self-assembly, and minimal immunogenicity with inherent neuroprotective properties. In murine models, they demonstrate therapeutic potential in Alzheimer’s disease, glioma, and cryptococcal meningitis. This berberine-inspired delivery system integrates precise receptor targeting with nucleic acid stabilization, offering a promising platform for brain-targeted therapeutics.
- Open Access
- 11 May 2024
- Published by Springer Nature in Nature Communications
- Vol. 15 (1) , 1-17
Regulation of cerebral blood flow boosts precise brain targeting of vinpocetine-derived ionizable-lipidoid nanoparticles
Despite advances in active drug targeting for blood-brain barrier penetration, two key challenges persist: first, attachment of a targeting ligand to the drug or drug carrier does not enhance its brain biodistribution; and second, many brain diseases are intricately linked to microcirculation disorders that significantly impede drug accumulation within brain lesions even after they cross the barrier. Inspired by the neuroprotective properties of vinpocetine, which regulates cerebral blood flow, we propose a molecular library design centered on this class of cyclic tertiary amine compounds and develop a self-enhanced brain-targeted nucleic acid delivery system. Our findings reveal that: (i) vinpocetine-derived ionizable-lipidoid nanoparticles efficiently breach the blood-brain barrier; (ii) they have high gene-loading capacity, facilitating endosomal escape and intracellular transport; (iii) their administration is safe with minimal immunogenicity even with prolonged use; and (iv) they have potent pharmacologic brain-protective activity and may synergize with treatments for brain disorders as demonstrated in male APP/PS1 mice.
- 11 May 2024
- Published by Springer Nature in Nature Communications
- Vol. 15 (1) , 1-17
Open AccessRegulation of cerebral blood flow boosts precise brain targeting of vinpocetine-derived ionizable-lipidoid nanoparticles
Despite advances in active drug targeting for blood-brain barrier penetration, two key challenges persist: first, attachment of a targeting ligand to the drug or drug carrier does not enhance its brain biodistribution; and second, many brain diseases are intricately linked to microcirculation disorders that significantly impede drug accumulation within brain lesions even after they cross the barrier. Inspired by the neuroprotective properties of vinpocetine, which regulates cerebral blood flow, we propose a molecular library design centered on this class of cyclic tertiary amine compounds and develop a self-enhanced brain-targeted nucleic acid delivery system. Our findings reveal that: (i) vinpocetine-derived ionizable-lipidoid nanoparticles efficiently breach the blood-brain barrier; (ii) they have high gene-loading capacity, facilitating endosomal escape and intracellular transport; (iii) their administration is safe with minimal immunogenicity even with prolonged use; and (iv) they have potent pharmacologic brain-protective activity and may synergize with treatments for brain disorders as demonstrated in male APP/PS1 mice.
- 31 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (3) , 4763-4774
Wireless IoT Monitoring System in Hong Kong–Zhuhai–Macao Bridge and Edge Computing for Anomaly Detection
The emergence of the Internet of Things (IoT) has facilitated the development and usage of low-computational microcontrollers at the edge of the network, which process data in the proximity of data sources and thereby offload the pressure of data transmission. Recently, IoT is becoming a key technology for structural health monitoring (SHM) systems. This study designs a novel wireless IoT monitoring system for the Hong Kong–Zhuhai–Macao Bridge, the world longest sea-crossing bridge. The 5G technology and edge computing are integrated to improve the system performance in sensor serviceability, data transmission, time synchronization, and data quality control. The artificial intelligent (AI) algorithm is embedded into the NVIDIA Xavier NX edge computing boards to preliminarily detect data anomalies caused by sensor faults, before uploading the massive data to the cloud platform. As training AI models requires a large amount of labeled data and is always time consuming, a novel data anomaly detection method is developed by transferring the model trained from the other bridge to the target bridge. Given that prestoring source data in edge devices consumes expensive storage resources, the source-free domain adaptation is developed by integrating the robust self-training mechanism and self-knowledge distillation strategy. Thus, the model transfer is achieved cross bridges in the absence of source data. This study provides a valuable and practical reference for developing a wireless IoT SHM system for large-scale infrastructure and enabling edge computing for data anomaly detection with high efficiency and accuracy.
- 31 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (3) , 4763-4774
Wireless IoT Monitoring System in Hong Kong–Zhuhai–Macao Bridge and Edge Computing for Anomaly Detection
The emergence of the Internet of Things (IoT) has facilitated the development and usage of low-computational microcontrollers at the edge of the network, which process data in the proximity of data sources and thereby offload the pressure of data transmission. Recently, IoT is becoming a key technology for structural health monitoring (SHM) systems. This study designs a novel wireless IoT monitoring system for the Hong Kong–Zhuhai–Macao Bridge, the world longest sea-crossing bridge. The 5G technology and edge computing are integrated to improve the system performance in sensor serviceability, data transmission, time synchronization, and data quality control. The artificial intelligent (AI) algorithm is embedded into the NVIDIA Xavier NX edge computing boards to preliminarily detect data anomalies caused by sensor faults, before uploading the massive data to the cloud platform. As training AI models requires a large amount of labeled data and is always time consuming, a novel data anomaly detection method is developed by transferring the model trained from the other bridge to the target bridge. Given that prestoring source data in edge devices consumes expensive storage resources, the source-free domain adaptation is developed by integrating the robust self-training mechanism and self-knowledge distillation strategy. Thus, the model transfer is achieved cross bridges in the absence of source data. This study provides a valuable and practical reference for developing a wireless IoT SHM system for large-scale infrastructure and enabling edge computing for data anomaly detection with high efficiency and accuracy.
- 13 July 2022
- Published by Wiley in Structural Control and Health Monitoring
- Vol. 29 (10)
Anomaly detection of sensor faults and extreme events based on support vector data description
- 13 July 2022
- Published by Wiley in Structural Control and Health Monitoring
- Vol. 29 (10)
Anomaly detection of sensor faults and extreme events based on support vector data description