I am currently a PhD candidate at the SKL-IOTSC, working under the guidance of Prof. Dingqi Yang. I am also affiliated with the Department of Computer and Information Science at the University of Macau.
My research lies at the intersection of artificial intelligence (AI), knowledge representation, transportation, and healthcare. I focus on developing algorithms and techniques that enable knowledge-driven transportation systems and smart healthcare solutions. My interests span deep learning, reinforcement learning, and generative AI, with applications in prediction, recognition, decision-making, planning, and human-machine interaction. To date, I have published over 30 papers in top-tier AI, IOT, transportation, and healthcare journals and conferences.
🔥 News
- 2025.08: 🎉🎉 One paper has been accepted by IEEE IOTJ.
- 2025.06: 🎉🎉 One paper has been accepted by IEEE T-KDE.
- 2025.05: 🎉🎉 One paper has been accepted by ACL 2025.
- 2025.04: 🎉🎉 One paper has been accepted by BMC Public Health.
- 2025.02: 🎉🎉 One paper has been accepted by IEEE T-ITS.
- 2024.12: 🎉🎉 One paper has been accepted by TR-C.
- 2024.12: 🎉🎉 One paper has been accepted by IEEE T-ITS.
- 2024.12: 🎉🎉 Two papers have been accepted by AAAI 2025.
- 2024.10: 🎉🎉 One paper has been accepted by EAAI.
- 2024.09: 🎉🎉 One paper has been accepted by IEEE T-ITS.
- 2024.09: 🎉🎉 One paper has been accepted by Information Fusion.
- 2024.05: 🎉🎉 One paper has been accepted by ACL 2024.
- 2024.05: 🎉🎉 One paper has been accepted by IEEE T-CSVT.
- 2023.09: 🎉🎉 One paper has been accepted by IEEE T-KDE.
- 2023.07: 🎉🎉 One paper has been accepted by ACMMM 2023.
📝 Publications
Highlights
HyperFM: Fact-Centric Multimodal Fusion for Link Prediction over Hyper-Relational Knowledge Graphs
Yuhuan Lu, Weijian Yu, Xin Jing, Dingqi Yang
ACL, 2025
- We propose HyperFM, a hyper-relational fact-centric multimodal fusion technique for link prediction tasks over multimodal hyper-relational KGs.
Schema-Aware Hyper-Relational Knowledge Graph Embeddings for Link Prediction
Yuhuan Lu, Dingqi Yang, Pengyang Wang, Paolo Rosso, Philippe Cudre-Mauroux
IEEE Transactions on Knowledge and Data Engineering, 2024
- We propose sHINGE, a schema-aware hyper-relational KG embedding model, which learns from hyper-relational facts directly and their corresponding hyper-relational schema in a KG.
Vehicle Trajectory Prediction in Connected Environments via Heterogeneous Context-Aware Graph Convolutional Networks
Yuhuan Lu, Wei Wang, Xiping Hu, Pengpeng Xu, Shengwei Zhou, Ming Cai
IEEE Transactions on Intelligent Transportation Systems, 2023
- We propose a novel Heterogeneous Context-Aware Graph Convolutional Networks following the Encoder-Decoder architecture, which simultaneously extracts the hidden contexts from individual historical trajectories, varying driving scenes, and inter-vehicle interactional behaviors.
HELIOS: Hyper-Relational Schema Modeling from Knowledge Graphs
Yuhuan Lu, Bangchao Deng, Weijian Yu, Dingqi Yang
ACMMM, 2023
- We propose HELIOS, a hyper-relational schema model designed to subtly learn from hyper-relational schema tuples by capturing not only the correlation between multiple types of a single entity, but also the correlation between types of different entities and relations in a schema tuple.
HyperCL: A Contrastive Learning Framework for Hyper-Relational Knowledge Graph Embedding With Hierarchical Ontology
Yuhuan Lu, Weijian Yu, Xin Jing, Dingqi Yang
ACL, 2024
- We propose a universal contrastive learning framework for hyper-relational KG embeddings (HyperCL), which is flexible to integrate different hyper-relational KG embedding methods and effectively boost their link prediction performance.
Dual-View Interaction-Aware Lane Change Prediction for Autonomous Driving
Yuhuan Lu, Zhen Zhang, Rufan Bai, Han Liu, Wei Wang
AAAI, 2025
- We propose to incorporate the concept of perceived safety into future interaction modeling and design a dual-view interaction-aware lane change prediction model.
Hyper-Relational Interaction Modeling in Multi-Modal Trajectory Prediction for Intelligent Connected Vehicles in Smart Cities
Yuhuan Lu, Wei Wang, Rufan Bai, Shengwei Zhou, Lalit Garg, Ali Kashif Bashir, Weiwei Jiang, Xiping Hu
Information Fusion, 2025
- We propose to model the hyper-relational interaction, which incorporates map elements into the inter-agent interaction. To tackle the hyper-relational interaction, we propose a novel Hyper-relational Multi-modal Trajectory Prediction (HyperMTP) approach.
Knowledge-Driven Lane Change Prediction for Secure and Reliable Internet of Vehicles
Yuhuan Lu, Zhen Zhang, Wei Wang, Yiting Zhu, Tiantian Chen, Yasser D Al-Otaibi, Ali Kashif Bashir, Xiping Hu
IEEE Transactions on Intelligent Transportation Systems, 2025
- We propose to employ the knowledge-driven paradigm and design KLEP, a knowledge-driven lane change prediction framework. KLEP incorporates driving knowledge into lane change modeling, presenting the top-down hierarchical cognitive process of drivers when performing lane change maneuvers.
Lane Change Prediction for Autonomous Driving With Transferred Trajectory Interaction
Yuhuan Lu, Pengpeng Xu, Xinyu Jiang, Ali Kashif Bashir, Thippa Reddy Gadekallu, Wei Wang, Xiping Hu
IEEE Transactions on Intelligent Transportation Systems, 2025
- We present a novel lane change prediction framework using Transformer-based transfer learning. Our design aims to leverage inter-vehicle interactions learned from trajectory data to improve lane-change prediction accuracy.
Automatic Incident Detection Using Edge-Cloud Collaboration Based Deep Learning Scheme for Intelligent Transportation Systems
Yuhuan Lu, Qinghai Lin, Haiyang Chi, Jin-Yong Chen
Applied Intelligence, 2023
- We propose a novel automatic incident detection paradigm using an edge-cloud collaboration mechanism. In particular, a Spatio-Temporal Variational Digraph Auto-Encoder model is developed to distinguish the incidents in dynamic traffic flows.
Dual Attentive Graph Neural Network for Metro Passenger Flow Prediction
Yuhuan Lu, Hongliang Ding, Shiqian Ji, NN Sze, Zhaocheng He
Neural Computing and Applications, 2021
- We develop a novel dual attentive graph neural network that can effectively predict the distribution of metro traffic flow considering the spatial and temporal influences.
Other Publications
-
Associations of Occupation Categories With Cardiovascular Diseases and All-Cause Mortality: An Analysis of NHANES 2005-2014, Haiyang Chi, Jia Zhou, Chao Li, Yuhuan Lu, Can Xie, Baoyu He, Wei Ke, BMC Public Health, 2025
-
CasFT: Future Trend Modeling for Information Popularity Prediction With Dynamic Cues-Driven Diffusion Models, Xin Jing, Yichen Jing, Yuhuan Lu, Bangchao Deng, Xueqin Chen, Dingqi Yang, AAAI (Oral), 2025
-
Multi-Node Joint Optimization for Fine-Grained Vehicle Trajectory Reconstruction Using Vehicle Appearance and Identity Data, Mingkai Qiu, Yuhuan Lu, Xiying Li, Transportation Research Part C: Emerging Technologies, 2025
-
Spatio-Temporal Attention Based Collaborative Local–Global Learning for Traffic Flow Prediction, Haiyang Chi, Yuhuan Lu, Can Xie, Wei Ke, Bidong Chen, Engineering Applications of Artificial Intelligence, 2025
-
Inter-Intra Cluster Reorganization for Unsupervised Vehicle Re-Identification, Mingkai Qiu, Yuhuan Lu, Xiying Li, Qiang Lu, IEEE Transactions on Intelligent Transportation Systems, 2024
-
Camera-Aware Differentiated Clustering With Focal Contrastive Learning for Unsupervised Vehicle Re-Identification, Mingkai Qiu, Yuhuan Lu, Xiying Li, Qiang Lu, IEEE Transactions on Circuits and Systems for Video Technology, 2024
-
A Crash Feature-Based Allocation Method for Boundary Crash Problem in Spatial Analysis of Bicycle Crashes, Hongliang Ding, Yuhuan Lu, NN Sze, Constantinos Antoniou, Yanyong Guo, Analytic Methods in Accident Research, 2023
-
City-Scale Holographic Traffic Flow Data Based on Vehicular Trajectory Resampling, Yimin Wang, Yixian Chen, Guilong Li, Yuhuan Lu, Zhaocheng He, Zhi Yu, Weiwei Sun, Scientific Data, 2023
-
Effect of Dockless Bike-Sharing Scheme on the Demand for London Cycle Hire at the Disaggregate Level Using A Deep Learning Approach, Hongliang Ding, Yuhuan Lu, NN Sze, Haojie Li, Transportation Research Part A: Policy and Practice, 2022
-
A Deep Generative Approach for Crash Frequency Model With Heterogeneous Imbalanced Data, Hongliang Ding, Yuhuan Lu, NN Sze, Tiantian Chen, Yanyong Guo, Qinghai Lin, Analytic Methods in Accident Research, 2022
-
A Resampling Approach to Disaggregate Analysis of Bus-Involved Crashes Using Panel Data With Excessive Zeros, Tiantian Chen, Yuhuan Lu, Xiaowen Fu, NN Sze, Hongliang Ding, Accident Analysis and Prevention, 2022
-
Missing Traffic Data Imputation and Pattern Discovery With A Bayesian Augmented Tensor Factorization Model, Xinyu Chen, Zhaocheng He, Yixian Chen, Yuhuan Lu, Jiawei Wang, Transportation Research Part C: Emerging Technologies, 2019
🎖 Honors and Awards
- 2025.04 Presentation Award of Postgraduate Forum, University of Macau
- 2025.01 First Prize of Annual Academic Rising Star Award, Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing
- 2024.12 Ultimate Report Award, Southeast University
- 2021.08 UM PhD Assistantship, University of Macau
- 2017.12 Crowdsourcing Program Excellence Award, Key Laboratory of Road and Traffic Engineering of the Ministry of Education
- 2017.06 Outstanding Graduate, Sun Yat-Sen University
💰 Grants
- Research on Driver Behavior Prediction Theory and Method for Autonomous Logistics Transportation. Yunnan Provincial Key Laboratory Open Project, duration: 2025-2026, PI
- Research on Key Technologies of Real-Time Perception and Intelligent Decision Making for Resilient Cities. FDCT-NSFC Joint Funding Project, duration: 2022-2024, Key Participant
- Basic Theory and Key Technologies of Intelligent Transportation Based on Big Data. Key Project of National Natural Science Foundation of China, duration: 2019-2022, Key Participant
📖 Education
- 2021 - 2025, Doctor of Philosophy, Computer Science, University of Macau, Macao
- 2017 - 2020, Master of Science, Transportation Engineering, Sun Yat-Sen University, Guangzhou, China
- 2013 - 2017, Bachelor of Science, Traffic Engineering, Sun Yat-Sen University, Guangzhou, China
📚 Academic Services
Program Committee
- Main Track, ACMMM
- Artificial Intelligence for Social Impact Track, AAAI
- Web4Good Special Track, WWW
- AI and Social Good Special Track, IJCAI
Journal Reviewer
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- IEEE Transactions on Knowledge and Data Engineering
- IEEE Transactions on Intelligent Transportation Systems
- IEEE Transactions on Vehicular Technology
- IEEE Internet of Things Journal
- IEEE Transactions on Consumer Electronics
- Machine Intelligence Research
- Transportation Research Part C: Emerging Technologies
- Accident Analysis and Prevention
- IET Intelligent Transport Systems
- Transportation Research Record