Full list of publications since 1990 can be found from papers

Short Bio:

Weiru Liu holds Chair of Artificial Intelligence (AI) at the University of Bristol. She held a number of senior management positions at the Faculty of Engineering between 2017 to 2023 (Associate Dean for TQEC (Research and Enterprise): March 2020 to August 2023; Engineering Faculty Research Director: August 2017 to May 2020 and Faculty International Director: May 2022 to August 2023).  Prior to joining the University of Bristol in 2017, she held the Chair of AI at Queen’s University Belfast (QUB), and was the Director of Research of the Knowledge and Data Engineering Research Cluster for 6 years. She has a sustained track record of securing peer-reviewed, highly competitive funding from a diverse range of funding bodies (over £58m as Principal Investigator or Co-Investigator).

She was a member of UK EPSRC ICT Strategic Advisory Team (ICT SAT);  was a member of UK Higher Education Research Excellence Framework (REF2021) Institutional Environment Pilot Panel;  and was Turing Fellow between October 2021 to September 2023. Currently, she is Co-Director for the EPSRC Centre for Doctoral Training in Future Autonomous and Robotic Systems: Towards Ubiquity (FARSCOPE-TU),  2019-2028; and holds the University Research Fellowship 2023/2024. 

Internationally, she was a member of Academy of Finland AI and Data Science Review Panel (2020-2021) and was a member of an international committee for Independent Research Fund Denmark (DFF) - Digital Technologies (2019).

Research Interests:

Her research interests include: explainable AI, data-driven intelligent autonomous systems; smart cyber-physical systems; large-scale sensor network event modelling, reasoning and correlation in uncertain environments;  information fusion under uncertainty, with a wide range of applications such as security, healthcare, robotics. She has published over 200 peer-reviewed papers,  chaired several international conferences, and was an invited keynote at a few international conferences.

1. Explainable Artificial Intelligence (XAI)

Our work in this space focuses on developing systems or tools to provide intuitive and interactive explanations to non-expert users.

• Developed an XAI system for an AI-enabled smart homes as part of the EPSRC funded project CHAI. The system was trialed at real-homes  in early 2023. 
• Developed an interactive system explaining global, local and counterfactual explanations
• Develop XAI approaches for graph neural networks, reinforcement learning and time series ML models. 
• Explore interplay between XAI and security.

2. Intelligent Autonomous Systems

Our theoretical research includes uncertain information modelling and fusion; event correlation and reasoning; belief modelling and revision; online planning under uncertainty; multi-criteria decision making under uncertainty. Specifically

• Develop multi-agent based, data-driven event reasoning frameworks for correlating dispersed events detected from heterogeneous sources in a distributed complex environment for achieving situation awareness. Applications include intelligent surveillance in cyber-physical systems, smart homes, and intelligent energy and transport management in smart cities.
• Develop intelligent autonomous systems using multi-agent techniques for complex control problems and for designing collaborative (software) agents, or mixed teams of multi-robots and human for working together in complex environment. Applications include smart cities, services, complex industrial control problems, and games for entertainment or education. 
• Handling ambiguous evidence in game theory for security and multi-criteria decision making under uncertainty in complex systems.
• Model, reason, and merge uncertain information from heterogeneous sources in any intelligent systems (e.g., large sensor networks). We particularly focus on the Dempster-Shafer theory of Evidence (belief function theory), possibility theory and possibilistic logic, and probability theory.

3. Data mining, large-scale data analytics 

We develop Machine Learning and Data Mining algorithms to discover knowledge. Recent work has been focusing on graph-based approaches for both historic and streaming data analytics, with numerous applications. 

• Develop anomaly detection algorithms for detecting abnormal behaviours (anomalies) in physical access control environment under the context of security.
• Develop graph-based algorithms for identifying exercise patterns and influences among participants in events.
• Discover social connection patterns from social networks with streaming data. 
• Develop various data analytical approaches, in collaboration with Belfast City Council, for analyzing data on CityBikes, Pollution, Waste disposal/treatment, Recycling; Anti-Social Behaviours, etc.  
• Develop graph neural network based approaches for social network analysis. 

4. Theoretical aspects of Merging and Revising Uncertain and Inconsistent Knowledgebases

Our research includes developing fusion methods (merging operators) and algorithms for merging multiple knowledgebases (maybe with constrains), especially, propositional and possibilistic knowledgebases, stratified knowledgebases, imprecise probabilistic logic based knowledge bases, and heterogeneous uncertain information. We also develop revision strategies/operators for revising such knowledge/belief bases.

Recent research has progressed to providing a toolkit for identifying minimal inconsistent subsets and calculating inconsistency values of knowledgbases or individual formulae in large-scale knowledge bases. This research has also been extended to developing approaches for detecting inconsistencies in probabilistic knowledge bases (learned by other machine learning systems) and repairing such inconsistencies.