Research

The lab focuses on AI systems for continuous learning, interactive decision making, and scientific knowledge discovery in streaming sensor based environments.  Our focus is on discovering and understanding complex physical and social processes by monitoring multiple heterogeneous sensor data streams. Examples of such systems include modeling and predicting the weather over some region, analysing patterns of household energy consumption behaviour in a country, monitoring and controlling indoor air quality, learning models for individualised and public health care, or understanding the dynamics of a stock market. Typically, sensors embedded in these systems continuously generate observational data, which when combined with expert domain knowledge allows us to gain some insight into the dynamics, i.e. the key processes and patterns that drive the system.

There are three project topics.

Topic 1 – Spatial-Temporal Graph Neural Networks (STGNN) 

  • New architectures and novel applications of STGNNs, e.g. stock market prediction, weather prediction, anomoly detection using STGNNs
  • Visual analysis and visual explanation of spatial temporal dependencies
  • STGNNs for causal reconstruction and theory construction
  • Continual learning mechanisms for STGNNs: automated machine learning for STGNNs, concept drift and model update

Topic 2 – Ontology driven Bayesian networks for scientific knowledge discovery

  • Ontology driven Bayesian networks for interactive decision making
  • Explanation using knowledge graphs and Bayesian networks
  • Theory construction using knowledge graphs, Bayesian networks and machine learning

Topic 3 – Emerging AI systems: architectures and paradigms

 
Scroll to Top