Current Projects

 

1) Effective Bayesian Modelling with Knowledge Before Data (Short Name: BAYES-KNOWLEDGE) 

This is a European Research Council Advanced Grant (value 1,572,562 euros for a 4-year programme April 2014-march 2018) awarded to Professor Norman Fenton. The full ERC code is ERC-2013-AdG339182-BAYES_KNOWLEDGE.

The project aims to improve evidence-based decision-making in areas such as medicine, law, forensics, and transport. What makes it radical is that it plans to do this in situations (common for critical risk assessment problems) where there is little or even no data, and hence where traditional statistics cannot be used.  Our solution is to develop a method to systemize the way expert driven causal (Bayesian Network) models can be built and used effectively either in the absence of data or as a means of determining what future data is really required.  Working with relevant domain experts, along with cognitive psychologists, our methods will be developed and tested experimentally on real-world critical decision-problems.  The proposed research has the potential to both reduce at source much unnecessary data collection and improve the results of analysis of data that is collected. It has the potential to provide rigorous, rational, auditable, visible and quantified probabilistic arguments to support decision-making and recommendations in areas where currently only ‘gut-feel’ is possible. This could lead to: more rational and defensible strategic policy making by decision makers in government, financial, and other organisations; better medical diagnostics; better understanding of the impact of different types of legal and forensic evidence.  The project will enable scientists, statisticians, medics and lawyers, to be better able to reason about probability and understand the role and limitations of data, making better decisions with less data.

The grant is for 4 years and it buys out 50% of Prof Fenton's time as well as some of the time of colleagues at Queen Mary. The project is also funding 3 postdoctoral research fellows and a part-time programmer. 

2) Deferred Restructuring of Experience in Autonomous Machines (Short Name: DREAM)

DREAM is a robotic project that incorporates sleep and dream-like processes within cognitive architecture. This enables an individual robot or groups of robots to consolidate their experience into more useful and generic formats, thus improving their future ability to learn and adapt. DREAM relies on Evolutionary Neurodynamic ensemble methods as a unifying principle for discovery, optimization, re-structuring and consolidation of knowledge. This new paradigm will make the robot more autonomous in its acquisition, organization and use of knowledge and skills just as long as they comply with the satisfaction of pre-established basic motivations.

DREAM will enable robots to cope with the complexity of being an information-processing entity in domains that are open-ended both in terms of space and time. It paves the way for a new generation of robots whose existence and purpose goes far beyond the mere execution of dull tasks.

DREAM stands for Deferred Restructuring of Experience in Autonomous Machines. DREAM is funded by the European Union’s Horizon 2020 research and innovation programme under grant agreement No 640891 (2015-2018). DREAM is a Future and Emerging Technologies proactive project (FET Proactive).  It involves several major european institutions from four different countries: Université Pierre et Marie Curie (coordinator), CNRS, ENSTA ParisTech, VU Amsterdam, Queen Mary University, Universidade da Coruña.

3) Transfer Learning for Person Re-identification

Person re-identification is an important task in distributed multi-camera surveillance. This is currently performed manually at great economic cost, and with high error rates due to operator attentive gaps. In this project we aim to achieve fast accurate and robust automated person re-identification that can be deployed to any given camera network scenario, without any expensive calibration steps.
Automated person re-identification is the task of associating people based on images captured in video across diverse spatially distributed camera views at different times. This is challenging because the articulation of the human body and variety of viewing conditions such as lighting, angle and distance means that observed appearance typically differs more for the same person in different views than it does for different people. At the same time, it is an important task to solve because re-identification underpins many key capabilities in visual surveillance such as multi-camera tracking. This in turn is a key capability for end-user organizations which need video analytics to achieve a variety of ends including retail optimization, operational efficiency, public safety, security, infrastructure protection and terrorism prevention. Moreover, it is important to automate re-identification because the manual process in large camera networks is both prohibitively costly and inaccurate due to attentive gaps.

Current state of the art re-identification systems use machine learning techniques to produce models for re- identifying across a particular pair of cameras based on manual annotation of person identity in those cameras. However, this is not scalable in practice, because every unique pair of cameras would need calibration with training data. In this project, we will develop new machine learning models that can automatically adapt re-identification models created for an initial set of source cameras to address the re-identification problem in each new pair of cameras without requiring new annotation. This will dramatically improve the practical impact of re-identification technology by making it significantly more accurate as well as cheaper and easier to deploy.

EPSRC: EP/L023385/1

Past Projects

Radar (http://rim.eecs.qmul.ac.uk/radar/)

The RADAR group is unique in the UK in its interest in combining data and human expertise to create intelligent solutions for high stakes decisions. RADAR’s interdisciplinary approach is built around computer science, statistics and machine learning and psychology, to solve problems involving uncertainty and the challenges presented by scale, complexity and variability. RADAR work with practitioners to produce intelligent ‘unified models’, that use both data and expertise as inputs, to support expert decision making in multiple application domains, including medical, legal, systems engineering, sports prediction, security, risk and safety. Since its creation in 2000 the RADAR Group has attracted over £2.5 million.