menu

School of Electronic Engineering and Computer Science

Research menu

Research projects

Our academics undertake world-leading research in a lively and supportive research community.

Click on a research group or centre to find out about current research projects.


Smart Antenna Systems for Cooperative Low-Power Wireless Personal and Body Area Networks

On body measuring equipmentWireless sensor networks are attractive solutions that can be used in healthcare and sport performance monitoring applications which will enable constant monitoring of health data and constant access to the patient regardless of the current location or activity and with a fraction of cost of the regular face-to-face examination... find out more.


Selective activation of chemical bonds by active coherent THz spectrometry

'Dial-a-Molecule' is a current EPSRC Grand Challenge. It seeks to tackle questions of the kind: 'How can we reliably predict how to convert one molecule into another?' 'How can we carry out a series of reactions sequentially?' and 'Can we invert modular reactions and/or reactors which can be linked to a myriad of ways to provide complex synthesis?'... find out more.


Antennas for Healthcare and Imaging

Antennas control, direct and filter electromagnetic waves and form a key component of the microwave wireless communications revolution . Future developments will climb the frequency spectrum to embrace millimetrewaves, where for example 60GHz offers short-range communication with Gigabit bandwidths... find out more.


Global - QM-CHINA

As China is set to be the major source of global economic growth for the next decades, it is clearly essential that the UK is linked into and can benefit both from the excellent research that is being fostered in China (China's engineering research is already in the world top three for impact, for example, and second in Physics, with nearly 20% of world papers), and from the potential for the exploitation and implementation of that research. Queen Mary has an outstanding track record of working in collaboration with Chinese partners... find out more.


The Quest for Ultimate Electromagnetics using Spatial Transformations (QUEST)

The idea of spatial transformations (ST) is to provide entirely fresh solutions to the distribution of the spatial arrangement of materials so as to enable new ways to manipulate the emission, propagation and absorption of EM radiation. This goes far beyond what can be accomplished with traditional materials in the form of lenses and mirrors, requiring both conventional materials and also those with properties that do not exist in nature (i.e., metamaterials)... find out more.


Text Severity
Funder: CQC
Project Summary: The Care Quality Commission (CQC) are the regulator for health and social care in England; one of their services is to receive feedback from the public on care quality. Sometimes, this feedback reveals severe problems which warrant intervention, but finding these manually in large unstructured text datasets is problematic. This project will produce a text mining tool to do this automatically, and flag potential issues for review by CQC staff. This will help make cover of severe cases more comprehensive, improve speed of detection and response – and ultimately lead to improved health and social care outcomes.


Promoting the Scientific Exploration of Computational Creativity (PROSECCO)

PROSECCO is a 3-year coordination action on the topic of Computational Creativity. It is funded by the 7th Framework Programme (FET Proactive initiatives and Fostering Interdisciplinary Dialogue). Computational Creativity (CC) is an emerging technology and maturing discipline that seeks to explore the capabilities of computers to perform tasks and assume responsibilities that would, if observed in a human producer, be considered "creative" by an unbiased judge. The goal of PROSECCO is to grow and nurture the field of CC research, by educating a new generation of CC researchers and by bringing existing researchers from neighboring disciplines into the fold. It will do this through a variety of exciting outreach mechanisms and engagements with the public, with academia, and with industry... find out more


Teaching Enquiry with Mysteries Incorporated (TEMI)

TEMI is a teacher training project with the aim to help transform science and mathematics teaching practice across Europe by giving teachers new skills to engage with their students, exciting new resources and the extended support needed to effectively introduce enquiry based learning into their classrooms. We do this by working with teacher training institutions and teacher networks across Europe where we wish to implement innovative training programmes called ‘enquiry labs’. These are based around the core scientific concepts and emotionally engaging activity of solving mysteries, i.e. exploring the unknown... find out more.


Machine Learning in Wireless Networks

With an ever increasing density of mobile broadband users, next generation wireless networks (5G) need to support a higher density of users compared to today’s networks. One approach for meeting this need is to more effectively share network resources through femtocells. However, lack of guidelines for providing fairness to users and significant interference caused by unplanned deployment of femtocells are important issues that have to be resolved to make heterogeneous networks (HetNets) viable. However, the interference caused by femtocells to neighboring cells is a limiting performance factor in dense HetNets. This interference is being managed via distributed resource allocation methods. However, as the density of the network increases so does the complexity of such resource allocation methods. Yet, unplanned deployment of femtocells requires an adaptable and self-organizing algorithm to make HetNets viable. As such, in this project a machine learning approach based on Q-learning will be developed to solve the resource allocation problem in such complex networks. By defining each base station as an agent, a cellular network will be modeled as a multi-agent network. Subsequently, cooperative Q-learning can be applied as an efficient approach to manage the resources of a multi-agent network. Furthermore, we can consider the quality of service (QoS) for each user and fairness in the network.


EU FP7 Security Programme Project SUNNY (2014-2018) – Smart UNmanned aerial vehicle sensor Network for detection of border crossing and illegal entrY

EU FP7 Security Programme Project SmartPrevent (2014-2016) – Smart video-surveillance system to detect and prevent local crimes in urban areas


Cross-Domain Behaviour Understanding
Current behaviour understanding approaches suffer from highly contraint on the uniform of behaviour distribution, feature representation and etc between training and testing data. These approaches might fail when the testing data is changing all the time (e.g. UAV surveillance). We developed a cross-domain traffic scene understanding framework to interpret unseen events in target domain without training procedure by transferring knowledge learned from existing source domains.


Sketch Recognition by Ensemble Matching of Structured Features
We present a method for the representation and matching of sketches by exploiting not only local features but also global structures of sketches, through a star graph based ensemble matching strategy. We further show that by encapsulating holistic structure matching and learned bag-of-features models into a single framework, notable recognition performance improvement over the state-of-the-art can be observed.


Attribute Learning for Understanding Unstructured Social Activity
The USAA dataset includes 8 different semantic class videos which are home videos of social occassions such e birthday party, graduation party,music performance, non-music performance, parade, wedding ceremony, wedding dance and wedding reception which feature activities of group of people.


Multi-agent Learning Malmo Competition
Funder: Microsoft
Grant: £31,000
Project Summary: The Multi-Agent Reinforcement Learning in Malmo (MARLO) competition is a new challenge that proposes research on Multi-Agent Reinforcement Learning using multiple games. Participants would create learning agents that will be able to play multiple 3D games as defined in the Malmo platform. The aim of the competition is to encourage AI research on more general approaches via multi-player games. For this, the challenge will consist of not one but several games, each one of them with several tasks of varying difficulty and settings. Some of these tasks will be public and participants will be able to train on them. Others, however, will be private, only used to determine the final rankings of the competition.  

A framework will be provided with easy instructions to install, create the first agent and submit it to the competition server. Documentation, tutorials and sample controllers for the development of entries will also be accessible to the participants of this challenge. The competition will be hosted on CrowdAI.org, which will determine the preliminary rankings of the competition.

Recurring tournaments at regular intervals will determine which agents perform better in the games proposed. This competition will be sponsored by Microsoft Research for framework development and competition awards.



Advanced automated human emotion-sensing for business

The Sensing Feeling project will create new technological capability that will significantly enhance the reliability and effectiveness of monitoring retail customer emotional responses to their surrounding environment. By combining current knowledge in retail environmental psychology with advanced techniques in affective computing and computer vision the project aims to develop sensing technology that when deployed into a physical retail setting will enable the retailer to derive a live and continuous feed of a well-defined "customer delight index" of the retail space being sensed. This will be achieved by detection and aggregation of the multi-modal affective (emotional) states of shoppers' interaction behaviours expressed within the retail setting. The aim is to provide retailers with the ability to unobtrusively and automatically derive a reliable measure of the emotional state of shoppers in response to in-store variables like products displayed, merchandising design, layout design, signage, atmospherics, staff dynamics etc. This will equip retailers with a smarter ability to make informed decisions that accelerate the provision of higher quality in-store customer experiences. Find out more.

Principal investigator: Dr Yiannis Patras
Consortium: 6 partners from industry and academia


Bringing maritime border security to new dimension

The mission of the SafeShore project is to tackle existing problems and gaps in coastal border surveillance by developing a system for detection of Remotely Piloted Aircraft Systems (RPAS) using state-of-the-art, low cost, and low-emission technology. The system will be integrated with existing systems and create a continuous detection line along the border to help border officials in preventing crime such trafficking of human beings and smuggling of drugs. Find out more.

Principal investigator: Prof. Ebroul Izquierdo

Consortium: 11 partners from industry and academia


Creating a 'Visually' Better Tomorrow

PROVISION is a network of leading academic and industrial organisations in Europe comprising of international researchers working on the problems plaguing most video coding technologies of the day. The ultimate goal is to make noteworthy technical advances and further improvements to the existing state-of-the-art techniques of compression video material.

The project shall not only aim to enhance broadcast and on-demand video material, but also produce a new generation of scientists equipped with research and soft skills needed by industry, academia and society by large. In line with the principles laid down by Marie Sk?odowska-Curie actions of the European Commission, PROVISION is a great example of an ensemble of researchers with varied geographical and academic backgrounds all channelling their joint effort towards creating a technologically, or more specifically a 'visually' better tomorrow. Find out more.

Principal investigator: Prof. Ebroul Izquierdo

Consortium: 11 partners from industry and academia

Covering broadcast and user generated content for interactive UHD services

The COGNITUS project aims to combine the advances in UHD broadcasting technologies with the explosion of UGC in order to create new interactive, immersive modes of production. Running from January 2016 to December 2018, COGNITUS is a joint research project comprising eight European participants, led by BBC R&D. The project is intended to optimise how UHD content is produced and distributed, by capitalising upon the knowledge of professional producers, the ubiquity of UGC and the power of interactive networked social creativity. Find out more.

Principal investigator: Prof. Ebroul Izquierdo

Consortium: 7 partners from industry and academia

 


 


OR-MASTER Mathematical Models and Algorithms for Allocating Scarce Airport Resources

Funding Source: EPSRC Amount Awarded: £2,262,469

Start Date: 01/10/2015

End Date: 30/09/2021

Partners: • Air France – KLM • Adv Syst for Air Traffic Control (SICTA) • Airport Services Association • Airports Council Intl (ACI) Europe • Athens International Airport • CRIDA A.I.E • Eurocontrol • German Aerospace Centre DLR • Goldair Handling • HALA SESAR Research Network • Massachusetts Institute of Technology • NATS Ltd • NEXTOR-II Consortium • Northrop Grumman Park Air Systems • SESAR • Zurich Airport

Project Description OR-MASTER is to be led by a team at Lancaster University Management School, working with Computing, Science and Mathematics researchers at the Queen Mary University of London. The research has been funded by the EPSRC (Engineering and Physical Sciences Research Council) in response to growing concerns over airport capacity, rising demand, and the impact of congestion on both the travelling public and the air transport industry. The work will build on the UK's world-leading expertise in Operational Research to find the most efficient ways to schedule flights, developing and testing new models and solution algorithms that take into account all the factors involved in the allocation of flight 'slots': individual airport operations, networks of airports, airline operations, air traffic management systems, airport authorities, civil aviation authorities, airlines and the travelling public.


TRANSIT Towards a Robust Airport Decision Support System for Intelligent Taxiing

Funding Source: EPSRC [1, 2, 3] Amount Awarded: £806,020

Start Date: 01/07/2016

End Date: 30/09/2019

Partners: • Air France – KLM • Manchester Airport Plc • Simio LLC • BAE Systems • Rolls-Royce Plc • Zurich Airport • University of Bristol • Beihang University

Project Description TRANSIT (Towards a Robust Airport Decision Support System for Intelligent Taxiing) is a four site project between Queen Mary University of London, The University of Sheffield, University of Stirling and Cranfield Universities. The research has been funded by the UK EPSRC (grant numbers EP/N029496/2, EP/N029356/1 and EP/N029577/1). The lead of each grant is, respectively, Dr Jun Chen, Professor Mahdi Mahfouf, Dr John Woodward, with Dr Jun Chen from Queen Mary University of London as the overall project director. The project also has an extensive list of industrial partners, which currently includes Air France – KLM, BAE Systems, Manchester Airport Plc, Rolls-Royce Plc, Simio LLC and Zurich Airport. The TRANSIT project aims to develop a unified routing and scheduling system which will be more realistic, robust, cost-effective and configurable, producing better conformance of flight crew in response to 4 Dimensional Trajectories.


DAASE Dynamic Adaptive Automated Software Engineering

Funding Source: EPSRC Amount Awarded: £6,834,903

Start Date: 01/06/2012

End Date: 31/05/2019

Partners: • Motorola • Berner and Mattner • BT Laboratories • Northrop Grumman Park Air Systems • Ericsson • GCHQ • Honda Research Institute Europe • IBM • Microsoft Research • ABB

Project Description DAASE (Dynamic Adaptive Automated Software Engineering) is a five site project between University College London, Queen Mary University of London, University of Birmingham, University of Stirling and University of York. The lead at each site is, respectively, Professors Harman, Burke, Yao and Clark and Dr Ochoa, with Professor Harman as the overall project director. The project also has a growing list of industrial partners, which currently includes Air France – KLM, Berner and Mattner, BT Laboratories, DSTL, Ericsson, GCHQ, Honda Research Institute Europe, IBM, Microsoft Research and VISA UK. DAASE builds on two successful longer larger projects, funded by the EPSRC and which were widely regarded as highly successful and ground breaking. The project also draws inspiration and support from and feeds into the rapidly growing worldwide Search-Based Software Engineering (SBSE) community. Current software development processes are expensive, laborious and error prone. They achieve adaptivity at only a glacial pace, largely through enormous human effort, forcing highly skilled engineers to waste significant time adapting many tedious implementation details. Often, the resulting software is equally inflexible, forcing users to also rely on their innate human adaptivity to find "workarounds". Yet software is one of the most inherently flexible engineering materials with which we have worked, DAASE seeks to use computational search as an overall approach to achieve the software's full potential for flexibility and adaptivity. In so-doing we will be creating new ways to develop and deploy software. This is the new approach to software engineering DAASE seeks to create. It places computational search at the heart of the processes and products it creates and embeds adaptivity into both. DAASE will also create an array of new processes, methods, techniques and tools for a new kind of software engineering, radically transforming the theory and practice of software engineering.


KNIFE - Knowledge Discovery from Health Use Data

KNIFE (Knowledge Discovery from Health Use Data) is a Turing Institute funded project (Oct 2018-Sept 2019) led by Dr William Marsh, with co-investigators Prof Norman Fenton, Prof Martin Neil, and Dr John Robson.

The increasing use and capability of Electronic Health Record (EHR) systems has made available large databases of patient records, linked across different health providers. These databases contain information about patients’ use of the different health services, treatments and prescriptions. The data, collected for clinical management or financial reporting, has many actual and potential uses including discovering causes, optimising health delivery, allocating resources and choosing treatment. However, there are both practical and technical challenges to overcome before these benefits can be achieved. The overall objective of the project is to lay the foundations for a transformative approach to patient-linked health data, making it accessible for both medical and data science researchers to fully exploit. We will achieve this by working with two groups who are custodians of data of this type in East London. Find out more.

 

BAYES-KNOWLEDGE (Effective Bayesian Modelling with Knowledge Before Data)

This is a European Research Council Advanced Grant (value 1,572,562 euros) for a 4-year programme from March 2014-March 2018. 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. 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. Find out more.


Development of a multi-stage, multi-model system for risk assessment of offending behaviour

Collaboration with the Forensic Psychiatry Research Unit in the Wolfson Institute, September 2012-2014 Principal Investigator (RIM): William Marsh Funded by NIHR as part of the FPRU’s ongoing NIHR-funded programme grant Improving Risk Management in Mental Health


Triage for Muscloskeletal Injuries

Collaboration with the Centre for Sports and Exercise Medicine, April 2012 - March 2013 Principal Investigator (RIM): William Marsh Funded by AXA PPP and ImpactQM KTA.


Developing and validating automated assays for zebrafish behavioural analysis and drug discovery

EPSRC Case Studentship, Co-supervisors: Dr Caroline Brennan (SBCS) and Dr Fabrizio Smeraldi, 2012-2015


A new drug discrimination assay with large scale pharmaceutical application

D Caroline Brennan (SBCS, Principal Investigator), Dr Fabrizio Smeraldi (RIM) and Dr Matthew Parker (SBCS), £36775 of which £18000 contributed by Pfizer International, ImpactQM, 2012-2013


Beating the bookies at Football Prediction

Using Bayesian network causal models to predict Premiership football results. This was a funded PhD studentship for Anthony Constantinou (2009-2012) and a KTA Scheme 1 secondment of Anthony Constantinou to Agena Ltd, 01.06.2012 to 31.08.2012, £4,798


Transfer Learning for Person Re-identification

In this project we will address how to make person re-identification systems scale effectively to many camera views. Effective many camera re-identification systems are currently infeasible because for this situation every O(N^2) pair of cameras defines a distinct machine learning problem. We will develop new transfer learning techniques to allow knowledge to be adaptively shared between camera pairs, making the task practically scalable for the first time.

Experts (including statisticians and forensic scientists) have argued for many years that Bayesian reasoning has the potential to improve the efficiency, transparency and fairness of the justice system, and to avoid the kind of fallacies in probabilistic reasoning that have not only troubled the appellate courts but are also likely to have misled tribunals of fact in many trials. This project was initiated by Norman Fenton, Professor of Risk Information Management at Queen Mary, University of London (QMUL), and is being developed with Amber Marks, Lecturer in Criminal Law and Evidence, QMUL. So far more than 80 interested parties from around the world have agreed to participate in a multi-disciplinary network that brings together world-class mathematicians, scientists, psychologists, legal academics and practitioners, police officers, journalists and lay people to collaborate on the issues surrounding the use of probabilistic reasoning in criminal law. This project was orginally a short term KT Project ECSA1F8R, 01/09/2011-28/02/2012, £26,338.


DIADEM (Data Information and Analysis for clinical DEcision Making)

Digital Economy Research Cluster EP/G001987/1. April 2008-March 2009. Funding to QM: £196,425. Partners: Department of Mathematics and the Center of Advanced Computing and Emerging Technologies (ACET), University of ReadingInstitute of Particle Science and Engineering, Leeds University, Statistics Research Group, in the School of Mathematical Science, Queen Mary, ·Trauma Care Unit, Royal London Hospital; ·Centre for Haematology, Institute of Cell and Molecular Science Barts and The London School of Medicine and Dentistry; Oral Growth and Development, Institute of Dentistry, Barts and The London School of Medicine and Dentistry; Forensic Psychiatry Research Unit, Barts and The London School of Medicine and Dentistry; Dept of Biosurgery and Surgical Technology, Imperial College;· Centre for Health Management, Tanaka Business School, Imperial College London; Centre for Reviews and Dissemination, University of York; Agena Ltd; ESiOR Ltd Finland;· Department of Computer Science, Surrey University (Prof Paul Krause)

View More

 

Return to top