Take a look at all the projects we are and have been working on over the years.

Past projects



The proposed research applies computer science solutions to an end-user-focussed challenge. The challenge is how to achieve an enhanced customer experience during a journey, through detailed knowledge of an individual traveller, whilst protecting the privacy of their data. As well as developing technical solutions to data privacy, this project aims to encourage passengers to provide this data by developing an evaluation framework to enhance their understanding of how it is used and how they can control it, thus maximising trust in the service. Currently, such a framework does not exist and this is an impediment to the opportunities offered by increased sharing of personal data, i.e. transport customers are, in the majority, unwilling to share personal data due to privacy concerns. The research findings will be applicable to a range of journey modes but the focus here will be on rail travel.

The project has been developed closely with the rail industry through partnership with the Association of Train Operating Companies (ATOC) and the Rail Safety and Standards Board (RSSB). In recent years, the availability of data in the rail industry has increased significantly in terms of timetabling, disruption and real-time provision to passengers. Currently there is little in the way of individual customer information but this is increasingly possible through smartphones and other mobile devices and will become more prevalent with the introduction of smartcards and contactless technologies. The industry's Rail Technical Strategy aims to establish rail as customers' preferred form of transport for reliability, ease of use and perceived value. Increased understanding of passengers through information such as their location, their plans, their mobility or luggage limitations, or where they are on the train would enable a more personalised service and an improved experience. The challenge is to assure customers that their data is being protected and used appropriately and that they are fully in control.

The consortium assembled for this project brings together the three academic disciplines required to solve this challenge: computer science, to develop the framework and technical solutions (University of Surrey and Royal Holloway, University of London); human factors, to develop the use cases, evaluate passenger perceptions and ensure usable solutions (Loughborough University) and transport systems to bring understanding of the data streams to be integrated (University of Southampton). To ensure the solutions are co-created with the industry and have a direct pathway to impact, ATOC and RSSB have a key role as stakeholders and on the project's External Advisory board, alongside other sector experts such as EnableID (Internet of Things and personal data), the Transport Systems Catapult (the UK government's innovation centre for intelligent mobility knowledge exchange) and ThalesUK (rail technology).

The objective is to develop a privacy evaluation framework underpinned by statistical analysis, data provenance and mobile technology. This framework will be integrated with emerging data systems being developed by the rail industry and also into a wider (sector-independent) framework being proposed by the Digital Catapult (the UK government's innovation centre for digital technologies). This will enable better communication to passengers as to why their data is needed and how it will be handled in order to increase trust and feelings of control, thus providing a virtuous circle of data provision, leading to enhanced customer experience and hence further data provision.


Read the news article about this project.


This project involves a group of researchers working in five academic disciplines (Computer Science, Crime Science, Business, Engineering, Behavioural Science) at four UK research institutes (University of Surrey, UCLUniversity of Warwick, and TRL). It has an overall budget of £~1.1m, with 80% (£~881k) funding from EPSRC. It is expected to start in April 2017 and will last for 24 months.


Researchers and practitioners have acknowledged human-related risks among the most important factors in cybersecurity, e.g. an IBM report (2014) shows that over 95% of security incidents involved “human errors”. Responses to human-related cyber risks remain undermined by a conceptual problem: the mindset associated with the term ‘cyber’-crime which has persuaded us that that crimes with a cyber-dimension occur purely within a (non-physical) ‘cyber’ space, and that these constitute wholly new forms of offending, divorced from the human/social components of traditional (physical) crime landscapes. In this context, the unprecedented linking of individuals and technologies into global social-physical networks – hyperconnection – has generated exponential complexity and unpredictability of vulnerabilities.

In addition to hyperconnectivity, the dynamic evolving nature of cyber systems is equally important. Cyber systems change far faster than biological/material cultures, and criminal behaviour and techniques evolve in relation to the changing nature of opportunities centring on target assets, tools and weapons, routine activities, business models, etc. Studying networks and relationships between individuals, businesses and organisations in a hyperconnected environment requires understanding of communities and the broader ecosystems. This complex, non-linear process can lead to co-evolution in the medium-longer term.

The focus on cybersecurity as a dynamic interaction between humans and socio-technic elements within a risk ecosystem raises implementation issues, e.g. how to mobilise diverse players to support security. Conventionally they are considered under ‘raising awareness’, and many initiatives have been rolled out. However, activities targeting society as a whole have limitations, e.g. the lack of personalisation, which makes them less effective in influencing human behaviours.

While there is isolated research across these areas, there is no holistic framework combining all these theoretical concepts (co-evolution, opportunity management, behavioural and business models, ad hoc technological research on cyber risks and cybercrime) to allow a more comprehensive understanding of human-related risks within cybersecurity ecosystems and to design more effective approaches for engaging individuals and organisations to reduce such risks.


The project’s overall aim is therefore to develop a framework through which we can analyse the behavioural co-evolution of cybersecurity/cybercrime ecosystems and effectively influence behaviours of a range of actors in the ecosystems in order to reduce human-related risks. To achieve the project’s overall aim, this research will:

  1. Be theory-informed: Incorporate theoretical concepts from social, evolutionary and behavioural sciences which provide insights into the co-evolutionary aspect of cybersecurity/cybercrime ecosystems.
  2. Be evidence-based: Draw on extensive real-world data from different sources on behaviours of individuals and organisations within cybersecurity/cybercrime ecosystems.
  3. Be user-centric: Develop a framework that can provide practical guidance to system designers on how to engage individual end users and organisations for reducing human-related cyber risks.
  4. Be real world-facing: Conduct user studies in real-world use cases to validate the framework’s effectiveness.
    The new framework and solutions it identifies will contribute towards enhanced safety online for many different kinds of users, whether these are from government, industry, the research community or the general public.


This project involves a group of researchers working in five academic disciplines (Computer Science, Crime Science, Business, Engineering, Behavioural Science) at four UK research institutes (University of Surrey, University College London, University of WarwickTRL). In addition to Surrey investigators listed below, this project also involves the following co-investigators:

This project is supported by an Advisory Board with 14 international/UK cybersecurity and cybercrime experts and a Stakeholder Group formed by 13 non-academic organisations in both the public and private sectors (including law enforcement agencies, industry and NGOs).


    The project regards the protection of personal data while using it to provide real-time customer service for passengers throughout a journey. The objective is to develop a privacy evaluation framework underpinned by statistical analysis, data provenance and mobile technology, to manage the trade-off between sharing private personal data and the benefits obtained by doing so. This interdisciplinary project involves four universities: University of Surrey, Loughborough UniversityUniversity of Southampton and Royal Holloway, University of London, in collaboration with the Association of Train Operating Companies (ATOC) and the Rail Safety and Standards Board (RSSB)Pervasive Intelligence Ltd and the Digital Catapult. It builds on a successful feasibility study that focused on improving the customer journey experience while ensuring personal data privacy for travellers who are mobility- and visually-impaired. The study involved a user study on the requirements of disabled passengers when making journeys and a mobile application which utilised wifi localisation and the DARWIN data feeds to provide personalised information to passengers during their journeys.

    Luisa Moisio, Head of R&D at RSSB said: “For the rail industry cyber-security is an increasing priority and RSSB is working with industry and academia on the issues. We are keen to support this project as the proposed work will build a strong foundation in the area of assessment and prevention of threats to railway customers and services arising from the exchange and use of data.”


    The proposed research applies computer science solutions to an end-user-focussed challenge. The challenge is how to achieve an enhanced customer experience during a journey, through detailed knowledge of an individual traveller, whilst protecting the privacy of their data. As well as developing technical solutions to data privacy, this project aims to encourage passengers to provide this data by developing an evaluation framework to enhance their understanding of how it is used and how they can control it, thus maximising trust in the service. Currently, such a framework does not exist and this is an impediment to the opportunities offered by increased sharing of personal data, i.e. transport customers are, in the majority, unwilling to share personal data due to privacy concerns. The research findings will be applicable to a range of journey modes but the focus here will be on rail travel.

    The project has been developed closely with the rail industry through partnership with the Association of Train Operating Companies (ATOC) and the Rail Safety and Standards Board (RSSB). In recent years, the availability of data in the rail industry has increased significantly in terms of timetabling, disruption and real-time provision to passengers. Currently there is little in the way of individual customer information but this is increasingly possible through smartphones and other mobile devices and will become more prevalent with the introduction of smartcards and contactless technologies. The industry's Rail Technical Strategy aims to establish rail as customers' preferred form of transport for reliability, ease of use and perceived value. Increased understanding of passengers through information such as their location, their plans, their mobility or luggage limitations, or where they are on the train would enable a more personalised service and an improved experience. The challenge is to assure customers that their data is being protected and used appropriately and that they are fully in control.

    The consortium assembled for this project brings together the three academic disciplines required to solve this challenge: computer science, to develop the framework and technical solutions (University of Surrey and Royal Holloway, University of London); human factors, to develop the use cases, evaluate passenger perceptions and ensure usable solutions (Loughborough University) and transport systems to bring understanding of the data streams to be integrated (University of Southampton). To ensure the solutions are co-created with the industry and have a direct pathway to impact, ATOC and RSSB have a key role as stakeholders and on the project's External Advisory board, alongside other sector experts such as EnableID (Internet of Things and personal data), the Transport Systems Catapult (the UK government's innovation centre for intelligent mobility knowledge exchange) and Thales UK Ltd (rail technology).

    The objective is to develop a privacy evaluation framework underpinned by statistical analysis, data provenance and mobile technology. This framework will be integrated with emerging data systems being developed by the rail industry and also into a wider (sector-independent) framework being proposed by the Digital Catapult (the UK government's innovation centre for digital technologies). This will enable better communication to passengers as to why their data is needed and how it will be handled in order to increase trust and feelings of control, thus providing a virtuous circle of data provision, leading to enhanced customer experience and hence further data provision.

    Consortium partners

    Collaborators (unfunded)


    Gift Aid is a UK tax benefit that increases the value of donations to charity by 25% at no extra cost to donors. Over the past decade, there has been a shift towards card payments over cash, which has had detrimental effects on the money charities have been able to collect with donation buckets. The industry is responding by adopting contactless terminals, but currently, there is no seamless way of attaching Gift Aid to these donations.

    Aims and objectives

    Our key objectives are:

    • Create a demonstrator running on a live payment system that submits live Gift Aid claims to HMRC on behalf of a charity and complies with all HMRC requirements.
    • Create a formal model of the system.
    • Investigate future distributed nature of the underlying blockchain.

    Areas of focus include:

    • Digital receipting linked to payments
    • Blockchain
    • Live payment system integration.

    With Swiftaid, a donor will sign up, register their card and authorise Swiftaid to generate the Gift Aid declaration on their behalf. All gifts then made by that card, Gift Aid will be automatically attached. The donor would remain in control, allowing them to manage and view all donations while staying anonymous to the charity. We are well aware that there will need to be a great value to both the charity and the donor in order for them to sign up for Swiftaid. The main benefits include:

    • Swiftaid handles the compliance with HMRC regarding record keeping and auditing, removing the burden from the charity.
    • Removes tax processing burden of both charity and donor making Gift Aid accessible to the smallest charities
    • No personal data passed to charity so can keep GDPR compliance to the minimum.
    • Full donation reporting for donors, simplifying the process for higher rate taxpayers and tax rebates.

    Blockchain is an obvious choice for such an application as it provides an immutable ledger, ensuring the 6 years of auditable records are available to HMRC, along with smart contracts, to guarantee the whole end-to- end process stays in lock step. By fully automating the Gift Aid process using blockchain it allows claiming Gift Aid on even the smallest donations to remain economical and results in increasing the money charities receive without costing the donors more.


    • Dates: 1 April 2015 - 31 March 2018
    • Funder: EPSRC EP/M017869/1
    • Funding amount: £1m (Surrey share £395K)
    • Investigator: Yaochu Jin
    • Co-investigator: John Doherty
    • Collaborators: Prof Richard Everson, University of Exeter.


    This research project aims to permit the application of evolutionary algorithms, a class of global search metaheuristics, to fluid dynamic optimisation of highly complex industrial systems by exploiting surrogate models and modern machine learning techniques. Advanced machine learning techniques such as active learning, on-line incremental learning and semi-supervised learning, will be employed to construct prediction and classification models, which are synergistically combined to assist evolutionary algorithms.

    The developed surrogate-assisted evolutionary optimisation algorithms will be applied to important industrial problems including aerodynamic high-lift wing design and drainage flow control.



      This project will introduce new approaches to develop an optimisation engine for a system which counters problems of flooding, freshwater supply, and ecological stress through storage of excess freshwater in a network of automatically controlled storage systems within the landscape.


        The University of Surrey has established the Surrey Centre for Cyber Security to consolidate, organise and promote our Cyber Security activities across the University. The Centre builds on the existing capability and resources across the University of Surrey, which has been investing in Cyber Security research as a high-priority research area since 2004. The Centre focuses on three main research directions - Privacy and Data Protection, Secure Communications, and Human-Centred Security - building on the University's strength and the background of members of the Centre. Recognition of the Centre as an Academic Centre of Excellence in Cyber Security Research will help in consolidating research activities that are currently carried out across three faculties, and in creating new synergies for long-term collaborative research projects on the emerging interdisciplinary challenges of Cyber Security. It will also foster the international visibility and positioning of the Centre and expand its linkage with businesses, industry research institutions, and governmental bodies.


        The key objective of this research proposal is to support the activity of the proposed Academic Centre of Excellence in Cyber Security Research (ACE-CSR), the Surrey Centre for Cyber Security. The objectives of the proposed Centre over the period of this funding are to support and further develop our research activities in the areas of Privacy and Data Protection, Secure Communications, and Human-Centred Security. In particular, our aims are:

        1. to consolidate and promote research activities currently carried out across the University, and to provide a focus and
          coordination for Surrey's security activity;
        2. to create new synergies internally and externally for long-term collaborative research projects in Cyber Security;
        3. to expand Surrey's linkage with businesses, industrial research institutions, and governmental bodies through enhanced
          visibility and high-profile events.


        This proposal is essentially concerned with impact: the funding requested is to support activities which are intended to achieve the maximum impact for our existing and future research work. Our planned activities are specifically aimed at strong engagement with industry, government, and the general public.

        Our engagement with industry will be enhanced by our Advisory Board. We have a strong network of industrial partners to draw on, and the Advisory Board will provide broad coverage across practitioners and beneficiaries. The Board will inform our planned engagement activities, and will be used to provide informed advice on the opportunities that will be most effective in achieving impact, and on our plans for specific events.

        The Surrey Centre for Cyber Security has created an Applied Security Lab, to support both teaching and research, with the infrastructure being provided by the University. The Centre coordinates the use of this lab to conduct applied security research, and showcase our Cyber Security work, in the form of demonstrators, projects and prototypes. This will provide a new "one-stop-shop" environment in which to host industrial visits. It will enable focused and detailed discussions, and will support our activities in developing new collaborative links with industry and engaging in meaningful dialogue with beneficiaries of our work.


        The initial composition of the Centre consists of 8 Core Members from Computing and Electronic Engineering (Institute for Communication Systems), with established track records in selected key areas of Cyber Security. Within the University there are also a further 19 Associate Members, who hold strong research expertise in areas that are strategically important in addressing interdisciplinary cyber security challenges and where existing mutual interests and potentials are likely to lead to the establishment of joint research initiatives within the proposed Centre.

        In the short-term the Surrey Centre for Security will:

        • Consolidate and promote its research activities,
        • Establish an efficient organisation and management structure (including an Advisory Board),
        • Identify new directions and bid for interdisciplinary and technology-focused cyber-security research projects,
        • Establish a regular seminar series,
        • Expand on its postgraduate teaching and PhD programmes,
        • Refine its strategy upon the consultations with its liaison officer from GCHQ (and other governmental stakeholders).

        In the medium-term the Centre will:

        • Actively bid for new research projects and increase its research output in high-quality publication venues,
        • Engage in collaborative projects with other ACE-CSRs and our partners.


        When you board a train today it is noticeable that travellers are occupied with their connected devices in some way. What if their interaction included instant, useful and personalised travel information about their journey, whilst helping the travel operator to gain valuable personalised feedback data at the same time?

        In this project a unique platform will be designed, created and tested that helps a user to customise their travel experience based on large-scale data analysis of real-time information from data feeds, end user community contribution, transport systems and sensors.



          CyberSecurity Malaysia (CSM or The Company) is interested to infer the "strength of evidence" from biometric systems. Although such a framework is well established in forensic speaker verification, this is not the case for the face recognition technology. They would like to establish this framework in order to solve crimes with evidence captured by CCTV cameras and covert cameras.


          The work to be undertaken is considered a feasibility study that is based on the existing face recognition literature.  The work answers essential questions that make use of the face recognition technology for forensic investigation, such as:

          • How to compute the strength of evidence using today's face recognition technology?
          • Can CCTV with higher image resolution lead to stronger strength of evidence (that is usable in the court)?
          • What aspects of face recognition technology need to be improved in order to cope with CCTV of the future?


          This project investigates how existing and new rail data sources can be used to enhance the passenger experience and to provide assistance to passengers with special needs and/or disabilities, for example those with limited mobility or vision impairment, particularly when unplanned disruption occurs. Technical prototypes will be created that demonstrate how relevant transport data can be integrated to meet the needs of customers, how the location of passengers can be determined and used to provide benefit to them, and how security and privacy of personal data can be maintained. The technical capabilities demonstrated will be used to create a customer walkthrough that shows how existing data can provide benefit, how other data sources can be integrated to further improve the customer experience, and also how future services might develop.


          In addition to three Surrey project investigators with expertise in computer science, cyber security and tourism, this project is also participated by external project investigators who have expertise on transportation systems (University of Southampton), and user-centred design (Loughborough University). It also involves an industrial partner Pervasive Intelligence.

          • Simon Blainey, Lecturer in Transportation, University of Southampton
          • Andrew May, Research Fellow, Loughborough University
          • Tracy Ross, Research Fellow, Loughborough University
          • Matthew Casey, Pervasive Intelligence.


          The organised nature of some crimes including drug trafficking and terrorism can be difficult to identify. One approach is to identify offenders travelling in 'convoy'. UK police forces have been using ANPR (automatic number plate recognition) data collected by traffic cameras to perform convoy analysis; however, this is typically done manually with prior information of one known vehicle. This project aims to develop a distributed processing system for large-scale ANPR convoy analysis and other criminal behaviours that currently go undetected. Our solution will enable criminal investigations to be more effective, accurate and resource-efficient. By applying automated data mining techniques to ANPR data, our solution will enable criminal investigations to focus on medium and high priority issues such organised crime as opposed to minor traffic infringements, and thus can help to justify the growing use of ANPR to the public at large.

          The project will be conducted by a consortium formed by researchers from the University of Surrey and two industrial partners, with input from ANPR stakeholders such as UK police forces and ANPR solution providers. The University of Surrey team will be contributing mainly to the ANPR convoy analysis part which includes visual analytic approaches used in HMI (human-machine interface) to assist ANPR operators to interpret the data and results more easily and more effectively. Human behaviour analysis and machine learning will be two key elements of the developed ANPR convoy analysis techniques. The possibility of making use of other data sources other than ANPR will be investigated to improve both the accuracy and efficiency of the convoy analysis results. The University of Surrey team will also work with the two industrial partners to generalise the convoy analysis work to other types of suspicious behaviours and activities that can be detected from ANPR data, and to verify the scalability of the developed algorithms to nationwide data sets.

          The project will involve use of anonymised police data and other public data sources such as Crime Map data on, public data from the Highways Agency, road topology, routing and labelling data on Google Maps and OpenStreetMap, which allows more effective analysis of the ANPR data without violating privacy of vehicles and their drivers.


            The Evolution and Resilience of Industrial Ecosystems programme (ERIE) will address a series of fundamental questions relating to the application of complexity science to social and economic systems. Our programme of research aims to embed cutting-edge complexity science methods and techniques within prototype computational tools that will provide policymakers with realistic and reliable platforms for strategy-testing in real-world socio-economic systems.


            The programme includes the gathering of data from case studies, the development and application of appropriate theoretical and computational techniques, simulation using agent-based models and the incorporation of all these elements into 'serious games' for use by policymakers. We will study the negotiation of policy goals and options, explore the role of models in policymaking and involve policymakers in the design and testing of our strategy tools.

            The programme will focus on a crucial aspect of the UK economy: the way in which firms are interdependent on each other, with the interrelationships being multi-level and multi-valued. Within an industrial 'ecosystem', there can be relationships of supply and demand; the transfer of knowledge; competition for labour; the transfer of materials down supply chains; negotiation over standards; collaboration in trade associations and unions; and innovation, product differentiation and branding.

            We will use mathematical and computational approaches to model these layered, nested, multiscale systems, where the links between actors are dynamic and the exchanges between them are unpredictable, fluctuating and perhaps sporadic. Within this context we will examine concepts and measures of resilience (the ability to recover from external shocks), emergence (the ways in which social institutions arise from individual activities) and immergence (the ways in which individuals react to institutional constraints). This leads us to some of the most intriguing open questions of complexity science. We will seek answers inspired by the real-world industrial ecosystems as captured in our case studies.

            Our vision is to provide models of multi-level socio-economic systems that are useful for decision-makers aiming to 'steer' towards policy-relevant goals. It is not our intention to provide 'the' policy solution to policy problems (specifically, it is not our intention just to show how particular ecosystems may be made more resilient or more sustainable), but rather to provide a suite of tools which will allow decision makers and their representatives to investigate alternative scenarios given a set of assumptions and initial conditions.

            We will apply the methods of data assimilation, largely developed in the context of weather forecasting, to incorporate the inevitably incomplete data from case studies into agent-based models, on an ongoing basis, with the aim of providing 'predictive' tools that are continually updated with real-world data. By 'prediction' here we mean the identification of alternative scenarios along with estimates of the probability that each will be realised over given time frames, and estimates of the sensitivity of these to uncertainties in the data and underlying model.

            It is an integral part of ERIE to study - and involve - those involved in the case study sites. One research stream is concerned with studying those with a stake in the system, as controllers, decision makers, customers, workers, etc., their goals, policy options and their links with the industrial ecosystems that they are interacting with.

            The research programme is divided into four streams, each consisting of a number of cross-disciplinary projects. Four post-doctoral researchers and a project officer will work on the programme, with seven Investigators from the disciplines of mathematics, computing science, environmental science and sociology, and 9 PhD research students, the latter funded from internal University of Surrey resources.


              • Dates: 1 October 2014 - 31 March 2015
              • Funder: Intellectual Property Office (IPO) through Innovate UK - Technology Strategy Board (TSB) SBRI programme
              • Funding amount: £74,408
              • Investigators: Shujun Li and Anthony T.S. Ho
              • Collaborator: Dr Julian Fells (industrial partner).


              This project is an extension of a former project funded by the IPO with the same title. The former project covers two phases (Proposal and Concept) and this new project focuses on Development (Phase III).

                • Dates: 1 March 2013 - 31 August 2015
                • Funder: FP7 STREP 601062
                • Investigator: Yaochu Jin
                • Research partners:
                  • University of Surrey
                  • Fundacio Privada Centre de Regulacio Genomics, Spain
                  • University of Amsterdam, the Netherlands
                  • The John Innes Centre, UK.


                The Swarm-Organ project focuses on systems containing large numbers of autonomous but relatively simple agents, whose goal is to collectively organise themselves into complex spatial arrangements despite each agent having only local awareness.

                This particular question is directly relevant to both biological morphogenesis, and to new paradigms of distributed technology such as robotic swarms and amorphous computing.

                Two levels of adaptation are either evident or required in these systems:

                1. As the whole system changes over time, individual agents find themselves in different local situations and must adapt and adjust their behavior accordingly, for example dealing with conflict resolution and/or cooperation with neighbours.
                2. The swarm must also adapt to the outside world (or the world it is embedded in) in various ways depending on its task – for example, coping with damage, maintaining functionality under changing environmental conditions, or tracking objects.

                A fundamental challenge in this field is how to design the local control system of each agent, and the Swarm-Organ project will extensively explore a specific approach – namely the use of GRNs (gene regulatory networks) – as a potentially powerful control method for these systems. By focusing on GRNs we will develop a theoretical framework about distributed adaptive control, which will be equally informative to both natural biological morphogenesis, as well as next generation technologies in robotics and computation.

                  • Dates: 1 October 2013 - 31 March 2015
                  • Funder: Technology Strategy Board (TSB) Smart
                  • Funding amount: £208,479
                  • Collaborator: Technotomy Ltd.


                  Despite recent efforts from giant corporations like Google to introduce clever ways to retrieve meaningful information from the Web, the results can only be described as single dimensional. This means that it is good at pointing searchers in the direction of where relevant information exists, but not providing a multi-dimensional view of a piece of information that puts it into context with other related data so that meaningful conclusions can be drawn. The reality is that searchers conducted by businesses continue to face dilemma and opportunity cost, because data is unstructured and often hidden in the deep Web. The proposed solution is designed to fill this yawning gap in the market and it will enable the limitations of existing search engines to be overcome, by locating, retrieving and visualising meaningful, contextualised semantic information about businesses and present that concisely and coherently as the company's "profile".

                  There are numerous potential applications for the InfoClew web intelligence mining system. However, the core focus of this proposal is the Foreign Direct Investment (FDI) market environment; since the techniques used currently to identify potential foreign investors can be best described as elementary and are therefore time consuming, very expensive, and most disappointing, inaccurate. We propose a system solution that will analyse, identify and target potential foreign investors, in a way that is automatic, visual and will offer accurate, in-time and cost-effective information. The system will search the Web to identify candidate companies of a certain profile. For example, the system could identify those companies that have a significant probability of expanding their operations into a foreign location. Although this might be a specialised application area, the possibilities of applying the techniques addressed in this proposal in other business sectors are very great.


                  The grant is a collaborative 3 year proposal to investigate how the pathogen Mycobacterium tuberculosis survives in the presence of antibiotics. The project will employ 2 PDRA's, one a biologist and the second an engineer who will construct microfluidic devices for study of growth of individual cells of M. tuberculosis and measurement of their response to antibiotics.

                  The second RA will be working closely with Lilian and Richard on the understanding of individual cell growth rate through analysing time-lapse images captured through microfluidic devices.


                    The proposed project will use University of Surrey expertise in business process re-engineering and IT technology for supporting the Networked Enterprise in order to: (a) transform the business base of the Trust so that it can fully and effectively enable the staff to realize the goals of the Trust; and, (b) engage effectively with its membership base and the wider community. The SWT will then provide a model for how all the County Wildlife Trusts in England and Wales can actively engage local communities with their environment.

                    The technology integration through this project will significantly reduce ITC consultancy and support, and trading administration costs; increase recruitment and retention of memberships; and will enable the Trust to dramatically extend the scope and range of their educational and outreach programmes.

                    The partnership is strategic in allowing SWT to create a model that best serves their membership needs, service excellence and communication and community involvement. We believe that the results obtained from this project will be transferable to a wide range of SMEs in general, as well as third sector organizations. They will provide a test of validity of much of the research work of the Digital Ecosystem research group in the Department of Computing and consequently this proposal is an important part of the research roadmap of that group.

                      • Dates 1 January 2013 - 31 December 2015
                      • Funder: Honda Research Institute Europe
                      • Funding amount: £116,733
                      • Investigator: Yaochu Jin


                      This project aims to address the main challenges in evolutionary many-objective optimisation using model-based techniques and surrogate-assisted evolutionary optimisation [2]. To this end, the objectives of the project include:

                      • To develop a model-based evolutionary algorithm, thereby making it easier to represent the Pareto-optimal solutions;
                      • To develop a preference-based approach to guide the evolutionary search. In additional to the use of preference for modifying the dominance, an inverse model that can map the preferred search space in the objective space to the decision space will be constructed. With the help of the inverse model, the search can be biased toward the preferred region in the decision space. An on-line adaptation of the preferred solution will be considered;
                      • In order to reduce computational time, surrogate models will be developed that predict the rank of the solutions;
                      • The developed algorithms will be verified on a real-world design optimisation problems


                      The project aims at the design and analysis of efficient provably private cryptographic protocols that will form a basis for a range of privacy-preserving applications. PRIMAKE protocols will give users full control over their own data, protect their anonymity, and eliminate user profiling. PRIMAKE protocols will have formal proofs of security and privacy, obtained using modern cryptographic techniques.

                        • Dates: 1 January 2013 - 30 June 2015
                        • Funder: EPSRC
                        • Funding amount: £390,000
                        • Investigator: Yaochu Jin.



                        The project will investigate a novel technology for protecting digital content like music and video downloaded via the internet. Digital content which has been obtained illegally is automatically blocked by the system. A key feature of the proposed technology is not to inconvenience legitimate users like existing Digital Rights Management systems do: Users don’t need to worry about how to configure and use the system; they just use their devices as usual without even knowing about its existence. The technology is patent-pending and further details will be available once it is published.

                        The proposal will benefit the media industry by drastically reducing the number of music and films pirated, protecting the future funding of new works, benefiting consumers.

                          • Dates: 1 January 2011 - 30 June 2014
                          • Funder: EPSRC CASE (10001560)
                          • Funding amount: £89,500
                          • Investigator: Yaochu Jin
                          • Collaborators: Intellas UK Ltd.


                          A current threat to the Intellectual Property and Copyrighted Material held by museums is bootleg images, taken by visitors in the museum using standard handheld cameras, and subsequently published on the Internet. With the rapidly increasing quality and storage capacity of consumer-range equipment the impact of the threat is increasing. The legal and moral basis is that a photo taken of a possession (picture or artefact) of the museum is also a possession of the museum. Watermarking is already used on electronic images produced by the museum, but can obviously not be applied on unauthorised photos taken by visitors. Further research is needed to find additional controls.

                          The aim of the project is to develop robust and efficient feature extraction algorithms for identifying bootlegged museum images put on the internet. The main challenge is that the algorithm should be able to search through a large number of images, which are taken from very different views and in various illumination conditions. Techniques developed in image processing and computational intelligence will be employed to address the challenge.

                            • Dates: 1 January 2012 - 31 December 2014
                            • Funder: EU FP7-SEC-2011-1
                            • Funding amount : €266,000 (total €2.98 million).


                            The protection of the national infrastructures is one of the main issues for national and international security. While FP7 MICIE project has proved that increasing cooperation among infrastructures increases their level of service and predictive capability, it is not enough to effectively counteract threats such as cyber attacks. Such attacks could be performed blocking communication from central SCADA to local equipment or inserting fake commands/measurements in the SCADA-field equipment communications (as happened with STUXNET worm).

                            The paradox is that critical infrastructures massively rely on the newest interconnected (and vulnerable) ICT technologies, while the control equipment is typically old, legacy software/hardware. Such a combination of factors may lead to very dangerous situations, exposing systems to a wide variety of attacks. To overcome such threats, the CockpitCI project aims on one hand to continue the work done in MICIE by refining and updating the on-line Risk Predictor deployed in the SCADA centre, on the other hand to provide some kind of intelligence to field equipment, allowing them to perform local decisions in order to self-identify and self-react to abnormal situations induced by cyber attacks.

                            It is mandatory to operate both at SCADA control centre and at field equipment because it is very dangerous to let field components operate autonomously. To address this issue an hybrid validation system will be implemented: at the Control Centre level an “Integrated Online Risk Predictor” will provide the operator with qualitative/quantitative measurements of near future level of risk integrating data coming from the field, from other infrastructures, and from smart detection agents monitoring possible cyber attacks; at field level, the system is complemented with a smart software layer for field equipment and a detection system for the TLC network. The system will be validated on real equipment and scenarios provided by Israel Electric Corp.

                            Apart from participating in a number of R&D tasks, Surrey is to lead two research tasks:

                            • Real-time intrusion detection strategies, to be investigated along the lines of anomaly detection and misuse detection via machine learning, pattern recognition, post-processing to reduce false positives as well as false negatives, and context awareness and adaptability approaches.
                            • Strategies for automatic reaction, to be investigated along the lines of decision support with multi-source information fusion, graph-based modelling and rule based approaches.


                            This project provides the design and associated development of a verifiable voting system, based on the principles of the original Pret a Voter system, to enable secure electronic voting in the state of Victoria, Australia. The aim is to provide a system using electronic ballot markers so that voters can construct their votes electronically, and then upload them to the system in a verifiable way. The system provides 'end-to-end verifiability' voters obtain cryptographically signed receipts of their votes so they can later check that the votes have been included in the tally and not altered or discarded, and the processing and tallying of the votes is done in a publicly verifiable way so that independent auditors can check that it has been done correctly. The application of the original design idea to its use in a real election gives rise to new research challenges and the need to develop new security protocols and algorithms.

                            Electronic voting in Victoria is motivated by the need for accessibility, and to support long distance out-of-state voting and voters for whom English is not their first language. The particular engineering challenges and security concerns associated with electronic voting have motivated the use of a highly secure and voter-verifiable system to provide the necessary guarantees in the integrity of the resulting election and the privacy of the votes.

                              • Dates: 15 March 2012 - 14 March 2014
                              • Funder: Royal Society International Exchanges Scheme - 2011 China Costshare (F020701)
                              • Funding amount: £9,000 (plus 68,800 CNY from NSFC)
                              • Investigator: Shujun Li
                              • Collaborators:
                                • Dr Chengqing Li and Dr Qin Li, University of Surrey
                                • College of Information Engineering, Xiangtan University, China.


                              When implemented in digital (time, space and value all discretized in binary form) domain, many good dynamical properties of chaotic systems in continuous domain may disappear or be degraded. Previous research shows that such dynamical degradation can create big problems to some applications, i.e., reducing security of chaos-based cryptosystems. Despite the importance of this issue in both theory and practice, it has not been well studied. In this project, we hope to achieve the following outcomes:

                              • Better understanding of the fine structure of the dynamical degradation for selected chaotic systems;
                              • New framework of studying the dynamical degradation in fixed-point and floating-point arithmetic;
                              • Some results that can be applied to chaos-based applications in digital domain.

                              • Dates: 1 February 2013 - 31 August 2014
                              • Funders: Royal Academy of Engineering and The Leverhulme Trust
                              • Funding amount: £19,700
                              • Investigator: Helen Treharne.

                              • Dates: 1 March 2013 - 31 August 2014
                              • Funder: Technology Strategy Board (TSB)
                              • Funding amount: £135,000
                              • Investigator: Lee Gillam
                              • Collaborators: Jaguar Land Rover and GeoLang Ltd.


                              The IPCRESS project addresses key industry barriers to Cloud adoption related to data security and resilience, focused in particular on the difficulties of entrusting highly valuable Intellectual Property (IP) to third parties through the Cloud.

                              We address concerns about IP leakage and IP theft: IP theft has been cited as a £9.2bn problem for UK industry (OCSIA and Detica, 2011) and described as greatly assisted by an 'insider'. But an 'insider' is hard to define in the deperimeterisation of Cloud and supply chains.

                              IPCRESS will develop a capability for tracking IP through supply chains, offering Cloud services to:

                              • Prevent IP leakage
                              • Detect IP leakage, or theft
                              • Identify retention beyond allowed periods.

                              The approach to be developed and embedded within Jaguar Land Rover is based on a computationally efficient method for finding IP without exposing IP, referred to as private search, but with an additional novelty (US patent filed by the University of Surrey) of avoiding costs of encryption.



                                Designing a machine listening system that mimics the human auditory system is an extremely challenging task. CVSSP, funded by EPSRC and Dstl, has developed the prototype of such a system using the techniques of blind source separation (BSS) and audio-visual (AV) signal processing.

                                This proposal, by bringing in the expertise from School of Psychology and Department of Computing, attempts to equip the system with certain cognitive capabilities e.g. attention switching, as used naturally by humans in real listening environments and explores its potentials for the detection of abnormal conversations in security applications, such as, safety surveillance and automated crime detection.

                                  • Dates: 20 August 2012 - 28 June 2013
                                  • Funder: EPSRC MILES (EP/I000992/1)
                                  • Funding amount: £9544.56
                                  • Investigators: Helen Treharne and Caroline Scarles.


                                  Imagine walking around touristic environments (museums, galleries, etc.) and by pointing your phone at an exhibit you are given the option to view a video, read a description or identify another relevant exhibit. This enriching experience has the potential to provide a personalised virtual tour and remove the need for clunky headsets. Existing approaches are dependent on GPS which is unavailable inside a building and therefore a different approach is needed. The project will explore the type and form of the augmented content that should be displayed, based on the context of the location and the tourist within a room.


                                  The project has three objectives aims:
                                  1. Develop an application for a smartphone using a fixed wifi environment for detecting location within a room
                                  2. Determine how best to augment the video feed with the contextual content so that that app is easy to use for different audiences
                                  3. Evaluation the app by testing it in appropriate locations.


                                  The project has successfully run public trials at Watts Gallery and The Lightbox, both of which combined location-based audio and images and augmentation of paintings to evaluate the impact that this variety of augmentation has on the visitor experience.


                                  The use of Augmented Reality on mobile phones and tablets has risen in popularity over the last few years. For example, Layar provides a generic augmented reality platform, or Google Sky Map, which provides a star gazing application.

                                  However, such systems are dependent on receiving a GPS signal to locate them in order to display the appropriate augmented content. As such they do not function within buildings. Some approaches, for example Junaio, have utilised markers, somewhat similar to 2D barcodes, to try and provide points of reference. Another approach used image recognition of paintings in art galleries to provide the contextual reference point.

                                  The use of image recognition is sufficient for art galleries, since the domain is fairly narrow and the viewing angle of the art works is well defined, generally straight on. However, for installations and museums, whereby three dimensional items are on display, for example a dinosaur, the viewing angle is potentially 360 degrees, making the image recognition approach infeasible. The use of marker images suffers from a similar problem, whereby the viewing angle of the visitor is restricted to that of the marker image, not the object on display. Augmented reality should supplement the experience, not define it.

                                    • Dates: 6 August 2012 - 31 March 2013
                                    • Funder: EPSRC MILES (EP/I000992/1)
                                    • Funding amount: £4,520.


                                    We will collect data in a reinforcement learning paradigm over varied temporal delivery programmes (hours to weeks) in the laboratory and in everyday life via stimulus delivery on participant's smartphones.

                                    A number of common learning models will be tested to identify which model best fits temporally intensive versus temporally sparse stimulus delivery. Model outputs will be used to generate prediction of personality type (risk seeking vs. risk averse / high vs. low obsessive-compulsive (OC) tendencies).

                                    • Dates: 2 January 2013 - 1 May 2013
                                    • Funder: EPSRC MILES (EP/I000992/1)
                                    • Funding amount: £2,000
                                    • Investigator: Paul Krause.


                                    Growing interest in mathematical computational and diagrammatic languages, and their relation to gesture has paved the way for the study of relations between the materiality and techniques of the body and what neuroscientist Rodolfo Llinas would call ‘mentality’.

                                    The link between ‘mentalility and motricity’, and the capability of gesture-haptic communication to bridge the division between the bodily and the virtual, has led to a growing interest in gestural mechanics for the creation of more physical and performative engagements in human-to-machine interaction and interfacing.

                                    Computer science and the performing arts research are two fields that share a keen interest in the gestural and gesture-performative. It is within the context of the gestural and the gesture-haptic that divergent forms of communicability are activated that make possible a passage from the corporeal to the conceptual, the bodily and the mechanic.

                                    This event, which will include two short performances, each exploring the interactions between computer languages and embodiment, will invite computer scientists, technology scholars, developers and body practitioners and theorists (particularly but not exclusively from the performing arts) to share their research at the intersection between computational and body languages, between motricity and mentality.

                                      • Dates: 15 February 2013 - 14 July 2013
                                      • Funder: EPSRC MILES (EP/I000992/1)
                                      • Funding amount: 7 weeks FTE + £4,000
                                      • Investigators: André Grüning, Claudio Avignone Rossa and Andrea Rocco.
                                      • Collaborations:
                                        • Dylan Childs (Animal and Plant Sciences, University of Sheffield)
                                        • Mark Rees (Animal and Plant Sciences, University of Sheffield)
                                        • Bill Sloane (Engineering, University of Glasgow).


                                      We undertake to extend existing and explore new modelling approaches for microbial populations in microbial ecology. The aim is to better understand robustness properties of such populations, such as in the soil or gut microbiomes or in bio-technological systems like microbial Fuel Cells (MFCs) with the objective to contribute to the design of robust microbial systems and increase their long-term yield and stability.


                                        MILES is an EPSRC 'Bridging the Gaps' interdisciplinary project that will stimulate new collaborations within the University between mathematics, computing, the physical sciences, engineering, life, and social sciences.

                                        Aims and objectives

                                        Mathematical contributors to the social and life sciences typically aim to provide insight by building a model and solving it using ingenious techniques and computer programmes whose details can be inaccessible to researchers in the host discipline. Mathematicians equally can be surprised to discover that these disciplines themselves use quite different kinds of models, in unfamiliar ways to seemingly perplexing ends.

                                        Revolutionary progress comes when researchers from all the relevant disciplines create new kinds of models together, owned and exploited by them all. We plan a programme of networking, idea-generation and collaboration activities focused on modelling approaches to the life and social sciences, their synergies and dissonances.

                                        We shall explore the different types of model used in different disciplines, the extent to which the models themselves, modelling methods (ways in which models are created and validated), methodologies (the philosophy of science behind modelling) and ways of using models (e.g. for understanding or prediction) can be transferred between disciplines, and when and how to create entirely new modelling frameworks.

                                        We shall emphasise three themes of particular interest to research groups in the university, where different disciplines have distinct perspectives:

                                        1. Sustainability
                                        2. The 'in silico' cell
                                        3. Mathematical and computational techniques in social science and biology.


                                        Our programme will, however, include activities across the wide span of life and social science modelling, with further occasional events on modelling in the broadest sense, to examine the opportunities for dialogue with other disciplines in the University (e.g. english, drama, music, film, psychology, management).

                                        The University hosts several highly successful multidisciplinary centres, such as the Centre for Environmental Strategy, the Advanced Technology Institute and the Surrey Space Centre and projects including the ESRC Research Group on Lifestyles, Value and Environment and the EngD programme in Environmental Technology.

                                        We see the potential for similar successful interaction between mathematics, computing, and the social and life sciences. To achieve it, we must create the circumstances that encourage individuals to take part in multidisciplinary projects, by suggesting to them that to approach another discipline with curiosity, but no immediate solutions is of great value. By providing opportunities to meet people from other disciplines and time to learn in detail about their perspectives, issues and interests and to develop a common language, and by offering incentives to embark on risky research adventures.

                                        Our three-year programme of activities to stimulate new collaborations in life and social science modelling will be coordinated by a dedicated full-time facilitator, and include: externally facilitated annual sandpits with research pump-priming fund prizes; discipline hopping funding for mathematicians, computer and physical scientists and engineers to spend time in life/social science departments; a monthly Caf Scientifique; multidisciplinary workshops and networking events; a visiting scholar programme; funding for feasibility studies; a virtual forum and wiki for online discussion and collaboration.

                                        Research projects conceived and developed during the programme will lead to follow-on grant applications. Owing to the strength of the contributing research groups, we expect the consequent impact on the UK cross-disciplinary research profile to be significant. Our ultimate aim is to create a sense of excitement about stepping beyond traditional subject boundaries and thinking creatively about working with a wide range of potential collaborators, so that the cultural changes initiated by this programme will be sustainable in the longer term, and cross-disciplinary research will continue to flourish at the University into the future.

                                          • Dates: 6 August 2012 - 31 March 2013
                                          • Funder: EPSRC MILES (EP/I000992/1)
                                          • Funding amount: £15,000
                                          • Investigator: Raffaella Guida.


                                          The project aims at monitoring the incidence of water-related diseases like diarrhea in Africa by correlating Remote Sensing (RS) data and local information such as the attendance of students.

                                          To achieve this goal, RS data (hyperspectral) will be collected on catchment areas in Malawi. The RS datasets will be processed to monitor the quality of water according to quality indicators suggested by experts. Maps of water quality will be produced. This information will be correlated with local information coming from local teachers who will be provided with smartphones to send us information about daily disease incidence amongst their students.

                                            • Dates: 1 January 2012 - 31 December 2013
                                            • Funder: FP7 EC Management Costs
                                            • Funding amount: €447,155.


                                            In 2010, the TOP500 project, which ranks and details the 500 (most powerful known computer systems in the world since the year of 1993, announced that the world's most powerful computer system is Tianhe 1A in China.

                                            Aims and objectives

                                            This project aims at establishing a strategic collaboration with the host and developer of this computer system in China to explore a range of research issues, which can be highlighted as:

                                            • Further test and evaluation with complex computing tasks, especially those in the areas of modelling, simulation, visualization and imaging etc, and hence identify a range of research challenges for further development in the area of computing systems as well as their applications
                                            • Discussion with series of targeted workshops and seminars to explore and generate ideas in further developing super computer architectures, algorithms, configurations, and any other important issues across the boundaries of software engineering, distributed computing, cloud computing, and grid computing etc.
                                            • Exchange visits and personnel in developing the discussed ideas into project proposals and research programmes.
                                            • Joint publications and other dissemination activities
                                            • Establishing long-term collaborations in addressing ambitious and challenging research issues.

                                            The SCC-Computing has drawn a strong consortium with complementary expertise and multi-disciplinary research know-how to ensure successful delivery of this project, leading to fruitful discussion and initiation of new ideas for further research on supercomputing systems.

                                            • Dates: 22 April 2009 - 21 April 2013
                                            • Funder: EPSRC (EP/G025797/1)
                                            • Funding amount: £1,056,891
                                            • Investigator: Steve Schneider.


                                            Governments all over the world are investing in electronic voting, but experiences in the USA and in the UK have shown that there are immense obstacles to be overcome before we can have secure and usable systems. The project aims to develop and implement robust voter-verifiable electronic voting systems that are usable in real large-scale elections. We will also conduct user-trials, and we will develop and extend techniques for analysis and verification of voting systems. To achieve these aims, we will work with the UK Ministry of Justice, which is charged with modernising UK elections, as well as two commercial election systems providers, namely Election Reform Services and Opt2Vote. We are also partnered with influential US organisations and individuals.


                                            1. Develop and extend the design of robust voter-verifiable electronic voting systems.
                                            2. Implement a system and conduct a user-trial.
                                            3. Develop and extend techniques for analysis and verification of voting systems.


                                              This project is to produce a design specification document for the back-end vote processing system to be used with the VEC front-end. The back-end should provide a verifiable voting system based on Pret a Voter, and the design is to give sufficient detail to specify the software components of the system to be developed.


                                              • Dates: 1 December 2011 - 31 May 2012
                                              • Funder: Home Office HOS/11/038
                                              • Funding amount: £32,511
                                              • Investigators: Anthony T.S. Ho and Shujun Li.


                                              In a wide range of law enforcement investigations, for both traditional and ‘cyber’ crimes. Law enforcement teams have developed methods of finding and extracting information from seized digital devices on an ad hoc basis, finding solutions to problems as they arise. With the move towards certification/accreditation for forensic laboratories, there is a need to formalise the techniques used in processing digital data and to develop methods of validating these processes.  This work should be informed by existing international standards and best practice documents in addition to the requirements of the Forensic Regulator.

                                              The underlying objectives of this project is to provide an understanding of existing and future international and domestic standards, best practice documents and legislation which will have an impact upon the processing of digital information for the purpose of law enforcement investigation.  

                                              The required deliverable is a literature survey detailing existing and future standards, best practice and legislative documents related to the process of digital forensics.

                                                • Dates: 1 April 2011 - 31 January 2012
                                                • Funder: EPSRC (EP/I034408/1)
                                                • Funding amount: £86,237
                                                • Investigator: Lee Gillam
                                                • Collaborators: 
                                                  • Professor Mark Baker, University of Reading, UK.
                                                  • Dr Terry Harmer, Belfast e-Science Centre, UK.
                                                  • EoverI Ltd, Belfast, UK / Mediasmiths International Ltd.


                                                Compute resource benchmarks are an established part of the high performance computing (HPC) research computing landscape, and are also in general evidence in non-HPC settings. As Cloud Computing technology becomes more widely adopted, there will be increasing need for well-understood benchmarks that offer fair evaluation of such generic systems in comparison other kinds of computing systems that have been optimized for specific purposes. Cloud Computing benchmarks need to be able to account for all parts of the lifecycle of cloud system use., and most existing benchmarks do not allow for this.

                                                Cloud-specific benchmarks will increase in importance because clouds have a wider range of possible applications than are offered by HPC, and also because the variety of options and configurations of cloud systems, and efforts needed to get to the point at which traditional benchmarks can be run, have various effects on the fairness of the comparison.

                                                In this pilot, we set out to create an academically focused cloud benchmark site that accounts fairly for such variations. The principal outcome will be a web portal that embodies such considerations and which can be used to access data about benchmark runs, and potentially to adapt benchmarks to run on other Cloud systems. The proposed portal will offer a service to a knowledgeable user that returns the closest matches, based on the closest portfolio of benchmark elements, to a set of requirements specified about their own application as a Service Level Agreement (SLA). The portal will also offer access to bundled benchmark tests (virtual machines containing such applications) that have been constructed during the project, and which will alleviate the need for other researchers to repeat such work and the associated costs of Cloud as well as of effort, in doing so.


                                                  This project provides for a PhD studentship at the University of Surrey, with support from AWE Ltd. The project is to explore meta-modelling technologies, which support transformations between languages such as UML and CSP.

                                                  High-integrity software/hardware development technology requires translation from one such language to another. This PhD is concerned with developing traceable and repeatable translation methods. James Sharp is the PhD student supported by this project.

                                                    • Dates: 1 January 2011 - 31 January 2012
                                                    • Funder: EPSRC First Grant (EP/I014934/1)
                                                    • Funding amount: £100,751
                                                    • Investigator: André Grüning.


                                                    How does the nervous system work? How does a cognitive system learn? And how is high-level human or animal learning related to changes in the nervous system? This research project will contribute to these research questions in context of research areas computational neuroscience, cognitive science and machine learning.

                                                    We want to develop general-purpose learning algorithms for spiking neural networks. Such learning algorithms are of great importance for their potential to tie together complementary approaches towards learning on the neuronal and cognitive level and could lead to a major break-through towards a unified understanding of learning and information processing in computational neuroscience and cognitive science.

                                                    The aim of computational neuroscience is to understand the detailed computational properties of nervous systems and build artificial neural network models that are biologically plausible, i.e. that model the function of a real neural network (in the brain) as closely as possible with an artificial neural network (on the computer).

                                                    In contrast, cognitive science looks at (human, animal or even artificial agent) cognitive behaviour from a more global point of view and tries to draw conclusions about the underlying mechanisms of information processing in the brain. Models for such processing are often inspired by neural models, but not necessarily biologically realistic, and it is an open problem how properties of cognitive systems are grounded in properties of neural systems.

                                                    On the cognitive (and also the technical) level, learning is often target-driven: a system needs to achieve a certain task, and gets feedback about how well it is doing. Based on this feedback, its behaviour is changed. Such learning also often involves inferring a priori arbitrary relations in the data given to the system. On the neural level, there are the neurons and their connections (synapses), and neuroscience has observed a number of ways in which these change when a system learns. It is however unknown how feedback on performance on the global level is broken down into localised changes to neurons and synapses on the neural level in a functional way and how known mechanisms of adaptability on this neural level "conspire" so that on the high-level goal-oriented learning emerges.

                                                    More specifically, we want to develop learning algorithms for artificial networks of spiking neurons that make use of known neural processes of adaptability in a way such that the networks are able to learn tasks in a goal-oriented, target-driven way. Furthermore algorithms shall allow for networks to develop internal representations of a task which can be analysed and conclusions drawn from about human or animal information processing in a similar cognitive task.

                                                    The project will deliver a series of learning algorithms for artificial networks of spiking neurons that are general-purpose (that is, not tied to a specific task but able to learn arbitrary input-output relationships), supervised and biologically plausible. No such algorithms exist so far.

                                                    The research will have significance for the following:

                                                    1. It grounds higher-level learning in low-level neural adaptability.
                                                    2. The project can trigger experiments into a novel combination of learning mechanisms in the nervous system.
                                                    3. It can bring forward the interpretation of the neural code through analysis of internal network dynamics in response to a learnt task.
                                                    4. Models of neural systems are of interest as learning devices in their own right with a range of applications in artificial intelligence. New learning algorithms for artificial neural networks can bring forward the quest for intelligent computers.
                                                    5. The research can contribute to understanding the (mal)functioning of the nervous system better, and it could consequently have a long-term impact on the medical sciences for curing neuronal disorders.

                                                      • Dates: 1 July 2010 - 30 September 2012
                                                      • Funder: EPSRC (EP/H500189/1)
                                                      • Funding amount: £65,171
                                                      • Investigator: H Lilian Tang.

                                                      • Dates: 1 September 2011 - 31 August 2012
                                                      • Funder: EPSRC Knowledge Transfer Account (GR/T10101/01)
                                                      • Funding amount: £51,112
                                                      • Investigators: Yaochu Jin and Andrew Crocombe
                                                      • Collaborators: Industrial partner: Aero Optimal Ltd.


                                                      Design of weight efficient Carbon Fibre Reinforced Plastics (CFRP) aero structures is a challenging task due to the following reasons. First, panel design involves in multi-disciplinary criteria such as stress, fatigue, buckling, control surface effectiveness, weight and cost. Second, the complexity of panel design is very high and a large number of parameters need to be optimised. Third, panel design is conducted in the presence of a large number of uncertainties, including changes in loading condition. Finally, the market is increasingly competitive and therefore, the allowed time for design becomes shorter. All these challenges require a generic tool and efficient design tool for panel design.

                                                      The aim of this project is to develop a user-friendly and powerful software tool for CTRP panel design. The software consists in a number of the state-of-the-art optimisation algorithms that can be chosen by the user. In addition, different criteria can also be specified for different purpose. The choice of optimisation algorithms, optimisation criteria as well as the constraints for optimisation can be made using a graphic user interface.

                                                        • Dates: 2 July 2007 - 1 February 2012
                                                        • Funder: TSB and CD02
                                                        • Funding amount: £195,366 (£132,588 from TSB)
                                                        • Investigator: Lee Gillam.


                                                        Grids harness resources for undertaking highly complex calculations and processing large volumes of data in heterogeneous distributed architectures to solve highly complex scientific and industrial problems. Grids exist as a variety of geographically distributed computers and high-performance computer clusters in combination with geographically distributed data repositories and databases.

                                                        This 3-year Knowledge Transfer Partnership (KTP) is being undertaken in collaboration with CDO2 Limited, providers of industry-leading pricing and risk technology to banks, hedge funds and investment firms that are involved in trading structured credit products. CDO2's premier financial risk simulation software, CDO Sheet, allows customers to accurately calculate the value of these complex investments and conduct risk analysis.

                                                          • Dates: 1 September 2008 - 10 May 2012
                                                          • Funder: TSB
                                                          • Funding amount: £111,983
                                                          • Investigator: Paul Krause.


                                                          This Knowledge Transfer Partnership between Surrey Wildlife Trust and the University of Surrey is applying Knowledge Sharing Technology developed at Surrey.  This will enable the Trust to offer members a range of services, which will add value to their membership, enable members to interact with each other, and strengthen the relationship between the Trust and its membership base..  These services will also make the Trust's valuable knowledge resources available to a wider community.

                                                            • Dates: 1 January 2012 - 30 June 2012
                                                            • Funder: EPSRC MILES (EP/I000992/1)
                                                            • Funding amount: £12,000
                                                            • Investigator: Paul Krause.


                                                            To develop a software tool (Algorhythmics 1.0), as part of a novel social/intellectual network model (MINDBEATS Quintet version), that would facilitate electronic spaces/times for the co-generation of cross-disciplinary ideas, aimed at the the creation of artistic and scientific artefacts.

                                                            MindBeats will create a virtual space where a mind ecology will be generated by periodic and self-regulated idea-exchanges between five participants in a period of half a year. This period will constitute an MB cycle, divided into regular beats (once every seven days). The cycle will thus contain around 25 beats.

                                                              • Dates: 1 June 2009 - 31 May 2012
                                                              • Funder: Leverhulme Trust
                                                              • Funding amount: £189,113
                                                              • Investigator: H Lilian Tang.


                                                              The MORPHIDAS project involves automatic extraction of leaf information from digital images of whole specimens, facilitating automated analysis of species variation over time. Advances in the field of image interpretation and automatic plant characterization, classification and species identification are expected.

                                                                • Dates: 1 January 2011 - 30 September 2012
                                                                • Funder: EPSRC EP/H500189/1
                                                                • Funding amount: £32,321
                                                                • Investigator: H Lilian Tang.


                                                                This project is to produce a demonstrator system which realises the Pret a Voter design for the Victorian Electoral Commission (VEC) for use in a State election. The purpose of the demonstrator is to show how the system would work with respect to the voter experience, in order for the VEC to take a go/nogo decision on whether to proceed with development of the full system for the November 2014 State Election.

                                                                  • Dates: 1 January 2012 - 30 June 2012
                                                                  • Funder: EPSRC Pathways to Impact grant
                                                                  • Funding amount: £11,500.


                                                                  Inward investment is a huge global business. In a highly competitive world corporate business (both large and small) are setting up operations across borders to access new markets, to seek lower costs, and gain know-how.

                                                                  This brings huge economic growth to the countries that attract foreign direct investment from around the world and national and regional investment promotion agencies are competing fiercely to identify and target potential foreign investors. The techniques used currently to identify potential foreign investors can be best described as primitive.

                                                                  Even the most sophisticated practitioners in FDI marketing still rely on either basic quantitative indicators drawn from published accounts (rate of growth, profitability, cash reserves, R&D spend etc.) or qualitative information in the form of key words or phrases are drawn from web searches (new chief executive, takeover, press cuttings,, analyst reports etc.) to create a 'score' for a company that denotes its value as a potential inward investor.

                                                                  At a time of continuing financial uncertainty in developed markets the ability to predict company growth could also have an even bigger application in the investment business. Working initially to support inward investment marketing the learning from BIWM supported data mining/predictive analytics process could offer the clear evidence needed to convince the investment community that a company's growth probability can be calculated within acceptable margins of error.

                                                                  This project continues on the "web entity investment profiling" KTA project that ended in February 2011, there has been significant progress in regards to developing the idea further and identifying potential business opportunities. Currently it is believed that there is great potential to continue the efforts for pushing this idea even further, due to the increasing interest from investors and also clients.

                                                                  The implementation of this system has been undertaken by Technotomy Ltd in collaboration with the Department of Computing, and is currently working on the development of the first produced prototype into a commercial application.


                                                                  • Dates 1 February 2011 - 30 June 2011
                                                                  • Funder: Amazon Web Services (AWS)
                                                                  • Investigator: Lee Gillam.

                                                                  • End date: 3 November 2011
                                                                  • Funder: EPSRC (EP/H500189/1)
                                                                  • Funding amount: £20,000
                                                                  • Investigator: Paul Krause
                                                                  • Co-investigator: Sotiris Moschoyiannis
                                                                  • Collaborators: Rulemotion and the Institute for Animal Health.

                                                                  • Dates: 1 February 2011 - 30 June 2011
                                                                  • Funder: EPSRC (EP/H500189/1)
                                                                  • Funding amount: £20,000 (approx)
                                                                  • Investigator: Lee Gillam.

                                                                  • Dates: 1 October 2010 - 31 May 2011
                                                                  • Funder: EPSRC (EP/H500189/1)
                                                                  • Funding amount: £19,500
                                                                  • Investigator: Paul Krause.

                                                                  • Dates: 14 March 2011 - 12 August 2011
                                                                  • Funder: EPSRC (EP/H500189/1)
                                                                  • Funding amount: £21,094
                                                                  • Investigator: Antony Browne.


                                                                  With the emergence of consumer devices capable of generating sensor data in real-time, there is a need for data mining techniques to make use of this data. One such area is the use of portable electroencephalograph (EEG) which can indicate different states of brain activity, such as sleep or concentration. Alpha-Active Ltd is an SME specialising in the development of EEG products which are used by customers to monitor EEG in real-time. Example customers include cognitive therapists, where EEG is used in therapies for addiction and chronic pain, and elite sports coaching, such as for archery and motorsport. However, one of the areas that Alpha-Active would like to develop is the use of real-time user feedback. The aim is to give the sports person feedback that is indicative of a figure of merit derived from the EEG data recorded during optimum performance. This may also be used to help patients in managing long term illness. While Alpha-Active can record and play back EEG signals, they lack the classification techniques needed to provide useful feedback for users.


                                                                  In this project, we propose to apply Surrey’s research on data mining in Alpha-Active’s product. We will develop a proof-of-concept plug-in for their HeadCoach product to classify EEG signals in real-time.


                                                                  The key outcome is to evaluate whether neural network techniques can be applied to the real-time analysis of EEG signals in Alpha-Active’s product. This will be achieved through the development of a proof-of-concept. If successful, the potential is for development into a customer product for Alpha-Active.

                                                                    • Dates: 1 September 2008 - 31 August 2011
                                                                    • Funders: TSB and Lhasa Ltd
                                                                    • Funding amount: £210,568 (£135,040 from TSB)
                                                                    • Investigator: Paul Krause.


                                                                    This Knowledge Transfer Partnership between Lhasa Ltd. and the University of Surrey seeks to develop the capability to deliver a fully integrated RFID system for the travel industry.  The project aims to re-engineer and develop existing Lhasa Ltd. products to incorporate novel machine learning enhancements.

                                                                      • Dates: 1 September 2010 - 31 August 2011
                                                                      • Funders: Royal Academy of Engineering and Leverhulme Trust
                                                                      • Funding amount: ca. £45,000
                                                                      • Collaborators: Ron Rivest (MIT), Vanessa Teague (Melbourne).


                                                                      Sabbatical funding to enable research into how to scale secure voting systems to real-world size and real-world complexity.

                                                                      • Dates: 3 January 2011 - 30 December 2011
                                                                      • Funder: Amazon Web Services (AWS)
                                                                      • Investigator: Lee Gillam.


                                                                      • Dates: 24 September 2007 - 23 March 2010
                                                                      • Funder: EPSRC (EP/E056407/1).


                                                                      Digital watermarking enables us to hide a message in another data file, such as an image.  For instance, an artist selling digital copies of his pictures on-line, can embed a watermark identifying himself as the copyright owner.  Watermarks are also used for authentication and self-restoration of images. Take photos from a crime scene for instance. Someone may try to tamper with the evidence, say replacing the section showing the unlicensed gun with a cup of tea. The watermark, containing information about the original image, can demonstrate that a change has been made, or even recover the original image.

                                                                      A main challenge is to make the watermark robust. Normal processes such as analogue transmission and image processing result in (imperceptible) noise to the image, and this can damage or destroy the watermark. In the criminal scenarios above, the criminal will obviously attempt to remove the watermark in order to get away with the crime. Known solutions exist resisting a wide range of attacks, but combinations of wide ranges of attacks remain a challenge. The clever criminal will obviously tailor his attack to the application, and is likely to find a weakness.

                                                                      Our vision is a new watermarking scheme which is secure against all known attacks.


                                                                      We propose research towards this long-term goal by:

                                                                      1. Using know results from error-control coding to develop a novel watermarking system which s robust to so-called local geometric attacks and cropping
                                                                      2. Defining a coding-theoretic model to facilitate further improvement of error-control codes for watermarking applications
                                                                      3. Exploring ways to combine features from different known solutions to get robustness against more attacks.

                                                                      • Dates: 1 October 2007 - 31 August 2010
                                                                      • Funder: EPSRC CASE (Thales)
                                                                      • Funding amount: £90,000
                                                                      • Investigators: Anthony T.S. Ho and Helen Treharne.


                                                                      This EPSRC CASE PhD Studentship is a joint collaboration between Thales Research and Technology and the university of Surrey. The main theme of the research is on the theoretical modelling, methodology and applications of formal methods to the security verification and validation of digital watermarking systems for multimedia content.


                                                                      The project is developing formal methods and adapting them to a number of watermarking algorithms including robust, semi-fragile and fragile watermarking. Formal methods at various stages of the watermarking and authentication processes are being investigated for verification and validation of their security protocols.

                                                                      These include the watermarking embedding, attack and detection processes, as well as the critical analysis on the role of the sender, attacker, and receiver.

                                                                      David Williams is the doctoral student on this project.

                                                                        • Dates: 7 June 2010 - 6 December 2010
                                                                        • Funder: EPSRC (EP/H500189/1)
                                                                        • Funding amount: £40,000
                                                                        • Investigator: Paul Krause.


                                                                        Over the last two years we have developed Bayesian Network (BN) models for the estimation of Greenhouse Gas (GHG) emissions in the agricultural sector. These capture a corpus of experience on the impact that farm management processes have on GHG emissions, in compliance with the IPCC guidelines. The models' predictions of the farm's total annual CO2 emissions validate well against the total emissions attributed to the UK agricultural sector according to the NAEI records. So far, however, it has not been possible to carry out a more thorough analysis on the reliability of these results given the absence of actual emissions figures at farm level in the UK Agricultural sector.

                                                                        Aims and objectives

                                                                        These preliminary results show that access to UK or, ideally, Europe wide data on emission figures would enable us to refine the models into a usable tool that would have significant value in aiding the agriculture sector to identifying recommendations for individual farms to optimise their businesses with regard to GHG emissions. Currently the only tool available is CALM provided (FoC) by the Country Land & Business Association (CLA), with support from EEDA & Crown Estates. This assists land managers identify the scale and source of land emissions as part of their corporate and social responsibility. It has been well received as "an excellent first step". However, our BN models can extend this in a number of important ways, such as adding a measure of the potential for carbon sequestration in the farm, and a measure of the costs to the farmer that result from the volumes of GHG emitted as a result of their farming practices.

                                                                        This six month project will involve collection of data, evaluation and refinement of the BN models. Support will come from Simon Ward of the CLA and Profs Norman Fenton and Martin Neil of Agena Ltd. Simon Ward will be involved in the user evaluation of the models and data collection. He will facilitate contact with additional agricultural consultants. Agena Ltd will evaluate the models from the perspective of best practice in developing BNs, and advise on their optimization.

                                                                          • Dates: 1 July 2010 - 31 December 2010
                                                                          • Funder: EPSRC (EP/H500189/1)
                                                                          • Funding amount: £20,000.

                                                                          • Dates: 21 December 2009 - 2 July 2010
                                                                          • Funder: EPSRC (EP/H500189/1)
                                                                          • Funding amount: £17,194.


                                                                          Understanding how neurobiological systems can process sensory information rapidly is an area of research which would benefit from exploitation. At Surrey, research into sensory systems has focused on the importance of low-level processing.

                                                                          For example, the superior colliculus is a small structure in the midbrain of humans that automatically orients our eyes to a movement, sound or touch that occurs around us. This automatic orientation is an important function that allows us to prioritise resources sub-consciously.

                                                                          Research into these low-level structures has taken place at Surrey as a result of an EPSRC funded workshop. The workshop brought together an interdisciplinary team to share expertise on how to combine sensory stimuli. The knowledge and collaborators gained from this workshop resulted in models of low-level sensory structures that have proven effective. The novelty of the developed technique is its ability to adapt its behaviour in response to arbitrary target stimuli. Nobody else has achieved this for multi-sensory inputs.


                                                                          In this project, we propose to apply Surrey’s model of adaptive low-level sensory processing to imagery systems from Waterfall Solutions. With a proof-of-concept, we hope to demonstrate that Surrey’s adaptive techniques can be applied to real-world tasks.


                                                                          The key outcome is to evaluate whether Surrey’s technique can be exploited. This will be achieved through the development of a proof-of-concept.  Further exploitation will be evaluated during the project.

                                                                          • Dates: 1 June 2006 - 31 May 2010
                                                                          • Funder: EU FP6
                                                                          • Funding amount: €536,832
                                                                          • Investigators: Paul Krause and Sotiris Moschoyiannis
                                                                          • Collaborator: Official OPAALS.


                                                                          OPAALS is a global Network of Excellence formed around multi-disciplinary research into Digital Ecosystems. OPAALS research covers social science, linguistics, computer science, software engineering, and biology.

                                                                          Digital Ecosystems are emerging as a novel approach for the catalysis of sustainable regional development driven by Small and Medium-sized Enterprises (SMEs). Digital Ecosystems are undoubtedly an important future development of the Internet, breaking it free from legacy systems that are based on centralised servers and require strict conformance to prescriptive processes and interfaces.


                                                                          The two overarching aims of the OPAALS Project are to build an interdisciplinary research community in the emerging area of Digital Ecosystems (DE), and to develop an integrated theoretical foundation for Digital Ecosystems research spanning three widely different disciplinary domains: social science, computer science, and natural science.

                                                                          Together, these two aims will result in a global Network of Excellence (NoE) in digital Ecosystems. The main claim that OPAALS makes is that in order to achieve sustainable digital business Ecosystems of SMEs and software components we need to understand in depth the collaborative processes and ICTs that underpin the continuous creation, formalisation, and sharing of knowledge in the form of business models, software infrastructure for e-Business transactions, and new formal and semi-formal languages.


                                                                            • Dates: 1 January 2009 - 31 December 2009
                                                                            • Funder: Royal Surrey County Hospital
                                                                            • Funding amount: £5,500.


                                                                            This project investigated the use of GRIDs in nuclear medicine with the Royal Surrey County Hospital.

                                                                            • Dates: 1 January 2007 - 30 June 2009
                                                                            • Funders: TSB and Ilutra Systems
                                                                            • Funding amount: £115,025.42 (£78537.27 from TSB)
                                                                            • Investigator: Paul Krause.


                                                                            This project aims to enhance Ilutra's i-TRAK active tracking system for luggage and personal items.  The overall aim is to develop a robust and scalable system for processing customer queries and online sales of i-TRAK, and to include new technology into i-TRAK airline and Travel Industry Integration.


                                                                              • Dates: 1 December 2004 - 30 June 2008
                                                                              • Funder: EPSRC (GR/S98450/01)
                                                                              • Funding amount: £126,556.


                                                                              During any major crime investigation, the establishment of the identity of vehicles and individuals involved in crime incidents necessitates the extremely time-consuming process of manually annotating all available CCTV tapes and digital archives.

                                                                              Therefore, any technology for recovering intelligence automatically from video footage must be a priority for development of the evidence-gathering capability of our police forces. This project aims to advance research in the recovery of evidence from video footage.

                                                                              There are two key crime-oriented applications that will directly benefit from this research. First, video summarisation of CCTV archives i.e. the automatic generation of a gallery of mugshots and number plates for all moving objects. Such a gallery represents the most effective method of enlisting the knowledge of local police officers and the general public.

                                                                              Second, automatic annotation of video footage to ensure all evidence should be capable of automatic entry into HOLMES 2 - the investigation management system used by police forces to collect, manage and analyse intelligence data.


                                                                              Two novel areas of investigation are proposed. First, methods for representing and analysing crowds are to be developed to process typically crowded scenes. Second, multimodal data fusion couples the linguistic structure of current police annotation practice with the metadata structure of the video interpretation process to generate a rich homogenous data representation that can drive the annotation process.


                                                                              • Dates: 2 January 2005 - 31 October 2007
                                                                              • Funder: EU FP5
                                                                              • Funding amount: £70,834
                                                                              • Investigator: Lee Gillam
                                                                              • Research assistant: Neil Newbold.


                                                                              LIRICS is a research project in the EU eContent programme with a consortium that brings together leading experts in the field of NLP and related standards development via participation in ISO committee and National Standardisation committees. The Consortium has strong Industry support and involvement through the 21 members of the LIRICS Industry Advisory Group.


                                                                              LIRICS aims are to:

                                                                              • Provide ISO ratified standards for language technology to enable the exchange and reuse of multilingual language resources
                                                                              • Facilitate the implementation of these standards for end-users by providing an open-source implementation platform, related web services and test suites building on legacy formats, tools and data
                                                                              • Gain full industry support and input to the standards development via the Industry Advisory group and demonstration workshops
                                                                              • Provide a pay-per-use business model for use by Industry and, in particular SMEs, validated during the project for the benefit of all actors in the content and language industries.

                                                                              Consortium members

                                                                              The LIRICS consortium consists of:

                                                                              • INRIA - French National Institute for Research in Computer Science and Control
                                                                              • DFKI - German Research Centre for Artificial Intelligence
                                                                              • The University of Sheffield
                                                                              • Consiglio Nazionale delle Ricerche - Istituto di Linguistica Computazionale
                                                                              • University of Vienna
                                                                              • University of Tilburg
                                                                              • Max Planck Institute
                                                                              • University of Surrey
                                                                              • Institute for Applied Linguistics, University Pompeu Fabra.


                                                                              The two overarching objectives of the DBE project are to provide Europe with a recognised advantage in innovative software application development by its small and medium-sized enterprises (software producer SMEs) and to achieve greater information and communication technology (ICT) adoption by SMEs in general.

                                                                              The DBE will achieve these objectives by adopting a multi-disciplinary approach based on biology, physics, business and social sciences mechanisms and models to develop an open-source distributed environment that can support the spontaneous evolution and composition of
                                                                              (not necessarily open-source) software services, components, and applications.

                                                                              DBE transposes mechanisms from living organisms like evolution, adaptation, autonomy, viability, introspection, knowledge sharing, and self-organisation, to arrive at novel architectures and technologies, business processes, and knowledge, thus creating a network of digital business ecosystems for SMEs and software providers to improve their value networks and foster local economic development.


                                                                              Four areas of research encompassed by the DBE project are:

                                                                              1. ICT transfer and adoption, training, ethnography, etc.
                                                                              2. Business modelling
                                                                              3. Computer science, software engineering and enabling technologies (web services, software agents, distributed architectures, ontologies, etc.)
                                                                              4. Fundamental models (maths, physics, biology, AI).

                                                                              One of the outputs of the project will be an opensource, component-based software infrastructure that will act as a commons to support the evolutionary optimisation of software services for SMEs. This digital infrastructure will fit the local cultural identities and socio-economic needs of SMEs to support their participation in regional and sectorial innovation clusters.

                                                                              The DBE will change the way SMEs and EU software providers use and distribute their products and services. It will allow SMEs to link enterprise-wide external resources and value networks, and to allocate them based on their business goals and priorities. The DBE is based on the key finding that with such an evolutionary and self-organising system Europe could harness the complexity of software production and its SME software industry could regain competitiveness in the market.


                                                                                • Dates: 1 December 1999 - 31 March 2003
                                                                                • Funder: EPSRC (GR/M89041/01)
                                                                                • Funding amount: £174,546.


                                                                                The scene of a crime will always contain forensic evidence with clues relating to the victim and the perpetrator of the crime. Documenting the evidence is a highly skilled task performed by dedicated officers. Information collected at the scene is subsequently used by a number of individuals and organisations, including forensic scientists.

                                                                                Accurate recall of this information is crucial to the administration of justice. A scene of crime officer sees much more at the scene of a crime than may be apparent in a image of the same, and he or she can articulate this information at the scene.


                                                                                SOCIS is a prototype R&D project set within a real application of considerable social importance, and which integrates a number of relatively mature research technologies to ask new questions. Most importantly, it asks whether a large complex computer data base of arbitrary objects can be populated from multimedia derived features (speech, transcribed language, digitised images etc) so as to enable the retrieval of digitised images in response to queries made by a range of interested parties.

                                                                                SOCIS will integrate off the shelf digital camera and speech recognition technologies to automate the hands-free collection and storage of images alongside verbatim commentaries (collateral texts) about images.

                                                                                • Funder: Santander Doctoral Student Award
                                                                                • Funding amount: £5,000.

                                                                                Project description

                                                                                The objective of the visiting project is to investigate and develop bio-inspired strategies to deal with Hierarchical Multi-label Classification (HMC) problems. Different from conventional classification problems, where there are no hierarchical relationships between classes, in hierarchical classification the classes can be subclasses or super-classes of other classes.

                                                                                Among the hierarchical problems, mainly in the field of bioinformatics and text classification, there are a great number of problems in which an instance can be associated to two or more classes. These problems are known in the machine learning literature as HMC problems, and the development of efficient strategies to deal with them is a current and relevant research topic.

                                                                                • Funder: EPSRC (EP/H500189/1)
                                                                                • Funding amount: £20,000
                                                                                • Investigator: Paul Krause.

                                                                                • Funder: KTN, Consult Hyperion
                                                                                • Funding amount: £90,000.


                                                                                EPSRC CASE PhD studentship awarded by the Cyber Security KTN, and in partnership with Consult Hyperion.

                                                                                • Funder: EPSRC (vacation bursary)
                                                                                • Funding amount: £2,500.

                                                                                Project description

                                                                                The ability to fuse, process and act upon sensory information is an important human attribute. Multisensory integration in mammalian brains is exemplified by the superior colliculus (SC).

                                                                                The SC serves an important function – it subconsciously shifts our gaze (saccades) to focus on prominent stimuli regardless of which sense the stimulus was detected by. Imagine seeing a car from the corner of your eye as you cross a road and turning to see it clearly, or reacting to a tap on the shoulder by turning around.

                                                                                As such, the SC prioritises the use of the fovea in our eyes to point it at stimuli it feels are important: events occurring in any one (or preferably more) sensory modality. Computational modelling has helped us develop a better understanding of the operation of the SC.

                                                                                For computer science, developing models of brain structures is important as they allow us to explore their application in the real-world, offering robustness and flexibility beyond currently constrained and brittle systems. As such, the application of these models may have significant impact in areas from intelligent surveillance to sensory fusion in health care monitoring.

                                                                                In this project, we propose that an existing abstract model of the SC be situated in the real-world to see whether it can operate in way that is similar to biological systems. This work has been conducted in discussion with nine leading research groups across the UK and US in preparation for a Programme Grant proposal.

                                                                                The model has already been implemented in a Java framework that can allow it to be connected to appropriate sensors (a camera and two microphones). However, the challenge is to provide the model with features in an appropriate format by developing software interfaces between the model and the sensors to produce an artificial saccade. This should be possible in the time using the existing code and libraries.

                                                                                This Vacation Bursary was used to fund Anthony Timotheou, a student studying on the BSc Computer Science programme at Surrey.

                                                                                Aims and objectives

                                                                                The aim of this project is to take an existing abstract model of the superior colliculus and situate this in a system that can react to video and sound stimuli from the real-world.

                                                                                Objectives are to:

                                                                                1. Develop a broad understanding of how biological systems route sensory signals (particularly visual and auditory stimuli) in the midbrain to the superior colliculus.
                                                                                2. Use this understanding to develop feature selectors for a camera and two microphones that can process stimuli and input them to an abstract model of the superior colliculus.
                                                                                3. Integrate the camera, microphones and feature selectors with the model.
                                                                                4. Evaluate the developed system in a number of systematic experiments on live input.
                                                                                5. Write-up the method and evaluation for publication.

                                                                                • Funder: EPSRC CASE (Charteris plc)
                                                                                • Funding amount: £90,000.

                                                                                Project description

                                                                                This project is an EPSRC CASE studentship with Charteris plc and the University of Surrey. The research focuses on the theoretical modelling and applications of digital forensics systems for text and image content. Phil Bateman is the research student supported by this project.