- (August 2015 – August 2018) “An Intelligent Augmented Reality Remote Workforce Management System” Funded by the Innovate UK and BT. Funded by Innovate UK and British Telecom, (Principal Investigator). This is a KTP project in which our total Essex funding is £222,000.
- (August 2015 – August 2018) “Enhanced Capability in Computer-Vision Based Decision-Making Systems”Funded by the Innovate UK and SelexES (Principal Investigator). This is a KTP project in which our total Essex funding is £210,000.
- (October 2014 – February 2017 )Advanced Resource Planning System for Organisational Design. Funded by British Telecom (Principal Investigator). The Essex funding was £84,250.
- (February 2014 – February 2015) “JUPITER & NEXT GENERATION FORECASTING MODELS” Funded by British Telecom (Principal Investigator). The Essex funding was £48,807.
- (August 2014 – December 2015) “Development of a hardware demonstration platform to monitor and detect human behaviours in a residential environment” Funded by Selex ES (Principal Investigator). The Essex funding was £21,375
- (October 2013 – October 2014) “Type-2 Fuzzy Logic Rule-based optimisation for operational supply planning” Funded by British Telecom. (Principal Investigator). The Essex funding was £48,807.
- (December 2012 – October 2014) “Rule Base Optimisation for Operational Supply Planning”. Funded by British Telecom. (Principal Investigator). The Essex funding was £31,753.
- (October 2011 – October 2014) “An Intelligent Type-2 Fuzzy Logic System for Schedule Adherence in BT”. Funded by British Telecom. (Principal Investigator). The Essex funding was £84,250.
- (September 2010 – September 2013) “Developing Intelligent Adaptive Systems for Process Control and Production Optimisation in the Oil Refining Industries”. Project No KTP 7919. Funded by the UK Technology Strategy Board and Sanctuary Personnel Ltd. (Principal Investigator). This is a KTP project in which our total Essex funding is £197,266.
- (December 2010 – December 2013) “Developing Fuzzy Logic Based Intelligent Data Integration and Visualisation Tools”. Project No KTP 7578.Funded by the Technology Strategy Board and Sanctuary Personnel Ltd (Principal Investigator). This is a KTP project in which our total Essex funding is £211,266.
- (October 2011 – October 2013) “An Intelligent Type-2 Fuzzy Logic System for Schedule Adherence in BT”. Funded by British Telecom. (Principal Investigator). The Essex funding was £58,056.
- (October 2010 – October 2011) “Distributed and Fuzzy Resource Planning”. Funded by British Telecom. (Principal Investigator). The Essex funding was £20,056.
- (April 2011 – April 2012) “Optimised Production Fuzzy Planning Model”. Funded by British Telecom (Principal Investigator). The Essex funding was £23,556.
- (January 2008 – June 2011) “Adaptive and Trusted Ambient Ecologies (ATRACO)”. Funded by the European Commission Seventh Framework Programme (FP7). (Principal Investigator). The total funding for this project is 2 Million Euros in which our funding is about £542,782. The project is in collaboration with the University of Ulm, Germany, LIMSI, France , CTI and InAccess Greece.
- (December 2010 – December 2015), “Scaling Intelligent Environments” Funded by King Abdulaziz University, (Co-Equal Investigator). Total Funding for Essex is about £800,000.
- (January 2011 – January 2012): “Realising Smart Intelligent virtual class within an intelligent home”. Funded by the Higher Education Funding Council of England (HEFCE) (Main Investigator). The total funding of this project was £110,000.
- (December 2010 – November 2011) “Type-2 Fuzzy Ontology Model and Its Applications” Funded by Taiwan National Science Council (NSC). Project number NSC 99-2911-I-024-004 under the framework of the NSC Initiative for Research Cooperation among Top UK and Taiwan Universities. Total Funding £60,000. In Cooperation with National University of Tainan, Taiwan.
- (September 2010 – September 2012): “Evaluation of Fuzzy Control Algorithms in Wind Energy Conversion Systems”. Project number STDF 599 (EGY-08-045). Funded by the International office of the German Federal Ministry of Education and Research (IB-BMBF) and the Egyptian Science and Technology Development Fund (STDF). (Co-Equal Investigator). The total funding of this project was £200,000. The project is in cooperation with Heilbronn University, Germany, Cairo University, Egypt.
- (September 2009 – September 2010): “Collaborative Distance Education within Intelligent Ambient Environments”. Funded by Hewlett–Packard (HP). (Co-Equal Investigator). The total funding of this project was £80,000.
- (August 2009 – August 2012) “Type-2 Fuzzy Ontology based Intelligent Agent for Healthcare Application” Project Number: NSC 98-2221-E-024 -009 -MY3. Funded by the Taiwan National Science Council. Total Fund is £54,000. In Cooperation with National University of Tainan, Taiwan.
- (April 2006 – October 2009) “An Embedded Agent Based System to Create Ambient Intelligent Virtual Care Homes”. Project No KTP001311.Funded by the DTI, ESRC, Sanctuary Social Care. (Principal Investigator). This is a KTP project in which our total Essex funding is £197,266.
- August 2009: British Telecom Short Term Fellowship. Total Fund is £4,000.
- (January 2008 – July 2010) “Ontology Based Intelligent Agent for CMMI Knowledge Management” Project No. NSC 97-2221-E-024-011-MY2. Funded by the Taiwan National Science Council. Total Fund 320,000NTD. In Cooperation with National University of Tainan, Taiwan and University of Salerno, Italy.
- (January 2003 – May 2006) “Self-Organised Societies of Connectionist Intelligent Agents capable of Learning“, Project No IST-2001-38911. Funded by the European Union (EU) Future and Emerging Technology programme. (Principal Investigator) . The total funding of this project is 1.8 million Euros shared between 4 partners; University of Patras Medical school (Greece), CTI (Greece), Tyndall National Institute (Ireland) and ourselves. Our Essex share is £292,863.
- (October 2002 – October 2006) “An Intelligent Embedded Agent for the speed Control of Marine Diesel Engines” . Funded by MAN B&W Ltd. (Principal Investigator). The total Essex funding is £56,000. MAN.
- (April 2005 – April 2007) “Building an Intelligent Living Space (iSpace)”. Funded by the Higher Education Funding Council of England (HEFCE). (Main Investigator). The total funding of this development was £400,000 where £250,000 were awarded for the equipment of the iSpace from the SRIF-3 initiative and about £150,000 were awarded for the building structure from the SRIF-1 initiative.
- (January 2001- January 2004) “eGadgets”, Project No IST200-25240. Funded by the EU Disappearing Computer programme. (Co- Equal Principal-Investigator). The total funding of this project was 1.2 million Euros shared between 3 partners; CTI (Greece), NMRC (Ireland) and ourselves. Our Essex share was £237,000. The overall aim of the project was to create a computing framework for the design and implementation of future generations of pervasive computing artefacts.
- (October 2003 – October 2005) “Pervasive Home Environment Networks (PHEN)” . Funded by the DTI New Wave Technologies and Markets Programme. (Co-Investigator). The total funding for this project is £280,000 in which our Essex share is £93,000.
- (February 2001 – February 2003) “A soft-computing based, multi-agent architecture with applications to intelligent building sensing and control”.Funded by the Korea-UK Science and Technology Collaboration Fund. (Co-Equal Investigator). Our total funding for the project was £30,000.This project was done in partnership with the Korean Advanced Institute of Science and Technology (KAIST).
- (June 2005- December 2005) ”Support for the IEE International workshop on Intelligent Environments”. Project No EP/C533607/1. Funded by the EPSRC. (Principal Investigator). The total Essex fund is £11,000.
- (March 2007 – August 2007) “Workshop on the Future of (UK) Fuzzy Systems Research”, Project No EP/E058388/1. Funded by EPSRC, total funding of £12,026. (Co-investigator )
- (January 2006 – January 2007) “Social, Cultural and Technical Aspects of Ambient Intelligence & Pervasive Computing”. Funded by the University of Essex RPF. (Co-Investigator). The total funding of this project is £6,170.
- (April 2000 – June 2001) “An Associative Experience Engine Prototype and Demonstrator” , Funded by a RPF grant from the University of Essex. (Principal Investigator). The total fund of this project was £6,200.
- (April 2006 – April 2009) “An Embedded Agent Based System to Create Ambient Intelligent Virtual Care Homes”. Project No KTP001311. Funded by the UKDepartment of Trade and Industry (DTI), The Economic & Social Research Council (ESRC) and Sanctuary Social Care
- (January 2003 – May 2006) “Self-Organised Societies of Connectionist Intelligent Agents capable of Learning” ,Project No IST-2001-38911. Funded by the European Union (EU) Future and Emerging Technology programme. The total funding of this project is 1.8 million Euros shared between 4 partners; University of Patras Medical school (Greece), CTI (Greece), Tyndall National Institute (Ireland) and ourselves. Our share is £292,863. The overall aim of the project is to investigate the creation of multi-embedded agent pervasive computing worlds, but at a nano-scale. The target application is under water autonomous vehicles. We are one of four partners and our contribution to the project concerns the development of nano-scale under water multi-agent systems. The agents are based on hybrid Neuro-Genetic systems which use spiking neural networks.
- (October 2002 – October 2007) “An Intelligent Embedded Agent for the speed Control of Marine Diesel Engines” .Funded by Regulateurs Europa . The total Essex funding is £56,000. Regulateurs Europa is recognised as a world leader providing diesel engine governors since the 1960s, and offering total integrated solutions for control and monitoring technology in the industrial, marine, traction and power generation industries. This project aimed to develop intelligent agents that can be embedded in huge diesel engines to produce accurate and robust speed controllers for marine diesel engines. The embedded agents are based on type-2 fuzzy controllers which are able to handle the different sources of uncertainties present in marine environments to produce an accurate and robust speed controller. The project also aims to learn and adapt the controllers using hybrid Neuro-Fuzzy methods.
- (March 2007 – August 2007) “Workshop on the Future of (UK) Fuzzy Systems Research”, Project No EP/E058388/1. Funded by The Engineering and Physical Sciences Research Council (EPSRC). The total funding of £12,026. This project workshop was in cooperation with University of Wales, Aberystwyth, De Montfort University, University of Bristol and University of Aberdeen. The Workshop on the Future of (UK) Fuzzy Systems Research provided a forum for discussions and debate into the strategic directions of future research on fuzzy systems and also, for tutoring and training of UK-based research students who are working on the relevant subjects. It was held in conjunction with the 2007 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2007) and the 2007 UK Workshop on Computational Intelligence (UKCI 2007).
- (February 2001 – February 2003) “A soft-computing based, multi-agent architecture with applications to intelligent building sensing and control”. Funded by the Korea-UK Science and Technology Collaboration Fund. Our total funding for the project was £30,000. This project was done in partnership with the Korean Advanced Institute of Science and Technology (KAIST) The overall aim was to produce an innovative intelligent environment consisting of buildings populated with a mix of mobile robots and fixed building based agents. The mobile robots and building agents collaborated together to provide advanced intelligent buildings where multiple agents support occupant needs. The work was applied to a care-giving rehabilitation environment. Our research was mostly directed towards the development of building embedded-agents that employed hybrid fuzzy systems that can learn the user’s behaviour in a care environment to produce ambient intelligence.
- (January 2001- January 2004) “eGadgets“, Project No IST200-25240. Funded by the EU Disappearing Computer programme. The total funding of this project was 1.2 million Euros shared between 3 partners; CTI (Greece), NMRC (Ireland) and ourselves. Our share was £237,000. The overall aim of the project was to create a computing framework for the design and implementation of future generations of pervasive computing artefacts. Our contribution to the project concerned research into distributed intelligent fuzzy embedded agents residing and moving between networked computers embedded into everyday artefacts (e.g. white goods, mobile phones etc). Such agent systems are characteristically complex structures involving large numbers of artefact-based agents of a highly compact and mobile nature operating in real-time. Our research was mostly directed at the development of compact learning mechanisms & embedded multi-agent systems based on fuzzy logic for intelligent buildings and environments.
- (April 2000- June 2001) “An Associative Experience Engine Prototype and Demonstrator”. Funded by a RPF grant from the University of Essex. (Principal Investigator). The total fund of this project was £6,200. The aim of this project was to develop an online fuzzy–genetic learning system that can be applied to challenging problems such the control of outdoor agricultural robots.
- High-frequency Finance Project. We propose to embark on a project to develop a High-frequency Finance Research Platform. This platform will be used to improve the understanding of market dynamics. The long-term goal is to build a platform that serves both researchers and the general public. For researchers, it will be a research and simulation platform. For the general public, it will generate online forecasts of the general economy and the financial markets, very much like a weather forecast. Affiliations: CCFEA | BRACIL || Sponsor: Olsen Ltd / Lykke.
- Related Projects:
- Olsenscale from Olsen Ltd provides indications on foreign exchange fluctuation analogous to weather forecast.
- Olsen Routes from Olsen Ltd demonstrates the idea of computer-aided wind-tunnel testing in high-frequency finance.
- Economic Wind-tunnel Project explains the general idea of economic wind-tunnel testing.
- Computer Aided Constraint Programming Project demonstrates an architecture that could be used by the proposed platform.
- Wikipedia demonstrates the impact of collective intelligence. We hope our system will be a rich repository of computational finance and economic modules.
- Related Projects:
- Modelling, Simulation and Machine Learning, Projects within CSEE, Essex:
- Vernon Smith (Economics Nobel Prize laureate, 2002) pioneered the idea of wind tunnel testing new auction designs. The idea is generalized to building economic wind-tunnels for market testing and strategy design. A number of projects have been developed in our Software Wind-tunnel project
- In the high frequency finance project (supported by Olsen Ltd), we attempt to model trader behaviour in order to understand the market.
- The automated bargaining project shows how Nash equilibrium can be approximated through reinforcement learning.
- In the flexible workforce management project (sponsored by BT), we study different ways to allocate jobs to technicians.
- Some of the above projects demonstrate the power of techniques in constraint satisfaction and optimization, a discipline in which the group is internationally renowned.
- Automated Bargaining Research
- Flexible Workforce Management (2004-)
The objective is to define bargaining mechanisms (which includes communication protocols) to enable various service regions in BT to schedule their workforce efficiently. By employing a market mechanism, we aim to help the management and the region managers to generate all-win solutions. A retractable contract network protocol (RECONNET) has been defined. This protocol enables the system to conduct local search methods to search for near-optimal solutions. Guided Local Search is one of those meta-heuristic methods under consideration due to its simplicity and success elsewhere. As the management has multiple objectives, this is a multi-objective optimization problem, which is also a major research area in the group.
Researchers at Essex: Edward Tsang, Qingfu Zhang, Tim Gosling, Wudong Liu, Yossi Borenstein and Dr Nazaraf Shah
Researchers at BT: Botond Virginas, Chris Voudouris, Raphael Dorne and G Owusu
- Evolutionary Approximation to Subgame Equilibriums in Game Theory (2002-2006)
Nanlin Jin‘s research is to evolve strategies under the Rubinstein model. A strategy is a function that maps (rA, rB, time) under the Rubinstein model to a value xA (or xB if this strategy is used by B).
We have obtained extensive results. We have looked at what happens if one player has less information than the other. We have also looked at the impact of outside options to bargaining results.
See, for example, results for Rubinstein’s 1985 model with incomplete information.
Acknowledgement: Thanks to input by Professor Abhinay Muthoo, (Department of Economics)
- 2-persons-game testbed (2003)
Tim Gosling‘s research is in constraint satisfaction and bargaining in supply-chains. He has implemented a web-based system, as a research tool, to allow players to define the payoff tables in a 2-players game. This software enables the user to experiment with an evolutionary algorithm to find equilibrium strategies, if they exist, for the payoff table defined. The emphasis in this project is in evolutionary dynamics. A number of analysis tools have been developed.
- Evolutionary simple bargaining game
Software: Bargaining 4.2 (148K) (2002-04):
This zipped directory contains programs (in Prolog) for running the Chain Constrained Bargaining Game. This directory contains all the players that participated in the tournament reported inTechnical Report 385 (1.5M).
Researcher: Edward Tsang
- Simple Bargaining Tournaments
Software: Bargaining 3.1 (196K) (2001-02):
This zipped directory contains programs (in Prolog) for running the One-to-one Simple Bargaining Game. This directory contains all the players that participated in the tournament reported in Tsang & Gosling, AAMAS-2002 (74K).
Researcher: Edward Tsang
- Flexible Workforce Management (2004-)
- Software Wind Tunnels for Testing Markets, Policies and Strategies
Projects (publications): Wind tunnel testing for Staff Empowerment
Sponsor: Staff empowerment is a management concept. The idea is to, within limit, give staff control over their work, with the aim to improve job satisfaction. It is hoped that improved job satisfaction will lead to increased productivity. The whole idea is based on the management philosophy that for an enterprise to succeed, everybody must have something to gain. Under this philosophy, the management’s role is to define policies that could lead to all-win situations. We propose to put these policies through wind tunnel tests before they are implemented. Card Payment Market Electronic payment is the norm in some countries, but is only starting in others. The card payment market is complex. It requires the willing participation of card issuers, merchants and customers. Models of the card payment market has been proposed, but they were only studied based on observations or small scale experimentation through human subjects. We have implemented a model and studied the equilibrium under different market conditions. We have also used evolutionary computation to evolve strategies for card issuers to maximize their market share or profit. Artificial Stock Markets By modelling the behaviour of the participants in a particular market, one can attempt to study the market’s dynamics and predict market equilibrium. We have identified conditions under which the prices in an artificial market share similar statistical properties as those in real markets. This does not mean that we have fully understood how prices change in a real market. However, it does give us means of better understanding the market mechanism and testing trading strategies. Related project:
Game theory is an important subject in many disciplines, such as economics, business, sociology. Game theory is relevant to wind tunnel research if agents may bargain with each other. Traditionally, equilibriums in bargaining are derived mathematically. Such derivations assume that players are fully rational. Unfortunately, this is not always true. Besides, mathematical derivations are often laborious. In order to relax the full rationality assumption, and to study more complex bargaining scenarios, we take an evolutionary approach. Experimental results so far show that evolutionary computation is an effective way to approximate equilibriums in bargaining.
- The Computer-aided Constraint Programming (CACP) Project, 1997-2000. The constraint programming research community has accumulated a vast amount of experience in solving constraint satisfaction/optimisation problems. Unfortunately, applying constraint technology to a particular problem requires expertise in the technology, which many potential users do not have. The CACP project attempts to provide a system that encompasses the entire process of applying constraint technology. It supports the tasks of problem formulation and entry, in addition to supplying pre-written solvers and aiding the user in choosing which of the available algorithms to apply. Users may specify their problems using a declarative language. The problem specification is decoupled from the solvers, so the users may experiment with different problem formulations easily. Solvers supplied include a generalized Forward Checking solver, a Linear Programming solver and local search solvers implementing Guided Local Search, Tabu Search and Genetic Algorithms. A carefully designed interface is provided to guide users in understanding the technology.
This project was funded by EPSRC, reference GR/L20122, from 1st March 1997 to 31st August 2000.
- The Adaptive Constraint Satisfaction Project, 1992-98
- Objectives of the project:
There were two main objectives in this project. Firstly, we aimed to systematically to map problems (according to their characteristics) to algorithms and heuristics whilst problem-solving is in progress, so that effort can be switched to more effective algorithms when appropriate. Secondly, we aimed to develop a unified adaptive constraint satisfaction strategy in this project, which could help researchers in the constraint satisfaction community to bring effective algorithms to applications. It was a major step towards the development of a new generation of constraint satisfaction systems which could significantly outperform existing ones in speed.
- Adaptive search:
The idea of monitoring the performance of a search algorithm and switch to another algorithsm was new.Ahead of “No Free Lunch“:
The philosophy in this project was: no signle algorithm is good for all problems. Different problems are better served by different algorithms. This idea was developed in 1992. Funding was sought in 1993, well before the “No Free Lunch Theorem” was published.
- First in Modelling:
In this project, James Borrett developed a framework for automating problem transformation. This was the first project on modelling in constraint satisfaction. Modelling is now high on the agenda of constraint satisfaction research.Achievements:
The project was an ambitious one. Following are some of our achievements:
- Mapping has been developed for, but was limited to, binary constraint satisfaction problems. Mapping for general problems depends on problem formulation (modelling), which was where the emphasis laid in the project.
- Adaptive Search: An effective chain of algorithms was developed, in which search performance is monitored. When the current algorithm fails to achieve what it is designed for (e.g. when a lookahead algorithm was found to fail in pruning future branches), the search switches to the next search algorithm in the chain.
- Adaptive search:
Ahead of time:
This project has made the first steps towards modelling and adaptive constraint satisfaction.
- Objectives of the project: