- Theme:
- Machine Learning
- Funding:
- Federal Mogul, EPSRC
This project investigates the problem of classifying and predicting fatigue crack initiation sites, through microstructure quantification in Austempered Ductile Iron. The aim of this work is to build data driven classifiers that provide enhanced understanding of a system through the ability to visualise input/output relationships, as well as providing good predictive performance for a set of imbalanced data.
Primary investigators
- Chris Harris
- Dr Philippa Reed
- Steve Gunn
Secondary investigator
- Gary Lee
Associated research group
- Information: Signals, Images, Systems Research Group
- Date:
- 2007-2010
- Themes:
- Intelligent Systems and Machine Learning, Image processing and Computer Vision
- Funding:
- General Dynamics
This research programme is aimed at extending current Southampton research on adaptive multi-spectral imaging techniques in 3D (2 spatial, 1 spectral), to hyper-spectral data fusion which allows dynamic re-configuration for specific target/background conditions enabling optimal performance to be achieved in terms of target detection and tracking, whilst minimising the number of spectral windows.
Primary investigators
- rid
- Steve Gunn
Associated research group
- Electronic and Software Systems
- Date:
- 2003-2006
- Themes:
- Agent Based Computing, E-Business Technologies, Machine Learning, Decentralised Information Systems
- Funding:
- Defence Technology Centre on Data and Information Fusion
In this research endeavour, we aim to develop flexible and robust methods for managing decentralised data fusion. We will be developing an agent-based control system for data fusion that:
- operates in a decentralised way while exhibiting desirable system-wide characteristics
- produces effective local decisions that contribute towards an effective overall system (emerging behaviour)
- operates in a computationally efficient manner
We will be using market-based approaches to view management of data fusion activities from an economic point of view and investigate market design for structuring marketplace to achieve various properties such as Pareto optimality, fairness and stability. In order to maximise their individual utility in such markets, strategies will be designed for agents while keeping in mind the overall protocol of the marketplace. These strategies can be augmented through adaptive behaviour (for example though some form of Q-Learning) that aims to utilise knowledge gained from past interactions.
Through this research project, we aim to develop novel market-based control algorithms (together with a simple demonstrator) that evaluate the effectiveness of decentralised control using market-based techniques. This research will also provide a theoretical analysis of the marketplace design to determine its effectiveness, efficiency and predictability and a systematic evaluation of the system's operational performance.
Primary investigator
Secondary investigators
- Etty David
- Xudong Luo
- pv03r
- tr03r
Associated research groups
- Intelligence, Agents, Multimedia Group
- Agents, Interaction and Complexity
- Date:
- 2002-2005
- Themes:
- Machine Learning, Image Processing, Machine Vision
- Funding:
- EU
LAVA is a 3 year EC funded Research and Technology Development project in the Information Society Technologies programme of the 5th Framework. Xerox Research Centre Europe is the co-ordinating partner in this project. The LAVA project began in May 2002. The main objective of the project is to devise machine learning technologies:
- for the reliable categorisation of generic object classes in real-world images
- and for the interpretation of events in video data.
Primary investigator
- jst
Associated research group
- Information: Signals, Images, Systems Research Group
- Date:
- 2003-2006
- Themes:
- Biometrics, Image Processing
- Funding:
- General Dynamics
We are investigating the use of biometric data fusion to provide for secure identity verification. This is an extension of our existing research programmes in automatic gait recognition and lies within the Defence Technology Centre's theme research on data fusion.
Primary investigators
- Mark Nixon
- jnc
Secondary investigators
- Chris Harris
- ljm
- gvv
Partner
- General Dynamics
Associated research group
- Information: Signals, Images, Systems Research Group
- Date:
- 1999-2001
- Theme:
- Machine Learning
- Funding:
- Unilever
The aim of this project is to develop parsimonious models for regression and classification based on kernel methods, to provide enhanced visualisation and generalisation in empirical modelling.
Primary investigator
Secondary investigator
- jg
Partner
- Unilever
Associated research group
- Information: Signals, Images, Systems Research Group
- Date:
- 2003-2008
- Themes:
- Agent Based Computing, E-Business Technologies, Grid and Distributed Computing, Decentralised Information Systems, Machine Learning, Sensor Technology
- Funding:
- Defence and Aerospace Research Partnerships (DARP), EPSRC, DTI, Ministry of Defence
The aim of this project is to perform the formative research required to construct a reactive decentralised data fusion system and to demonstrate its value in industrially relevant applications. Such a system must fuse information from disparate and varied sources, whilst coping with unreliable data and limited communication bandwidth, in a time critical environment.
The core of the project concerns the integration of agent technologies and Bayesian statistical methods, and we are working on this aspect with academic partners at Oxford University. We are specifically interested in designing the mechanisms by which self interested agents will trade for information, computation resources and bandwidth. The goal of this work is to ensure that the self-interested actions of the individual agents results in desirable system-wide properties.
The project involves three industrial partners, each of whom is providing a distinct application area - BAE SYSTEMS, Rolls-Royce and QinetiQ. The project is a Defence Aerospace and Research Partnerships (DARP) project, with joint funding from the Department of Trade and Industry (DTI), the Ministry of Defence (MoD) and the Engineering and Physical Sciences Research Council (EPSRC).
Primary investigators
- Nick Jennings
- acr
Secondary investigators
- tr
- pv
Partners
- Oxford University
- BAE Systems
- Rolls Royce
- QinetiQ
Associated research groups
- Intelligence, Agents, Multimedia Group
- Agents, Interaction and Complexity
- Date:
- 2002-2007
- Theme:
- Pervasive Computing and Networks
MAST is a set of audio streaming tools using RTP over IPv6 (and IPv4) Multicast.
Primary investigator
- njh
Associated research group
- Intelligence, Agents, Multimedia Group
- Date:
- 2002-2003
- Theme:
- Multimedia
Primary investigator
- njh
Associated research group
- Intelligence, Agents, Multimedia Group
- Date:
- 2001-2008
- Themes:
- Agent Based Computing, E-Business Technologies
Software agents are increasingly being used to represent humans in on-line auctions. Such agents have the advantages of being able to systematically monitor a wide variety of auctions and then make rapid decisions about what bids to place in what auctions. They can do this continuously and repetitively without losing concentration. To provide a means of evaluating and comparing (benchmarking) research methods in this area the Trading Agent Competition (TAC). This competition involves a number of agents bidding against one another in a number of related auctions (operating different protocols) to purchase travel packages for customers. Our agent, WhiteDolphin, is one of the most successful participants in the last two competitions.
We are now participating in a new competition , the CATallaxy competition (CAT) where the focus is on designing marketplaces.
Primary investigators
- Nick Jennings
- pv
- bs07r
- iv