Details of Grant 

EPSRC Reference:	GR/R85914/01
Title:	Feature-Sailience Identification and Methodological Diversity for Improved Prediction
Principal Investigator:	Wang, Professor W
Other Investigators:	Partridge, Professor D
Researcher Co-Investigators:
Project Partners:
Department:	Computing Sciences
Organisation:	University of East Anglia
Scheme:	Fast Stream
Starts:	01 December 2002	Ends:	31 July 2004	Value (£):	59,809
EPSRC Research Topic Classifications:	Information & Knowledge Mgmt Intelligent & Expert Systems
EPSRC Industrial Sector Classifications:	Sports and Recreation
Related Grants:
Panel History:
Summary on Grant Application Form
The goal of the proposed research is to develop and evaluate a proposed enhancement of the ensemble methodology for data mining, as applied to predict the likelihood of injury of army recruits during military training. Building upon our previous research, the proposed investigations will exploit Bayesian models along with inductive techniques such as neural networks and automatically induced decision trees, for constructing a methodologically diverse, or hybrid, ensemble in order to utilise the strengths of each individual predictor modules and thus compensate for their weaknesses to produce better overall predictions. This methodological diversity will be further exploited by the use of feature-salience ranking techniques that are specialized to the individual module technologies employed. Capitalising on the previous findings on these aspects, the focus of this proposal is to investigate and develop such a system to identify the risk factors associated with the injury problem and to predict the injury likelihood for army recruits.Ail army recruits, about 15,000 a year, must undergo an intensive military skill training for 12 weeks. Injuries occur frequently (up to 45% of the recruits get at least one injury) during the training. This is a serious problem and costs huge financial and human resources. Improved prediction of the likelihood of training injury will certainly help to reduce injury occurrence and the drop-out rate, which will directly benefit the army and the young recruits themselves as well.
Key Findings
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Potential use in non-academic contexts
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Impacts
Description This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk Summary Date Materialised
Sectors submitted by the Researcher
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Project URL:
Further Information:
Organisation Website:	http://www.uea.ac.uk