Skip to the content

Data mining application: case of road traffic accidents in the UK West Midlands area 2000

Saraee, M, Kerry, J, Lloyd, M and Markey, C 2004, Data mining application: case of road traffic accidents in the UK West Midlands area 2000 , in: IC-AI, 21-24 June 2004, Las Vegas, USA.

[img]
Preview
PDF - Published Version
Download (403kB) | Preview

    Abstract

    We are aiming to use data mining techniques in the analysis of data recorded about road traffic accidents in the UK West Midlands Area in the year 2000. This data will then hopefully provide drivers with guidelines relating to what measures can be taken to help reduce the chances of them being injured in a road traffic accident. This analysis is therefore important in order to identify potential risks and circumstances which contribute to such accidents, and attempt to highlight measures which can be taken to minimise them. The data is currently in an unmanageable format which hinders the investigation of finding specific links between attributes. This means that no useful conclusions can be accurately drawn at present. We therefore intend to complete the analysis by using Envisioner software and classification techniques to determine attributes of high relevance within the data. Conclusions will then be drawn, helping to identify factors such as speed, weather and road conditions which contribute to an accident occurrence.

    Item Type: Conference or Workshop Item (Paper)
    Additional Information: ISBN: 1-932415-32-7
    Themes: Health and Wellbeing
    Schools: Colleges and Schools > College of Science & Technology > School of Computing, Science and Engineering > Data Mining and Pattern Recognition Research Centre
    Journal or Publication Title: Proceedings of the International Conference on Machine Learning; Models, Technologies and Applications
    Publisher: CSREA Press
    Refereed: Yes
    Depositing User: Dr Mo Saraee
    Date Deposited: 02 Nov 2011 12:08
    Last Modified: 20 Aug 2013 18:16
    URI: http://usir.salford.ac.uk/id/eprint/18821

    Document Downloads

    More statistics for this item...

    Actions (login required)

    Edit record (repository staff only)