Improved classification for a data fusing Kohonen self organizing map using a dynamic thresholding technique

  • Authors:

  • Odin Taylor;John Tait;John Macintyre

  • Affiliations:

  • School of Computing, Engineering and Technology, University of Sunderland, Sunderland, UK;School of Computing, Engineering and Technology, University of Sunderland, Sunderland, UK;School of Computing, Engineering and Technology, University of Sunderland, Sunderland, UK

  • Venue:
  • IJCAI'99 Proceedings of the 16th international joint conference on Artificial intelligence - Volume 2
  • Year:
  • 1999

Quantified Score

Hi-index 0.00

Visualization

Abstract

The use of linear data fusion is a fast developing area in the field of military information and combat systems. However, the use of data fusion in conventional application areas is not as wide spread. To date linear data fusion has been used only in applications in which substantial knowledge of both the problem domain and the sensor devices in use are available. However, in applications such as condition monitoring the problem domain can be very complex, with little or no knowledge about the interactions between measured parameters. This paper describes the use of non-linear self-learning or self-organising systems as a tool for data fusion, since these systems can learn complex interrelationships between a number of parameters, and use this information as a tool for improved classification.