Twinned topographic maps for decision making in the cockpit

  • Authors:

  • Steve Thatcher;Colin Fyfe

  • Affiliations:

  • Aviation Education, Research and Operations Laboratory (AERO Lab), University of South Australia, South Australia;Applied Computational Intelligence Research Unit, The University of Paisley, Scotland

  • Venue:
  • KES'06 Proceedings of the 10th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part II
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

There is consensus amongst aviation researchers and practitioner that some 70% of all aircraft accidents have human error as a root cause [1]. Thatcher, Fyfe and Jain [2] have suggested an intelligent landing support system, comprising of three agents, that will support the flight crew in the most critical phase of a flight, the approach and landing. The third agent is envisaged to act as a pattern matching agent or an ‘extra pilot’ in the cockpit to aid decision making. This paper will review a new form of self-organizing map which is based on a nonlinear projection of latent points into data space, identical to that performed in the Generative Topographic Mapping (GTM) [3]. But whereas the GTM is an extension of a mixture of experts, our new model is an extension of a product of experts [4]. We show visualisation results on some real and artificial data sets and compare with the GTM. We then introduce a second mapping based on harmonic averages and show that it too creates a topographic mapping of the data.