Évaluation of air traffic complexity metrics using neural networks and sector status

This paper presents an original method to evaluate air traffic complexity metrics. Several complexity indicators, found in the litterature, were implemented and computed, using recorded radar data as input. A principal component analysis (PCA) provides some results on the correlations between these indicators. Neural networks are then used to find a relationship between complexity indicators and the actual sector configurations. Assuming that the decisions to group or split sectors are somewhat related to the controllers workload, this method allows to identify which types of complexity indicators are significantly related to the actual workload.

[1]  Jean-Marc Alliot,et al.  Optimization of air traffic control sector configurations using tree search methods and genetic algorithms , 2002, Proceedings. The 21st Digital Avionics Systems Conference.

[2]  P. Kopardekar.  1 MEASUREMENT AND PREDICTION OF DYNAMIC DENSITY , 2004 .

[3]  S. Puechmorel,et al.  Air Traffic Complexity: Towards an Intrinsic Metric , 2000 .

[4]  D. Signorini,et al.  Neural networks , 1995, The Lancet.

[5]  Banavar Sridhar,et al.  Measures for air traffic controller workload prediction , 2001 .

[6]  Mustapha Mouloua,et al.  TOWARD A NON-LINEAR APPROACH TO MODELING AIR TRAFFIC COMPLEXITY Brian Hilburn Center for Human Performance Research The Hague, The Netherlands Geraldine Flynn EUROCONTROL Research Centre Brétigny s/Orge , France , 2005 .

[7]  Brian Hilburn,et al.  COGNITIVE COMPLEXITY IN AIR TRAFFIC CONTROL: A LITERATURE REVIEW , 2004 .

[8]  Banavar Sridhar,et al.  Airspace Complexity and its Application in Air Traffic Management , 1998 .

[9]  Laudeman,et al.  DYNAMIC DENSITY: AN AIR TRAFFIC MANAGEMENT METRIC , 1998 .

[10]  Yoshua Bengio,et al.  Pattern Recognition and Neural Networks , 1995 .

[11]  S. Puechmorel,et al.  AIR TRAFFIC COMPLEXITY : TOWARDS INTRINSIC METRICS , 2000 .

[12]  Jean-Marc Alliot,et al.  Optimal Combinations of Air Traffic Control Sectors using Classical and Stochastic Methods , 2002, IC-AI.

[13]  Arnab Majumdar.  The factors affecting airspace capacity in Europe : A Framework Methodology based on Cross Sectional Time-Series Analysis using Simulated Controller Workload Data , 2005 .

[14]  J H Crump,et al.  Review of stress in air traffic control: its measurement and effects. , 1979, Aviation, space, and environmental medicine.

[15]  David Gianazza.  Optimisation des flux de trafic aérien , 2004 .

[16]  P. Averty,et al.  Evaluating a new index of mental workload in real ATC situation using psychophysiological measures , 2002, Proceedings. The 21st Digital Avionics Systems Conference.

[17]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..