Evaluation of advanced Air Traffic Management
concepts is a challenging task due to the
limitations in the existing scenario generation
methodologies. Their rigorous evaluation on safety
metrics, in a variety of complex scenarios, can
provide an insight into their performance, which can
help improve upon them while developing new ones.
In this work, I propose an air traffic simulation
system, with a novel representation of airspace,
which can prototype advanced ATM concepts. I then
propose a novel evolutionary computation methodology
to algorithmically generate conflict scenarios of
increasing complexity in order to evaluate conflict
detection algorithms.
I illustrate the methodology by quantitative
evaluation of three conflict detection algorithms on
safety metrics. I then propose the use of data
mining techniques for the discovery of interesting
relationships, that may exist implicitly, in the
algorithm''s performance data.
This relationships are formed as a predictive model
for algorithm''s vulnerability which can then be
included in an ensemble that can
minimize the overall vulnerability of the system.
concepts is a challenging task due to the
limitations in the existing scenario generation
methodologies. Their rigorous evaluation on safety
metrics, in a variety of complex scenarios, can
provide an insight into their performance, which can
help improve upon them while developing new ones.
In this work, I propose an air traffic simulation
system, with a novel representation of airspace,
which can prototype advanced ATM concepts. I then
propose a novel evolutionary computation methodology
to algorithmically generate conflict scenarios of
increasing complexity in order to evaluate conflict
detection algorithms.
I illustrate the methodology by quantitative
evaluation of three conflict detection algorithms on
safety metrics. I then propose the use of data
mining techniques for the discovery of interesting
relationships, that may exist implicitly, in the
algorithm''s performance data.
This relationships are formed as a predictive model
for algorithm''s vulnerability which can then be
included in an ensemble that can
minimize the overall vulnerability of the system.