ISAE-SUPAERO Conference paper
The 1st International Conference on Cognitive Aircraft
Systems – ICCAS
March 18-19, 2020
https://events.isae-supaero.fr/event/2
Scientific Committee
•
Mickaël Causse, ISAE-SUPAERO
•
Caroline Chanel, ISAE-SUPAERO
•
Jean-Charles Chaudemar, ISAE-SUPAERO
•
Stéphane Durand, Dassault Aviation
•
Bruno Patin, Dassault Aviation
•
Nicolas Devaux, Dassault Aviation
•
Jean-Louis Gueneau, Dassault Aviation
•
Claudine Mélan, Université Toulouse Jean-Jaurès
•
Jean-Paul Imbert, ENAC
Permanent link :
https://doi.org/10.34849/cfsb-t270
Rights / License:
ICCAS 2020 The Application of Machine Learn …
The Application of Machine Learning in Student
Pilots Evaluation Under a Simulated Environment
Content
Machine learning has been widely applied to many traditional fields. The aviation field is not a stranger to automation, but the increasing number of automation systems in the cockpit makes pilots experience difficulty in keeping themselves within the decision loop. One possible solution to this situation is creating an A.I. assisting system instead of replacing humans with machines. The first step of creating this assistant system in the cockpit is to make the computer understand the pilots’ performance. This paper is intended to demonstrate the application of machine learn-ing classifier algorithms in student pilot evaluation. In this paper, the researcher first created a pilot performance matrix. The Principle Component Analysis indicated that the constructed per-formance matrix could explain 80% of the variations of the perper-formance. This study then compared different machine learning algorithms to classify student pilots’ performance. Machine learning algorithms that had been tested include Logistic Regression, Support Vector Machine(SVM), Near-est Neighbors, Artificial Neural Network (ANN), and Random ForNear-est. The Random ForNear-est has the best result in predicting the student cockpit performance.
Mr WU, Xiaoyu (Bowling Green State University)