THE INTELLIGENT FORECASTING APPROACH OF LEARNING- CURVE IN FITS TRAINING OF STUDENT PILOT

Chung-Lin Huang

Department of Tourism Management,

Taiwan Shoufu University, Taiwan, R.O.C.

Email: This email address is being protected from spambots. You need JavaScript enabled to view it.

Chung-Chi Huang

Department of Automation and Control Engineering,

Far East University, Taiwan, R.O.C.

Email: This email address is being protected from spambots. You need JavaScript enabled to view it.

Po-Hsien Chiu*

Department of Tourism and Recreation,

Cheng Shiu University, Taiwan, R.O.C.

*Corresponding Author Email: This email address is being protected from spambots. You need JavaScript enabled to view it.

Abstract

In this research, we were forecasting the Learning-curve of student pilot for instructors to recommend the training hours and furthermore the total cost of training. From the previously research, most of them are using the Qualitative Methods such as interview and observation. We are using the Quantitative Method, an intelligent approach – Machine Learning (ML). In flight academics, they recommend courses and training hours based on the regulation of civil aeronautics administration. In the real world, not each student could accomplish or satisfied the criteria by recommend hours. If an extend-training course occurred, and it has to be a more precisely recommended by hours. We build up an intelligent system by using linear regression method and collected data from the flight academics which training student for Recreational Pilot Licensee in Taiwan. And provide a learning-curve prediction by intelligent system. Traditionally, any training method that grading students by different scale. We need an objective grading method, in order to keep the precision in prediction. Compare to the traditional ways, the FITS training methodology is more objective in grading. The FITS program must include: Scenario Based Training, Single Pilot Resource Management, and Learner Centered Grading concepts. By the intelligent forecasting system that predict the learning-curve to estimate the training hours and cost. For further applications, it can be used on the airlines to evaluate the train-worthy of student pilots.

Keywords: Learning Curve, FAA-Industry Training Standards, Machine Learning, Linear Regression

Attachments:
Download this file (0955 Final.pdf)0955 Final.pdf[ ]379 kB
Go to Top
JSN Solid 2 is designed by JoomlaShine.com | powered by JSN Sun Framework