CEC Theses and Dissertations

Title

Predicting Naval Aviator Flight Training Performances using Multiple Regression and an Artificial Neural Network

Date of Award

1995

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Graduate School of Computer and Information Sciences

Advisor

John Kingsburry

Committee Member

John A. Scigliano

Committee Member

Laurie Dringus

Abstract

The Navy needs improved methods for assigning naval aviators (pilots) to fixed-wing and rotary-winged aircraft. At present, individual flight grades in primary training are used to assign naval aviator trainees to intermediate fixed wing or helicopter training. This study evaluated the potential of a series of single- and multitask tests to account for additional significant variance in the prediction of flight grade training performance for a sample of naval aviator trainees. Subjects were tested on a series of cognitive and perceptual psychomotor tests. The subjects then entered the Navy Flight Training Program. Subject's flight grades were obtained at the end of primary training. Multiple regression and artificial neural network procedures were evaluated to determine their relative efficiency in the prediction of flight grade training performance.

All single- and multitask test measures evaluated as a part of this study were significantly related to the primary training flight grade criterion. Two psychomotor and one dichotic listening test measures contributed significant added variance to a multiple regression equation , beyond that of selection tests E (5, 428) = 27.19, R squared = .24, multiple R = .49 , 2 < .01. A follow-on analysis indicated a split-half validation correlation coefficient of £ = .38, 2 < .01 using multiple regression and as high as £ = .41, 2 < .01 using a neural network procedure. No statistically significant differences were found between the correlation coefficients resulting from the application of multiple regression and neural network validation procedures. Both procedures predicted the flight grade criterion equally well, although the neural network applications consistently provided slightly higher correlations between actual and predicted flight grades.

This document is currently not available here.

  Link to NovaCat

Share

COinS