Date of Award

3-24-2016

Document Type

Thesis

Degree Name

Master of Science in Computer Science

Department

Department of Electrical and Computer Engineering

First Advisor

Brett Borghetti, PhD.

Abstract

Operator functional state (OFS) in remotely piloted aircraft (RPA) simulations is modeled using electroencephalograph (EEG) physiological data and continuous analytic workload profiles (CAWPs). A framework is proposed that provides solutions to the limitations that stem from lengthy training data collection and labeling techniques associated with generating CAWPs for multiple operators/trials. The framework focuses on the creation of scalable machine learning models using two generalization methods: 1) the stochastic generation of CAWPs and 2) the use of cross-subject physiological training data to calibrate machine learning models. Cross-subject workload models are used to infer OFS on new subjects, reducing the need to collect truth data or train individualized workload models for unseen operators. Additionally, stochastic techniques are used to generate representative workload profiles using a limited number of training observations. Both methods are found to reduce data collection requirements at the cost of machine learning prediction quality. The costs in quality are considered acceptable due to drastic reductions in machine learning model calibration time for future operators.

AFIT Designator

AFIT-ENG-MS-16-M-018

DTIC Accession Number

AD1053814

Download

Share

COinS