Study of Human Factors Variables in Battle Outcome Prediction Models

<p>Over time there have been many improvements in models that are used to predict the outcome of battles. Currently there is much supposition and speculation surrounding the use of human performance related factors as additional inputs to battle simulation models to improve their accuracy. However there is no conclusive scientific evidence which shows that these factors do make a significant difference. This study investigates the use of factors that may impact on the human performance directly or indirectly in battle prediction models. These factors consist of traditional human factors and external factors that may influence the human performance. The research performs hypothesis testing to determine if these human factors aspects of a battle have a significant effect on the accuracy of battle prediction models. The data for this research consisted of a database from Concepts Analysis Agency with 660 data records, 138 different variables, and spans over 400 years. Neural networks and regression algorithms are used to create models based upon these inputs and test the significance of adding these variables to the traditionally used variables. This research failed to reject the hypothesis, which states there is no significant difference between battle outcome prediction models using the available human factors variables and battle outcome prediction models that do not include these variables. Also reflected in this study is the need for additional research leading to more complete and appropriate human factors data to be used in battle outcome simulation models.</p>

Name thesis:degree_name

Doctor of Philosophy (PhD)

Level thesis:degree_level

Dissertation

Discipline thesis:degree_discipline

Engineering Management & Systems Engineering

Year dc:date.available

1998

Author dc:creator

• Glovier, David Andrew

Contributors dc:contributor

• Derya A. Jacobs
• Charles B. Keating
• Resit Unal
• Mark A. Scerbo

• Neural networks
• Models
• Human performance
• Factors
• Artificial Intelligence and Robotics
• Industrial Engineering
• Operational Research

Identifier

9780591815764

OAI identifier oai:identifier

oai:digitalcommons.odu.edu:emse_etds-1075