Automatic Target Recognition User Interface Tool

David A Kerns

ISBN 10: 1249593956 / ISBN 13: 9781249593959

Published by Creative Media Partners, LLC Okt 2012, 2012

About this Item

Neuware - A computer tool to aid in selecting the best Automatic Target Recognition (ATR) algorithm is developed. The program considers many quantifiers, accepts user-defined parameters, allows for changes in the operational environment and presents results in a meaningful way. It is written for Microsoft Excel. An ATR algorithm assigns a class label to a recognized target. General designations can include 'Friend' and 'Foe.' The error of designating 'Friend' as 'Foe' as well as 'Foe' as 'Friend' comes with a high cost. Studying each algorithm's error can minimize this cost. Receiver Operating Characteristic (ROC) curves provide only information on the probabilities given a system state of declaring up to three class labels: 'True,' 'False' or 'Unknown.' Other quantifiers, including an alternate ROC curve, are developed in this study to provide information on the probability of a system state given any of multiple declarations, which is more useful to the user. Sensitivity to prior probabilities, suggestions for user-defined parameters and areas for future research are identified as the User Interface Tool is described in detail in this thesis.

Seller Inventory # 9781249593959

Bibliographic Details

• Title: Automatic Target Recognition User Interface Tool
• Publisher: Creative Media Partners, LLC Okt 2012
• Publication Date: 2012
• Language: English
• ISBN 10: 1249593956
• ISBN 13: 9781249593959
• Binding: Taschenbuch
• Condition: Neu

About this title

Synopsis

A computer tool to aid in selecting the best Automatic Target Recognition (ATR) algorithm is developed. The program considers many quantifiers, accepts user-defined parameters, allows for changes in the operational environment and presents results in a meaningful way. It is written for Microsoft Excel. An ATR algorithm assigns a class label to a recognized target. General designations can include "Friend" and "Foe." The error of designating "Friend" as "Foe" as well as "Foe" as "Friend" comes with a high cost. Studying each algorithm's error can minimize this cost. Receiver Operating Characteristic (ROC) curves provide only information on the probabilities given a system state of declaring up to three class labels: "True," "False" or "Unknown." Other quantifiers, including an alternate ROC curve, are developed in this study to provide information on the probability of a system state given any of multiple declarations, which is more useful to the user. Sensitivity to prior probabilities, suggestions for user-defined parameters and areas for future research are identified as the User Interface Tool is described in detail in this thesis.