Further investigation of the application of deep learning for electromagnetic simulation prediction

Steven R. Price; Stanton R. Price; Carey D. Price; Clay B. Blount

doi:10.1117/12.2518975

3 May 2019 Further investigation of the application of deep learning for electromagnetic simulation prediction

Steven R. Price, Stanton R. Price, Carey D. Price, Clay B. Blount

Proceedings Volume 11003, Radar Sensor Technology XXIII; 110030X (2019) https://doi.org/10.1117/12.2518975
Event: SPIE Defense + Commercial Sensing, 2019, Baltimore, MD, United States

Abstract

Applications seeking to exploit electromagnetic scattering characteristics of an imaging or detection problem typically require a large number of electromagnetic simulations in order to understand relevant object phenomena. It has been shown in a previous work that deep learning may be used to increase the efficiency of creating such datasets by providing estimations comparable to simulation results. In this work, we further investigate the utility of deep learning for electromagnetic simulation prediction by adding to the existing training and testing dataset while also incorporating additional material properties. Specifically, we explore using artificial neural networks to learn the connection between a generic object and its resulting bistatic radar cross section, thereby removing the need to repeatedly perform timely simulations. While deep learning can be seen as a computationally expensive technique, this cost is only experienced during the training of the system and not subsequently in the acquisition of results. The goal of this work is to further investigate the applicability of deep learning for electromagnetic simulation prediction as well as its potential limitations. Additionally, performance is compared for different data pre-processing techniques focused on data reduction.

Citation Download Citation

Steven R. Price, Stanton R. Price, Carey D. Price, and Clay B. Blount "Further investigation of the application of deep learning for electromagnetic simulation prediction", Proc. SPIE 11003, Radar Sensor Technology XXIII, 110030X (3 May 2019); https://doi.org/10.1117/12.2518975

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
10 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Finite-difference time-domain method

Neural networks

Computer simulations

Feature extraction

Radar

Electromagnetic simulation

RELATED CONTENT

Classification method for spatial targets based on convolutional neural network
Proceedings of SPIE (December 28 2022)

Feature analysis for indoor radar target classification
Proceedings of SPIE (May 12 2016)

Investigating the application of deep learning for electromagnetic simulation prediction
Proceedings of SPIE (May 04 2018)

Simulated ship recognition using two-dimensional PCA
Proceedings of SPIE (November 15 2007)

Physics based features for identifying contextual factors affecting landmine detection...
Proceedings of SPIE (May 23 2011)

A new method for ship classification and recognition
Proceedings of SPIE (November 03 2005)

Feature extraction and classification of radar targets using neural networks
Proceedings of SPIE (April 06 1995)

Subscribe to Digital Library

Receive Erratum Email Alert

Keywords/Phrases

Search In:

Publication Years