Share Email Print

Proceedings Paper

A deep neural network model for hazard classification
Author(s): Joseph N. Wilson; Ferit Toska; Maksim Levental; Peter J. Dobbins
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Hazard learning algorithms employing ground penetrating radar (GPR) data for purposes of discrimination, detection, and classification suffer from a pernicious robustness problem; models trained on a particular physical region using a given sensor (antenna system) typically do not transfer effectively to diverse regions interrogated with differing sensors. We implement a novel training paradigm using region-based stratified cross-validation that improves learning induction across disparate data sets. We test this training paradigm on a novel deep neueral network architecture (DNN) and report empirical results from testing/training on data collected from multiple sites. Furthermore, we discuss the relationship between penalty loss and evaluation metrics.

Paper Details

Date Published: 19 September 2019
PDF: 9 pages
Proc. SPIE 11169, Artificial Intelligence and Machine Learning in Defense Applications, 1116903 (19 September 2019); doi: 10.1117/12.2535681
Show Author Affiliations
Joseph N. Wilson, Univ. of Florida (United States)
Ferit Toska, Univ. of Florida (United States)
Maksim Levental, Univ. of Florida (United States)
Peter J. Dobbins, Univ. of Florida (United States)

Published in SPIE Proceedings Vol. 11169:
Artificial Intelligence and Machine Learning in Defense Applications
Judith Dijk, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?