If training data appears to be mislabeled, should we relabel it?  Improving supervised learning algorithms for threat detection in ground penetrating radar data

Daniël Reichman; Leslie M. Collins; Jordan M. Malof

doi:10.1117/12.2305881

30 April 2018 If training data appears to be mislabeled, should we relabel it? Improving supervised learning algorithms for threat detection in ground penetrating radar data

Daniël Reichman, Leslie M. Collins, Jordan M. Malof

Author Affiliations +

Proceedings Volume 10628, Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXIII; 106280F (2018) https://doi.org/10.1117/12.2305881
Event: SPIE Defense + Security, 2018, Orlando, FL, United States

Abstract

This work focuses on the development of automatic buried threat detection (BTD) algorithms using ground penetrating radar (GPR) data. Buried threats tend to exhibit unique characteristics in GPR imagery, such as high energy hyperbolic shapes, which can be leveraged for detection. Many recent BTD algorithms are supervised, and therefore they require training with exemplars of GPR data collected over non-threat locations and threat locations, respectively. Frequently, data from non-threat GPR examples will exhibit high energy hyperbolic patterns, similar to those observed from a buried threat. Is it still useful therefore, to include such examples during algorithm training, and encourage an algorithm to label such data as a non-threat? Similarly, some true buried threat examples exhibit very little distinctive threat-like patterns. We investigate whether it is beneficial to treat such GPR data examples as mislabeled, and either (i) relabel them, or (ii) remove them from training. We study this problem using two algorithms to automatically identify mislabeled examples, if they are present, and examine the impact of removing or relabeling them for training. We conduct these experiments on a large collection of GPR data with several state-of-the-art GPR-based BTD algorithms.

Citation Download Citation

Daniël Reichman, Leslie M. Collins, and Jordan M. Malof "If training data appears to be mislabeled, should we relabel it? Improving supervised learning algorithms for threat detection in ground penetrating radar data", Proc. SPIE 10628, Detection and Sensing of Mines, Explosive Objects, and Obscured Targets XXIII, 106280F (30 April 2018); https://doi.org/10.1117/12.2305881

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