Title

Performance Of Emi Based Mine Detection Using Back-Propagation Neural Networks

Keywords

δ-Technique; Back-propagation; False alarm filtering; Mine detection; S-Statistic

Abstract

We propose and evaluate a neural network approach to mine detection using Electromagnetic Induction (EMI) sensors which provides a robust non-parametric approach. In our approach, a neural network with the well-known back-propagation learning algorithm combines the S-Statistic with the δ-Technique to discriminate between non-mine patterns and mines. Experimental results show that this approach reduces false alarms substantially over using just the δ-Technique or the energy detector.

Publication Date

12-1-2007

Publication Title

ESANN 2005 Proceedings - 13th European Symposium on Artificial Neural Networks

Number of Pages

229-234

Document Type

Article; Proceedings Paper

Personal Identifier

scopus

Socpus ID

84887011712 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/84887011712

This document is currently not available here.

Share

COinS