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
Copyright Status
Unknown
Socpus ID
84887011712 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84887011712
STARS Citation
Draper, Matthew and Kocak, Taskin, "Performance Of Emi Based Mine Detection Using Back-Propagation Neural Networks" (2007). Scopus Export 2000s. 5943.
https://stars.library.ucf.edu/scopus2000/5943