Performance of EMI based mine detection using back-propagation neural networks

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 SStatistic 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. Key-words: Mine Detection, Back-Propagation, δ-Technique, S-Statistic, False Alarm Filtering.