Translator Disclaimer
Paper
21 September 2004 Holographic neural networks versus conventional neural networks: a comparative evaluation for the classification of landmine targets in ground-penetrating radar images
Author Affiliations +
Abstract
This paper evaluates the performance of a holographic neural network in comparison with a conventional feedforward backpropagation neural network for the classification of landmine targets in ground penetrating radar images. The data used in the study was acquired from four different test sites using the landmine detection system developed by General Dynamics Canada Ltd., in collaboration with the Defense Research and Development Canada, Suffield. A set of seven features extracted for each detected alarm is used as stimulus inputs for the networks. The recall responses of the networks are then evaluated against the ground truth to declare true or false detections. The area computed under the receiver operating characteristic curve is used for comparative purposes. With a large dataset comprising of data from multiple sites, both the holographic and conventional networks showed comparable trends in recall accuracies with area values of 0.88 and 0.87, respectively. By using independent validation datasets, the holographic network’s generalization performance was observed to be better (mean area = 0.86) as compared to the conventional network (mean area = 0.82). Despite the widely publicized theoretical advantages of the holographic technology, use of more than the required number of cortical memory elements resulted in an over-fitting phenomenon of the holographic network.
© (2004) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Naga R. Mudigonda, Ray Kacelenga, and Mark Edwards "Holographic neural networks versus conventional neural networks: a comparative evaluation for the classification of landmine targets in ground-penetrating radar images", Proc. SPIE 5415, Detection and Remediation Technologies for Mines and Minelike Targets IX, (21 September 2004); https://doi.org/10.1117/12.532532
PROCEEDINGS
12 PAGES


SHARE
Advertisement
Advertisement
Back to Top