Feature Extraction and Classification of Simulated Monostatic Acoustic Echoes from Spherical Targets of Various Materials Using Convolutional Neural Networks

Active sonar target classification remains an ongoing area of research due to the unique challenges associated with the problem (unknown target parameters, dynamic oceanic environment, different scattering mechanisms, etc.). Many feature extraction and classification techniques have been proposed, but there remains a need to relate and explain the classifier results in the physical domain. This work examines convolutional neural networks trained on simulated data with a known ground truth projected onto two time-frequency representations (spectrograms and scalograms). The classifiers were trained to discriminate the target material type, geometry, and internal fluid filling, while the hyperparameters were tuned to the classification task using Bayesian optimization. The trained networks were examined using an explainable artificial intelligence technique, gradient-weighted class activation mapping, to uncover the informative features used in discrimination. This analysis resulted in visual representations that allowed the CNN choices to be related to the physical domain. It was found that the scalogram representation provided a negligible classification accuracy increase compared with the spectrograms. Networks trained to discriminate between target geometries resulted in the highest accuracy, and the networks trained to discriminate the internal fluid of the target resulted in the lowest accuracy.

Automated summary

This study trained convolutional neural networks on simulated data and related and explained the classifier results in the physical domain. The informative features used in discrimination were uncovered using the explainable artificial intelligence technique of gradient-weighted class activation mapping. It was found that the scalogram representation provided a negligible classification accuracy increase compared with the spectrograms, and the networks trained to discriminate between target geometries resulted in the highest accuracy, while the networks trained to discriminate the internal fluid of the target resulted in the lowest accuracy.