Passive Shallow Water Automated Target Recognition using Deep Convolutional Bi directional Long Short Term Memory

  • Suraj Kamal Department of Electronics, Cochin University of Science and Technology, Kochi - 682 022 https://orcid.org/0000-0002-6561-0155
  • C. Satheesh Chandran Department of Electronics, Cochin University of Science and Technology, Kochi - 682 022 https://orcid.org/0000-0003-0728-0941
  • H.M. Supriya Department of Electronics, Cochin University of Science and Technology, Kochi - 682 022
Keywords: Shallow waters, Passive sonar, Automated target recognition, CNN, LSTM

Abstract

The extremely challenging nature of passive acoustic surveillance makes it a key area of research in Naval
Non-Co-operative Target Recognition especially in Anti-Submarine Warfare systems. In shallow waters, the
complex acoustics due to the highly varying ambient background noise as well as the multi-modal propagation in the surface-bottom bounded channel makes surveillance even difficult. In this work, an ensemble of Convolutional Neural Networks and Bidirectional Long Short Term Memory stages employing soft attention is used to effectively capture the spectro-temporal dynamics of the target signature. In order to alleviate the overall computational cost associated with the optimal model search in the extensive hyperparameter space, a recursive model elimination scheme, making frugal use of the available resources, is also proposed. Experimental analysis on acoustic target records, collected from the shallows of Arabian Sea, has yielded encouraging results in terms of model accuracy, precision and recall.

Published
2021-02-01
How to Cite
Kamal, S., Chandran, C. S., & Supriya, H. (2021). Passive Shallow Water Automated Target Recognition using Deep Convolutional Bi directional Long Short Term Memory. Defence Science Journal, 71(1), 117-123. https://doi.org/10.14429/dsj.71.14929
Section
Naval Systems