kumoh national institute of technology
Networked Systems Lab.

V.S. Doan, T. Huynh-The, D. S. Kim, "Underwater Acoustic Target Classification based on Dense Convolutional Neural Network", IEEE Geoscience and Remote Sensing Letters, (Early Access), pp.1-5, Oct. 2020. DOI: 10.1109/LGRS.2020.3029584
By :
Date : 2020-10-03
Views : 230

In oceanic remote sensing operations, underwater acoustic target recognition is always a difficult and extremely important task of sonar systems, especially in the condition of complex sound wave propagation characteristics. The expensively learning recognition model for big data analysis is typically an obstacle for most traditional machine learning (ML) algorithms, whereas the convolutional neural network (CNN), a type of deep neural network, can automatically extract features for accurate classification. In this study, we propose an approach using a dense CNN model for underwater target recognition. The network architecture is designed to cleverly reuse all former feature maps to optimize classification rates under various impaired conditions while satisfying low computational cost. In addition, instead of using time-frequency spectrogram images, the proposed scheme allows directly utilizing the original audio signal in the time domain as the network input data. Based on the experimental results evaluated on the real-world data set of passive sonar, our classification model achieves the overall accuracy of 98.85% at 0-dB signal-to-noise ratio (SNR) and outperforms traditional ML techniques, as well as other state-of-the-art CNN models.

Final review comments,
Reviewer: 1

Comments to the Author
The authors have addressed all my previous comments.
I recommend the publication of this manuscript.

Reviewer: 2

Comments to the Author
I very much appreciate the author's careful and thoughtful responses to the reviewer comments. I am satisfied with their revisions and the paper can be published as is or with minor revision. I have one suggestion, that if using absolute times to describe complexity (e.g. final paragraph of revision) that the authors have some sort of statistical description of the simulations like standard deviation from multiple runs. Otherwise it is difficult to distinguish run-run variation.