Source localization using deep neural networks in a shallow water environment

Abstract

Deep neural networks (DNNs) are advantageous for representing complex nonlinear relationships. This paper applies DNNs to source localization in a shallow water environment. Two methods are proposed to estimate the range and depth of a broadband source through different neural network architectures. The first adopts the classical two-stage scheme, in which feature extraction and DNN analysis are independent steps. The eigenvectors associated with the modal signal space are extracted as the input feature. Then, the time delay neural network is exploited to model the long term feature representation and constructs the regression model. The second concerns a convolutional neural network-feed-forward neural network (CNN-FNN) architecture, which trains the network directly by taking the raw multi-channel waveforms as input. The CNNs are expected to perform spatial filtering for multi-channel signals, in an operation analogous to time domain filters. The outputs of CNNs are summed as the input to FNN. Several experiments are conducted on the simulated and experimental data to evaluate the performance of the proposed methods. The results demonstrate that DNNs are effective for source localization in complex and varied water environments, especially when there is little precise environmental information.

Machine learning in acoustics: Theory and applications

“…While NNs achieved high accuracy, MFP was challenged by so- The neural network was trained on a large, simulated dataset with various environments. 176 lution ambiguity (Fig. 22).…”

“…42,172 Studies of ocean source localization using ML appeared soon thereafter, 4,152 including applications to experimental data for broadband ship localization, 151 and target characterization. 173 Recently, studies have examined underwater source localization with CNNs 174 and DL, 175,176 taking advantage of 2D data structure, shared weighting, and huge modelgenerated datasets.…”

Underwater Acoustic Research Trends with Machine Learning: Passive SONAR Applications

“…They applied the SBL-based MFP to both the simulated and actually measured sound fields and demonstrated its effectiveness. In addition, Huang et al (2018) used a different type of DNN for the localization of a sound source. The crucial difference between the two proposed DNNs is in the presence of a direct design of features to be used for learning.…”

Sound source ranging using a feed-forward neural network trained with fitting-based early stopping

“…It can have limited performance due to its sensitivity to the mismatch between modelgenerated replica fields and measurements. With the development of machine learning, source localization methods based on machine learning have been revived [7][8][9][10][11] . As early as 1991, Steinberg et al 12 applied perceptrons for source localization in a homogeneous medium.…”