|
|
|
|
LEADER |
02121nam a2200421Ia 4500 |
001 |
10.1121-1.5116016 |
008 |
220511s2019 CNT 000 0 und d |
020 |
|
|
|a 00014966 (ISSN)
|
245 |
1 |
0 |
|a Deep-learning source localization using multi-frequency magnitude-only data
|
260 |
|
0 |
|b Acoustical Society of America
|c 2019
|
856 |
|
|
|z View Fulltext in Publisher
|u https://doi.org/10.1121/1.5116016
|
520 |
3 |
|
|a A deep learning approach based on big data is proposed to locate broadband acoustic sources using a single hydrophone in ocean waveguides with uncertain bottom parameters. Several 50-layer residual neural networks, trained on a huge number of sound field replicas generated by an acoustic propagation model, are used to handle the bottom uncertainty in source localization. A two-step training strategy is presented to improve the training of the deep models. First, the range is discretized in a coarse (5 km) grid. Subsequently, the source range within the selected interval and source depth are discretized on a finer (0.1 km and 2 m) grid. The deep learning methods were demonstrated for simulated magnitude-only multi-frequency data in uncertain environments. Experimental data from the China Yellow Sea also validated the approach. © 2019 Acoustical Society of America.
|
650 |
0 |
4 |
|a Acoustic fields
|
650 |
0 |
4 |
|a Acoustic propagation
|
650 |
0 |
4 |
|a article
|
650 |
0 |
4 |
|a Backpropagation
|
650 |
0 |
4 |
|a Broadband acoustic source
|
650 |
0 |
4 |
|a China
|
650 |
0 |
4 |
|a deep learning
|
650 |
0 |
4 |
|a Deep learning
|
650 |
0 |
4 |
|a Learning approach
|
650 |
0 |
4 |
|a Learning sources
|
650 |
0 |
4 |
|a Magnitude only data
|
650 |
0 |
4 |
|a simulation
|
650 |
0 |
4 |
|a sound
|
650 |
0 |
4 |
|a Source localization
|
650 |
0 |
4 |
|a Two-step training
|
650 |
0 |
4 |
|a Uncertain environments
|
650 |
0 |
4 |
|a uncertainty
|
650 |
0 |
4 |
|a Uncertainty analysis
|
650 |
0 |
4 |
|a Yellow Sea
|
700 |
1 |
|
|a Gerstoft, P.
|e author
|
700 |
1 |
|
|a Gong, Z.
|e author
|
700 |
1 |
|
|a Li, Z.
|e author
|
700 |
1 |
|
|a Niu, H.
|e author
|
700 |
1 |
|
|a Ozanich, E.
|e author
|
700 |
1 |
|
|a Wang, H.
|e author
|
773 |
|
|
|t Journal of the Acoustical Society of America
|