SSANet: normal-mode interference spectrum extraction via SSA algorithm-unrolled neural network
In ocean acoustic fields, extracting the normal-mode interference spectrum (NMIS) from the received sound intensity spectrum (SIS) plays an important role in waveguide-invariant estimation and underwater source ranging. However, the received SIS often has a low signal-to-noise ratio (SNR) owing to o...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-02-01
|
| Series: | Frontiers in Marine Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmars.2023.1342090/full |
| _version_ | 1827367374379024384 |
|---|---|
| author | Shuping Zhu Wei Gao Xiaolei Li |
| author_facet | Shuping Zhu Wei Gao Xiaolei Li |
| author_sort | Shuping Zhu |
| collection | DOAJ |
| description | In ocean acoustic fields, extracting the normal-mode interference spectrum (NMIS) from the received sound intensity spectrum (SIS) plays an important role in waveguide-invariant estimation and underwater source ranging. However, the received SIS often has a low signal-to-noise ratio (SNR) owing to ocean ambient noise and the limitations of the received equipment. This can lead to significant performance degradation for the traditional methods of extracting NMIS at low SNR conditions. To address this issue, a new deep neural network model called SSANet is proposed to obtain NMIS based on unrolling the traditional singular spectrum analysis (SSA) algorithm. First, the steps of embedding and singular value decomposition (SVD) in SSA is achieved by the convolutional network. Second, the grouping step of the SSA is simulated using the matrix multiply weight layer, ReLU layer, point multiply weight layer and matrix multiply weight layer. Third, the diagonal averaging step was implemented using a fully connected network. Simulation results in canonical ocean waveguide environments demonstrate that SSANet outperforms other traditional methods such as Fourier transform (FT), multiple signal classification (MUSIC), and SSA in terms of root mean square error, mean absolute error, and extraction performance. |
| first_indexed | 2024-03-08T09:06:39Z |
| format | Article |
| id | doaj.art-a5223c7758c24334ac71f6e679a23cf9 |
| institution | Directory Open Access Journal |
| issn | 2296-7745 |
| language | English |
| last_indexed | 2024-03-08T09:06:39Z |
| publishDate | 2024-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Marine Science |
| spelling | doaj.art-a5223c7758c24334ac71f6e679a23cf92024-02-01T04:42:34ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452024-02-011010.3389/fmars.2023.13420901342090SSANet: normal-mode interference spectrum extraction via SSA algorithm-unrolled neural networkShuping ZhuWei GaoXiaolei LiIn ocean acoustic fields, extracting the normal-mode interference spectrum (NMIS) from the received sound intensity spectrum (SIS) plays an important role in waveguide-invariant estimation and underwater source ranging. However, the received SIS often has a low signal-to-noise ratio (SNR) owing to ocean ambient noise and the limitations of the received equipment. This can lead to significant performance degradation for the traditional methods of extracting NMIS at low SNR conditions. To address this issue, a new deep neural network model called SSANet is proposed to obtain NMIS based on unrolling the traditional singular spectrum analysis (SSA) algorithm. First, the steps of embedding and singular value decomposition (SVD) in SSA is achieved by the convolutional network. Second, the grouping step of the SSA is simulated using the matrix multiply weight layer, ReLU layer, point multiply weight layer and matrix multiply weight layer. Third, the diagonal averaging step was implemented using a fully connected network. Simulation results in canonical ocean waveguide environments demonstrate that SSANet outperforms other traditional methods such as Fourier transform (FT), multiple signal classification (MUSIC), and SSA in terms of root mean square error, mean absolute error, and extraction performance.https://www.frontiersin.org/articles/10.3389/fmars.2023.1342090/fullnormal-mode interference spectrumsingular spectrum analysisdeep unrolled neural networklow signal-to-noise ratioocean acoustic waveguide |
| spellingShingle | Shuping Zhu Wei Gao Xiaolei Li SSANet: normal-mode interference spectrum extraction via SSA algorithm-unrolled neural network Frontiers in Marine Science normal-mode interference spectrum singular spectrum analysis deep unrolled neural network low signal-to-noise ratio ocean acoustic waveguide |
| title | SSANet: normal-mode interference spectrum extraction via SSA algorithm-unrolled neural network |
| title_full | SSANet: normal-mode interference spectrum extraction via SSA algorithm-unrolled neural network |
| title_fullStr | SSANet: normal-mode interference spectrum extraction via SSA algorithm-unrolled neural network |
| title_full_unstemmed | SSANet: normal-mode interference spectrum extraction via SSA algorithm-unrolled neural network |
| title_short | SSANet: normal-mode interference spectrum extraction via SSA algorithm-unrolled neural network |
| title_sort | ssanet normal mode interference spectrum extraction via ssa algorithm unrolled neural network |
| topic | normal-mode interference spectrum singular spectrum analysis deep unrolled neural network low signal-to-noise ratio ocean acoustic waveguide |
| url | https://www.frontiersin.org/articles/10.3389/fmars.2023.1342090/full |
| work_keys_str_mv | AT shupingzhu ssanetnormalmodeinterferencespectrumextractionviassaalgorithmunrolledneuralnetwork AT weigao ssanetnormalmodeinterferencespectrumextractionviassaalgorithmunrolledneuralnetwork AT xiaoleili ssanetnormalmodeinterferencespectrumextractionviassaalgorithmunrolledneuralnetwork |