Array-based underwater acoustic target classification with spectrum reconstruction based on joint sparsity and frequency shift invariant feature
The target spectrum, which is commonly used in feature extraction for underwater acoustic target classification, can be improperly recovered via conventional beamformer (CBF) owing to its frequency-variant spatial response and lead to degraded classification performance. In this paper, we propose a...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/171689 |
| _version_ | 1826117475503177728 |
|---|---|
| author | Lu, Chenxiang Zeng, Xiangyang Wang, Qiang Wang, Lu Jin, Anqi |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Lu, Chenxiang Zeng, Xiangyang Wang, Qiang Wang, Lu Jin, Anqi |
| author_sort | Lu, Chenxiang |
| collection | NTU |
| description | The target spectrum, which is commonly used in feature extraction for underwater acoustic target classification, can be improperly recovered via conventional beamformer (CBF) owing to its frequency-variant spatial response and lead to degraded classification performance. In this paper, we propose a target spectrum reconstruction method under a sparse Bayesian learning framework with joint sparsity priors that can not only achieve high-resolution target separation in the angular domain but also attain beamwidth constancy over a frequency range at no cost of reducing angular resolution. Experiments on real measured array data show the recovered spectrum via our proposed method can effectively suppress interference and preserve more detailed spectral structures than CBF. This indicates our method is more suitable for target classification because it has the capability of retaining more representative and discriminative characteristics. Moreover, due to target motion and the underwater channel effect, the frequency of prominent spectral line components can be shifted over time, which is harmful to classification performance. To overcome this problem, we proposed a frequency shift-invariant feature extraction method with the help of elaborately designed frequency shift-invariant filter banks. The classification experiments demonstrate that our proposed methods outperform traditional CBF and Mel-frequency features and can help improve underwater recognition performance. |
| first_indexed | 2024-10-01T04:28:12Z |
| format | Journal Article |
| id | ntu-10356/171689 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:28:12Z |
| publishDate | 2023 |
| record_format | dspace |
| spelling | ntu-10356/1716892023-11-10T15:40:28Z Array-based underwater acoustic target classification with spectrum reconstruction based on joint sparsity and frequency shift invariant feature Lu, Chenxiang Zeng, Xiangyang Wang, Qiang Wang, Lu Jin, Anqi School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Array Signal Processing Structured Sparsity The target spectrum, which is commonly used in feature extraction for underwater acoustic target classification, can be improperly recovered via conventional beamformer (CBF) owing to its frequency-variant spatial response and lead to degraded classification performance. In this paper, we propose a target spectrum reconstruction method under a sparse Bayesian learning framework with joint sparsity priors that can not only achieve high-resolution target separation in the angular domain but also attain beamwidth constancy over a frequency range at no cost of reducing angular resolution. Experiments on real measured array data show the recovered spectrum via our proposed method can effectively suppress interference and preserve more detailed spectral structures than CBF. This indicates our method is more suitable for target classification because it has the capability of retaining more representative and discriminative characteristics. Moreover, due to target motion and the underwater channel effect, the frequency of prominent spectral line components can be shifted over time, which is harmful to classification performance. To overcome this problem, we proposed a frequency shift-invariant feature extraction method with the help of elaborately designed frequency shift-invariant filter banks. The classification experiments demonstrate that our proposed methods outperform traditional CBF and Mel-frequency features and can help improve underwater recognition performance. Published version This research was funded by the National Natural Science Foundation of China under grant number 52271351. 2023-11-06T01:08:31Z 2023-11-06T01:08:31Z 2023 Journal Article Lu, C., Zeng, X., Wang, Q., Wang, L. & Jin, A. (2023). Array-based underwater acoustic target classification with spectrum reconstruction based on joint sparsity and frequency shift invariant feature. Journal of Marine Science and Engineering, 11(6), 1101-. https://dx.doi.org/10.3390/jmse11061101 2077-1312 https://hdl.handle.net/10356/171689 10.3390/jmse11061101 2-s2.0-85164177383 6 11 1101 en Journal of Marine Science and Engineering © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https:// creativecommons.org/licenses/by/ 4.0/). application/pdf |
| spellingShingle | Engineering::Electrical and electronic engineering Array Signal Processing Structured Sparsity Lu, Chenxiang Zeng, Xiangyang Wang, Qiang Wang, Lu Jin, Anqi Array-based underwater acoustic target classification with spectrum reconstruction based on joint sparsity and frequency shift invariant feature |
| title | Array-based underwater acoustic target classification with spectrum reconstruction based on joint sparsity and frequency shift invariant feature |
| title_full | Array-based underwater acoustic target classification with spectrum reconstruction based on joint sparsity and frequency shift invariant feature |
| title_fullStr | Array-based underwater acoustic target classification with spectrum reconstruction based on joint sparsity and frequency shift invariant feature |
| title_full_unstemmed | Array-based underwater acoustic target classification with spectrum reconstruction based on joint sparsity and frequency shift invariant feature |
| title_short | Array-based underwater acoustic target classification with spectrum reconstruction based on joint sparsity and frequency shift invariant feature |
| title_sort | array based underwater acoustic target classification with spectrum reconstruction based on joint sparsity and frequency shift invariant feature |
| topic | Engineering::Electrical and electronic engineering Array Signal Processing Structured Sparsity |
| url | https://hdl.handle.net/10356/171689 |
| work_keys_str_mv | AT luchenxiang arraybasedunderwateracoustictargetclassificationwithspectrumreconstructionbasedonjointsparsityandfrequencyshiftinvariantfeature AT zengxiangyang arraybasedunderwateracoustictargetclassificationwithspectrumreconstructionbasedonjointsparsityandfrequencyshiftinvariantfeature AT wangqiang arraybasedunderwateracoustictargetclassificationwithspectrumreconstructionbasedonjointsparsityandfrequencyshiftinvariantfeature AT wanglu arraybasedunderwateracoustictargetclassificationwithspectrumreconstructionbasedonjointsparsityandfrequencyshiftinvariantfeature AT jinanqi arraybasedunderwateracoustictargetclassificationwithspectrumreconstructionbasedonjointsparsityandfrequencyshiftinvariantfeature |