Research on a Feature Enhancement Extraction Method for Underwater Targets Based on Deep Autoencoder Networks
The low-frequency line spectrum of the radiated noise signals of hydroacoustic targets contains features describing the intrinsic properties of the target that make the target susceptible to exposure. In order to extract the line spectral features of underwater acoustic targets, a method combining i...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/4/1341 |
| _version_ | 1797299010711584768 |
|---|---|
| author | Fang Ji Guonan Li Shaoqing Lu Junshuai Ni |
| author_facet | Fang Ji Guonan Li Shaoqing Lu Junshuai Ni |
| author_sort | Fang Ji |
| collection | DOAJ |
| description | The low-frequency line spectrum of the radiated noise signals of hydroacoustic targets contains features describing the intrinsic properties of the target that make the target susceptible to exposure. In order to extract the line spectral features of underwater acoustic targets, a method combining image processing and a deep autoencoder network (DAE) is proposed in this paper to enhance the low-frequency weak line spectrum of underwater targets in an extremely low signal-to-noise ratio environment based on the measured data of large underwater vehicles. A Gauss–Bernoulli restricted Boltzmann machine (G–BRBM) for real-value signal processing was designed and programmed by introducing a greedy algorithm. On this basis, the encoding and decoding mechanism of the DAE network was used to eliminate interference from environmental noise. The weak line spectrum features were effectively enhanced and extracted under an extremely low signal-to-noise ratio of 10–300 Hz, after which the reconstruction results of the line spectrum features were obtained. Data from large underwater vehicles detected by far-field sonar arrays were processed and the results show that the method proposed in this paper was able to adaptively enhance the line spectrum in a data-driven manner. The DAE method was able to achieve more than double the extractable line spectral density in the frequency band of 10–300 Hz. Compared with the traditional feature enhancement extraction method, the DAE method has certain advantages for the extraction of weak line spectra. |
| first_indexed | 2024-03-07T22:44:21Z |
| format | Article |
| id | doaj.art-2f5ecb6bba1b4f8abaefd7de080c6198 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-07T22:44:21Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-2f5ecb6bba1b4f8abaefd7de080c61982024-02-23T15:05:41ZengMDPI AGApplied Sciences2076-34172024-02-01144134110.3390/app14041341Research on a Feature Enhancement Extraction Method for Underwater Targets Based on Deep Autoencoder NetworksFang Ji0Guonan Li1Shaoqing Lu2Junshuai Ni3China Ship Research and Development Academy, Beijing 100192, ChinaChina Ship Research and Development Academy, Beijing 100192, ChinaChina Ship Research and Development Academy, Beijing 100192, ChinaChina Ship Research and Development Academy, Beijing 100192, ChinaThe low-frequency line spectrum of the radiated noise signals of hydroacoustic targets contains features describing the intrinsic properties of the target that make the target susceptible to exposure. In order to extract the line spectral features of underwater acoustic targets, a method combining image processing and a deep autoencoder network (DAE) is proposed in this paper to enhance the low-frequency weak line spectrum of underwater targets in an extremely low signal-to-noise ratio environment based on the measured data of large underwater vehicles. A Gauss–Bernoulli restricted Boltzmann machine (G–BRBM) for real-value signal processing was designed and programmed by introducing a greedy algorithm. On this basis, the encoding and decoding mechanism of the DAE network was used to eliminate interference from environmental noise. The weak line spectrum features were effectively enhanced and extracted under an extremely low signal-to-noise ratio of 10–300 Hz, after which the reconstruction results of the line spectrum features were obtained. Data from large underwater vehicles detected by far-field sonar arrays were processed and the results show that the method proposed in this paper was able to adaptively enhance the line spectrum in a data-driven manner. The DAE method was able to achieve more than double the extractable line spectral density in the frequency band of 10–300 Hz. Compared with the traditional feature enhancement extraction method, the DAE method has certain advantages for the extraction of weak line spectra.https://www.mdpi.com/2076-3417/14/4/1341large underwater vehiclesdeep autoencoder networkvery low signal-to-noise ratioline spectrum enhancement |
| spellingShingle | Fang Ji Guonan Li Shaoqing Lu Junshuai Ni Research on a Feature Enhancement Extraction Method for Underwater Targets Based on Deep Autoencoder Networks Applied Sciences large underwater vehicles deep autoencoder network very low signal-to-noise ratio line spectrum enhancement |
| title | Research on a Feature Enhancement Extraction Method for Underwater Targets Based on Deep Autoencoder Networks |
| title_full | Research on a Feature Enhancement Extraction Method for Underwater Targets Based on Deep Autoencoder Networks |
| title_fullStr | Research on a Feature Enhancement Extraction Method for Underwater Targets Based on Deep Autoencoder Networks |
| title_full_unstemmed | Research on a Feature Enhancement Extraction Method for Underwater Targets Based on Deep Autoencoder Networks |
| title_short | Research on a Feature Enhancement Extraction Method for Underwater Targets Based on Deep Autoencoder Networks |
| title_sort | research on a feature enhancement extraction method for underwater targets based on deep autoencoder networks |
| topic | large underwater vehicles deep autoencoder network very low signal-to-noise ratio line spectrum enhancement |
| url | https://www.mdpi.com/2076-3417/14/4/1341 |
| work_keys_str_mv | AT fangji researchonafeatureenhancementextractionmethodforunderwatertargetsbasedondeepautoencodernetworks AT guonanli researchonafeatureenhancementextractionmethodforunderwatertargetsbasedondeepautoencodernetworks AT shaoqinglu researchonafeatureenhancementextractionmethodforunderwatertargetsbasedondeepautoencodernetworks AT junshuaini researchonafeatureenhancementextractionmethodforunderwatertargetsbasedondeepautoencodernetworks |