A Fine-Grained Ship-Radiated Noise Recognition System Using Deep Hybrid Neural Networks with Multi-Scale Features
Fine-grained ship-radiated noise recognition methods of different specific ships are in demand for maritime traffic safety and general security. Due to the high background noise and complex transmission channels in the marine environment, the accurate identification of ship radiation noise becomes q...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/8/2068 |
| _version_ | 1797603599173287936 |
|---|---|
| author | Shuai Liu Xiaomei Fu Hong Xu Jiali Zhang Anmin Zhang Qingji Zhou Hao Zhang |
| author_facet | Shuai Liu Xiaomei Fu Hong Xu Jiali Zhang Anmin Zhang Qingji Zhou Hao Zhang |
| author_sort | Shuai Liu |
| collection | DOAJ |
| description | Fine-grained ship-radiated noise recognition methods of different specific ships are in demand for maritime traffic safety and general security. Due to the high background noise and complex transmission channels in the marine environment, the accurate identification of ship radiation noise becomes quite complicated. Existing ship-radiated noise-based recognition systems still have some shortcomings, such as the imperfection of ship-radiated noise feature extraction and recognition algorithms, which lead to distinguishing only the type of ships rather than identifying the specific vessel. To address these issues, we propose a fine-grained ship-radiated noise recognition system that utilizes multi-scale features from the amplitude–frequency–time domain and incorporates a multi-scale feature adaptive generalized network (MFAGNet). In the feature extraction process, to cope with highly non-stationary and non-linear noise signals, the improved Hilbert–Huang transform algorithm applies the permutation entropy-based signal decomposition to perform effective decomposition analysis. Subsequently, six learnable amplitude–time–frequency features are extracted by using six-order decomposed signals, which contain more comprehensive information on the original ship-radiated noise. In the recognition process, MFAGNet is designed by applying unique combinations of one-dimensional convolutional neural networks (1D CNN) and long short-term memory (LSTM) networks. This architecture obtains regional high-level information and aggregate temporal characteristics to enhance the capability to focus on time–frequency information. The experimental results show that MFAGNet is better than other baseline methods and achieves a total accuracy of 98.89% in recognizing 12 different specific noises from ShipsEar. Additionally, other datasets are utilized to validate the universality of the method, which achieves the classification accuracy of 98.90% in four common types of ships. Therefore, the proposed method can efficiently and accurately extract the features of ship-radiated noises. These results suggest that our proposed method, as a novel underwater acoustic recognition technology, is effective for different underwater acoustic signals. |
| first_indexed | 2024-03-11T04:34:16Z |
| format | Article |
| id | doaj.art-a76b96dbf1cc4417bbb4f774d8dc9495 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T04:34:16Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-a76b96dbf1cc4417bbb4f774d8dc94952023-11-17T21:11:36ZengMDPI AGRemote Sensing2072-42922023-04-01158206810.3390/rs15082068A Fine-Grained Ship-Radiated Noise Recognition System Using Deep Hybrid Neural Networks with Multi-Scale FeaturesShuai Liu0Xiaomei Fu1Hong Xu2Jiali Zhang3Anmin Zhang4Qingji Zhou5Hao Zhang6School of Marine Science and Technology, Tianjin University, Tianjin 300072, ChinaSchool of Marine Science and Technology, Tianjin University, Tianjin 300072, ChinaSchool of Social Sciences, Nanyang Technological University, Singapore 639798, SingaporeSchool of Marine Science and Technology, Tianjin University, Tianjin 300072, ChinaSchool of Marine Science and Technology, Tianjin University, Tianjin 300072, ChinaSchool of Marine Science and Technology, Tianjin University, Tianjin 300072, ChinaSchool of Marine Science and Technology, Tianjin University, Tianjin 300072, ChinaFine-grained ship-radiated noise recognition methods of different specific ships are in demand for maritime traffic safety and general security. Due to the high background noise and complex transmission channels in the marine environment, the accurate identification of ship radiation noise becomes quite complicated. Existing ship-radiated noise-based recognition systems still have some shortcomings, such as the imperfection of ship-radiated noise feature extraction and recognition algorithms, which lead to distinguishing only the type of ships rather than identifying the specific vessel. To address these issues, we propose a fine-grained ship-radiated noise recognition system that utilizes multi-scale features from the amplitude–frequency–time domain and incorporates a multi-scale feature adaptive generalized network (MFAGNet). In the feature extraction process, to cope with highly non-stationary and non-linear noise signals, the improved Hilbert–Huang transform algorithm applies the permutation entropy-based signal decomposition to perform effective decomposition analysis. Subsequently, six learnable amplitude–time–frequency features are extracted by using six-order decomposed signals, which contain more comprehensive information on the original ship-radiated noise. In the recognition process, MFAGNet is designed by applying unique combinations of one-dimensional convolutional neural networks (1D CNN) and long short-term memory (LSTM) networks. This architecture obtains regional high-level information and aggregate temporal characteristics to enhance the capability to focus on time–frequency information. The experimental results show that MFAGNet is better than other baseline methods and achieves a total accuracy of 98.89% in recognizing 12 different specific noises from ShipsEar. Additionally, other datasets are utilized to validate the universality of the method, which achieves the classification accuracy of 98.90% in four common types of ships. Therefore, the proposed method can efficiently and accurately extract the features of ship-radiated noises. These results suggest that our proposed method, as a novel underwater acoustic recognition technology, is effective for different underwater acoustic signals.https://www.mdpi.com/2072-4292/15/8/2068ship-radiated noise recognitionunderwater acousticsmuti-scale featuresartificial intelligencefeature extractiondeep learning |
| spellingShingle | Shuai Liu Xiaomei Fu Hong Xu Jiali Zhang Anmin Zhang Qingji Zhou Hao Zhang A Fine-Grained Ship-Radiated Noise Recognition System Using Deep Hybrid Neural Networks with Multi-Scale Features Remote Sensing ship-radiated noise recognition underwater acoustics muti-scale features artificial intelligence feature extraction deep learning |
| title | A Fine-Grained Ship-Radiated Noise Recognition System Using Deep Hybrid Neural Networks with Multi-Scale Features |
| title_full | A Fine-Grained Ship-Radiated Noise Recognition System Using Deep Hybrid Neural Networks with Multi-Scale Features |
| title_fullStr | A Fine-Grained Ship-Radiated Noise Recognition System Using Deep Hybrid Neural Networks with Multi-Scale Features |
| title_full_unstemmed | A Fine-Grained Ship-Radiated Noise Recognition System Using Deep Hybrid Neural Networks with Multi-Scale Features |
| title_short | A Fine-Grained Ship-Radiated Noise Recognition System Using Deep Hybrid Neural Networks with Multi-Scale Features |
| title_sort | fine grained ship radiated noise recognition system using deep hybrid neural networks with multi scale features |
| topic | ship-radiated noise recognition underwater acoustics muti-scale features artificial intelligence feature extraction deep learning |
| url | https://www.mdpi.com/2072-4292/15/8/2068 |
| work_keys_str_mv | AT shuailiu afinegrainedshipradiatednoiserecognitionsystemusingdeephybridneuralnetworkswithmultiscalefeatures AT xiaomeifu afinegrainedshipradiatednoiserecognitionsystemusingdeephybridneuralnetworkswithmultiscalefeatures AT hongxu afinegrainedshipradiatednoiserecognitionsystemusingdeephybridneuralnetworkswithmultiscalefeatures AT jializhang afinegrainedshipradiatednoiserecognitionsystemusingdeephybridneuralnetworkswithmultiscalefeatures AT anminzhang afinegrainedshipradiatednoiserecognitionsystemusingdeephybridneuralnetworkswithmultiscalefeatures AT qingjizhou afinegrainedshipradiatednoiserecognitionsystemusingdeephybridneuralnetworkswithmultiscalefeatures AT haozhang afinegrainedshipradiatednoiserecognitionsystemusingdeephybridneuralnetworkswithmultiscalefeatures AT shuailiu finegrainedshipradiatednoiserecognitionsystemusingdeephybridneuralnetworkswithmultiscalefeatures AT xiaomeifu finegrainedshipradiatednoiserecognitionsystemusingdeephybridneuralnetworkswithmultiscalefeatures AT hongxu finegrainedshipradiatednoiserecognitionsystemusingdeephybridneuralnetworkswithmultiscalefeatures AT jializhang finegrainedshipradiatednoiserecognitionsystemusingdeephybridneuralnetworkswithmultiscalefeatures AT anminzhang finegrainedshipradiatednoiserecognitionsystemusingdeephybridneuralnetworkswithmultiscalefeatures AT qingjizhou finegrainedshipradiatednoiserecognitionsystemusingdeephybridneuralnetworkswithmultiscalefeatures AT haozhang finegrainedshipradiatednoiserecognitionsystemusingdeephybridneuralnetworkswithmultiscalefeatures |