An Underwater Acoustic Target Recognition Method Based on AMNet

Wang, Biao; Zhang, Wei; Zhu, Yunan; Wu, Chengxi; Zhang, Shizhen

doi:10.1109/lgrs.2023.3235659

Cited by 19 publications

(10 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Under various impaired conditions of the collected data, Doan et al [11] proposed a dense CNN model that improves classification accuracy over traditional machine learning models. In complex underwater acoustic contexts, Wang et al [12] proposed an AMNet network with a convolutional attention module to improve the performance of the UATR task. Transformer-based models are gradually being introduced for underwater target recognition due to their anti-interference and generalization capabilities.…”

Section: A Underwater Acoustic Target Recognition and Localizationmentioning

confidence: 99%

“…Recognition (Acoustic vs Visual classification): Our Symb-Trans and comparative methods are validated in acoustic and visual classification tasks. We retrained acoustic recognition models, such as AMNet [12], STM [34] and UATR-Transformer [13], on acoustic modality. As well as retrained visual detection models, such as ImageNet [35], Xception [36], and ViT [26], on visual modality.…”

Section: B Underwater Target Recognition and Localizationmentioning

confidence: 99%

See 1 more Smart Citation

Cross-scale cascade transformer for multimodal human action recognition

Liu

Qin

Song

et al. 2023

Pattern Recognition Letters

View full text Add to dashboard Cite

Section: A Underwater Acoustic Target Recognition and Localizationmentioning

confidence: 99%

Section: B Underwater Target Recognition and Localizationmentioning

confidence: 99%

Cross-scale cascade transformer for multimodal human action recognition

Liu

Qin

Song

et al. 2023

Pattern Recognition Letters

View full text Add to dashboard Cite

“…Regarding features for classification and recognition, the power spectrum was often used in early research [ 19 ]. Detection of envelope modulation on noise (DEMON) and low-frequency analysis and recording (LOFAR) are commonly used spectral analysis methods as manually designed features in UATR [ 20 , 21 , 22 , 23 ]. Constant-Q transform (CQT) [ 24 ], Mel frequency cepstral coefficients (MFCC) [ 25 ], and Gammatone frequency cepstral coefficients (GFCC) [ 26 ] also perform well which simulate the auditory perception of human ears.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Based Underwater Acoustic Target Recognition: Introduce a Recent Temporal 2D Modeling Method

Tang,

Gao,

et al. 2024

Sensors

View full text Add to dashboard Cite

In recent years, the application of deep learning models for underwater target recognition has become a popular trend. Most of these are pure 1D models used for processing time-domain signals or pure 2D models used for processing time-frequency spectra. In this paper, a recent temporal 2D modeling method is introduced into the construction of ship radiation noise classification models, combining 1D and 2D. This method is based on the periodic characteristics of time-domain signals, shaping them into 2D signals and discovering long-term correlations between sampling points through 2D convolution to compensate for the limitations of 1D convolution. Integrating this method with the current state-of-the-art model structure and using samples from the Deepship database for network training and testing, it was found that this method could further improve the accuracy (0.9%) and reduce the parameter count (30%), providing a new option for model construction and optimization. Meanwhile, the effectiveness of training models using time-domain signals or time-frequency representations has been compared, finding that the model based on time-domain signals is more sensitive and has a smaller storage footprint (reduced to 30%), whereas the model based on time-frequency representation can achieve higher accuracy (1–2%).

show abstract

“…And the equivalent source method can invert the model parameters based on the magnetic field measurements once the location of the magnetic sources is determined. Ship magnetic field equivalent source models include single magnetic dipole model 9 – 12 , magnetic monopole model 13 , magnetic dipole array model, multiple magnetic dipole model 5 , single ellipsoid model, hybrid ellipsoid and magnetic dipole array model 14 , and long ellipsoid harmonic model 15 . The single magnetic dipole model has fewer unknown parameters, less computational effort, and is suitable for far-field conditions, but cannot accurately simulate the target magnetic field in the near field.…”

Section: Introductionmentioning

confidence: 99%

An improved composite ship magnetic field model with ellipsoid and magnetic dipole arrays

Lu,

Zhang

2024

Sci Rep

View full text Add to dashboard Cite

In order to simultaneously maintain the ship magnetic field modeling accuracy, reduce the number of coefficient matrix conditions and the model computational complexity, an improved composite model is designed by introducing the magnetic dipole array model with a single-axis magnetic moment on the basis of the hybrid ellipsoid and magnetic dipole array model. First, the improved composite model of the ship's magnetic field is established based on the magnetic dipole array model with 3-axis magnetic moment, the magnetic dipole array model with only x-axis magnetic moment, and the ellipsoid model. Secondly, the set of equations for calculating the magnetic moments of the composite model is established, and for the problem of solving the pathological set of equations, the least-squares estimation, stepwise regression method, Tikhonov, and truncated singular value decomposition regularization methods are introduced in terms of the magnetic field, and generalized cross-validation is used to solve the optimal regularization parameters. Finally, a ship model test is designed to compare and analyze the effectiveness of the composite and hybrid models in four aspects: the number of coefficient matrix conditions of the model equation set, the relative error of magnetic field fitting, the relative error of magnetic field extrapolation, and the computational time complexity. The modeling results based on the ship model test data show that the composite model can be used for modeling the magnetic field of ships, and compared with the hybrid model, it reduces the number of coefficient matrix conditions and improves the computational efficiency on the basis of retaining a higher modeling accuracy, and it can be effectively applied in related scientific research and engineering.

show abstract

An Underwater Acoustic Target Recognition Method Based on AMNet

Cited by 19 publications

References 28 publications

Cross-scale cascade transformer for multimodal human action recognition

Cross-scale cascade transformer for multimodal human action recognition

Deep Learning Based Underwater Acoustic Target Recognition: Introduce a Recent Temporal 2D Modeling Method

An improved composite ship magnetic field model with ellipsoid and magnetic dipole arrays

Contact Info

Product

Resources

About