Underwater Acoustic Target Recognition with a Residual Network and the Optimized Feature Extraction Method

Hong, Feng; Li, Chengwei; Guo, Lijuan; Chen, Feng; Feng, Huihui

doi:10.3390/app11041442

Cited by 51 publications

(18 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep belief networks [33] were also applied to the same signals and obtained an accuracy up to 96.96%, while the overall accuracy of CNN models was 94.75%. Hong et al [34] used the ShipsEar acoustic database in order to train and classify underwater targets using an 18-layer residual network (ResNet18) combined with a feature extraction method based upon the use of the mel-frequency cepstral coefficients (MFCC) and log mel methods. The work achieved 94.3% in class accuracy.…”

Section: Related Workmentioning

confidence: 99%

Deep Learning Models for Passive Sonar Signal Classification of Military Data

Fernandes¹,

Moura²,

Seixas³

2022

Remote Sensing

View full text Add to dashboard Cite

The noise radiated from ships can be used for their identification and classification using passive sonar systems. Several techniques have been proposed for military ship classification based on acoustic signatures, which can be acquired through controlled experiments performed in an acoustic lane. The cost for such data acquisition is a significant issue since the ship and crew have to be dislocated from the fleet. In addition, the experiments have to be repeated for different operational conditions, taking a considerable amount of time. Even with this massive effort, the scarce amount of data produced by these controlled experiments may limit further detailed analyses. In this paper, deep learning models are used for full exploitation of such acquired data, envisaging passive sonar signal classification. A drawback of such models is the large number of parameters, which requires extensive data volumes for parameter tuning along the training phase. Thus, generative adversarial networks (GANs) are used to synthesize data so that a larger data volume can be produced for training convolutional neural networks (CNNs), which are used for the classification task. Different GAN design approaches were evaluated and both maximum probability and class-expert strategies were exploited for signal classification. Special attention was paid to how the expert knowledge might give a handle on analyzing the performance of the various deep learning models through tests that mirrored actual deployment. An accuracy as high as 99.0±0.4% was achieved using experimental data, which improves upon previous machine learning designs in the field.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Learning Models for Passive Sonar Signal Classification of Military Data

Fernandes¹,

Moura²,

Seixas³

2022

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…However, the above CNN model extracts single-scale features with the fixed size of the convolution kernel, which lose a lot of feature information. Hong [ 14 ] proposes a deep convolution stack network with a multi-scale residual unit (MSRU) to extract multi-scale features while exploring using generative adversarial networks (GAN) to synthesize underwater acoustic waveforms. The method modifies two advanced GAN models and improves their performance.…”

Section: Introductionmentioning

confidence: 99%

A Novel Deep-Learning Method with Channel Attention Mechanism for Underwater Target Recognition

Lingzhi

Zeng

Jin

2022

Sensors

View full text Add to dashboard Cite

The core of underwater acoustic recognition is to extract the spectral features of targets. The running speed and track of the targets usually result in a Doppler shift, which poses significant challenges for recognizing targets with different Doppler frequencies. This paper proposes deep learning with a channel attention mechanism approach for underwater acoustic recognition. It is based on three crucial designs. Feature structures can obtain high-dimensional underwater acoustic data. The feature extraction model is the most important. First, we develop a ResNet to extract the deep abstraction spectral features of the targets. Then, the channel attention mechanism is introduced in the camResNet to enhance the energy of stable spectral features of residual convolution. This is conducive to subtly represent the inherent characteristics of the targets. Moreover, a feature classification approach based on one-dimensional convolution is applied to recognize targets. We evaluate our approach on challenging data containing four kinds of underwater acoustic targets with different working conditions. Our experiments show that the proposed approach achieves the best recognition accuracy (98.2%) compared with the other approaches. Moreover, the proposed approach is better than the ResNet with a widely used channel attention mechanism for data with different working conditions.

show abstract

“…Li et al [ 5 ] introduced slope entropy into underwater acoustic signal processing to obtain higher recognition rate. Hong et al [ 6 ] used fused features to train an 18-layer residual neural network containing the central loss function of the embedding layer (namely ResNet18 in this paper) and adopted various strategies to prevent model overfitting, which improved the accuracy to 94.3% on the ShipsEar dataset. Hong et al [ 6 ] used a joint loss function containing a central loss function to monitor the characteristics of different underwater acoustic targets.…”

Section: Introductionmentioning

confidence: 99%

“…Hong et al [ 6 ] used fused features to train an 18-layer residual neural network containing the central loss function of the embedding layer (namely ResNet18 in this paper) and adopted various strategies to prevent model overfitting, which improved the accuracy to 94.3% on the ShipsEar dataset. Hong et al [ 6 ] used a joint loss function containing a central loss function to monitor the characteristics of different underwater acoustic targets. However, using the joint loss function will equally monitor all features, including ocean background noise and other interference information, reducing the network’s recognition effect.…”

Section: Introductionmentioning

confidence: 99%

Underwater Acoustic Target Recognition Based on Attention Residual Network

Bao-xiang

Cui

et al. 2022

Entropy

View full text Add to dashboard Cite

Underwater acoustic target recognition is very complex due to the lack of labeled data sets, the complexity of the marine environment, and the interference of background noise. In order to enhance it, we propose an attention-based residual network recognition method (AResnet). The method can be used to identify ship-radiated noise in different environments. Firstly, a residual network is used to extract the deep abstract features of three-dimensional fusion features, and then a channel attention module is used to enhance different channels. Finally, the features are classified by the joint supervision of cross-entropy and central loss functions. At the same time, for the recognition of ship-radiated noise in other environments, we use the pre-training network AResnet to extract the deep acoustic features and apply the network structure to underwater acoustic target recognition after fine-tuning. The two sets of ship radiation noise datasets are verified, the DeepShip dataset is trained and verified, and the average recognition accuracy is 99%. Then, the trained AResnet structure is fine-tuned and applied to the ShipsEar dataset. The average recognition accuracy is 98%, which is better than the comparison method.

show abstract

Underwater Acoustic Target Recognition with a Residual Network and the Optimized Feature Extraction Method

Cited by 51 publications

References 20 publications

Deep Learning Models for Passive Sonar Signal Classification of Military Data

Deep Learning Models for Passive Sonar Signal Classification of Military Data

A Novel Deep-Learning Method with Channel Attention Mechanism for Underwater Target Recognition

Underwater Acoustic Target Recognition Based on Attention Residual Network

Contact Info

Product

Resources

About