Underwater Acoustic Target Recognition Research Articles

Mobile_ViT: Underwater Acoustic Target Recognition Method Based on Local–Global Feature Fusion

To overcome the challenges of inadequate representation and ineffective information exchange stemming from feature homogenization in underwater acoustic target recognition, we introduce a hybrid network named Mobile_ViT, which synergizes MobileNet and Transformer architectures. The network begins with a convolutional backbone incorporating an embedded coordinate attention mechanism to enhance the local details of inputs. This mechanism captures the long-term temporal dependencies and precise frequency–domain relationships of signals, focusing the features on the time–frequency positions. Subsequently, the Transformer’s Encoder is integrated at the end of the backbone to facilitate global characterization, thus effectively overcoming the convolutional neural network’s shortcomings in capturing long-range feature dependencies. Evaluation on the Shipsear and DeepShip datasets yields accuracies of 98.50% and 94.57%, respectively, marking a substantial improvement over the baseline. Notably, the proposed method also demonstrates obvious separation coefficients, signifying enhanced clustering effectiveness, and is lighter than other Transformers.

An Underwater Acoustic Target Recognition Method Based on Transfer Learning

An Underwater Acoustic Target Recognition Method Based on Transfer Learning

Unraveling complex data diversity in underwater acoustic target recognition through convolution-based mixture of experts

Underwater acoustic target recognition is a difficult task owing to the intricate nature of underwater acoustic signals. The complex underwater environments, unpredictable transmission channels, and dynamic motion states greatly impact the real-world underwater acoustic signals, and may even obscure the intrinsic characteristics related to targets. Consequently, the data distribution of underwater acoustic signals exhibits high intra-class diversity, thereby compromising the accuracy and robustness of recognition systems. To address these issues, this work proposes a convolution-based mixture of experts (CMoE) that recognizes underwater targets in a fine-grained manner. The proposed technique introduces multiple expert layers as independent learners, along with a routing layer that determines the assignment of experts according to the characteristics of inputs. This design allows the model to utilize independent parameter spaces, facilitating the learning of complex underwater signals with high intra-class diversity. Furthermore, this work optimizes the CMoE structure by balancing regularization and an optional residual module. To validate the efficacy of our proposed techniques, we conducted detailed experiments and visualization analyses on three underwater acoustic databases across several acoustic features. The experimental results demonstrate that our CMoE consistently achieves significant performance improvements, delivering superior recognition accuracy when compared to existing advanced methods.

Cross-Domain Contrastive Learning-Based Few-Shot Underwater Acoustic Target Recognition

Underwater Acoustic Target Recognition (UATR) plays a crucial role in underwater detection devices. However, due to the difficulty and high cost of collecting data in the underwater environment, UATR still faces the problem of small datasets. Few-shot learning (FSL) addresses this challenge through techniques such as Siamese networks and prototypical networks. However, it also suffers from the issue of overfitting, which leads to catastrophic forgetting and performance degradation. Current underwater FSL methods primarily focus on mining similar information within sample pairs, ignoring the unique features of ship radiation noise. This study proposes a novel cross-domain contrastive learning-based few-shot (CDCF) method for UATR to alleviate overfitting issues. This approach leverages self-supervised training on both source and target domains to facilitate rapid adaptation to the target domain. Additionally, a base contrastive module is introduced. Positive and negative sample pairs are generated through data augmentation, and the similarity in the corresponding frequency bands of feature embedding is utilized to learn fine-grained features of ship radiation noise, thereby expanding the scope of knowledge in the source domain. We evaluate the performance of CDCF in diverse scenarios on ShipsEar and DeepShip datasets. The experimental results indicate that in cross-domain environments, the model achieves accuracy rates of 56.71%, 73.02%, and 76.93% for 1-shot, 3-shot, and 5-shot scenarios, respectively, outperforming other FSL methods. Moreover, the model demonstrates outstanding performance in noisy environments.

Underwater acoustic target recognition based on knowledge distillation under working conditions mismatching

Underwater acoustic target recognition based on knowledge distillation under working conditions mismatching

Underwater acoustic target recognition method based on WA-DS decision fusion

Deep learning methods can recognize the various underwater acoustic targets in complex marine environments. In this study, we apply deep learning methods in decision recognition of underwater acoustic targets. However, decision recognition methods rely on a complex evidence theory that combines the probabilities of various scenarios as evidence sources, and in the process of combination produces conflicting evidence. For this reason, we propose an underwater acoustic target recognition method based on weighted average Dempster -Shafer (WA-DS) decision fusion, which replaces anomalous evidence with weighted average evidence, and solves the problem of synthesizing anomalous evidence. Firstly, the underwater acoustic dataset is preprocessed with downsampling, denoising, and audio segmentation. Then, the Mel-frequency cepstral coefficients (MFCC), Gammatone frequency cepstral coefficients (GFCC), and time–frequency (TF) features are extracted, and the category probabilities are output using the ResNet18 network to learn and train the multi-feature and then output the category probabilities. Finally, the category probabilities of multi-feature are computed as evidence using the Basic Probability Assignment (BPA) function, and the various types of evidence are fused using our decision fusion algorithm. Experimental results show that our decision fusion method is more capable of synthesizing anomalous evidence than traditional decision fusion methods. Our work achieves recognition accuracy of up to 98.34% on the ShipsEar dataset, which is a significant improvement in recognition rate compared to single features.

A Novel Underwater Acoustic Target Recognition Method Based on MFCC and RACNN.

In ocean remote sensing missions, recognizing an underwater acoustic target is a crucial technology for conducting marine biological surveys, ocean explorations, and other scientific activities that take place in water. The complex acoustic propagation characteristics present significant challenges for the recognition of underwater acoustic targets (UATR). Methods such as extracting the DEMON spectrum of a signal and inputting it into an artificial neural network for recognition, and fusing the multidimensional features of a signal for recognition, have been proposed. However, there is still room for improvement in terms of noise immunity, improved computational performance, and reduced reliance on specialized knowledge. In this article, we propose the Residual Attentional Convolutional Neural Network (RACNN), a convolutional neural network that quickly and accurately recognize the type of ship-radiated noise. This network is capable of extracting internal features of Mel Frequency Cepstral Coefficients (MFCC) of the underwater ship-radiated noise. Experimental results demonstrate that the proposed model achieves an overall accuracy of 99.34% on the ShipsEar dataset, surpassing conventional recognition methods and other deep learning models.

Masking Hierarchical Tokens for Underwater Acoustic Target Recognition With Self-Supervised Learning

Masking Hierarchical Tokens for Underwater Acoustic Target Recognition With Self-Supervised Learning

Model for Underwater Acoustic Target Recognition with Attention Mechanism Based on Residual Concatenate

Underwater acoustic target recognition remains a formidable challenge in underwater acoustic signal processing. Current target recognition approaches within underwater acoustic frameworks predominantly rely on acoustic image target recognition models. However, this method grapples with two primary setbacks; the pronounced frequency similarity within acoustic images often leads to the loss of critical target data during the feature extraction phase, and the inherent data imbalance within the underwater acoustic target dataset predisposes models to overfitting. In response to these challenges, this research introduces an underwater acoustic target recognition model named Attention Mechanism Residual Concatenate Network (ARescat). This model integrates residual concatenate networks combined with Squeeze-Excitation (SE) attention mechanisms. The entire process culminates with joint supervision employing Focal Loss for precise feature classification. In our study, we conducted recognition experiments using the ShipsEar database and compared the performance of the ARescat model with the classic ResNet18 model under identical feature extraction conditions. The findings reveal that the ARescat model, with a similar quantity of model parameters as ResNet18, achieves a 2.8% higher recognition accuracy, reaching an impressive 95.8%. This enhancement is particularly notable when comparing various models and feature extraction methods, underscoring the ARescat model’s superior proficiency in underwater acoustic target recognition.

MGFGNet: an automatic underwater acoustic target recognition method based on the multi-gradient flow global feature enhancement network

The recognition of underwater acoustic targets plays a crucial role in marine vessel monitoring. However, traditional underwater target recognition models suffer from limitations, including low recognition accuracy and slow prediction speed. To address these challenges, this article introduces a novel approach called the Multi-Gradient Flow Global Feature Enhancement Network (MGFGNet) for automatic recognition of underwater acoustic targets. Firstly, a new spectrogram feature fusion scheme is presented, effectively capturing both the physical and brain-inspired features of the acoustic signal. This fusion technique enhances the representation of underwater acoustic data, resulting in more accurate recognition results. Moreover, MGFGNet utilizes the multi-gradient flow network and incorporates a multi-dimensional feature enhancement technique to achieve fast and precise end-to-end recognition. Finally, a loss function is introduced to mitigate the influence of unbalanced data sets on model recognition performance using Taylor series. This further enhances model recognition performance. Experimental evaluations were conducted on the DeepShip dataset to assess the performance of our proposed method. The results demonstrate the superiority of MGFGNet, achieving a recognition rate of 99.1%, which significantly surpasses conventional methods. Furthermore, MGFGNet exhibits improved efficiency compared to the widely used ResNet18 model, reducing the parameter count by 51.28% and enhancing prediction speed by 33.9%. Additionally, we evaluated the generalization capability of our model using the ShipsEar dataset, where MGFGNet achieves a recognition rate of 99.5%, indicating its superior performance when applied to unbalanced data. The promising results obtained in this study highlight the potential of MGFGNet in practical applications.

Real-Time Underwater Acoustic Homing Weapon Target Recognition Based on a Stacking Technique of Ensemble Learning

Underwater acoustic homing weapons (UAHWs) are formidable underwater weapons with the capability to detect, identify, and rapidly engage targets. Swift and precise target identification is crucial for the successful engagement of targets via UAHWs. This study presents a real-time target recognition method for UAHWs based on stacking ensemble technology. UAHWs emit active broadband detection signals that manifest distinct reflection characteristics on the target. Consequently, we have extracted energy and spatial distribution features from the target’s broadband correlation detection output. To address the problem of imbalanced original sea trial data, we employed the SMOTE algorithm to generate a relatively balanced dataset. Then, we established a stacking ensemble model and performed training and testing on both the original dataset and relatively balanced dataset separately. In conclusion, we deployed the stacking ensemble model on an embedded system. The proposed method was validated using real underwater acoustic homing weapon sea trial data. The experiment utilized 5-fold cross-validation. The results indicate that the method presented in this study achieved an average accuracy of 93.3%, surpassing that of individual classifiers. The model’s single-cycle inference time was 15 ms, meeting real-time requirements.

Deep attention-based multi-task learning for underwater acoustic target recognition

Underwater acoustic target recognition is a key step in underwater acoustic signal processing, which is to judge the target attributes by extracting the features of the target radiated noise. However, the traditional feature extraction method is easily affected by the complex marine environment, resulting in a great decline in the correct recognition rate. In previous studies, the deep learning method was introduced to underwater acoustic target recognition and achieved good results. In this study, deep attention-based multi-task learning for underwater acoustic target recognition is proposed. This strategy trains encoder, decoder, and classifier in a multi-task framework to extract features that are more essential and suitable for classification. In addition, the attention mechanism is introduced in the process of feature extraction by the encoder, and the feature weight is given in the process of extraction, so as to improve the representation ability of the network. Experiments on measured underwater acoustic data are performed and the results show that this method can achieve a high accuracy rate in target recognition.

An effective hybrid deep neural network for underwater acoustic target recognition

Underwater acoustic target recognition is an important support technology for underwater information detection and signal processing. Due to the high complexity of the marine environment, it is not easy to obtain clear and reliable features from ship-radiated noise, which makes underwater acoustic target recognition difficult. We propose a new hybrid network of transformer networks and convolutional neural networks to alleviate this problem. It consists of three convolution modules and a transformer module. The convolution modules are used to learn the local features of the time-frequency map, and the features are enhanced using the residual structure and channel attention. The transformer module is used to extract the global features of the time-frequency map. The proposed network can obtain global and local features of the ship-radiated noise from the time-frequency map of the raw data, which can improve the accuracy of recognition. Experiments were conducted on DeepShip, a public benchmark dataset of ship-radiated noise, and compared with the current state-of-the-art methods. The results show that the proposed hybrid network achieves the highest recognition accuracy on the DeepShip dataset.

Adversarial Attacks in Underwater Acoustic Target Recognition with Deep Learning Models

Deep learning models can produce unstable results by introducing imperceptible perturbations that are difficult for humans to recognize. This can have a significant impact on the accuracy and security of deep learning applications due to their poorly understood interpretability. As a field critical to security research, this problem clearly exists in underwater acoustic target recognition for ocean sensing. To address this issue, this article investigates the reliability of state-of-the-art deep learning models by exploring adversarial attack methods that add small, exquisite perturbations on acoustic Mel-spectrograms to generate adversarial spectrograms. Experimental results based on real-world datasets reveal that these models can be forced to learn unexpected features when subjected to adversarial spectrograms, resulting in significant accuracy drops. Specifically, when employing the iterative attack method, the overall accuracy of all models experiences a significant decrease of approximately 70% for two datasets under stronger perturbations.

Research on Feature Extraction of Underwater Acoustic Target Radiation Noise Based on Machine Learning Algorithm

Underwater acoustic target recognition is a very important technology in the field of underwater acoustics, with great economic and military value. Feature extraction technology for underwater acoustic target radiation noise signals is the key to achieving acoustic target recognition. This study aims at the feature extraction task of acoustic targets and extracts 10 types of 252-dimensional feature vectors from three domains: time domain, frequency domain, and auditory domain. Through 7 machine learning algorithms for classification and recognition experiments, the experimental results show that the recognition performance of the ensemble classifier is much better than that of a single classifier. For different types of features, this study combines three ensemble learning algorithms and feature selection algorithms to select the original 252-dimensional features. The feature selection experiment shows that the wrapper feature selection algorithm has the best effect, and the feature vector dimension can be reduced to 40 dimensions. The recognition accuracy rate is not less than 92.8%, which provides feature extraction guidance for acoustic target recognition based on feature extraction.

Underwater acoustic target recognition using RCRNN and wavelet-auditory feature

Underwater acoustic target recognition using RCRNN and wavelet-auditory feature

Few-shot learning for joint model in underwater acoustic target recognition

In underwater acoustic target recognition, there is a lack of massive high-quality labeled samples to train robust deep neural networks, and it is difficult to collect and annotate a large amount of base class data in advance unlike the image recognition field. Therefore, conventional few-shot learning methods are difficult to apply in underwater acoustic target recognition. In this report, following advanced self-supervised learning frameworks, a learning framework for underwater acoustic target recognition model with few samples is proposed. Meanwhile, a semi-supervised fine-tuning method is proposed to improve the fine-tuning performance by mining and labeling partial unlabeled samples based on the similarity of deep features. A set of small sample datasets with different amounts of labeled data are constructed, and the performance baselines of four underwater acoustic target recognition models are established based on these datasets. Compared with the baselines, using the proposed framework effectively improves the recognition effect of four models. Especially for the joint model, the recognition accuracy has increased by 2.04% to 12.14% compared with the baselines. The model performance on only 10 percent of the labeled data can exceed that on the full dataset, effectively reducing the dependence of model on the number of labeled samples. The problem of lack of labeled samples in underwater acoustic target recognition is alleviated.

Underwater Acoustic Target Recognition Based on Deep Residual Attention Convolutional Neural Network

Underwater acoustic target recognition methods based on time-frequency analysis have shortcomings, such as missing information on target characteristics and having a large computation volume, which leads to difficulties in improving the accuracy and immediacy of the target recognition system. In this paper, an underwater acoustic target recognition model based on a deep residual attention convolutional neural network called DRACNN is proposed, whose input is the time-domain signal of the underwater acoustic targets radiated noise. In this model, convolutional blocks with attention to the mechanisms are used to focus on and extract deep features of the target, and residual networks are used to improve the stability of the network training. On the full ShipsEar dataset, the recognition accuracy of the DRACNN model is 97.1%, which is 2.2% higher than the resnet-18 model with an approximately equal number of parameters as this model. With similar recognition accuracies, the DRACNN model parameters are 1/36th and 1/10th of the AResNet model and UTAR-Transformer model, respectively, and the floating-point operations are 1/292nd and 1/46th of the two models, respectively. Finally, the DRACNN model pre-trained on the ShipsEar dataset was migrated to the DeepShip dataset and achieved recognition accuracy of 89.2%. The experimental results illustrate that the DRACNN model has excellent generalization ability and is suitable for a micro-UATR system.

Underwater acoustic target recognition based on spectrum component analysis of ship radiated noise

Underwater acoustic target recognition based on ship radiated noise has always been a challenging task due to the complexity of underwater environment and the antagonism of targets. An underwater acoustic target recognition network based on Ship radiated Noise spectrum component Analysis (SNANet) is proposed in this paper by extracting the spectrum features of each component in different frequency bands, which improves the recognition accuracy as compared with existing end-to-end recognition methods. Adaptive weight based on forward weight and backward weight is used to fuse main and auxiliary features. Experiments have demonstrated that SNANet surpasses currently existing models in performance on the public dataset DeepShip.

Underwater acoustic target recognition based on smoothness-inducing regularization and spectrogram-based data augmentation

Underwater acoustic target recognition is a challenging task owing to the intricate underwater environments and limited data availability. Insufficient data can hinder the ability of recognition systems to support complex modeling, thus impeding their advancement. To improve the generalization capacity of recognition models, techniques such as data augmentation have been employed to simulate underwater signals and diversify data distribution. However, the complexity of underwater environments can cause the simulated signals to deviate from real scenarios, resulting in biased models that are misguided by non-true data. In this study, we propose two strategies to enhance the generalization ability of models in the case of limited data while avoiding the risk of performance degradation. First, as an alternative to traditional data augmentation, we utilize smoothness-inducing regularization, which only incorporates simulated signals in the regularization term. Additionally, we propose a specialized spectrogram-based data augmentation strategy, namely local masking and replicating (LMR), to capture inter-class relationships. Our experiments and visualization analysis demonstrate the superiority of our proposed strategies.