Search Results (48)

Underwater sonar target recognition is crucial in fields such as national defense, navigation, and environmental monitoring. However, it faces issues such as the complex characteristics of ship-radiated noise, imbalanced data distribution, non-stationarity, and bottlenecks of existing technologies. This paper proposes the MultiFuseNet-AID network, aiming to address these challenges. The network includes the TriFusion block module, the novel lightweight attention residual network (NLARN), the long- and short-term attention (LSTA) module, and the Mamba module. Through the TriFusion block module, the original, differential, and cumulative signals are processed in parallel, and features such as MFCC, CQT, and Fbank are fused to achieve deep multi-domain feature fusion, thereby enhancing the signal representation ability. The NLARN was optimized based on the ResNet architecture, with the SE attention mechanism embedded. Combined with the long- and short-term attention (LSTA) and the Mamba module, it could capture long-sequence dependencies with an O(N) complexity, completing the optimization of lightweight long sequence modeling. At the same time, with the help of feature fusion, and layer normalization and residual connections of the Mamba module, the adaptability of the model in complex scenarios with imbalanced data and strong noise was enhanced. On the DeepShip and ShipsEar datasets, the recognition rates of this model reached 98.39% and 99.77%, respectively. The number of parameters and the number of floating point operations were significantly lower than those of classical models, and it showed good stability and generalization ability under different sample label ratios. The research shows that the MultiFuseNet-AID network effectively broke through the bottlenecks of existing technologies. However, there is still room for improvement in terms of adaptability to extreme underwater environments, training efficiency, and adaptability to ultra-small devices. It provides a new direction for the development of underwater sonar target recognition technology. Full article

In order to improve the efficiency of the deep network model in processing the radiated noise signals of underwater acoustic targets, this paper introduces a Singular Spectrum Analysis and Channel Attention Convolutional Neural Network (SSA-CACNN) model. The front end of the model is designed as an SSA filter, and its input is the time-domain signal that has undergone simple preprocessing. The SSA method is utilized to separate the noise efficiently and reliably from useful signals. The first three orders of useful signals are then fed into the CACNN model, which has a convolutional layer set up at the beginning of the model to further remove noise from the signal. Then, the attention of the model to the feature signal channels is enhanced through the combination of multiple groups of convolutional operations and the channel attention mechanism, which facilitates the model’s ability to discern the essential characteristics of the underwater acoustic signals and improve the target recognition rate. Experimental Results: The signal reconstructed by the first three-order waveforms at the front end of the SSA-CACNN model proposed in this paper can retain most of the features of the target. In the experimental verification using the ShipsEar dataset, the model achieved a recognition accuracy of 98.64%. The model’s parameter count of 0.26 M was notably lower than that of other comparable deep models, indicating a more efficient use of resources. Additionally, the SSA-CACNN model had a certain degree of robustness to noise, with a correct recognition rate of 84.61% maintained when the signal-to-noise ratio (SNR) was −10 dB. Finally, the pre-trained SSA-CACNN model on the ShipsEar dataset was transferred to the DeepShip dataset with a recognition accuracy of 94.98%. Full article

Many studies have used various time-frequency feature extraction methods to convert ship-radiated noise into three-dimensional (3D) data suitable for computer vision (CV) models, which have shown good results in public datasets. However, traditional feature engineering (FE) has been enhanced to interface matching–feature engineering (IM-FE). This approach requires considerable effort in feature design, larger sample duration, or a higher upper limit of frequency. In this context, this paper proposes a one-dimensional network design for underwater acoustic target recognition (UATR-ND1D), only combined with fast Fourier transform (FFT), which can effectively alleviate the problem of IM-FE. This method is abbreviated as FFT-UATR-ND1D. FFT-UATR-ND1D was applied to the design of a one-dimensional network, named ResNet1D. Experiments were conducted on two mainstream datasets, using ResNet1D in 4320 and 360 tests, respectively. The lightweight model ResNet1D_S, with only 0.17 M parameters and 3.4 M floating point operations (FLOPs), achieved average accuracies were 97.2% and 95.20%. The larger model, ResNet1D_B, with 2.1 M parameters and 5.0 M FLOPs, both reached optimal accuracies, 98.81% and 98.42%, respectively. Compared to existing methods, those with similar parameter sizes performed 3–5% worse than the methods proposed in this paper. Additionally, methods achieving similar recognition rates require more parameters of 1 to 2 orders of magnitude and FLOPs. Full article

In the context of a complex marine environment, extracting and recognizing underwater acoustic target features using ship-radiated noise present significant challenges. This paper proposes a novel deep neural network model for underwater target recognition, which integrates 3D Mel frequency cepstral coefficients (3D-MFCC) and 3D Mel features derived from ship audio signals as inputs. The model employs a serial architecture that combines a convolutional neural network (CNN) with a long short-term memory (LSTM) network. It replaces the traditional CNN with a multi-scale depthwise separable convolutional network (MSDC) and incorporates a multi-scale channel attention mechanism (MSCA). The experimental results demonstrate that the average recognition rate of this method reaches 87.52% on the DeepShip dataset and 97.32% on the ShipsEar dataset, indicating a strong classification performance. Full article

Feature selection and fusion in ship radiated noise-based underwater target recognition have remained challenging tasks. This paper proposes a novel feature extraction method based on multi-dimensional feature selection and fusion. Redundant features are filtered through feature visualization techniques. The Sub-regional Feature Enhancement modules (SFE) and Multi-activated Channel Aggregation modules (MCA) within the neural network are utilized to achieve underwater target recognition. Experimental results indicate that our network, named Sub-Regional Channel Aggregation Net (SRCA-Net), utilizing 3-s sound segments for ship radiated noise recognition, surpasses existing models, achieving an accuracy of 78.52% on the public DeepShip dataset. Full article

Due to the complexity of underwater environments, underwater target recognition based on radiated noise has always been challenging. This paper proposes a multi-scale frequency-adaptive network for underwater target recognition. Based on the different distribution densities of Mel filters in the low-frequency band, a three-channel improved Mel energy spectrum feature is designed first. Second, by combining a frequency-adaptive module, an attention mechanism, and a multi-scale fusion module, a multi-scale frequency-adaptive network is proposed to enhance the model’s learning ability. Then, the model training is optimized by introducing a time–frequency mask, a data augmentation strategy involving data confounding, and a focal loss function. Finally, systematic experiments were conducted based on the ShipsEar dataset. The results showed that the recognition accuracy for five categories reached 98.4%, and the accuracy for nine categories in fine-grained recognition was 88.6%. Compared with existing methods, the proposed multi-scale frequency-adaptive network for underwater target recognition has achieved significant performance improvement. Full article

Estimating the line spectra of ship-radiated noise is a crucial remote sensing technique for detecting and recognizing underwater acoustic targets. Improving the signal-to-noise ratio (SNR) makes the low-frequency components of the target signal more prominent. This enhancement aids in the detection of underwater acoustic signals using sonar. Based on the characteristics of low-frequency narrow-band line spectra signals in underwater target radiated noise, we propose a dual-stream deep learning network with frequency characteristics transformation (DS_FCTNet) for line spectra estimation. The dual streams predict amplitude and phase masks separately and use an information exchange module to swap learn features between the amplitude and phase spectra, aiding in better phase information reconstruction and signal denoising. Additionally, a frequency characteristics transformation module is employed to extract convolutional features between channels, obtaining global correlations of the amplitude spectrum and enhancing the ability to learn target signal features. Through experimental analysis on ShipsEar, a dataset of underwater acoustic signals by hydrophones deployed in shallow water, the effectiveness and rationality of different modules within DS_FCTNet are verified.Under low SNR conditions and with unknown ship types, the proposed DS_FCTNet model exhibits the best line spectrum enhancement compared to methods such as SEGAN and DPT_FSNet. Specifically, SDR and SSNR are improved by 14.77 dB and 13.58 dB, respectively, enabling the detection of weaker target signals and laying the foundation for target localization and recognition applications. Full article

In order to extract the line-spectrum features of underwater acoustic targets in complex environments, an auditory convolutional neural network (ACNN) with the ability of frequency component perception, timbre perception and critical information perception is proposed in this paper inspired by the human auditory perception mechanism. This model first uses a gammatone filter bank that mimics the cochlear basilar membrane excitation response to decompose the input time-domain signal into a number of sub-bands, which guides the network to perceive the line-spectrum frequency information of the underwater acoustic target. A sequence of convolution layers is then used to filter out interfering noise and enhance the line-spectrum components of each sub-band by simulating the process of calculating the energy distribution features, after which the improved channel attention module is connected to select line spectra that are more critical for recognition, and in this module, a new global pooling method is proposed and applied in order to better extract the intrinsic properties. Finally, the sub-band information is fused using a combination layer and a single-channel convolution layer to generate a vector with the same dimensions as the input signal at the output layer. A decision module with a Softmax classifier is added behind the auditory neural network and used to recognize the five classes of vessel targets in the ShipsEar dataset, achieving a recognition accuracy of 99.8%, which is improved by 2.7% compared to the last proposed DRACNN method, and there are different degrees of improvement over the other eight compared methods. The visualization results show that the model can significantly suppress the interfering noise intensity and selectively enhance the radiated noise line-spectrum energy of underwater acoustic targets. Full article

With the aim of solving the problem of identifying complex underwater acoustic targets using a single signal feature in the Time–Frequency (TF) feature, this paper designs a method that recognizes the underwater targets based on the Delay-Doppler joint feature. First, this method uses symplectic finite Fourier transform (SFFT) to extract the Delay-Doppler features of underwater acoustic signals, analyzes the Time–Frequency features at the same time, and combines the Delay-Doppler (DD) feature and Time–Frequency feature to form a joint feature (TF-DD). This paper uses three types of convolutional neural networks to verify that TF-DD can effectively improve the accuracy of target recognition. Secondly, this paper designs an object recognition model (TF-DD-CNN) based on joint features as input, which simplifies the neural network’s overall structure and improves the model’s training efficiency. This research employs ship-radiated noise to validate the efficacy of TF-DD-CNN for target identification. The results demonstrate that the combined characteristic and the TF-DD-CNN model introduced in this study can proficiently detect ships, and the model notably enhances the precision of detection. Full article

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%). Full article

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. Full article

Ship-radiated noise classification is critical in ocean acoustics. Recently, the feature extraction method combined with time–frequency spectrograms and convolutional neural networks (CNNs) has effectively described the differences between various underwater targets. However, many existing CNNs are challenging to apply to embedded devices because of their high computational costs. This paper introduces a lightweight network based on multi-scale asymmetric CNNs with an attention mechanism (MA-CNN-A) for ship-radiated noise classification. Specifically, according to the multi-resolution analysis relying on the relationship between multi-scale convolution kernels and feature maps, MA-CNN-A can autonomously extract more fine-grained multi-scale features from the time–frequency domain. Meanwhile, the MA-CNN-A maintains its light weight by employing asymmetric convolutions to balance accuracy and efficiency. The number of parameters introduced by the attention mechanism only accounts for 0.02‰ of the model parameters. Experiments on the DeepShip dataset demonstrate that the MA-CNN-A outperforms some state-of-the-art networks with a recognition accuracy of 98.2% and significantly decreases the parameters. Compared with the CNN based on three-scale square convolutions, our method has a 68.1% reduction in parameters with improved recognition accuracy. The results of ablation explorations prove that the improvements benefit from asymmetric convolution, multi-scale block, and attention mechanism. Additionally, MA-CNN-A shows a robust performance against various interferences. Full article

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. Full article

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. Full article

The fractal dimension (FD) is a classical nonlinear dynamic index that can effectively reflect the dynamic transformation of a signal. However, FD can only reflect signal information of a single scale in the whole frequency band. To solve this problem, we combine refined composite multi-scale processing with FD and propose the refined composite multi-scale FD (RCMFD), which can reflect the information of signals at a multi-scale. Furthermore, hierarchical RCMFD (HRCMFD) is proposed by introducing hierarchical analysis, which successfully represents the multi-scale information of signals in each sub-frequency band. Moreover, two ship-radiated noise (SRN) multi-feature extraction methods based on RCMFD and HRCMFD are proposed. The simulation results indicate that RCMFD and HRCMFD can effectively discriminate different simulated signals. The experimental results show that the proposed two-feature extraction methods are more effective for distinguishing six types of SRN than other feature-extraction methods. The HRCMFD-based multi-feature extraction method has the best performance, and the recognition rate reaches 99.7% under the combination of five features. Full article