In the field of underwater acoustic recognition, machine learning methods rely on a large number of datasets to achieve high accuracy, while the actual collected signal samples are often very scarce, which has a great impact on the recognition performance. This paper presents a recognition method of an underwater acoustic target by the data augmentation technique and the residual convolutional neural network (CNN) model, which is used to expand training samples to improve recognition performance. As a representative model in residual CNN, the ResNet18 model is used for recognition. The whole process mainly includes mel-frequency cepstral coefficient (MFCC) feature extraction, data augmentation processing, and ResNet18 model recognition. On the base of the traditional data augmentation, this study used the deep convolutional generative adversarial network (DCGAN) model to realize the expansion of underwater acoustic samples and compared the recognition performance of support vector machine (SVM), common CNN, VGG19, and ResNet18. The recognition results of the MFCC, constant Q transform (CQT), and low-frequency analyzer and recorder (LOFAR) spectrum were also analyzed and compared. Experimental results showed that the recognition accuracy of the MFCC feature was better than that of other features at the same method, and using the data augmentation method could obviously improve the recognition performance. Moreover, the recognition performance of ResNet18 using data enhancement technology was better than that of other models, which was due to the combination of the data expansion advantage of data augmentation technology and the deep feature extracting ability of the residual CNN model. In addition, although this method was used for ship recognition in this paper, it is not limited to this. This method is also applicable to other target voice recognition, such as natural sound and underwater voice biometrics.

Within the conventional sparse Bayesian learning (SBL) framework, only Gaussian scale mixtures have been adopted to model sparsity-inducing priors that guarantee the exact inverse recovery. In light of the relative scarcity of formal SBL tools in enforcing a proper sparsity profile of signal vectors, we explore the use of hierarchical synthesis lasso (HSL) priors for representing the same small subset of features among multiple responses. We outline a viable approximation to this particular choice of sparse prior, leading to tractable marginalization over all weights and hyperparameters. We then discuss how the statistical variables of the hierarchical Bayesian model can be estimated via an adaptive updating formula, and include a refined one dimensional searching procedure to extraordinarily improve the direction of arrival (DOA) estimation performance when take the off-grid DOAs into account. Using these modifications, we show that exploiting HSL priors are very helpful in encouraging sparseness. Numerical simulations also verify the superiority of the proposal in terms of convergence speed and root mean squared estimation error, as compared to the traditional and more recent sparse Bayesian algorithms.

There are numerous studies showing that there is a constant increase in the ocean ambient noise level and the ever-growing demand for developing algorithms for detecting weak signals in ambient noise. In this study, we utilize dynamical and statistical complexity to detect the presence of weak ship noise embedded in ambient noise. The ambient noise and ship noise were recorded in the South China Sea. The multiscale entropy (MSE) method and the complexity-entropy causality plane (C-H plane) were used to quantify the dynamical and statistical complexity of the measured time series, respectively. We generated signals with varying signal-to-noise ratio (SNR) by varying the amplification of a ship signal. The simulation results indicate that the complexity is sensitive to change in the information in the ambient noise and the change in SNR, a finding that enables the detection of weak ship signals in strong background ambient noise. The simulation results also illustrate that complexity is better than the traditional spectrogram method, particularly effective for detecting low SNR signals in ambient noise. In addition, complexity-based MSE and C-H plane methods are simple, robust and do not assume any underlying dynamics in time series. Hence, complexity should be used in practical situations.

In deep-sea source localization, some of the existing methods only estimate the source range, while the others produce large errors in distance estimation when estimating both the range and depth. Here, a convolutional neural network-based method with high accuracy is introduced, in which the source localization problem is solved as a regression problem. The proposed neural network is trained by a normalized acoustic matrix and used to predict the source position. Experimental data from the western Pacific indicate that this method performs satisfactorily: the mean absolute percentage error of the range is 2.10%, while that of the depth is 3.08%.

In recent years, more attention has been paid to water surface environment protection. Current water surface waste cleaning mainly relies on manual operations, which are low-efficiency and dangerous. Therefore, in this paper, we design a fully autonomous water surface cleaning robot, SMURF, which achieves high-efficiency water surface cleaning without human operation and adapts to be used in various types of real-world water bodies. In addition, we propose a novel coverage path planning method on water surfaces and an improved nonlinear model predictive controller. The real-world experiment shows that SMURF works well in different kinds of water bodies and achieves much higher efficiency than traditional water surface cleaning methods.