Underwater acoustics is the study of all phenomena related to the occurrence, propagation, and reception of sound waves in the water medium. Because electromagnetic waves undergo a significant attenuation in water, sound waves, which have relatively low propagation loss and high propagation speed, are used for underwater communication and detection. In the field of underwater acoustics, studies are mainly conducted on underwater communications, underwater target detection, marine resources, and measurement and analysis of underwater sound sources. Most applications for underwater acoustics can be described as remote sensing. Remote sensing is employed when an object, condition, or phenomenon of interest cannot be directly observed and information about the target of interest is acquired indirectly using data. In underwater acoustics, this can be described simply as a sound navigation and ranging (sonar) system. Sonar systems can be broadly classified into passive and active systems. Passive sonar systems acquire information by using sensors to measure the acoustic energy (signal) emitted by the target of interest. In active sonar systems, the observer obtains information by directly emitting an acoustic pulse and gathering the returning signals that are reflected by the target. Machine learning, which is widely known today, was initially used in academia for developing artificial intelligence. Recently, the use of machine learning has become widespread owing to the introduction of high-speed parallel computing that uses graphics processing units (GPUs) and can perform reliable learning based on big data, as well as develop various machine learning techniques that can find optimal solutions. Machine learning has contributed to the evolution of acoustic signal processing and voice recognition, and it is also utilized in various ways in the field of underwater acoustics. It is used for traditional remote sensing, such as in detection/classification of underwater sound sources and targets and localization. In addition, it is being used in the field of acoustic signal processing for seabed classification and marine environment information extraction and is producing an abundance of scientific results. Data-driven machine learning divides the data into a training set and test set. The training set is used to create a model that is suitable for machine learning, and the model's accuracy is increased through a repetitive model update process in which the model is validated via the

In this article, we propose an active target detector by using a shallow neural network (NN) with novel features under small sonar data, where deep learning (DL) models are restricted. The features are contrived by considering differences between target and clutter signals in the temporal variation of amplitude and frequency when using an active ping; these are extracted from preprocessed spectrograms of beam time series. The classification ability of the features is demonstrated through comparison with that of prevalent timbral features in the training data set that reflect the human auditory system. Finally, the detection performance of the shallow NN trained using the proposed features is compared with those from the fine-tuned DL models. During the generalization test, the DL models miss a significant number of targets in the test data set—including target signals with patterns unseen during training—and the VGG16 used for detailed comparison has a detection probability of 0.69. The probability increases to 0.86 via the shallow NN, with remarkably enhanced target detection. This demonstrates the competitive performance and generalization ability of the shallow NN, using features that consider active sonar returns under a lack of data.

The use of accelerometer signals for early recognition of severe slugging is investigated in a pipeline-riser system conveying an air–water two-phase flow, where six accelerometers are installed from the bottom to the top of the riser. Twelve different environmental conditions are produced by changing water and gas superficial velocities, of which three conditions are stable states and the other conditions are related to severe slugging. For online recognition, simple parameters using statistics and linear prediction coefficients are employed to extract useful features. Binary classification to recognize stable flow and severe slugging is performed using a support vector machine and a neural network. In multiclass classification, the neural network is adopted to identify four flow patterns of stable state, two types of severe slugging, and an irregular transition state between severe slugging and dual-frequency severe slugging. The performance is compared and analyzed according to the signal length for three cases of sensor location: six accelerometers, one accelerometer at the riser base, and one accelerometer at the top of the riser.

In this article, an extended block sparse Bayesian learning (SBL) is applied to a linear system for estimating the direction of arrival (DOA). DOA estimation using conventional SBL deteriorates when inconsistent noise occurs (e.g., some sensors in the array are malfunctioning). The SBL is extended to accommodate the nonuniform noise variance and shows superior robustness in DOA estimation owing to its selective usage of sensors under normal conditions. Furthermore, a block SBL framework is adopted to exploit the commonality of DOAs over broadband signal frequency components and their correlation at the array. The transformation matrix in the linear system is composed of replicas for preset arrival angles as its basis. Practically, the DOAs deviate from the on-grid angles in the matrix, which results in degradation by basis mismatch. An off-grid SBL incorporating an inconsistent noise variance and block sparsity is formulated to estimate the DOAs reliably. The extended SBL is applied to simulated and measured data (SWellEx-96), and its results are compared with those from conventional approaches. It exhibits better performance in terms of resolution and denoising. In particular, when a part of the array is malfunctioning, the extended SBL can still estimate the DOAs clearly, whereas other approaches fail.