Underwater acoustic target recognition (UATR) technology has been implemented widely in the fields of marine biodiversity detection, marine search and rescue, and seabed mapping, providing an essential basis for human marine economic and military activities. With the rapid development of machine-learning-based technology in the acoustics field, these methods receive wide attention and display a potential impact on UATR problems. This paper reviews current UATR methods based on machine learning. We focus mostly, but not solely, on the recognition of target-radiated noise from passive sonar. First, we provide an overview of the underwater acoustic acquisition and recognition process and briefly introduce the classical acoustic signal feature extraction methods. In this paper, recognition methods for UATR are classified based on the machine learning algorithms used as UATR technologies using statistical learning methods, UATR methods based on deep learning models, and transfer learning and data augmentation technologies for UATR. Finally, the challenges of UATR based on the machine learning method are summarized and directions for UATR development in the future are put forward.

To acquire the enhanced underwater ship-radiated noise signal in the presence of array shape distortion in a passive sonar system, the phase difference of the line-spectrum component in ship-radiated noise is often exploited to estimate the time-delay difference for the beamforming-based signal enhancement. However, the time-delay difference estimation performance drastically degrades with decreases of the signal-to-noise ratio (SNR) of the line-spectrum component. Meanwhile, although the time-delay difference estimation performance of the high-frequency line-spectrum components is generally superior to that of the low-frequency one, the phase difference measurements of the high-frequency line-spectrum component often easily encounter the issue of modulus 2$\pi$ ambiguity. To address the above issues, a novel time-frequency joint time-delay difference estimation method is proposed in this paper. The proposed method establishes a data-driven hidden Markov model with robustness to phase difference ambiguity by fully exploiting the underlying property of slowly changing the time-delay difference over time. Thus, the phase difference measurements available for time-delay difference estimation are extended from that of low-frequency line-spectrum components in a single frame to that of all detected line-spectrum components in multiple frames. By jointly taking advantage of the phase difference measurements in both time and frequency dimensions, the proposed method can acquire enhanced time-delay difference estimates even in a low SNR case. Both simulation and at-sea experimental results have demonstrated the effectiveness of the proposed method.

The convergence of artificial intelligence and the Internet of Things (IoT) has made remarkable strides in the realm of industry. In the context of AIoT edge computing, where IoT devices collect data from diverse sources and send them for real-time processing at edge servers, existing message queue systems face challenges in adapting to changing system conditions, such as fluctuations in the number of devices, message size, and frequency. This necessitates the development of an approach that can effectively decouple message processing and handle workload variations in the AIoT computing environment. This study presents a distributed message system for AIoT edge computing, specifically designed to address the challenges associated with message ordering in such environments. The system incorporates a novel partition selection algorithm (PSA) to ensure message order, balance the load among broker clusters, and enhance the availability of subscribable messages from AIoT edge devices. Furthermore, this study proposes the distributed message system configuration optimization algorithm (DMSCO), based on DDPG, to optimize the performance of the distributed message system. Experimental evaluations demonstrate that, compared to the genetic algorithm and random searching, the DMSCO algorithm can provide a significant improvement in system throughput to meet the specific demands of high-concurrency AIoT edge computing applications.

We propose a backscattering compensation based procedure to enhance the performance of multibeam echosounder systems (MBESs). High resolution in a wide field of view is the main benefit of MBESs, and this property makes them increasingly important for measuring scattering in water body. The performance of these systems is vulnerable to the anisotropic characteristics of scatterers, and thus, the results provided by MBESs can be inaccurate. To enhance the performance of MBESs, we compensate for the echo data on the basis of backscattering strength. The compensation considers the reflected sound energy by introducing interlayer coefficients calculated from the amounts of energy that penetrate into and are reflected from each layer. To demonstrate the effectiveness of the proposed method, we perform numerical simulations with randomly positioned scatters having anisotropic properties. Furthermore, anechoic pool experiments are conducted using bubbles generated by air compressors and propellers. The after-compensation results reveal richer details, thereby confirming the effectiveness of the proposed method.

This paper proposes a method for visualizing three-dimensional non-uniformly sampled data from multibeam echosounder systems (MBESs), aimed at addressing the requirements of monitoring complex and dynamic underwater flow fields. To tackle the challenges associated with spatially non-uniform sampling, the proposed method employs linear interpolation along the radial direction and arc length weighted interpolation in the beam direction. This approach ensures consistent resolution of three-dimensional data across the same dimension. Additionally, an opacity transfer function is generated to enhance the visualization performance of the ray casting algorithm. This function leverages data values and gradient information, including the first and second directional derivatives, to suppress the rendering of background and non-interest regions while emphasizing target areas and boundary features. The simulation and experimental results demonstrate that, compared to conventional two-dimensional beam images and three-dimensional images, the proposed algorithm provides a more intuitive and accurate representation of three-dimensional data, offering significant support for the observation and analysis of spatial flow field characteristics.