Search

The detection of minerals (mines) or rocks would have been extremely difficult without the expansion of the Sound Navigation Ranging methodology, which uses specific parameters to determine if a barrier or a surface is a mine or rock. Hence, this proposed work is concerned with the progression of distinctive among metal cylinder which is named as mines and cylindrical shape material which is named as rocks using deep learning based algorithms. Moreover, this work introduced novel technique as Rock or mine Detection Neural Network for performing rock/mine prediction and classification in underwater acoustics. The proposed RDNN method outperforms the outcomes by attaining high accuracy as 92.85% mean accuracy that makes better model performance.

Object detection in underwater acoustics especially sea floor object has been overwhelming mission chiefly owing to strident environment of sonar images as well as because of visibly existing sonar images. Side Scan Sonar is the primary sensor for Autonomous Underwater Vehicles to perform survey on sea water. Hence, we are using this SSS images for categorizing several objects like sand, mud, clay, graves, ridges and sediments in underwater sea through any size subsequent to training. We applied two-layer CNN architecture to train the model as well as we utilized three pre-trained network models such as VGG-19, ResNet50 and EfficientNet model for evaluating the performance of the model based on training and validation accuracy measures. Moreover, we utilized deep learning based transfer learning approach in which the parameters are tuned for classifying the images into sediments, clay, mud, stones etc. Our experimental outcomes shows that pre-trained EfficientNet model generates better accuracy of 100% after fine tuning the parameter in object recognition along with classification using SSS images.

Underwater acoustic sensor networks (UASNs) have gradually received attention due to their widespread applications, such as in disaster prevention, environmental monitoring and military activities, and they simultaneously face security challenges. In recent years, trust management mechanisms have become important tools for responding to internal attackers. However, most of the existing trust management mechanisms do not consider the adverse influence of complex underwater environment on node evaluation, and do not deal with the case that normal nodes are misjudged as malicious nodes. To achieve accurate trust evaluation of nodes and reduce the possibility of misjudgment of normal nodes, a redeemable Support Vector Machine-Dempster-Shafer (SVM-DS) fusion-based trust management mechanism (SDFTM) is proposed for UASNs in this paper. First, according to the characteristics of attacks, three kinds of trust evidence are selected: packet-based evidence, data-based evidence and energy-based evidence. Then the support vector machine (SVM) is applied to classify the trust of node from the aspect of each kind of trust evidence, while Dempster-Shafer (DS) evidence theory is used to fuse the different trust classification results of nodes. Second, to deal with cases where a normal node may be misclassified as a malicious node, trust redemption process is carried out based on the historical performance and environmental influence (unreliable acoustic channel, weak link connectivity). Finally, the trust value is calculated and updated. The simulation results prove that the proposed scheme yields satisfactory performance in malicious detection and reduce the possibility of misjudgment of normal nodes.

In order to better explore the ocean, autonomous underwater vehicles (AUVs) have been widely applied to facilitate the information collection. However, considering the extremely large-scale deployment of sensor nodes in the Internet of Underwater Things (IoUT), a homogeneous AUV-enabled information collection system cannot support timely and reliable information collection considering the time-varying underwater environment as well as AUV’s energy and mobility constraints. In this article, we propose a multi-AUV-assisted heterogeneous underwater information collection scheme for the sake of optimizing the peak Age of Information (AoI). Moreover, the limited service M/G/1 vacation queueing model is utilized to model the process of information exchange, where the optimal upper limit of the number of AUVs served in the queueing system as well the steady-state distribution of the queue length are derived. A low-complexity adaptive algorithm for adjusting the upper limit of the queuing length is also proposed. Finally, simulation results validate the effectiveness of our proposed scheme and algorithm, which outperform traditional methods in terms of the peak AoI.

The black box plays an important role in transportation security, and the underwater acoustic localization (UWAL) methods are the most effective way to find the black box sunken undersea. The traditional UWAL methods suffer from a significant decrease in the localization precision due to the signal period drift of the black box in the cold and high-pressure undersea environment. In our former work, we carried out the second-order time-difference-of-arrival (STDOA) algorithm to address the problem. However, for a real maneuvering ship, the localization precision has the potential to be further improved with the help of the uniformly distributed localization nodes. In this article, a generalized STDOA (GSTDOA) algorithm is proposed. First, we establish the general form of the STDOA information, where the localization nodes can be selected arbitrarily. Second, we analyze the localization precision of the GSTDOA algorithm, and it shows that the localization precision is closely related to the selected nodes. Third, we optimize the localization nodes for maximum localization precision. Finally, experiments in different scenes validate the effectiveness of the proposed method.

Underwater acoustic communication (UAC) modem is an important infrastructure of underwater network construction. In recent years, with the performance improvement of the STM32 processor, the realization of reliable UAC through high-performance STM32 processor is conducive to reduce the system power consumption, cheapen the hardware cost, and ease the development difficulty. In this letter, we propose an embedded UAC system with the STM32H743 processor as the core and the peripheral sending/receiving circuit as the signal conditioning circuit module. The system can support a variety of modulation and demodulation methods, including single/multi-carrier frequency-shift keying and orthogonal frequency division multiplexing. Furthermore, in order to reduce the computational cost of the system, a fast and robust frame synchronization algorithm based on the segmented fast Fourier transform is applied. The sea trials show that the system can realize the reliable UAC transmission of 100 b/s–1 kb/s in the distance of 5–8 km in the shallow water area.

In this article, we present an unmanned aerial vehicle (UAV)-aided ocean monitoring network for remote oceanic data collection, in which monitoring data are transmitted first from battery-powered underwater sensor nodes (USNs) to sea surface sink nodes (SNs) in a data collection cycle using underwater acoustic communication, and then a UAV hovering in air collects all the data from SNs and relays them to a ground base station via wireless communication links. Aiming at maximizing network lifetime, we model the resource allocation, USN-to-SN access, and SN-to-UAV access issues as a mixed-integer nonconvex optimization problem. To efficiently solve it, we decompose the optimization into two stages. The first stage is to minimize time consumption in an SN-to-UAV nonorthogonal multiple access process and we solve it by designing a UAV deployment scheme, a subchannel matching scheme, and a joint power and time allocation scheme, based on which, the second stage is to maximize the residual energies of USNs in USN-to-SN transmissions under a modified frequency-division multiple access strategy in each collection cycle. The second-stage optimization is further decomposed into some similar subproblems, and each of them is considered as a bipartite graph matching problem between USNs and underwater acoustic channels. For each subproblem, we propose improved weight-based matching and bisection-based searching algorithms. Finally, we design a low-complexity iteration algorithm to approximate the optimal solution of the original problem by solving these subproblems. The simulation results validate the effectiveness of our proposals.

Underwater environments create a challenging channel for communications. In this paper, we design a novel receiver system by exploring the machine learning technique--Deep Belief Network (DBN)-- to combat the signal distortion caused by the Doppler effect and multi-path propagation. We evaluate the performance of the proposed receiver system in both simulation experiments and sea trials. Our proposed receiver system comprises of DBN based de-noising and classification of the received signal. First, the received signal is segmented into frames before the each of these frames is individually pre-processed using a novel pixelization algorithm. Then, using the DBN based de-noising algorithm, features are extracted from these frames and used to reconstruct the received signal. Finally, DBN based classification of the reconstructed signal occurs. Our proposed DBN based receiver system does show better performance in channels influenced by the Doppler effect and multi-path propagation with a performance improvement of 13.2dB at $10^{-3}$ Bit Error Rate (BER).

Security is a critical consideration in Underwater Acoustic Networks (UANs) due to the importance of the applications in which these types of networks are often employed, from military applications to marine natural disaster prevention. Furthermore, even simple Denial of Service (DoS) attacks such as jamming can be very effective in disrupting the communication, with significant negative consequences for these critical applications. While jamming has been widely studied in the context of terrestrial networks, the peculiarities of propagation in UANs, such as the low propagation speed, the multipath, and the high delay spread, need to be considered: the relative positions of the jammer, transmitter, and receiver can have a huge impact on the feasibility and impact of reactive jamming, opening the way for the exploitation of other jamming models. In this paper, we analyze the effectiveness of a reactive and a blind jammer through a game theoretical framework, comparing them for different geometries of the scenario. We assess the impact of the different jammers, employing different active and evasive strategies, where the first type of countermeasure implies the use of additional energy to protect the communication, while the second tries to avoid the jamming signals by randomizing the transmission pattern.

A key technology in the movement tracking of marine animals is localization using acoustic transmitters. These are attached to marine animals and are detected by an array of receivers. Then, offline localization is performed by multilateration. However, due to the transmitter's low power and environmental conditions, emissions may be detected by only a limited number of receivers, causing localization ambiguities to arise. This work proposes a solution for such localization ambiguities. The proposed method assumes that the position of acoustically-tagged marine animals follows a hidden Markov model, such that localization ambiguities can probabilistically be resolved using a Forward-Backward algorithm. Our method is able to extrapolate the positions in a data series, as long as one sample in that series is picked up by three receivers, or if the identity of the receivers changes during tracking. Performance analysis shows that the localization accuracy of our method approaches the Cramer-Rao lower bound. Furthermore, to demonstrate the suitability of our method in a real sea environment, we have established a testbed that operated for three months, demonstrating localization of 20 acoustically-tagged sandbar sharks. Compared to the available solutions, roughly 20 times more location estimates were made; thereby, significantly increasing the impact of the test-site.

The accurate localization of nodes is one of the most basic tasks in underwater acoustic sensor networks (UASNs). However, in large-scale UASNs, nodes are difficult to be accurately located because GPS signals cannot be received and because underwater nodes cannot establish one-hop communication with beacons due to the limited transmission range. With the development of self-sinking beacon technology, in this article, we propose a mobile-beacon-based iterative localization (MBIL) mechanism to realize node hierarchically positioning of large-scale multihop UASNs with an aim at increasing the percentage of localized nodes and reducing the localization error in the network. The proposed mechanism first uses mobile beacon nodes to localize adjacent sensor nodes. Once the location information is obtained, the sensor node will calculate its confidence value to determine whether it is a qualified reference node. Then, the unknown nodes select three adjacent reference nodes with the highest evaluation index for localization, and the remaining unknown nodes are iteratively localized. Simulation results show that the proposed mechanism can not only achieve a higher proportion of localized nodes in a shorter time, but also effectively reduce the localization error. In addition, MBIL effectively balances the energy consumption of sensor nodes, which can prolong the network’s lifetime.

Underwater Acoustic Networks (UANs) use acoustic waves for communications, which consume excessive energy. Conversely, the nodes in UANs have scarce energy resources, thus energy saving is a vital objective of routing protocol design for UANs. Due to the high cost, nodes are usually deployed sparsely. Moreover the nodes in water can move with water current or other underwater activities. Consequently, the data transmission with traditional routing protocol is subject to the routing problem of “void area” in UANs. In this paper, we propose a Connectivity-and-Energy-aware Layering Routing (CELR) protocol to achieve two objectives of energy-saving and reliable routing. Addressing the routing problem of “void area”, a connectivity-aware layering algorithm is presented based on the minimum hop-count from the sink to underwater nodes. To reduce the energy consumption, on the basis of connectivity aware layering algorithm, a connectivity and energy aware layering algorithm is proposed. Further, taking the residual energy and hop-distance into account, we present a CELR routing protocol for UANs. Experiments results show that the CELR protocol outperforms the depth-based routing (DBR) and layer-based and energy-efficient routing (LEER) protocol in terms of packet delivery rate, average energy consumption and end-to-end delay.

Automatic modulation recognition (AMR) is one of the essential parts in the intelligent communication system. In the underwater acoustic communication, it is a challenging work that promptly and easily recognizes the signal modulation schemes by conventional methods. The deep neural network method is a good solution to the problem, which creates a better recognition effect. The packets of data that are fed to the familiar neural network is constant. However, the packets of signal data on the communication course consistently change, which seriously reflects on the signal recognition veracity. A novel deep learning network with the sequence convolutional network in this paper is proposed, which is composed of one-dimensional sequence convolution of residual network modules and the variable convolution kernel range. By extracting the time-domain signal characteristics, the affection of various signal packets can be mitigated. In experiments, the employed network not only has more concentrated on the modulation recognition veracity, but also owns a lower parameter quantity and a shorter training time, which indicates ideal recognition results in the underwater communication environment. Moreover, it is more valuable to the real underwater communication system.

Contention-basedmedium access control (MAC) protocols for underwater acoustic sensor networks are designed to handle packet collisions that are caused by long propagation delays. However, existing protocols are known to suffer from relatively high collisions, which decrease system performance. To enhance system performance, we propose a contention-based MAC protocol that employs a widely-popular machine learning technique, namely, Q-learning. Using Q-learning, the proposed protocol allows the sensor nodes to intelligently select the back-off slots and accordingly schedule the transmission of data packets such that collisions are minimized at the receiver. Unlike in existing protocols, the sensor nodes are not required to exchange scheduling information, which implies that the proposed protocol has low complexity and overhead. Under varying traffic loads and node numbers, the proposed protocol is compared with the state-of-the-art ALOHA-Q for underwater environment (UW-ALOHA-Q), multiple access collision avoidance for underwater (MACA-U) and exponential increase exponential decrease (EIED) protocols. Results demonstrate the effectiveness of the proposed protocol in terms of energy efficiency, channel utilization, and latency.

Autonomous underwater vehicle (AUV) mostly relies on an integrated navigation system, which consists of a strap-down inertial navigation system (SINS) and Doppler velocity log (DVL). The integrated system provides continuous and accurate navigation information when compared to stand-alone SINS or DVL. However, the dependence of DVL signals on the acoustic environment may cause any DVL malfunction due to marine organisms or strong wave-absorbing material. This article introduces a novel method utilizing Dempster–Shafer (DS) theory augmented by least squares support vector machines (LSSVMs) known as DS-LSSVM. The SINS and DVL data fusion are designed by DS theory whereas LSSVM models the SINS error. The virtual DVL is built by the proposed DS-LSSVM method, which makes AUV navigation purposes possible during the long-term DVL outage. The test results demonstrate the effectiveness of the proposed virtual DVL signal estimation method. In addition, the positioning accuracy of the proposed method outperforms that of the LSSVM method.

Underwater acoustic communication plays an important role in underwater wireless sensor network. Different from terrestrial radio channel, modeling of underwater acoustic channel is very challenging due to its unique and dynamic characteristics. In order to verify the proposed acoustic communication algorithms, a general emulation platform which can reduce the verification cost has a wide application prospect. In this paper, we design a general hardware in the loop underwater communication emulation system based on the LabVIEW and MATLAB software and real acoustic transducer. In the emulation system, LabVIEW calls MATLAB script to achieve algorithm implementation, and then uses DAQmx to send and receive data through the acquisition card. The proposed system supports a variety of modulation and demodulation methods, such as multiple frequency-shift-keying(MFSK), multi-carrier frequency-shift-keying(MCFSK), orthogonal frequency division multiplexing(OFDM), etc. In addition, in order to detect frame efficiently, we propose a light-weight frame synchronous algorithm. To verify the function of the systems, lake test and sea test are conducted for different algorithms.

Underwater wireless communication is a rapidly growing field, especially with the recent emergence of technologies such as autonomous underwater vehicles (AUVs) and remotely operated vehicles (ROVs). To support the high-bandwidth applications using these technologies, underwater optics has attracted significant attention, alongside its complementary technology – underwater acoustics. In this paper, we propose a hybrid opto-acoustic underwater wireless communication model that reduces network power consumption and supports high-data rate underwater applications by selecting appropriate communication links in response to varying traffic loads and dynamic weather conditions. Underwater optics offers high data rates and consumes less power. However, due to the severe absorption of light in the medium, the communication range is short in underwater optics. Conversely, acoustics suffers from low data rate and high power consumption, but provides longer communication ranges. Since most underwater equipment relies on battery power, energy-efficient communication is critical for reliable underwater communications. In this work, we derive analytical models for both underwater acoustics and optics, and calculate the required transmit power for reliable communications in various underwater communication environments. We then formulate an optimization problem that minimizes the network power consumption for carrying data from underwater nodes to surface sinks under varying traffic loads and weather conditions. The proposed optimization model can be solved offline periodically, hence the additional computational complexity to find the optimum solution for larger networks is not a limiting factor for practical applications. Our results indicate that the proposed technique yields up to 35% power savings compared to existing opto-acoustic solutions.

Underwater acoustic target recognition is one of the main functions of the SONAR systems. In this paper, a target recognition method based on combined features with automatic coding and reconstruction is proposed to classify ship radiated noise signals. In the existing underwater acoustic target recognition systems, the target category features are mostly constructed based on the power spectrum according to a certain presupposed model, and some useful information in the data is discarded artificially. In the proposed recognition method, a feature extractor based on auto-encoding is designed. The feature extractor uses the restricted Boltzmann machine (RBM) to automatically encode the combined data of the power spectrum and demodulation spectrum of ship radiated noise without supervision and extracts the deep data structure layer by layer to obtain the signal feature vector. The extracted feature vector is sent to a Back Propagation (BP) neural network to realize target recognition. Due to the high cost of ship radiated noise acquisition, the sample size of ship radiated noise signals is often hard to meet the needs of neural network training. A method of data augmentation is designed by RBM auto-encoder to construct the expanded sample set, which improves the performance of the recognition system. The experimental results based on the actual ship’s radiated noise show that the proposed method has better performance than the traditional methods.

The localization and tracking of underwater objects have many applications. In a proactive underwater sensor array, some nodes will periodically broadcast linear frequency modulated (LFM) signals, which will hit the targets, get reflected and received by the other nodes. Depending on the target's position and velocity, the received signals will also be LFM signals of different frequencies and frequency rates. We can use the Fractional Fourier Transform (FrFT) to analyze the received signal's spectrum and find the peak. Based on the location of the peak, the target's distance and radial velocity can be estimated. However, the accuracy is highly dependent on the sampling interval of the spectrum. Smaller sampling interval leads to higher accuracy but also induces considerable complexity. To overcome this issue, we propose a machine learning-based approach to automatically detect the existence of the target, and roughly estimate the peak's location if targets exist. Then over-sampling can be conducted for a small area around the peak, leading to improved accuracy and reduced complexity. The idea is based on the following observation: if a target exists, we will be able to observe an “X” pattern on the spectrum. Extensive simulations are conducted to verify the effectiveness of the proposed architecture.

Underwater acoustics, which is the study of the phenomena related to sound waves in water, has been applied mainly in research on the use of sound navigation and range (SONAR) systems for communication, target detection, investigation of marine resources and environments, and noise measurement and analysis. Underwater acoustics is mainly applied in the field of remote sensing, wherein information on a target object is acquired indirectly from acoustic data. Presently, machine learning, which has recently been applied successfully in a variety of research fields, is being utilized extensively in remote sensing to obtain and extract information. In the earlier parts of this work, we examined the research trends involving the machine learning techniques and theories that are mainly used in underwater acoustics, as well as their applications in active/passive SONAR systems (Yang et al., 2020a; Yang et al., 2020b; Yang et al., 2020c). As a follow-up, this paper reviews machine learning applications for the inversion of ocean parameters such as sound speed profiles and sediment geoacoustic parameters.

Underwater acoustic signal processing is one of the research hotspots in underwater acoustics. Noise reduction of underwater acoustic signals is the key to underwater acoustic signal processing. Owing to the complexity of marine environment and the particularity of underwater acoustic channel, noise reduction of underwater acoustic signals has always been a difficult challenge in the field of underwater acoustic signal processing. In order to solve the dilemma, we proposed a novel noise reduction technique for underwater acoustic signals based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), minimum mean square variance criterion (MMSVC) and least mean square adaptive filter (LMSAF). This noise reduction technique, named CEEMDAN-MMSVC-LMSAF, has three main advantages: (i) as an improved algorithm of empirical mode decomposition (EMD) and ensemble EMD (EEMD), CEEMDAN can better suppress mode mixing, and can avoid selecting the number of decomposition in variational mode decomposition (VMD); (ii) MMSVC can identify noisy intrinsic mode function (IMF), and can avoid selecting thresholds of different permutation entropies; (iii) for noise reduction of noisy IMFs, LMSAF overcomes the selection of decomposition number and basis function for wavelet noise reduction. Firstly, CEEMDAN decomposes the original signal into IMFs, which can be divided into noisy IMFs and real IMFs. Then, MMSVC and LMSAF are used to detect identify noisy IMFs and remove noise components from noisy IMFs. Finally, both denoised noisy IMFs and real IMFs are reconstructed and the final denoised signal is obtained. Compared with other noise reduction techniques, the validity of CEEMDAN-MMSVC-LMSAF can be proved by the analysis of simulation signals and real underwater acoustic signals, which has the better noise reduction effect and has practical application value. CEEMDAN-MMSVC-LMSAF also provides a reliable basis for the detection, feature extraction, classification and recognition of underwater acoustic signals.

In underwater acoustic sensor networks (UASNs), the spatially and temporally varying acoustic channel causes random route interruptions and transmission void region. Further, the long propagation delay of acoustic links causes complicated randomness of packet collisions. Inspired by the unpredictability of both route interruptions and packet collisions in UASNs, a collision and interruption tolerant protocol (CITP) is proposed to jointly address the two challenges in a smart way. By exploiting the opportunistic transmission strategy, CITP forms the optimized route on the fly, which bypasses nodes that undergo collisions or interrupted links and void regions. Simulation results show that CITP achieves a high packet delivery ratio with reduced energy consumption.

Underwater acoustics, which is the domain that addresses phenomena related to the generation, propagation, and reception of sound waves in water, has been applied mainly in the research on the use of sound navigation and ranging (SONAR) systems for underwater communication, target detection, investigation of marine resources and environment mapping, and measurement and analysis of sound sources in water. The main objective of remote sensing based on underwater acoustics is to indirectly acquire information on underwater targets of interest using acoustic data. Meanwhile, highly advanced data-driven machine-learning techniques are being used in various ways in the processes of acquiring information from acoustic data. The related theoretical background is introduced in the first part of this paper (Yang et al., 2020). This paper reviews machine-learning applications in passive SONAR signal-processing tasks including target detection/identification and localization.

Goal: Chronic obstructive pulmonary disease (COPD) is one of the deadliest diseases in the world. Because COPD is an incurable disease and requires considerable time to be diagnosed even by an experienced specialist, it becomes important to provide analysis abnormalities in simple ways. The aim of the study is to compare multiple machine-learning algorithms for the early diagnosis of COPD using multichannel lung sounds. Methods: Deep learning (DL) is an efficient machine-learning algorithm, which comprises unsupervised training to reduce optimization and supervised training by a feature-based distribution of classification parameters. This study focuses on analyzing multichannel lung sounds using statistical features of frequency modulations that are extracted using the Hilbert–Huang transform. Results: Deep-learning algorithm was used in the classification stage of the proposed model to separate the patients with COPD and healthy subjects. The proposed DL model with the Hilbert–Huang transform based statistical features was successful in achieving high classification performance rates of 93.67%, 91%, and 96.33% for accuracy, sensitivity, and specificity, respectively. Conclusion: The proposed computerized analysis of the multichannel lung sounds using DL algorithms provides a standardized assessment with high classification performance. Significance: Our study is a pioneer study that directly focuses on the lung sounds to separate COPD and non-COPD patients. Analyzing 12-channel lung sounds gives the advantages of assessing the entire lung obstructions.

Underwater acoustics that is the study of the phenomenon of underwater wave propagation and its interaction with boundaries, has mainly been applied to the fields of underwater communication, target detection, marine resources, marine environment, and underwater sound sources. Based on the scientific and engineering understanding of acoustic signals/data, recent studies combining traditional and data-driven machine learning methods have shown continuous progress. Machine learning, represented by deep learning, has shown unprecedented success in a variety of fields, owing to big data, graphical processor unit computing, and advances in algorithms. Although machine learning has not yet been implemented in every single field of underwater acoustics, it will be used more actively in the future in line with the ongoing development and overwhelming achievements of this method. To understand the research trends of machine learning applications in underwater acoustics, the general theoretical backgroundof several related machine learning techniques is introduced in this paper.

We propose a sequential method to extract 3-dimensional information for mapping by using sensor fusion of two sonar devices. The 3D reconstruction using sonar images from forward-looking multibeam sonar (FLMS) is an ill-posed problem due to the loss of elevation angle; thus we used an additional sonar and its complementary information. Our approach is to utilize geometric constraints between the installation of two sonar devices and complementary characteristics such as a different angle of the acoustic beams and data acquisition method. The fusion process proceeds in three stages. The first stage is to build a likelihood map using geometric constraints of the installation between two sonar devices. The second stage is to calculate the feasible elevation angle of the FLMS. The elevation angle of FLMS is limited by its vertical beam spreading angle, which can be represented by particles. The third stage is Monte-Carlo experiment using the generated particles by computing the weight, and correct the data of FLMS. To verify the proposed method, we applied the proposed method in simulations and experiments in engineering basin with an AUV.

In sonar applications, important information such as distributions of minerals, underwater creatures has a high probability of being contained in sonar images. In many underwater applications such as underwater rescue and biometric tracking, it is necessary to send sonar images underwater for further analysis. Due to the bad conditions of underwater acoustic channel and current underwater acoustic communication technologies, sonar images very possibly suffer from several typical types of distortions. As far as we know, limited efforts have been made to gather meaningful sonar image databases and benchmark reliable objective quality model, so far. This paper develops a new objective sonar image quality predictor (SIQP), whose core is the combination of two features specific to a quality measure of sonar images. These two features, which come from statistical and structural information inspired by the characteristics of sonar images and the human visual system, reflect image quality from the global and detailed aspects. The performance comparison of the proposed metric with popular and prevailing quality evaluation models is conducted using a newly established sonar image quality database. The results of experiments show the superiority of our SIQP metric over the available quality evaluation models. This work was supported in part by the National Natural Science Foundation of China under Grant 61571377, Grant 61871336, Grant 61527804, and Grant 61703009, in part by the Beijing Advanced Innovation Center for Future Internet Technology under Grant 110000546619001, in part by the Young Elite Scientist Sponsorship Program by China Association for Science and Technology under Grant 2017QNRC001, and in part by the Nova Programme Interdisciplinary Cooperation Project under Grant Z161100004916041.

Using single transponder ranging (STR) information to aid positioning satisfies the needs of frogman autonomous positioning in waters emergency rescue, where miniaturized and low-cost devices are preferred. On this basis, a frogman self-navigation method based on virtual transponder array (VTA) and dead reckoning (DR) is proposed in this article, to solve the problem that calculation results of DR still accumulate with time when STR information is taken as the external measurement. In the proposed method, firstly, by constructing the VTA with depth information constraint, frogman autonomous positioning under the condition of single transponder configuration is realized. Then, to combine the characteristics that DR positioning data is smooth and short-term stable, and that VTA positioning error is not cumulative, the DR navigation system is used to describe frogman’s motion law, the frogman positioning coordinates that calculated by VTA are taken as external measurement and the Kalman filter is designed, which solves the problem of DR accumulated errors. Compared to traditional STR-DR method, the proposed VTA-DR method further improves the accuracy and stability of frogman navigation and positioning. Finally, based on the high-precision three-dimensional motion capture system, the semi-physical simulation experimental environment is built to verify the proposed method. The experimental results under different tracks indicate that the average total location error of VTA-DR method is 0.149m, which is reduced by 53.5% compared with STR-DR method. The proposed VTA-DR method can better suppress the accumulation of positioning errors and has better positioning accuracy and robustness.

This letter proposes a correlation detection algorithm based on multi-channelization. The existing method has poor performance for detecting a time-varying signal with a low signal-to-noise ratio(SNR). To overcome this problem, we use the method of correlation summation after multi-channelization. According to the difference between the correlation between signals and noise in the received data, the single-channel data is converted into multi-channel data by a multi-channelization method without changing the signals. Then the noise is filtered by correlation calculation of multi-channel data, which can improve the detection probability of signals under low SNR. Based on the theory of multi-channelization, we propose two different methods to detect signals. To better reflect the performance of the algorithm, we compared several classical signal detection methods, such as energy detection (ED), correlation detection (CD), and cyclic spectrum detection (CSD). Simulation analysis and experimental results show that the multi-channelization correlation detection algorithm has better detection performance when the SNR is low.

Underwater acoustic networks (UANs) have emerged as a new wireless sensor network structure widely used in many applications. Sensor nodes are usually placed in a hostile and unattended underwater environment to gather information with limited resource. Since the underwater information is sensitive and special, only authenticated users have rights to get the information. The existing secure resource-constrained authentication schemes are not inapplicable for underwater acoustic networks, so a lightweight authentication scheme is the primarily task in underwater acoustic networks. In this paper, we present a chaotic maps remote user authentication and key agreement scheme for underwater acoustic networks based on the DLP and DHP, in which only authenticated users have rights to obtain the information. The proposed scheme applies the lightweight cryptographic primitives, such as one-way hash function and chaotic maps to accomplish mutual authentication and key agreement for underwater acoustic networks. The security of the proposed scheme is certified by applying the BAN logic and Random Oracle Model. Security analysis shows that our proposed scheme is safe and can meet ten security requirements and seven security goals. Performance analysis shows that our proposed scheme is more efficient compared with other resource-constrained schemes.

[EN] In this work, we show that scattered acoustic vortices generated by metasurfaces with chiral symmetry present broadband unusual properties in the far-field. These metasurfaces are designed to encode the holographic field of an acoustical vortex, resulting in structures with spiral geometry. In the near field, phase dislocations with tuned topological charge emerge when the scattered waves interference destructively along the axis of the spiral metasurface. In the far field, metasurfaces based on holographic vortices inhibit specular reflections because all scattered waves also interfere destructively in the normal direction. In addition, the scattering function in the far field is unusually uniform because the reflected waves diverge spherically from the holographic focal point. In this way, by triggering vorticity, energy can be evenly reflected in all directions except to the normal. As a consequence, the designed metasurface presents a mean correlation-scattering coefficient of 0.99 (0.98 in experiments) and a mean normalized diffusion coefficient of 0.73 (0.76 in experiments) over a 4 octave frequency band. The singular features of the resulting metasurfaces with chiral geometry allow the simultaneous generation of broadband, diffuse and non-specular scattering. These three exceptional features make spiral metasurfaces extraordinary candidates for controlling acoustic scattering and generating diffuse sound reflections in several applications and branches of wave physics as underwater acoustics, biomedical ultrasound, particle manipulation devices or room acoustics., We acknowledge financial support from the Spanish Ministry of Science, Innovation and Universities through Grant "Juan de la Cierva-Incorporacion" (IJC2018-037897-I) and PID2019-111436RB-C22, and by the Agencia Valenciana de la Innovacio through grants INNVAL10/19/016. This article is based upon work from COST Action DENORMS CA15125, supported by COST (European Cooperation in Science and Technology). JPG and VRG gratefully acknowledge the ANR-RGC METARoom (ANR-18-CE08-0021) project and the project HYPERMETA funded under the program Etoiles Montantes of the Region Pays de la Loire.

The application of deep learning to solving acoustic detection and identification challenges is a rapidly-evolving subfield of underwater acoustics. Automatic signal identification can be used for many applications, like enabling thecompilation of large datasets from many sources, which can be used to better constrain source-specific characteristics and trends. Earlier analyses (Garibbo et al., 2020) identified the different contributions of wind, weather, shippingand earthquakes. The long-term acoustic measurements regularly include calls from fin whales, whose presence and vocal activities in the area vary with seasons; their 20-Hz calls are sometimes mixed with other signals, likeearthquakes or shipping. We present here the application of deep learning to automatically identify these whale calls. Percentile analyses of the temporal variation of the frequency of calls, their Power Spectral Density (PSD), and SoundPressure Level (SPL) is carried out to determine their respective contributions to the overall soundscape and highlight relevant information about these whale populations. The deep learning approaches selected here can also beused for other types of animal vocalisations and for other short-term processes (e.g. passing ships, earthquakes of different types), assisting in their identification and in the statistical and temporal analyses of low-frequencysoundscapes.

Underwater acoustics is one of the primary areas of emphasis in the Ocean Engineering Department at the University of Rhode Island, the first Ocean Engineering program in the United States. The program offers Bachelors, Masters (thesis and non-thesis options) and Ph.D. degrees in Ocean Engineering. These programs are based at the Narragansett Bay campus, providing access to a living laboratory for student learning. Some key facilities of the program are an acoustics tank, a 100-foot-long wave tank, and currently the R/V Endeavor, a UNOLS oceanographic research vessel operated by the University of Rhode Island. A new Regional Class vessel is anticipated in 2021. At the graduate level, students are actively involved in research focused in areas such as acoustical oceanography, propagation modeling, acoustic positioning and navigation, geoacoustic inversion, marine mammal acoustics, ocean acoustic instrumentation, and transducers. An overview of classroom learning and ongoing research will be provided, along with information regarding the requirements of entry into the program.

An important vision of next generation mobile system is to provide global internet access. The Space-Terrestrial Integrated Network(STIN) has been proposed and intensively studied to tackle this challenge. Due to the severe attenuation of radio signals in water, the STIN cannot be directly applied in underwater scenarios. In this paper we envision a framework of integrated radio-acoustic network arming at high-efficient data transmission in underwater scenarios, where acoustic signal is for underwater communication and radio signal is for surface and air communications. Since radio links have much higher data transmission rate and lower delay, in the integrated radio-acoustic network, the acoustic links easily become congested, at the same time the radio links are not fully utilized. We therefore propose that the integrated radio-acoustic network should be properly designed to minimize the hop count of acoustic links, as well as the signaling overhead in the acoustic subnetwork. We then present a novel network framework and the relative technologies to help moving the signaling overhead to the radio subnetwork.

The demand for acoustic positioning is increasing in various fields, meanwhile, it is very important to disturb acoustic positioning for underwater acoustics countermeasure and ship stealth technology. In this paper, a one-dimensional (ID) deep neural network based on adversarial learning to generate pseudo ship-radiated noises is presented, and a ID convolutional network for classification is also given for evaluating the generated pseudo ship-radiated noises. The experimental results show that the proposed solution is effective to generate pseudo ship-radiated noises.

Highly-reverberate underwater environments pose challenges for conventional localization techniques due to the highly non-linear nature of reflective surfaces, multi-path, and scattering fields. In this paper, we compare different machine learning methods for passive localization and tracking of single, non-stationary, underwater acoustic sources using multiple underwater acoustic vector sensors. We incorporate ordinal classification for localization in a novel approach to acoustic localization and compare the results with other standard methods. Realworld experiments demonstrate that both categorical and ordinal classification using deep LSTM networks significantly reduce localization error.

Due to the difficulty of acquiring underwater target data, the recognition of small samples of underwater acoustic targets has always been a difficult problem in the field of underwater acoustics. To solve this problem, this paper proposes a few-shot learning method based on data enhancement and transfer learning for underwater target recognition. This paper takes two-dimensional time-frequency spectrum as input, and uses a variety of data enhancement schemes, combined with transfer learning methods to achieve target classification. In terms of experiments, we used hydrophones to collect 3 times data in different sea areas as a data set for verification, including 10 types of targets. The experimental results show that our system could achieve the accuracy of 0.82.

Wireless communication in an aquatic environment constitutes an active field of research and opens up new prospects for the future. Underwater wireless communication is practically unexplored field compared with terrestrial wireless communication. The growing interest in underwater acoustic communications is due to the expansion of applications, which were, at the beginning exclusively military and nowadays commercial ones. In this study, the fundamental of underwater acoustics (sound velocity, absorption, attenuation, SNR…) governing the wireless communication systems in seawater are presented, then some optimal parameters (optimal frequency, bandwidth, attenuation…) for a communication characterized by a weak loss of transmission are deduced. This investigation is based not only on Mackenzie’s model, which provides a good representation of the sound velocity profile in seawater, but also on Francois and Garrison model taking into account all absorption phenomena. The simulation of Mackenzie’s model by analyzing the effects of some parameters on sound velocity is carried out and due to the accuracy of the model, Mackenzie’s equation can be selected as the basis of all propagation delay modeling. As for Francois and Garrison model based upon a large number of previous experimental results and theoretical studies, it is adopted in this study to analyze with an accurate assessment the frequency dependent component of SNR.

This paper proposes the detection and removal of crosstalk noise using a convolutional neural network in the images of forward scan sonar. Because crosstalk noise occurs near an underwater object and distorts the shape of the object, underwater object detection is limited. The proposed method can detect crosstalk noise using the neural network and remove crosstalk noise based on the detection result. Thus, the proposed method can be applied to other sonar-image-based algorithms and enhance the reliability of those algorithms. We applied the proposed method to a three-dimensional point cloud generation and generated a more accurate point cloud. We verified the performance of the proposed method by performing multiple indoor and field experiments.

Collisions in underwater acoustic networks can not be tolerated due to the fundamental differences between underwater acoustic propagation and terrestrial radio propagation. Thus, conceiving medium access protocols that avoid collision to the most possible extent is of paramount importance. In this paper, a multi-channel MAC protocol, MC-UWMAC, especially designed for underwater acoustic sensor networks, is proposed and evaluated. MC-UWMAC is an energy efficient MAC protocol that aims at achieving a collision free communication. MC-UWMAC operates on a single slotted control channel to avoid the missing receiver problem and multiple data channels to improve the network throughput. To guarantee to the most possible extent a collision free communication, MC-UWMAC uses two key newly designed procedures: i) a grid based slot assignment procedure on the common slotted control channel that approaches the 2-hop conflict free slot assignment and ii) a quorum based data channel allocation procedure. More precisely, according to MC-UWMAC, a sender uses its own dedicated slot on the common control channel for handshaking with an intended neighbor receiver. However, data transmission takes place in a unique data channel especially reserved for this pair of neighbor nodes. In fact, MC-UWMAC reserves for each pair of neighbor nodes a unique data channel that aims at being 2-hop conflict free. As such, the probability of collision is highly reduced and even completely mitigated in some scenarios. In addition, by using multiple channels, MC-UWMAC allows multiple data communications along with handshaking on the common control channel to take place at the same time and hence the network throughput as well as energy efficiency are improved. Simulation results show that MC-UWMAC can greatly improve the network performance especially in terms of energy consumption, throughput, and end-to-end delay.

In this paper, we investigate an automatic repeat request (ARQ) for reliable transmission over half-duplex links. We design a method based on grouped packet coding (GPC) that combines a stop-and-wait (S&W) ARQ procedure with random linear packet coding and selective acknowledgments applied to groups of coded packets. Our goal in doing so is to boost the throughput efficiency on poor-quality links with long delay. Such links are notably encountered in underwater acoustic channels, where the bit error rate may be as high as $10^{-3}$ and round-trip delays can be measured in thousands of bits. To quantify the benefits of the proposed S&W-GPC method, we evaluate its throughput efficiency analytically and compare it with the throughput efficiency of standard S&W methods, as well as the benchmark efficiency of full-duplex methods. Our results show that S&W-GPC outperforms all other techniques on half-duplex links with long delay, as well as rateless packet coding on full-duplex links with long delay. We present results for a point-to-point link, as well as for a multicast network. In addition to the performance analysis, we offer guidelines for an optimal system design, which involves a judicious choice of the packet size, packet coding, and grouping parameters.

With the advance of the Internet of Underwater Things, underwater acoustic sensor network (UASN) has been considered as a promising technology for oceanic engineering to explore and exploit marine resources. Due to the time variability, frequency selectivity, and the very limited available bandwidth, underwater acoustic (UWA) channels are generally known as one of the most challenging communication media in use today. The highly dynamic nature of UWA links calls for adaptive, scalable, and efficient routing schemes for UASNs. Depth-based routing has attracted much attention because it can work efficiently without the need for full-dimensional location information of sensors. However, it suffers from the problems of void region and detouring forwarding. To this end, this paper proposes a distance-vector-based opportunistic routing (DVOR) scheme to address these problems. DVOR uses a query mechanism to establish the distance vectors for UWA nodes, which record the smallest hop counts toward the sink. Then, an opportunistic routing is developed to coordinate the packet forwarding based on the distance vectors. DVOR has a low signaling overhead in opportunistic forwarding, as well as the ability to avoid the problems of void region and long detour. Simulation results show that DVOR outperforms the existing routing protocols in terms of packet delivery ratio, energy-efficiency, and average end-to-end delay.

This paper proposes cooperative routing algorithms to improve the performance of underwater acoustic sensor networks (UW-ASNs). With the consideration of the poor acoustic link quality, a cross-layer design of physical layer and network layer is described for selecting simultaneously routing relays (RR) for forwarding data on routing paths and cooperative relays (CR) for one-hop cooperative communications. In the networks, sources that have data to transmit independently selects their own relays (i.e., both RR and CR) among their neighbors based on their link quality indicators (i.e., signal-to-noise ratio (SNR), time of arrival (ToA)) and their physical distances represented by hop count (HC) to the destination. Exploiting packet receiving or overhearing in the networks, these parameters are averaged and updated frequently to adapt to the unreliable and varying characteristics of acoustic channel over the time. By this way, the “best” relays with the “best” estimated measurements are selected reliably. Our simulation results show that the proposed algorithms improve the network performance in terms of end-to-end delay, energy consumption and packet delivery ratio.

In this letter, we propose a physical (PHY)-layer authentication framework to detect spoofing attacks in underwater sensor networks. This scheme exploits the power delay profile of the underwater acoustic channel to discriminate the sensors and applies reinforcement learning (RL) to choose the authentication parameter without being aware of the network and spoofing model. We propose an RL-based authentication scheme to provide light-weight spoofing detection and a deep RL-based authentication scheme to further improve the authentication accuracy for sinks that support deep learning. Experiment results show that this scheme improves the spoofing detection accuracy and increases the utility of the network compared with the benchmark PHY-layer authentication.

This paper mainly investigates the application of underwater acoustic sensor networks (UASNs), which are characterized by large-scale, sparse distribution, and varying traffic loads. Since the underwater acoustic channel is known for limited bandwidth, time variation, and long propagation delays, the strategy to access the common communication medium is required to improve the performance of UASNs. This paper proposes a delay and queue aware adaptive scheduling-based medium access control (DQA-MAC) protocol for UASNs. It combines adaptive scheduling transmission, reduction of handshaking packets, and concurrent transmission with the propose of improving the performance of network throughput, shortening end-to-end delay, reducing average energy consumption, and enhancing the fairness of transmission. Data transmission time is scheduled based on the information of propagation delays and the number of data packets waiting in each node queue. Furthermore, the strategy of concurrent transmission is implemented to leverage the long propagation delays. At last, reducing the number of handshaking packets is achieved with the approach of exchanging information by specially designed packets frames. The simulation results show that the proposed protocol outperforms the related traditional protocols in networks with varying traffic loads.

The development of a compact, battery-powered sensor platform intended for underwater applications and using hydroacoustic communication is reported. The design and manufacturing of the device is described with emphasis on the method used to monitor and reduce the current consumption. The devices have been encapsulated in epoxy and evaluated under field conditions, which showed that the system is usable in its current form. In addition to hardware improvements, e.g., in order to increase battery lifetime, the next generation of the system will implement forward error correction and improved receiver signal processing to reduce the impact of signal reflections.

Target recognition is one of the most important technologies in the field of underwater acoustic detection, and has been widely used in the military. Target radiation noise and environmental noise are random signals, environmental noise has obvious time-varying characteristics, so a specific method is difficult to achieve multi-class similar target classification and recognition. For the targets with similar auditory characteristics, take first preliminary classification and then accurate recognition as technical ideas, a feature extraction method based on continuous spectrum in Gammatone frequency bands is proposed. Initial target classification is realized through Gammatone feature extraction, and accurate identification is realized through extracting Continuous spectrum feature in Gammatone subband. By using the real recording data of surface target, verifying the proposed method. Results show that the proposed method can effectively classify and recognize two kinds of objects with similar auditory characteristics.

Internet of Underwater Things (IoUT) consists of numerous sensor nodes distributed in an underwater area for sensing, collecting, processing information, and sending related messages to the data processing center. However, the characteristics of the underwater environment will bring strict limitations on communication coverage and power scarcity to IoUT networks. Applying cooperative communications to IoUT networks can expand the communication range and alleviate power shortages. In this article, we investigate the cooperative communication problem in a power-limited cooperative IoUT system and propose a reinforcement learning-based underwater relay selection strategy. Specifically, we first determine the optimal transmit powers of the source node and the selected underwater relay to maximize the end-to-end signal-to-noise ratio of the system. Then, we formulate the underwater cooperative relaying process as a Markov process and apply reinforcement learning to obtain an effective underwater relay selection strategy. The simulation results show that the performance of the proposed scheme outperforms that of the equal transmit power settings under the same conditions. In addition, the proposed deep Q-network-based underwater relay selection strategy improves the communication efficiency compared with the Q-learning-based strategy, and the number of iterations needed for convergence can be effectively reduced. This work was supported in part by the National Natural Science Foundation of China under Grant 61871339, Grant 61971365, and Grant 61901403; in part by the Natural Science Foundation of Fujian Province under Grant 2019J05001 and Grant 2019J01046; and in part by the Key Laboratory of Digital Fujian on IoT Communication, Architecture and Safety Technology under Grant 2010499.