For classification of underwater acoustic signals, we propose a novel sparse anisotropic chirplet transform (ACT) to reveal fine time-frequency structures. The signal features in the form of a time-frequency map are fed into a deep convolutional neural network, referred to as a time-frequency feature network (TFFNet), which brings flexibility to signal classification. The TFFNet is based on a novel efficient feature pyramid enhancing feature (EFP) maps by aggregating the context information at different scales. To remove the gridding artifacts on enhanced feature maps, a form of aggregating transformation, a forward feature fusion, is utilized to merge the forward feature maps. Main contributions of this work are a novel sparse ACT, a TFFNet classifier, and an EFP with forward feature fusion. Experimental results demonstrate that the sparse ACT provides a high-resolution time-frequency representation of underwater signals and the TFFNet improves the classification performance compared to known networks and two machine learning methods (random forest and support vector machine with radial basis function kernel) on two real data sets, an underwater acoustic communication signal data set and whale sounds data set.

The impulsive noise and the time-varying channel are two major detrimental factors which greatly constrain the performance of underwater acoustic communications (UACs). Utilizing the joint sparsity of the impulsive noise and the channel impulse response, the paper proposes the generalized approximate message passing (GAMP)-based sparse Bayesian learning (SBL) frameworks for joint impulsive noise mitigation and channel estimation and tracking for orthogonal frequency division multiplexing (OFDM) UACs. Firstly, the SBL framework for the joint estimation is employed. To reduce the computational complexity, the GAMP is introduced into the expectation-maximization (EM) algorithm, and a low-complexity GAMP based SBL framework is formulated without performance degradation. To further estimate and track the impulsive noise and channel state information in the slow time-varying scenarios, we propose a novel GAMP-based temporal SBL framework. The factor graph and GAMP are used to achieve the approximated estimation for the posterior statistics of both the channel state information and the impulsive noise. The algorithm formulates the message passing scheduling for the EM algorithm to solve the joint multiple sparse signal recovery problem. Simulations and sea-trial results demonstrate that the proposed algorithms significantly improve the performance in terms of the mean square error of channel estimation, impulsive noise estimation, bit error rate and computational complexity compared with their corresponding SBL-based counterparts.

Classic multireceiver synthetic sonar (SAS) reconstruction algorithms relying upon Loffeld’s bistatic formula (LBF) should firstly utilize the data segmentation approach to remove the multireceiver deformation (MD) term. Usually, the small sub-block is required by traditional LBF based imaging algorithms to produce the high performance result. To address this issue, we describe a receiver-by-receiver based imaging algorithm. The presented method firstly reformulates the original LBF to range dependent and independent terms. Then, the image reconstruction receiver-by-receiver is carried out. The LBF reformulation and the quadratic expansion of range-dependent term needed by subsequent range-Doppler (RD) algorithm would generate approximation error corrected by data segmentation approach in frequency domain. After performing the range cell migration correction (RCMC) receiver-by-receiver, the signal in range-Doppler domain related to each receiver is coherently synthesized, and the azimuth offset is thereafter corrected. The focusing result would be produced when the azimuth inverse Fourier transform (IFT) is completed. On the basis of simulation and real data test experiments, conventional focusing approach with wide sub-block is seriously affected by ghost targets, which are successfully avoided by presented method with the same wide sub-block. It indicates that the presented method relaxes the requirement for the sub-block width.

Noise fitting plays a key role in underwater acoustic communications. Traditional approximate models can fit global heavy-tail distribution of the impulsive noise with fixed parameters. These models are unable to cover local distributions with arbitrary lengths. In this paper, we propose a generative-adversarial-network-based underwater noise simulator (GUNS), which constructs a deep-neural-network-based generator and a convolutional-neural-network-based discriminator are constructed to learn the heavy-tail distribution of the impulsive noise. Based on the noise collected in the Wuyuanwan Bay, Xiamen, probability distribution function of the underwater acoustic noise simulated by the proposed GUNS performs lower Kullback-Leibler divergence, Jensen-Shannon divergence and mean square error than that employed traditional approximate models.

A spatial modulation (SM) scheme has been developed as a hopeful candidate for spectral and energy-efficient wireless communication systems, as it provides a great judgment for the system performance, data transmission rate, receiver complexity, and energy/spectrum efficiency. In SM, the data is conveyed by both habitual M-ary signal constellations and the transmit antennas indices. Therefore, the system data rate improvement due to the side information bits transmitted, encapsulated in indices of the transmit antennas, improves the SM transmission efficiency compared to the different MIMO players. The information bits transmitted over the antenna index and data symbol constellation using M-ary signal performance have different levels of bit error rate (BER) performance. This paper proposes unequal error protection (UEP) scheme for image transmission over the Internet of Underwater Things (IoUTs) using SM. The Set Partitioning in Hierarchical Trees (SPIHT) coders encode the underwater image and classify the encoded bits in two categories: critical and uncritical bits. The critical bits are transmitted over the SM index bits and have a low BER while the uncritical bits are transmitted over high order M-ary signal constellation to resolve the underwater acoustic channel bandwidth limitation problem. The proposed SM-UEP technique has been developed carefully with enough justification and evaluation over the measured underwater acoustic channel and the simulated channel. The simulation results show that the proposed SM-UEP can increase the average peak signal-to-noise ratio (PSNR) of the reconstructed received image considerably, and significantly.

This letter presents a new scheme to solve the issue of high redundant energy in Unique Word Orthogonal Frequency Division Multiplexing (UW-OFDM). The proposed scheme, called Low-Redundant Energy UW-OFDM (LRE-UW-OFDM), is suitable for time-varied harsh channels such as the Underwater Acoustic (UWA) channel were inserting the UW data in the time domain leads to huge redundant energy and a dramatic deterioration in Bit Error Rate (BER) performance. The insertion of UW in the proposed LRE-UW-OFDM is done in frequency domain to be any desired sequences in time domain with constant redundant subcarriers energy regardless of the size and the location of data subcarriers. The proposed scheme is evaluated over a long-delay UWA channel demonstrating its outperformance against conventional schemes in terms of BER and mean symbol energy.