Impulsive noise can greatly affect the performance of underwater acoustic (UA) orthogonal frequency-division multiplexing (OFDM) systems. In this paper, by utilizing the sparsity of the UA channel impulse response and impulsive noise, we first propose a novel sparse Bayesian learning (SBL) based expectation maximization (EM) algorithm for joint channel estimation and impulsive noise mitigation in UA OFDM systems. Secondly, considering that the UA channel and impulsive noise are fast time-varying, we develop a new approach which combines the SBL with the forward-backward Kalman filtering to track the UA channel and impulsive noise. To further improve the system performance, we utilize the information available on data subcarriers for joint time-varying channel estimation and data detection, based on the SBL algorithm and the Kalman filter. The performance of our proposed algorithms is verified through both numerical simulations and by data collected during a UA communication experiment conducted in the estuary of the Swan River, Perth, Australia. The results demonstrate that compared with existing approaches, the proposed algorithms achieve a better system bit-error-rate and frame-error-rate performance.
17 February 2023 in ACM Transactions on Multimedia Computing, Communications, and Applications
Generating food images from recipe and ingredient information can be applied to many tasks such as food recommendation, recipe development, and health management. For the characteristics of food images, this paper proposes ML-CookGAN, a novel CGAN. This network enables the generation of food images based on recipe and ingredient labels. The generator of ML-CookGAN, Multi-Label Fusion Generator, converts recipe and ingredient labels into different granularity features and generates corresponding food images. The discriminator of ML-CookGAN, Multi-Branch Discriminator, implements discrimination and classification with a multi-branch structure. In addition, we propose two training strategies, Region-Wise Pooling and Image Style Distillation, to better the network performance. Region-Wise Pooling handles region-wise features with the discriminator. Image Style Distillation aims at extracting image latent features to assist image generation by an unsupervised method. The experiments conducted on VIREO Food-172 databases validate the proposed method to generate high-quality Chinese food images. And Region-Wise Pooling and Image Style Distillation are proven to enhance the diversity and realism of generated food images.
11 November 2022 in Computerized Medical Imaging and Graphics
Targeting at a better design of the analogue network coding (ANC)-assisted two-way amplify-and-forward (AF) multiple-input multiple-output (MIMO) multi-relay communication systems, we bring in the nonlinear minimal mean-squared error (MMSE)-decision feedback equalization (DFE) receiving technique to jointly optimize the source precoding, relay amplifying, feed-forward and feedback matrices. Under the transmission power constraints at both source nodes and each relay node, the two-way sum mean-squared error (MSE) of the signal waveform estimation of all data streams is minimized. To solve the complicated nonconvex optimization problem with four groups of system parameters, this paper develops an iterative block coordinate descent (BCD) algorithm, which converges to at least a Nash point. On the basis of it, for mitigating the error propagation in MMSE-DFE receivers, a group of permutation matrix variables, determining the detection orders of all data streams, are further introduced in our system optimization. Moreover, in case there is no sufficiently precise channel state information (CSI), we also make an extension of the developed algorithms, yielding a robust design scheme, to handle the channel uncertainties. Numerical simulation results show that, compared with the existing linear MMSE receiving-based algorithm, our proposed nonlinear ones provide improved MSE and bit-error-rate (BER) performance as well as good robustness against the imperfect CSI, indicating a promising application prospect of this research.
Recently the orthogonal frequency division multiplexing (OFDM) technique has attracted increasing interests in underwater acoustic (UA) communications. In this paper, we present an OFDM-based UA communication system, which is designed based on the National Instruments LabVIEW software and the CompactDAQ device. Details on both the transmitter and receiver system design are discussed. The performance of this UA OFDM system is verified through recent UA communication experiments performed in a tank, in the Canning River, and in the estuary of the Swan River, Western Australia. Experimental results show that the system achieves a reliable bit error rate performance even with high-order modulation schemes. Compared with conventional field-programmable gate array and digital signal processor based designs, the proposed implementation simplifies the prototype design process and reduces the software development time. The proposed system provides a flexible and reconfigurable prototype for researchers to test and validate the performance of UA communication algorithms in real UA channels.