It has always been difficult to achieve accurate information of the channel for underwater acoustic communications because of the severe underwater propagation conditions, including frequency-selective property, high relative mobility, long propagation latency, and intensive ambient noise, etc. To this end, a deep unfolding neural network based approach is proposed, in which multiple layers of the network mimic the iterations of the classical iterative sparse approximation algorithm to extract the inherent sparse features of the channel by exploiting deep learning, and a scheme based on the Sparsity-Aware DNN (SA-DNN) for UAC estimation is proposed to improve the estimation accuracy. Moreover, we propose a Denoising Sparsity-Aware DNN (DeSA-DNN) based enhanced method that integrates a denoising CNN module in the sparsity-aware deep network, so that the degradation brought by intensive ambient noise could be eliminated and the estimation accuracy can be further improved. Simulation results demonstrate that the performance of the proposed schemes is superior to the state-of-the-art compressed sensing based and iterative sparse recovery schems in the aspects of channel recovery precision, pilot overhead, and robustness, particularly under unideal circumstances of intensive ambient noise or inadequate measurement pilots.

The video transmission in the Internet-of-Things (IoT) system must guarantee the video quality and reduce the packet loss rate and the delay with limited resources to satisfy the requirement of multimedia services. In this paper, we propose a reinforcement learning based energy-efficient IoT video transmission scheme that protects against interference, in which the base station controls the transmission action of the IoT device including the encoding rate, the modulation and coding scheme, and the transmit power. A reinforcement learning algorithm state-action-reward-state-action is applied to choose the transmission action based on the observed state (the queue length of the buffer, the channel gain, the previous bit error rate, and the previous packet loss rate) without knowledge of the transmission channel model at the transmitter and the receiver. We also propose a deep reinforcement learning based energy-efficient IoT video transmission scheme that uses a deep neural network to approximate $Q$ value to further accelerate the learning process involved in choosing the optimal transmission action and improve the video transmission performance. Moreover, both the performance bounds of the proposed schemes and the computational complexity are theoretically derived. Simulation results show that the proposed schemes can increase the peak signal-to-noise ratio and decrease the packet loss rate, the delay, and the energy consumption relative to the benchmark scheme.