In this paper, we present a channel estimation approach based on deep learning to solve the problem that the orthogonal frequency division multiplexing (OFDM) system channel estimation algorithm cannot accurately obtain the channel state information in the complex environment of the mine, resulting in system performance degradation. First, LS channel estimation matrix is considered as a low-resolution image and the actual channel state information is considered as a high-resolution image. Then the optimization of the LS channel estimation matrix is achieved by the FSRCNN image super-resolution algorithm. We validate the effectiveness of the proposed algorithm by conducting experiments in different channel environments, different number of pilots, and mismatched signal-to-noise ratio scenarios. The simulation results show that the proposed scheme is much better than the traditional LS channel estimation method and the DFT-LS channel estimation method, and the accuracy of the proposed scheme approaches that of the MMSE channel estimation method when the number of pilots is low.

The critical environment of the underground mines is a risky zone for mining applications and it is very hazardous to engage the miners without a sophisticated communication system. The existing wired networks are susceptible to damage and the wireless radio systems experience severe fading that restricts the complete access to the entire assembly of a mine. Wireless optical communication is a better approach that can be incorporated in the erratic atmosphere of underground mines to overcome such issues, as lights are already used to illuminate the mine galleries. This study is focused on investigating the characteristics of visible light communication (VLC) in an underground coal mine. The entire scope of VLC is elaborated along with the influence of coal dust particles and the scattering model. The impact of coal dust clouds on visibility and attenuation is analyzed for visible light transmission. The shadowing effect generated by the pillars and mining machinery is estimated by employing the bimodal Gaussian distribution (BGD) approach in coal mines. The characteristic model of VLC for underground coal mines is presented by classifying the area of the mine into mine gallery and sub-galleries. The transmission links of VLC are categorized as the line of sight (LOS) link for direct propagation and the non-LOS (NLOS) link for reflected propagation. The scenarios of LOS and NLOS propagation are considered for each evaluating parameter. Furthermore, the performance of the proposed framework is examined by computing the received signal power, path loss, delay spread (DS), and signal to noise ratio (SNR).

Incontrast to the steady angle-dependent transmit beampattern of the conventional phased array, the counterpart of a frequency diverse array (FDA) is basically time variant and range–angle coupled, which limits its potential application in many scenarios. In this article, we consider the beamforming in joint transmit and receive domains to handle the time-variant problem and propose a novel range–angle transceiver beamforming approach based on the semicircular-FDA scheme. In particular, the transceiver scheme of semicircular-FDA is first established.In the sequel, the periodicities of its transceiver beampattern in range and angle dimensions are briefly analyzed. Based on this analysis, a semicircular-FDA applied with nonlinearly increasing frequency offset (NIFO), termed as NIFO semicircular-FDA, is proposed to achieve the beampattern with a single mainlobe peak in range–angle space. Then, an optimization problem is constructed based on an advanced bat algorithm to further reduce the sidelobe level (SLL) of the NIFO semicircular-FDA. Numerical results show that focused time-invariant beampattern with low SLL in both range and angle dimensions can be achieved with the proposed approach.

In the complex and dynamically varying underwater acoustic (UWA) channel, cooperative communication can improve throughput for UWA sensor networks. In this paper, we design a reasonable relay selection strategy for efficient cooperation with reinforcement learning (RL), considering the characteristics of UWA channel variation and long transmission delay. The proposed scheme establishes effective state and reward expression to better reveal the relationship between RL and UWA environment. Meanwhile, simulated annealing (SA) algorithm is integrated with RL to improve the performance of relay selection, where exploration rate of RL is dynamically adapted by SA optimization through the temperature decline rate. Furthermore, the fast reinforcement learning (FRL) strategy with pre-training process is proposed for practical UWA network implementation. The whole proposed SA-FRL scheme has been evaluated by both simulation and experimental data. The simulation and experimental results show that the proposed relay selection scheme can converge more quickly than classical RL and random selection with the increase of the number of iterations. The reward, access delay and data rate of SA-FRL can converge at the highest value and are close to the ideal optimum value. All in all, the proposed SA-FRL relay selection scheme can improve the communication efficiency through the selection of the relay nodes with high link quality and low access delay.

To address the problems of gradient vanishing and limited feature extraction capability of traditional CNN spectrum sensing methods in deep network structures and to effectively avoid network degradation issues under deep network structures, this paper proposes a collaborative spectrum sensing method based on Residual Dense Network and attention mechanisms. This method involves stacking and normalizing the time-domain information of the signal, constructing a two-dimensional matrix, and mapping it to a grayscale image. The grayscale images are divided into training and testing sets, and the training set is used to train the neural network to extract deep features. Finally, the test set is fed into the well-trained neural network for spectrum sensing. Experimental results show that, under low signal-to-noise ratios, the proposed method demonstrates superior spectral sensing performance compared to traditional collaborative spectrum sensing methods.

The environment of underground coal mines has challenging properties that makes this zone inadaptable for a stable communication system. Additionally, various deteriorating physical parameters strongly affect the performance of wireless networks, which leads to limited network coverage and poor quality of data communication. This study investigates the communication capability in underground coal mines by optimizing the wireless link to develop a stable network for an underground hazardous environment. A hybrid channel-modeling scheme is proposed to characterize the environment of underground mines for wireless communication by classifying the area of a mine into the main gallery and sub-galleries. The complex segments of mine are evaluated by categorizing the wireless links for the line-of-sight (LOS) zones and hybrid modeling is employed to examine the characteristics of electromagnetic signal propagation. For hybrid channel modeling, the multimode waveguide model and geometrical optic (GO) model are used for developing an optimal framework that improves the accessibility of the network in the critical time-varying environment of mines. Moreover, the influence of various deteriorating factors is analyzed using 2.4 GHz to 5 GHz frequency band to study its relationship with the vital constraints of an underground mine. The critical factors such as path loss, roughness loss, delay spread, and shadow fading are examined under detailed analysis with variation in link structure for the mine.