Gas disaster is one of the major disasters faced by coal mines, and more than 50 in the working face. However, due to the small number of gas monitoring sensors and the heavy workload of artificial inspection of the working face, it is very difficult to monitor the high coverage of the working face. Aiming at the problems of low coverage of monitoring data and high acquisition cost, this paper uses sparse mobile crowdsensing (MCS) to monitor the gas concentration, which specifically involves the cell selection of sensing area and the data inference of gas concentration in unaware area. First, this paper combines gas source distribution and working face air flow characteristics to efficiently divide the gas concentration sensing cells. We propose cell selection based on distributed weighted self-attention mechanism deep reinforcement learning (DWS-DQN). The cell selection algorithm utilizes attention mechanism capture the key states of reinforcement learning to assist in optimization and decisionmaking. Second, we propose gas concentration inference based on diffusion coefficient weighting (DCW). Based on the gas concentration diffusion coefficient of coal mine working face, we weighted the quantitative results of different characteristics to construct the gas concentration inference model. Finally, experiments on two real coal mines sensing datasets verify the effectiveness of our proposed algorithms. Compared to the baseline method, the DWS-DQN model and DCW model both exhibit good performance. The method based on the combination of DWS-DQN and DCW reduces the average MAPE result by 6.87%.

An improved Retinex fusion image enhancement algorithm is proposed for the traditional image denoising methods and problems of halo enlargement and image overexposure after image enhancement caused by the existing Retinex algorithm. First, a homomorphic filtering algorithm is used to enhance each RGB component of the underground coal mine surveillance image and convert the image from RGB space to HSV space. Second, bilateral filtering and multi-scale retinex with color restoration (MSRCR) fusion algorithms are used to enhance the luminance V component while keeping the hue H component unchanged. Third, adaptive nonlinear stretching transform is used for the saturation S-component. Last, the three elements are combined and converted back to RGB space. MATLAB simulation experiments verify the superiority of the improved algorithm. Based on the same dataset and experimental environment, the improved algorithm has a more uniform histogram distribution than the multi-scale Retinex (msr) algorithm and MSRCR algorithm through comparative experiments. At the same time, the peak signal-to-noise ratio (PSNR), structural similarity (SSIM), standard deviation, average gradient, mean value, and colour picture information entropy of the images were improved by 8.28, 0.15, 4.39, 7.38, 52.92 and 2.04, respectively, compared to the MSR algorithm, and 3.97, 0.02, 34.33, 60.46, 26.21, and 1.33, respectively, compared to the MSRCR algorithm. The experimental results show that the image quality, brightness and contrast of the images enhanced by the improved Retinex algorithm are significantly enhanced, and the amount of information in the photos increases, the halo and overexposure in the images are considerably reduced, and the anti-distortion performance is also improved.

The Internet of Health Things (IoHT) enables health devices to connect to the Internet and communicate with each other, which provides the high-accuracy and high-security diagnosis result in the medical area. As essential parts of the IoHT, computed tomography (CT) images help doctors diagnose disease. In the traditional disease diagnosing process, low-resolution medical CT images produce low-accuracy diagnosis results for microlesions. Moreover, CT images can only provide 2D information about organs, and doctors should estimate the 3D shape of a lesion based on experience. To solve these problems, we propose a 3D reconstruction method for secure super-resolution computed tomography (SRCT) images in the IoHT using deep learning. First, we use deep learning to obtain secure SRCT images from low-resolution images in the IoHT. To this end, we adopt a conditional generative adversarial network (CGAN) based on the edge detection loss function (EDLF) in the deep learning process, namely EDLF-CGAN algorithm. In this algorithm, the CGAN is employed to generate SRCT images with luminance and contrast as the input auxiliary conditions, which can improve the accuracy of super-resolution (SR) images. An EDLF is proposed to consider the edge features in the generated SRCT images, which reduces the deformation of generated image. Second, we apply the secure SR images generated from the deep learning method to perform 3D reconstruction. An advanced ray casting 3D reconstruction algorithm that can reduce the number of rays by selecting the appropriate bounding box is proposed. Compared with the traditional algorithm, the proposed ray casting 3D reconstruction algorithm can reduce the time and memory cost. The experimental results show that our EDLF-CGAN has a better SR reconstruction effect than other algorithms via the indicators of the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). In addition, our advanced ray casting 3D reconstruction algorithm greatly improves the efficiency compared with the traditional ray casting algorithm.

Image super-resolution reconstruction is one of the methods to improve resolution by learning the inherent features and attributes of images. However, the existing super-resolution models have some problems, such as missing details, distorted natural texture, blurred details and too smooth after image reconstruction. To solve the above problems, this paper proposes a Multi-scale Dual-Attention based Residual Dense Generative Adversarial Network (MARDGAN), which uses multi-branch paths to extract image features and obtain multi-scale feature information. This paper also designs the channel and spatial attention block (CSAB), which is combined with the enhanced residual dense block (ERDB) to extract multi-level depth feature information and enhance feature reuse. In addition, the multi-scale feature information extracted under the three-branch path is fused with global features, and sub-pixel convolution is used to restore the high-resolution image. The experimental results show that the objective evaluation index of MARDGAN on multiple benchmark datasets is higher than other methods, and the subjective visual effect is better. This model can effectively use the original image information to restore the super-resolution image with clearer details and stronger authenticity.

Edge computing can provide many key functions without connecting to centralized servers, which enables remote areas to obtain real-time medical diagnoses. The combination of edge computing and Internet of things (IoT) devices can send remote patient data to the hospital, which will help to more effectively address long-term or chronic diseases. CT images are widely used in the diagnosis of clinical diseases, and their characteristics are an important basis for pathological diagnosis. In the CT imaging process, speckle noise is caused by the interference of ultrasound on human tissues, and its component information is complex. To solve these problems, we propose a 3D reconstruction method for noisy CT images in the IoT using edge computing. First, we propose a multi-stage feature extraction generative adversarial network (MF-GAN) denoising algorithm. The generator of MF-GAN adopts the multi-stage feature extraction, which can ensure the reconstruction of the image texture and edges. Second, we apply the denoised images generated from the MF-GAN method to perform the 3D reconstruction. A marching cube (MC) algorithm based on regional growth and trilinear interpolation (RGT-MC) is proposed. With the idea of regional growth, all voxels containing iso-surfaces are selected and calculated, which accelerates the reconstruction efficiency. The intersection point of the voxel and iso-surface is calculated by the trilinear interpolation algorithm, which effectively improves the reconstruction accuracy. The experimental results show that MF-GAN has a better denoising effect than other algorithms. Compared to other representative 3D algorithms, the RGT-MC algorithm greatly improves the efficiency and precision.