The health of trees has become an important issue in forestry. How to detect the health of trees quickly and accurately has become a key area of research for scholars in the world. In this paper, a living tree internal defect detection model is established and analyzed using model-driven theory, where the theoretical fundamentals and implementations of the algorithm are clarified. The location information of the defects inside the trees is obtained by setting a relative permittivity matrix. The data-driven inversion algorithm is realized using a model-driven algorithm that is used to optimize the deep convolutional neural network, which combines the advantages of model-driven algorithms and data-driven algorithms. The results of the comparison inversion algorithms, the BP neural network inversion algorithm, and the model-driven deep learning network inversion algorithm, are analyzed through simulations. The results shown that the model-driven deep learning network inversion algorithm maintains a detection accuracy of more than 90% for single defects or homogeneous double defects, while it can still have a detection accuracy of 78.3% for heterogeneous multiple defects. In the simulations, the single defect detection time of the model-driven deep learning network inversion algorithm is kept within 0.1 s. Additionally, the proposed method overcomes the high nonlinearity and ill-posedness electromagnetic inverse scattering and reduces the time cost and computational complexity of detecting internal defects in trees. The results show that resolution and accuracy are improved in the inversion image for detecting the internal defects of trees.

The quality of the veneer directly affects the quality and grade of a blockboard made of veneer. To improve the quality and utilization of a defective veneer, a novel deep generative model-based method is proposed, which can generate higher-quality inpainting results. A two-phase network is proposed to stabilize the network training process. Then, region normalization is introduced to solve the inconsistency problem between the mean and standard deviation, improve the convergence speed of the model, and prevent the model gradient from exploding. Finally, a hybrid dilated convolution module is proposed to reconstruct the missing areas of the panels, which alleviates the gridding problem by changing the dilation rate. Experiments on our dataset prove the effectiveness of the improved approach in image inpainting tasks. The results show that the PSNR of the improved method reaches 33.11 and the SSIM reaches 0.93, which are superior to other methods.

A novel kernel recursive second-order sine adaptive (KRSOSA) algorithm was devised for identifying non-linear systems, which was constructed using a symmetry squared sine function to develop a novel kernel loss function and recursive scheme. In the proposed KRSOSA algorithm, the squared sine function provides resistance to impulsive noise due to the sine operation, which was well-derived and investigated in the framework of kernel adaptive filtering (KAF). The behavior of the proposed KRSOSA algorithm was investigated and analyzed using computer simulations, which provided good performance for identifying non-linear systems under impulsive noises.

This article proposes a deep unfolding algorithm based on Multiple Signal Classification (MUSIC) to address the structural distortions caused by the high contrast in electromagnetic parameters between trees and insects, as well as nonlinear coupling effects. Termed RTU-MUSIC, this unfolding network embeds the physical characteristics of the MUSIC subspace projection criterion into the network design process. RTU-MUSIC adopts a dual-branch structure comprising parallel angle and distance estimation modules. The angle branch mimics the orthogonal structure of the MUSIC subspace spectrum and incorporates a frequency attention mechanism to ensure robust angle estimation. The distance branch leverages the frozen angular information as a prior to simulate the spectral-peak extraction of MUSIC in the radial dimension, thereby estimating the target distance. Furthermore, by integrating Rayleigh-scattering priors via multi-scale features, the network achieves joint classification and regression for target sizing. By fusing angular and radial information, RTU-MUSIC reconstructs the scattering profile in a polar coordinate system to achieve high-resolution imaging. Experimental results demonstrate that RTU-MUSIC outperforms both traditional physical methods and conventional deep learning approaches, exhibiting superior generalization capability. Through deep unfolding, RTU-MUSIC bridges the gap between conventional physical models and deep learning, providing a novel perspective for the nondestructive imaging detection of internal insect infestations in trees.