Search

The fabric defect models based on deep learning often demand numerous training samples to achieve high accuracy. However, obtaining a complete dataset containing all possible fabric textures and defects is a big challenge due to the sophisticated and various fabric textures and defect forms. This study created a two-stage deep pix2pixGAN network called Dual Deep pix2pixGAN Network (DPGAN) to address the above problem. The defect generation model was trained based on the DPGAN network to automatically “transfer” defects from defected fabric images to clean, defect-free fabric images, thus strengthening the training data. To evaluate the effectiveness of the defect generation model, extensive comparative experiments were conducted to assess the performance of the fabric defect detection before and after data enhancement. The results indicate that the detection accuracy was improved regarding the belt_yarn, hole, and stain defect.

Non-rigid 3D shape correspondence aims to establish dense correspondences between two non-rigidly deformed 3D shapes. However, the variability and symmetry of non-rigid shapes usually lead to mismatches due to shape deformation, topological changes, or data with severe noise. To finding an accurate correspondence between 3D dynamic shapes for the local deformation complexity, this article proposes a Relation Constrained Capsule Graph Network (RC-CGNet), which combines global and local features by encouraging the relation constraints between the embedding feature space and the input shape space based on the functional maps framework. Specifically, we design a Diffusion Graph Attention Network (DGANet) to segment the surface into parts with correct edge boundary between two regions. The Minimum Spanning Tree (MST) of geodesic curves among the singularities obtained from the segmented parts is added as relation constraints, which can compute isometric correspondences in both direct and symmetric directions. Besides that, the relation-and-attention constrained neural networks are designed to learn the shape correspondence via attention-aware CapsNet and functional maps under relation constraints. To improve the convergence speed and matching accuracy, we propose an optimized residual network structure based on the Nesterov Accelerated Gradient (NAG) to extract local features, and use graph convolution structure to extract global features. Moreover, a lightweight Gated Attention Module (GAM) is designed to fuse global and local features to obtain a richer feature representation. Since the capsule network has better spatial reasoning ability than the traditional convolutional neural network, our novel network architecture is a dual-route capsule network based on Routing Attention Fusion Block (RAFB), filtering low-discriminative capsules from a holistic view by exploiting geometric hierarchical relationships of semantic parts. Experiments on open datasets show that our method has excellent accuracy and wide adaptability. [ABSTRACT FROM AUTHOR]

Electromagnetic metamaterial (EM metamaterial) with a double‐layer spiral structure is often used to enhance the transmission efficiency of wireless power transfer (WPT). When EM metamaterial is used as an array, its AC resistance and loss cannot be ignored due to the high‐frequency magnetic field of WPT. This paper decreases EM metamaterial's loss by increasing its quality factor according to the quality factor theory and proposes a novel structure. This structure adopts a non‐uniform linewidth, which can decrease the proximity effect resistance of the EM metamaterial as well as maintain its high inductance. When using the proposed EM metamaterial to form an array, to enhance its effect in modulating the magnetic field, a hybrid EM metamaterial slab (HMS) is constructed by adjusting the series resonance capacitor. The corresponding samples of EM metamaterial with the non‐uniform linewidth structure are developed. The experiment results prove that compared to the uniform linewidth structure, the equivalent resistance and loss of the non‐uniform linewidth structure respectively are decreased by about 5.48% and 19.73%, and the quality factor is enhanced to 556.874. The HMS constructed by the proposed EM metamaterial can enhance the transmission efficiency of the experimental WPT system to 59.8%, which is about 2.1% higher than the HMS constructed by the normal EM metamaterial. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

Cysteine is an amino acid present in thiol proteins and often dictates their secondary structures. Although considered nonessential, cysteine may be essential for patients with certain metabolic diseases and can reduce the requirement for dietary methionine. Cysteine and some of its derivatives, such as N‐acetylcysteine, are considered antioxidants and widely used in animal aging studies. To provide insights into the potential anti‐aging effects of cysteine, we systematically reviewed and performed a meta‐analysis to investigate the impact of cysteine supplementation on lifespan using three model organisms: mice, nematodes, and fruit flies. A total of 13 mouse studies, 13 C. elegans studies, and 5 Drosophila studies were included in the analysis. The findings revealed that cysteine supplementation significantly reduced the risk of mortality in mice and C. elegans. Subgroup analysis showed consistent results across different starting times and administration methods and revealed adverse effects of high doses on worms and a lack of effect in nondisease mouse models. Similar to mice, the effects of cysteine supplementation on Drosophila were not statistically significant, except in transgenic flies. The study identified certain limitations, including the quality of the included studies and the potential for publication bias. We also discussed uncertainties in the underlying molecular mechanisms and the clinical application of dietary cysteine. [ABSTRACT FROM AUTHOR]