Search

Abstract Recent advances in deep convolutional neural networks have shown improved performance in face super‐resolution through joint training with other tasks such as face analysis and landmark prediction. However, these methods have certain limitations. One major limitation is the requirement for manual marking information on the dataset for multi‐task joint learning. This additional marking process increases the computational cost of the network model. Additionally, since prior information is often estimated from low‐quality faces, the obtained guidance information tends to be inaccurate. To address these challenges, a novel Decoder Structure Guided CNN‐Transformer Network (DCTNet) is introduced, which utilises the newly proposed Global‐Local Feature Extraction Unit (GLFEU) for effective embedding. Specifically, the proposed GLFEU is composed of an attention branch and a Transformer branch, to simultaneously restore global facial structure and local texture details. Additionally, a Multi‐Stage Feature Fusion Module is incorporated to fuse features from different network stages, further improving the quality of the restored face images. Compared with previous methods, DCTNet improves Peak Signal‐to‐Noise Ratio by 0.23 and 0.19 dB on the CelebA and Helen datasets, respectively. Experimental results demonstrate that the designed DCTNet offers a simple yet powerful solution to recover detailed facial structures from low‐quality images.

Abstract Background Kidney and eye diseases may be closely linked. Tears of the retinal pigment epithelium (RPE) have been reported to be related to kidney diseases, such as IgA nephropathy and light-chain deposition disease. However, pigment epithelium tears associated with membranous nephropathy have not been reported or systematically analysed. Case presentation A 68-year-old man presented with decreased right eye visual acuity. Optical coherence tomography (OCT) revealed cystic macular edema, localized serous detachment of the retina and loss of the outer retinal structure in the right eye and retinal pigment epithelium detachment (PED) combined with serous detachment of the retina in the left eye. Fundus fluorescein angiography (FFA) and indocyanine green angiography (ICGA) revealed giant RPE tears in the right eye and exudative age-related macular degeneration in the left eye. The patient also suffered from severe membranous nephropathy-autoimmune glomerulonephritis. Renal biopsy immunofluorescence revealed a roughly granular pattern, with immunoglobulin G (IgA), immunoglobulin G (IgG), IgM, complement C3(Components 3), λ light chain and κ light chain subepithelial staining. Conclusions It is hypothesized that severe membranous nephropathy caused immune complex deposition on the surface of Bruch membrane, resulting in weakened adhesion between the RPE and Bruch membrane and impaired RPE pump function, combined with age-related macular degeneration, leading to giant RPE tears in the right eye. Close attention should be given to the ocular condition of patients with membranous nephropathy to facilitate timely treatment and avoid serious consequences.

We propose a data-driven, model-free adaptive sliding mode control (MFASMC) approach to address the Haidou-1 ARV under-actuated motion control problem with uncertainties, including external disturbances and parameter perturbations. Firstly, we analyzed the two main difficulties in the motion control of Haidou-1 ARV. Secondly, in order to address these problems, a MFASMC control method was introduced. It is combined by a model-free adaptive control (MFAC) method and a sliding mode control (SMC) method. The main advantage of the MFAC method is that it relies only on the real-time measurement data of an ARV instead of any mathematical modeling information, and the SMC method guarantees the MFAC method’s fast convergence and low overshooting. The proposed MFASMC control method can maneuver Haidou-1 ARV cruising at the desired forward speed, heading, and depth, even when the dynamic parameters of the ARV vary widely and external disturbances exist. It also addresses the problem of under-actuated motion control for the Haidou-1 ARV. Finally, the simulation results, including comparisons with a PID method and the MFAC method, demonstrate the effectiveness of our proposed method.

Previous studies propose that NH4+ storage in metal oxides and metallic ion storage using Poly(3,4‐ethylenedioxythiophene) (PEDOT) both undergo diffusion‐controlled processes. This study, employing experimental and simulation studies, reveals that flower‐like PEDOT shells predominantly store NH4+ ions storage through surface‐controlled processes, constituting over 80 percent of the overall storage. NH4+ ions interact with PEDOT′s π–π stacking via van der Waals interactions, circumventing ionization energy and entropy barriers. Additionally, the controlled polymerization and crystallinity of PEDOT contribute significantly to this storage process. The reduction in lamellar packing distance and face‐to‐face distance between the molecular chains, coupled with an increase in crystalline domains, intensifies inter‐chain weak interactions and extends the overlap length of wave functions. These findings offer a comprehensive insight into cation storage using organic polymers. [ABSTRACT FROM AUTHOR]