Medical image fusion aims to fuse multiple images from a single or multiple imaging modes to enhance their corresponding clinical applications in diagnosing and evaluating medical problems, a trend that has attracted increasing attention. However, most recent medical image fusion methods require prior knowledge, making it difficult to select image features. In this paper, we propose a novel deep medical image fusion method based on a deep convolutional neural network (DCNN) for directly learning image features from original images. Specifically, source images are first decomposed by low rank representation to obtain the principal and salient components, respectively. Following that, the deep features are extracted from the decomposed principal components via DCNN and fused by a weighted-average rule. Then, considering the complementary between the salient components obtained by the low rank representation, a simple yet effective sum rule is designed to fuse the salient components. Finally, the fused result is obtained by reconstructing the principal and salient components. The experimental results demonstrate that the proposed method outperforms several state-of-the-art medical image fusion approaches in terms of both objective indices and visual quality.

The hyperspectral feature extraction technique is one of the most popular topics in the remote sensing community. However, most hyperspectral feature extraction methods are based on region-based local information descriptors while neglecting the correlation and dependencies of different homogeneous regions. To alleviate this issue, this paper proposes a multi-view structural feature extraction method to furnish a complete characterization for spectral–spatial structures of different objects, which mainly is made up of the following key steps. First, the spectral number of the original image is reduced with the minimum noise fraction (MNF) method, and a relative total variation is exploited to extract the local structural feature from the dimension reduced data. Then, with the help of a superpixel segmentation technique, the nonlocal structural features from intra-view and inter-view are constructed by considering the intra- and inter-similarities of superpixels. Finally, the local and nonlocal structural features are merged together to form the final image features for classification. Experiments on several real hyperspectral datasets indicate that the proposed method outperforms other state-of-the-art classification methods in terms of visual performance and objective results, especially when the number of training set is limited.

Improving the evaporation rate of solar steam generation (SSG) has always been a research hotspot to solve the shortage of water resources. Using cotton, Fe₃O₄, polyvinyl alcohol (PVA) and diatomite (DM) as raw materials, DM/PVA/Fe₃O₄@cotton composites with both firmness and hydrophilicity were prepared. Fe₃O₄ has a wide range of light absorption characteristics and good photothermal conversion performance, and is an ideal photothermal conversion material. PVA enhances the adhesion between Fe₃O₄, cotton and DM and enhances the hardness of the sample and the internal porous structure. The existence of DM greatly improves the hydrophilicity of the sample, ensuring that the water in the lower layer can be continuously transported to the surface of the sample, and DM makes the surface of the sample rough, which reduces the reflection of sunlight and improves the efficiency of light heat conversion. Under one-sun irradiation, the temperature of the sample surface increases by 52.6 °C, the evaporation rate can reach 1.32 kg m⁻² h⁻¹ and the evaporation efficiency is 82.9%. Using this sample as the photothermal conversion layer of the SSG device, the removal rate of salt ions in seawater is more than 98% and the removal rate of heavy metal ions in sewage is close to 100%. This work provides a new idea and design method for SSG in the field of seawater desalination and sewage treatment.

Due to their almost zero relative hydrogen atom adsorption-free energy, MoS₂-based materials have received substantial study. However, their poor electronic conductivity and limited number of catalytic active sites hinder their widespread use in hydrogen evolution reactions. On the other hand, metal clusters offer numerous active sites. In this study, by loading Ni metal clusters on MoS₂ and combining them with the better electrical conductivity of graphene, the overpotential of the hydrogen evolution reaction was reduced from 165 mV to 92 mV at 10 mA·cm⁻². This demonstrates that a successful method for effectively designing water decomposition is the use of synergistic interactions resulting from interfacial electron transfer between MoS₂ and Ni metal clusters.

With the rapid development of artificial intelligence technology, image editing technology has evolved from relying on software such as Photoshop and GIMP for manual modification to using artificial intelligence technology to achieve intelligent and automated tampering of images. Editing, falsifying, and disseminating digital images have become simple and easy, leading to a crisis of confidence in digital images and reducing their reliability as judicial evidence. Therefore, how to identify falsified images, improve their trustworthiness, and avoid judicial injustice has become a problem that must be overcome in the information age. In this paper, we propose a target detection and adaptive feature analysis in image forensics based on a dual-flow layer CNN model, which can effectively perform image forensics. The results show that our algorithm has a clear theoretical basis, a small operational complexity, and a high detection accuracy.