Image and Feature Space Based Domain Adaptation for Vehicle Detection

The application of deep learning in the field of object detection has experienced much progress. However, due to the domain shift problem, applying an off-the-shelf detector to another domain leads to a significant performance drop. A large number of ground truth labels are required when using another domain to train models, demanding a large amount of human and financial resources. In order to avoid excessive resource requirements and performance drop caused by domain shift, this paper proposes a new domain adaptive approach to cross-domain vehicle detection. Our approach improves the cross-domain vehicle detection model from image space and feature space. We employ objectives of the generative adversarial network and cycle consistency loss for image style transfer in image space. For feature space, we align feature distributions between the source domain and the target domain to improve the detection accuracy. Experiments are carried out using the method with two different datasets, proving that this technique effectively improves the accuracy of vehicle detection in the target domain.     

Mixed-Metal MOF-74 Templated Catalysts for Efficient Carbon Dioxide Capture and Methanation

The vast chemical and structural tunability of metal–organic frameworks (MOFs) are beginning to be harnessed as functional supports for catalytic nanoparticles spanning a range of applications. However, a lack of straightforward methods for producing nanoparticle-encapsulated MOFs as efficient heterogeneous catalysts limits their usage. Herein, a mixed-metal MOF, NiMg-MOF-74, is utilized as a template to disperse small Ni nanoclusters throughout the parent MOF. By exploiting the difference in Ni O and Mg O coordination bond strength, Ni²⁺ is selectively reduced to form highly dispersed Ni nanoclusters constrained by the parent MOF pore diameter, while Mg²⁺ remains coordinated in the framework. By varying the ratio of Ni to Mg in the parent MOF, accessible surface area and crystallinity can be tuned upon thermal treatment, influencing CO₂ adsorption capacity and hydrogenation selectivity. The resulting Ni nanoclusters prove to be an active catalyst for CO₂ methanation and are examined using extended X-ray absorption fine structure and X-ray photoelectron spectroscopy. By preserving a segment of the Mg²⁺-containing MOF framework, the composite system retains a portion of its CO₂ adsorption capacity while continuing to deliver catalytic activity. The approach is thus critical for designing materials that can bridge the gap between carbon capture and CO₂ utilization.     

Structural,morphological, dielectric and magnetic properties of Zn-Zr co-doping yttrium iron garnet

In this study, yttrium iron garnet co-doped with Zn and Zr atoms with a chemical formula Y₃Zn_xZr_xFe_(5−2x)O₁₂ (x = 0.0-0.3) has been successfully prepared by the solid-state reaction method. The effects of doping concentration on the microstructure, crystal structure, magnetic properties, and dielectric properties of Y₃Zn_xZr_xFe_(5−2x)O₁₂ were investigated. The microstructure analysis indicates that co-doping of YIG with Zn and Zr can effectively reduce the grain size of the ceramic. The crystal structure results reveal that the doping concentration of Zn–Zr has substantial influence on the lattice parameters of YIG, such as, increases the lattice constant, crystal cell size, and interplanar spacing. However, the second phase of ZrO₂ appears once x ≥ 0.15. Additionally, the dielectric properties of YIG ferrite can be regulated using this Zn–Zr co-doping method. Zn–Zr co-doping can improve the dielectric stability and reduce the dielectric loss at high temperature. The magnetization measurement shows that the saturation magnetization is stabilized at x < 0.15, and the magnetic loss is decreased with the increase in the doping concentration. Overall, the findings show that the ceramic with x = 0.1 exhibits better properties included high saturation magnetization (24.607 emu/g), low magnetic loss (0.0025 @ 1 MHz), and relatively low dielectric loss (496 @ 400°C).     

基于图像增强的去雾快速算法的FPGA实现

基于图像增强方法，本文提出了一种使用亮度映射的图像去雾快速算法。此算法通过调整室外多雾场景图像的对比度，提高了雾中物体的辨识度。算法的复杂度低、处理延迟小，实时性高，利于FPGA的实现。实现时不需外存储器，延时为ns级，并提供了强度调节接口，以适应较广的应用环境。     

Single-Crystalline TiO2(B) Nanobelts with Unusual Large Exposed {100} Facets and Enhanced Li-Storage Capacity

The {100} facet of single-crystalline TiO₂(B) is an ideal platform for inserting Li ions, but it is hard to be obtained due to its high surface energy. Here, the single-crystalline TiO₂(B) nanobelts from H₂Ti₃O₇ with nearly 70% {100} facets exposed are synthesized, which significantly enhances Li-storage capacity. The first-principle calculations demonstrate an ab in-plane 2D diffusion through the exposed {100} facets. As a consequence, the nanobelts can significantly accommodate Li ions in LiTiO₂ formula with specific capacity up to 335 mAh g⁻¹, which is in good agreement with the electrochemical characterizations. Coating with conductive and protective poly(3,4-ethylenedioxythiophene)-poly(styrenesulfonate), the cut-off discharge voltage is as low as 0.5 V, leading to a capacity of 160.7 mAh g⁻¹ after 1500 cycles with a retention rate of 66% at 1C. This work provides a practical strategy to increase the Li-ion capacity and cycle stability by tailoring the crystal orientation and nanostructures.     

A dynamic SVR–ARMA model with improved fruit fly algorithm for the nonlinear fiber stretching process

Natural Computing - The fiber stretching process plays the key role in the process of fiber production and its effects is measured by the stretching ratio. The stretching ratio is determined by the...     

基于注意力机制与文本信息的用户关系抽取

随着社交媒体的发展,用户之间的关系网络对于社交媒体的分析有很大的帮助。因此,该文主要研究用户好友关系检测。以往的关于用户好友关系抽取的研究主要基于社交媒体上的结构化信息,比如其他好友关系,用户的不同属性等。但是,很多时候用户本身并没有大量的好友信息存在,同时也不一定有很多确定的属性。因此,我们希望基于用户发表的文本信息来对用户关系进行预测。不同于以往的潜在好友推荐算法,该文提出了一种基于注意力机制以及长短时记忆网络(long short-term memory,LSTM)的好友关系预测模型,将好友之间的评论分开处理,通过分析用户之间的评论来判断是否具备一定的好友关系。该模型将好友双方信息拼接后的结果作为输入,并将注意力机制应用于LSTM的输出。实验表明,用户之间的评论对于好友关系预测确实有较大的实际意义,该文提出的模型较之于多个基准系统的效果,取得了明显的提升。在不加入任何其它非文本特征的情况下,实验结果的准确率达到了77%。     

Facile construction of composition-tuned ruthenium-nickel nanoparticles on g-C3N4 for enhanced hydrolysis of ammonia borane without base additives

Developing high-efficiency and low-cost catalysts for hydrogen evolution from hydrolysis of ammonia borane (AB) is significant and critical for the exploitation and utilization of hydrogen energy. Herein, the in-situ fabrication of well-dispersed and small bimetallic RuNi alloy nanoparticles (NPs) with tuned compositions and concomitant hydrolysis of AB are successfully achieved by using graphitic carbon nitride (g-C₃N₄) as a NP support without additional stabilizing ligands. The optimized Ru₁Ni_7.5/g-C₃N₄ catalyst exhibits an excellent catalytic activity with a high turnover frequency of 901 min^?1 and an activation energy of 28.46 kJ mol^?1 without any base additives, overtaking the activities of many previously reported catalysts for AB hydrolysis. The kinetic studies indicate that the AB hydrolysis over Ru₁Ni_7.5/g-C₃N₄ is first-order and zero-order reactions with respect to the catalyst and AB concentrations, respectively. Ru₁Ni_7.5/g-C₃N₄ has a good recyclability with 46% of the initial catalytic activity retained even after five runs. The high performance of Ru₁Ni_7.5/g-C₃N₄ should be assigned to the small-sized alloy NPs with abundant accessible active sites and the synergistic effect between the composition-tuned Ru–Ni bimetals. This work highlights a potentially powerful and simple strategy for preparing highly active bimetallic alloy catalysts for AB hydrolysis to generate hydrogen.     

Control of reactive distillation production of high-purity isopropanol

The process characteristics and control strategy of a high-purity IPA reactive distillation column were investigated. A robust nominal operation was found by maintaining an excess of propylene feed to the column and recycling the unreacted propylene to the feed instead of the top stage. Stage temperature and propylene composition with one-to-one relationship with reboiler duty and propylene feed are selected as controlled variables for maintaining bottom purity and feed ratio in the presence of possible measurement bias respectively. High nonlinearity between selected input–output pair was reduced by using variable transformation. Dynamic simulations demonstrated that such a control scheme with nonlinear transformed variable was capable of providing much superior control performance than the one using natural variable.