WavNet — Visual saliency detection using Discrete Wavelet Convolutional Neural Network

In the recent advancements in image and video analysis, the detection of salient regions in the image becomes the initial step. This plays a crucial role in deciding the performance of such algorithms. In this work, a Multi-Resolution Feature Extraction (MRFE) technique that makes use of Discrete Wavelet Convolutional Neural Network (DWCNN) for generating features is employed. An Enhanced Feature Extraction (EFE) module extracts additional features from the high level features of the DWCNN, which are used to frame both channel as well as spatial attention models for yielding contextual attention maps. A new hybrid loss function is also proposed, which is a combination of Balanced Cross Entropy (BCE) loss and Edge based Structural Similarity (ESSIM) loss that effectively identifies and segments the salient regions with clear boundaries. The method is tested exhaustively with five different benchmark datasets and is proved superior to the existing state-of-the-art methods with a minimum Mean Absolute error (MAE) of 0.03 and F-measure of 0.956.     

Influence of temperature on acoustic emission source location accuracy in underground structure

An acoustic emission (AE) experiment was carried out to explore the AE location accuracy influenced by temperature. A hollow hemispherical specimen was used to simulate common underground structures. In the process of heating with the flame, the pulse signal of constant frequency was stimulated as an AE source. Then AE signals received by each sensor were collected and used for comparing localization accuracy at different temperatures. Results show that location errors of AE keep the same phenomenon in the early and middle heating stages. In the later stage of heating, location errors of AE increase sharply due to the appearance of cracks. This provides some beneficial suggestions on decreasing location errors of structural cracks caused by temperature and improves the ability of underground structure disaster prevention and control.     

CuO-SiO2气凝胶@TiO2纳米纤维无牺牲剂光催化还原CO2

采用溶胶-凝胶法制备CuO-SiO2复合气凝胶,通过在气凝胶孔道内填充TiCl4,然后将其气相水解,得到了在CuO-SiO2气凝胶表面生长了高结晶度的TiO2纳米纤维(CuO-SiO2@TiO2),纤维直径～16 nm.通过XPS、UPS、UV-Vis DRS、荧光光谱(PL)等表征了材料的结构及光电性能.结果表明,制备的CuO-SiO2@TiO2对可见光有明显吸收,且荧光强度较商用TiO2(P25)大幅降低,光生电子-空穴对更加稳定.再在纳米纤维上负载CuO,所得CuO-SiO2@TiO2/CuO在可见光区的荧光强度进一步增强.以300 W氙灯为光源,分别以CuO-SiO2@TiO2及CuO-SiO2@TiO2/CuO为催化剂,无牺牲剂条件下光催化还原CO2,4 h后甲醇产率分别为1304.0及1589.0μmol/g-cat,转换频率(TOF)分别为0.038及0.046 h–1.循环实验表明,纳米纤维具有较好的光催化稳定性,经过4次光催化循环实验后,CuO-SiO2@TiO2/CuO的保留率～94％,甲醇产率可达1472.0μmol/g-cat,TOF为0.042 h–1.     

Single image dehazing using a new color channel

Images with hazy scene suffer from low-contrast, which reduces the visible quality of the scene, thus making object detection a more challenging task. Low-contrast can result from foggy weather conditions during image acquisition. Dehazing is a process of removal of haze from the photography of a hazy scene. Single-image dehazing based on dark channel priors are well-known techniques in this field. However, the performance of such techniques is limited to priors or constraints. Moreover, this type of method fails when images have sky-region. So, a method is proposed, which can restore the visibility of hazy images. First, a hazy image is divided into blocks of size 32 × 32, then the score of each block is calculated to select a block having the highest score. Atmospheric light is calculated from the selected block. A new color channel is considered to remove atmospheric scattering, obtained channel value and atmospheric light are then used to calculate the transmission map in the second step. Third, radiance is computed using a transmission map and atmospheric light. The illumination scaling factor is adopted to enhance the quality of a dehazed image in the final step. Experiments are performed on six datasets namely, I-HAZE, O-HAZE, BSDS500, FRIDA, RESIDE dataset and natural images from Google. The proposed method is compared against 11 state-of-the-art methods. The performance is analyzed using fourteen quantitative evaluation metrics. All the results demonstrate that the proposed method outperforms 11 state-of-the-art methods in most of the cases.     

基于光刀图像的机器人示教纠偏方法

为了解决机器人辅助在线检测系统示教过程中效率低、人为干预多的问题,针对孔类特征,提出一种通过处理光刀图像获取机器人位姿纠正参数的方法。在该方法中,纠偏过程按照将图像光刀线调整为水平方向、将被测特征调整至图像中央、根据不同特征调整最优扫描方向3个步骤进行。根据光刀图像可以求出测量坐标系与被测特征的位姿关系,并得到该位姿与理想测量位姿的偏差。经过坐标变换即可得到在机器人基坐标系下的调整参数。另外,可利用电脑控制机器人运动,从而实现了纠偏过程的自动化。实验结果表明,该方法可将初始的示教位姿修正为理想位姿,且比传统方式效率更高。     

化学微发泡成型外观表面技术研究

从汽车内饰轻量化方向考虑,研究了化学微发泡技术,从成核和气泡长大阶段进行研究,通过特殊的柔性后退core-back工艺,在充模过程中控制气泡的变形和破裂以保证成型制品的表面质量,实现化学微发泡成型制品无外观缺陷、质量减轻20%以上的目的。     

Microstructural,mechanical properties and strengthening mechanism of DLP produced β-tricalcium phosphate scaffolds by incorporation of MgO/ZnO/58S bioglass

The inherent brittleness of bioceramics restricts their applications in load-bearing implant, although they possess good biocompatibility and bioactivity. ZnO, MgO and 58S bioglass (BG) were incorporated as additives to further improve the mechanical properties and biocompatibility of β-TCP and ZnO/MgO/BG-β-TCP composite scaffolds were manufactured via digital light processing (DLP). The composite with the best comprehensive performance was selected for degradation behavior and biocompatibility evaluation. The effects of different proportions of ZnO/MgO/BG on mechanical strength were analyzed and ZnO0·5/MgO1/BG2-β-TCP (ZMBT) samples exhibited superior mechanical strength. The improvement by 272% and 99% respectively was achieved in fracture toughness and compressive strength with the optimal recipe. The enhancement effect is realized through phase transition, alterative sliding actions and transgranular fracture to effectively prevent the load transfer combining the functions of bioglass and metal oxide. ZMBT scaffolds exhibited a more desirable pH environment and an enhanced ability of apatite-mineralization formation, meanwhile Si⁴⁺, Mg²⁺ and Zn²⁺ were gradually released from scaffolds. Furthermore, in vitro evaluation indicated that ZMBT scaffolds presented not only excellent cell attachment, proliferation, alkaline phosphatase (ALP) activity, but they up-regulated osteogenic gene (ALP, OCN, Runx2). These results suggest that the addition of ZnO/MgO/BG to DLP-printed β-TCP scaffolds offer a smart strategy to fabricate porous scaffolds with conspicuously better biological and physicochemical properties including compressive strength, bioactivity, osteogenesis and osteogenesis-related gene expression. Metal-oxide and BG synergistically enhanced the mechanical and biological properties which make the ZMBT scaffolds a strong candidate for bone repair applications.     

Structural silicone sealants after exposure to laboratory test for durability assessment

During the service life of structural sealant glazing (SSG) facades, the load-bearing capacity of the silicone bonds needs to be guaranteed. Laboratory tests can assess the durability of SSG-systems based on mechanical characteristics of the bond after simultaneous exposure to both climatic and mechanical loads. This article studies how the material characteristics of two common structural sealants are affected by laboratory and field exposure. Dynamic mechanical analysis (DMA) confirms a reduction in the dynamic modulus of exposed silicone samples. Results from thermogravimetric analysis, Fourier-transform infrared spectroscopy, differential scanning calorimetry, and small-angle X-ray scattering/wide-angle X-ray scattering show differences between the two sealants and indicate no/minor changes in the composition and morphology of the laboratory and field exposed sealants. Mechanical characterization methods, such as DMA, and tensile and shear testing of the structural bond, are shown to be sensitive toward the combined climatic and mechanical loadings, and are hence suitable for studying degradation mechanisms of structural sealants.     

LED light-induced enhanced photocatalytic hydrogen evolution on Au@TiO2 core–shell modified by nitrogen doping and reduced graphene oxide

This study focused on the large band gap of TiO₂ for its use as a photocatalyst under light emitting diode (LED) light irradiation. The photocatalytic activities of core–shell structured Au@TiO₂ nanoparticles (NPs), nitrogen doped Au@TiO₂ NPs, and Au@TiO₂/rGO nanocomposites (NCs) were investigated under various light intensities and sacrificial reagents. All the materials showed better photocatalytic activity under white LED light irradiation than under blue LED light. The N-doped core–shell structured Au@TiO₂ NPs (Au@N–TiO₂) and Au@TiO₂/rGO NCs showed enhanced photocatalytic activity with an average H₂ evolution rate of 9205 μmol h^?1g^?1 and 9815 μmol h^?1g^?1, respectively. All these materials showed an increasing rate of hydrogen evolution with increasing light intensity and catalyst loading. In addition, methanol was more suitable as a sacrificial reagent than lactic acid. The rate of hydrogen evolution increased with increasing methanol concentration up to 25% in DI water and decreased at higher concentrations. Overall, Au@TiO₂ core–shell-based nanocomposites can be used as an improved photocatalyst in photocatalytic hydrogen production.     

Evaluation of in-situ formed La2O3–TiO2–La2O2CO3 nanocomposite photocatalyst for H2 production

The photocatalytic evolution of H₂ over La₂O₃ decorated TiO₂ catalyst was examined under solar light. It was observed that during the course of the reaction, the transformation of La₂O₃/TiO₂ into La₂O₃–TiO₂–La₂O₂CO₃ occurred and these species effectively suppressed electron-hole pair recombination by forming electron trapping centres on the surface, resulting in an increased visible light absorption and improved H₂ yield. The 2 wt%La₂O₃/TiO₂ nanocomposite demonstrated better H₂ yield (～8.76 mmol (g_cat)^?1) than the bare TiO₂ (～1.1 mmol (g_cat)^?1). The catalyst was stable even after several consecutive recycles with no substantial loss of hydrogen production rate. The H₂ rates were correlated with the physicochemical characteristics of the catalysts examined by BET–SA, H₂-TPR, XRD, UV-DRS, Raman spectroscopy, FTIR, HRTEM, EPR and PL spectroscopy.