High quality 3D reconstruction based on fusion of polarization imaging and binocular stereo vision

Polarization imaging can retrieve inaccurate objects’ 3D shapes with fine textures, whereas coarse but accurate depths can be provided by binocular stereo vision. To take full advantage of these two complementary techniques, we investigate a novel 3D reconstruction method based on the fusion of polarization imaging and binocular stereo vision for high quality 3D reconstruction. We first generate the polarization surface by correcting the azimuth angle errors on the basis of registered binocular depth, to solve the azimuthal ambiguity in the polarization imaging. Then we propose a joint 3D reconstruction model for depth fusion, including a data fitting term and a robust low-rank matrix factorization constraint. The former is to transfer textures from the polarization surface to the fused depth by assuming their relationship linear, whereas the latter is to utilize the low-frequency part of binocular depth to improve the accuracy of the fused depth considering the influences of missing-entries and outliers. To solve the optimization problem in the proposed model, we adopt an efficient solution based on the alternating direction method of multipliers. Extensive experiments have been conducted to demonstrate the efficiency of the proposed method in comparison with state-of-the-art methods and to exhibit its wide application prospects in 3D reconstruction.     

Tabular data: Deep learning is not all you need

A key element in solving real-life data science problems is selecting the types of models to use. Tree ensemble models (such as XGBoost) are usually recommended for classification and regression problems with tabular data. However, several deep learning models for tabular data have recently been proposed, claiming to outperform XGBoost for some use cases. This paper explores whether these deep models should be a recommended option for tabular data by rigorously comparing the new deep models to XGBoost on various datasets. In addition to systematically comparing their performance, we consider the tuning and computation they require. Our study shows that XGBoost outperforms these deep models across the datasets, including the datasets used in the papers that proposed the deep models. We also demonstrate that XGBoost requires much less tuning. On the positive side, we show that an ensemble of deep models and XGBoost performs better on these datasets than XGBoost alone.     

基于VMD和BSA-KELM的高陡边坡位移预测模型研究

边坡位移的时间序列曲线存在复杂的非线性特性,传统的预测模型精度不足以满足预测要求。为此提出了基于变分模态分解的鸟群优化-核极限学习机的预测模型,并用于河北省某水泥厂的边坡位移预测。该方法首先采用VMD把边坡位移序列分解为一系列的有限带宽的子序列,再对各子序列分别采用相空间重构并用核极限学习机预测,采用鸟群算法优化相空间重构的嵌入维度和KELM中惩罚系数和核参数三个数值,以取得最优预测模型。最后将各个子序列预测值叠加,得到边坡位移的最终预测值。结果表明：和KELM、BSA-KELM、EEMD-BSA-KELM模型相比,基于VMD的BSA-KELM预测精度更高,为边坡位移的预测提供一种有效的方法。     

Pulsed Electromagnetic Field Stimulation in Osteogenesis and Chondrogenesis: Signaling Pathways and Therapeutic Implications

Mesenchymal stem cells (MSCs) are the main cell players in tissue repair and thanks to their self-renewal and multi-lineage differentiation capabilities, they gained significant attention as cell source for tissue engineering (TE) approaches aimed at restoring bone and cartilage defects. Despite significant progress, their therapeutic application remains debated: the TE construct often fails to completely restore the biomechanical properties of the native tissue, leading to poor clinical outcomes in the long term. Pulsed electromagnetic fields (PEMFs) are currently used as a safe and non-invasive treatment to enhance bone healing and to provide joint protection. PEMFs enhance both osteogenic and chondrogenic differentiation of MSCs. Here, we provide extensive review of the signaling pathways modulated by PEMFs during MSCs osteogenic and chondrogenic differentiation. Particular attention has been given to the PEMF-mediated activation of the adenosine signaling and their regulation of the inflammatory response as key player in TE approaches. Overall, the application of PEMFs in tissue repair is foreseen: (1) in vitro: to improve the functional and mechanical properties of the engineered construct; (2) in vivo: (i) to favor graft integration, (ii) to control the local inflammatory response, and (iii) to foster tissue repair from both implanted and resident MSCs cells.     

Learn decision trees with deep visual primitives

In this paper, we strive to propose a self-interpretable framework, termed PrimitiveTree, that incorporates deep visual primitives condensed from deep features with a conventional decision tree, bridging the gap between deep features extracted from deep neural networks (DNNs) and trees’ transparent decision-making processes. Specifically, we utilize a codebook, which embeds the continuous deep features into a finite discrete space (deep visual primitives) to distill the most common semantic information. The decision tree adopts the spatial location information and the mapped primitives to present the decision-making process of the deep features in a tree hierarchy. Moreover, the trained interpretable PrimitiveTree can inversely explain the constituents of the deep features, highlighting the most critical and semantic-rich image patches attributing to the final predictions of the given DNN. Extensive experiments and visualization results validate the effectiveness and interpretability of our method.     

Surface Reconstruction Engineering with Synergistic Effect of Mixed-Salt Passivation Treatment toward Efficient and Stable Perovskite Solar Cells

Surface passivation treatment is a widely used strategy to resolve trap-mediated nonradiative recombination toward high-efficiency metal-halide perovskite photovoltaics. However, a lack of passivation with mixture treatment has been investigated, as well as an in-depth understanding of its passivation mechanism. Here, a systematic study on a mixed-salt passivation strategy of formamidinium bromide (FABr) coupled with different F-substituted alkyl lengths of ammonium iodide is demonstrated. It is obtained better device performance with decreasing chain length of the F-substituted alkyl ammonium iodide in the presence of FABr. Moreover, they unraveled a synergistic passivation mechanism of the mixed-salt treatment through surface reconstruction engineering, where FABr dominates the reformation of the perovskite surface via reacting with the excess PbI₂. Meanwhile, ammonium iodide passivates the perovskite grain boundaries both on the surface and top perovskite bulk through penetration. This synergistic passivation engineer results in a high-quality perovskite surface with fewer defects and suppressed ion migration, leading to a champion efficiency of 23.5% with mixed-salt treatment. In addition, the introduction of the moisture resisted F-substituted groups presents a more hydrophobic perovskite surface, thus enabling the decorated devices with excellent long-term stability under a high humid atmosphere as well as operational conditions.     

Enhanced wide-activated residual network for efficient and accurate image deblocking

To save bandwidth and storage space as well as speed up data transmission, people usually perform lossy compression on images. Although the JPEG standard is a simple and effective compression method, it usually introduces various visually unpleasing artifacts, especially the notorious blocking artifacts. In recent years, deep convolutional neural networks (CNNs) have seen remarkable development in compression artifacts reduction. Despite the excellent performance, most deep CNNs suffer from heavy computation due to very deep and wide architectures. In this paper, we propose an enhanced wide-activated residual network (EWARN) for efficient and accurate image deblocking. Specifically, we propose an enhanced wide-activated residual block (EWARB) as basic construction module. Our EWARB gives rise to larger activation width, better use of interdependencies among channels, and more informative and discriminative non-linearity activation features without more parameters than residual block (RB) and wide-activated residual block (WARB). Furthermore, we introduce an overlapping patches extraction and combination (OPEC) strategy into our network in a full convolution way, leading to large receptive field, enforced compatibility among adjacent blocks, and efficient deblocking. Extensive experiments demonstrate that our EWARN outperforms several state-of-the-art methods quantitatively and qualitatively with relatively small model size and less running time, achieving a good trade-off between performance and complexity.     

Effect of support and reduction temperature in the hydrogenation of CO2 over the Cu–Pd bimetallic catalyst with high Cu/Pd ratio

Metal-support interaction and catalyst pretreatment are important for industrial catalysis. This work investigated the effect of supports (SiO₂, CeO₂, TiO₂ and ZrO₂) for Cu–Pd catalyst with high Cu/Pd ratio (Cu/Pd = 33.5) regarding catalyst cost, and the reduction temperatures of 350 °C and 550 °C were compared. The activity based on catalyst weight follows the order of Si > Ce > Zr > Ti when reduced at 350 °C. The reduction temperature leads to the surface reconstruction over the SiO₂, CeO₂ and TiO₂ catalysts, while results in phase transition over Cu–Pd/ZrO₂. The effect of reduction temperature on catalytic performance is prominent for the SiO₂ and ZrO₂ supported catalysts but not for the CeO₂ and TiO₂ ones. Among the investigated catalysts, Zr-350 exhibits the highest methanol yield. This work reveals the importance of the supports and pretreatment conditions on the physical-chemical properties and the catalytic performance of the Cu–Pd bimetallic catalysts.     

Generating Questions Based on Semi-Automated and End-to-End Neural Network

With the emergence of large-scale knowledge base, how to use triple information to generate natural questions is a key technology in question answering systems. The traditional way of generating questions require a lot of manual intervention and produce lots of noise. To solve these problems, we propose a joint model based on semi-automated model and End-to-End neural network to automatically generate questions. The semi-automated model can generate question templates and real questions combining the knowledge base and center graph. The End-to-End neural network directly sends the knowledge base and real questions to BiLSTM network. Meanwhile, the attention mechanism is utilized in the decoding layer, which makes the triples and generated questions more relevant. Finally, the experimental results on SimpleQuestions demonstrate the effectiveness of the proposed approach.     

基于神经网络和遗传算法的锭子弹性管性能优化

为得到减振弹性管对下锭胆的支承弹性和锭子高速运动下的稳定性等性能的最优匹配效率,依据减振弹性管的等效抗弯刚度及底部等效刚度系数公式,利用MatLab数值分析软件构建弹性管抗弯刚度和底部挠度数学模型。首先,结合Isight优化软件基于径向基神经网络构建其近似模型,且使精度达到可接受水平,并以模型的关键结构参数弹性模量、螺距、槽宽、壁厚为设计变量,结合遗传算法对弹性管抗弯刚度和底部挠度进行多目标优化设计,得到Pareto最优解集和Pareto前沿图,确定出减振弹性管结构工艺参数的优化方案。通过对优化数据进行分析发现,该方案在保证减振弹性管弹性的同时,其底部振幅明显减弱。