基于多注意力长短时记忆的实体属性情感分析

属性情感分析是细粒度的情感分类任务。针对传统神经网络模型无法准确构建属性情感特征的问题，提出了一种融合多注意力和属性上下文的长短时记忆（LSTM-MATT-AC）神经网络模型。在双向长短时记忆（LSTM）的不同位置加入不同类型的注意力机制，充分利用多注意力机制的优势，让模型能够从不同的角度关注句子中特定属性的情感信息，弥补了单一注意力机制的不足；同时，融合双向LSTM独立编码的属性上下文语义信息，获取更深层次的情感特征，有效识别特定属性的情感极性；最后在SemEval2014 Task4和Twitter数据集上进行实验，验证了不同注意力机制和独立上下文处理方式对属性情感分析模型的有效性。实验结果表明，模型在Restaurant、Laptop和Twitter领域数据集上的准确率分别达到了80.6%、75.1%和71.1%，较之前基于神经网络的情感分析模型在准确率上有了进一步的提高。     

基于词法特征的恶意域名快速检测算法

针对互联网中恶意域名攻击事件频发，现有域名检测方法实时性不强的问题，提出一种基于词法特征的恶意域名快速检测算法。该算法根据恶意域名的特点，首先将所有待测域名按照长度进行正则化处理后赋予权值；然后利用聚类算法将待测域名划分成多个小组，并利用改进的堆排序算法按照组内权值总和计算各域名小组优先级，根据优先级降序依次计算各域名小组中每一域名与黑名单上域名之间的编辑距离；最后依据编辑距离值快速判定恶意域名。算法运行结果表明，基于词法特征的恶意域名快速检测算法与单一使用域名语义和单一使用域名词法的恶意域名检测算法相比，准确率分别提高1.7%与2.5%，检测速率分别提高13.9%与6.8%，具有更高的准确率和实时性。     

生物预处理技术在天然产物提取中的应用研究进展

生物预处理技术运用于天然产物提取是借助微生物或生物酶的作用，在适当条件下对天然资源进行处理，破坏植物原料的细胞壁，促进天然产物释放到提取介质中，以提高分离效率，有助于保证天然产物活性。生物预处理技术按形式可以分为微生物发酵技术和生物酶处理技术。针对2种生物预处理技术的作用机制和应用进行综述，旨在为天然产物开发利用提供参考。     

Isolation of peanut protein aggregates using aqueous extraction processing combined with membrane separation

A two-stage microfiltration and ultrafiltration (MF/UF) for peanut protein recovery and water recycling from aqueous extraction processing (AEP) were investigated. Peanut protein aggregates and alkaline water were obtained using flat and wound MF/UF and alkaline water recycled in AEP. With this approach, most of the wastewater could be recycled to produce reusable water to solve wastewater problems in aqueous oil extraction processing from oilseeds. The result showed that a little oil and protein were lost (1.21% and 4.35%, respectively) during the recycling of permeate in AEP, which was still acceptable. Peanut protein aggregations (PPAs) were characterised by analysis with Fourier-transform infrared spectroscopy (FTIR), sodium dodecyl sulphate–polyacrylamide gel electrophoresis (SDS-PAGE), high-performance gel filtration chromatography (HPGFC) and binding force analysis. Solubility analysis suggested that PPA had molecular structures with more hydrophobic groups on the surface than in the peanut protein isolate (PPI). In vitro, PPA was digested by both pepsin and trypsin more than PPI. FTIR profiles demonstrated there were more β-sheet and less α-helix in PPA, which means much more aggregation. In addition, binding force analysis showed hydrophobic interaction was the major force that restricted dissolution of PPA and disulfide bonds were of second importance, which provided a possible physical treatment opportunity for improving the solubility of PPA.     

用于盐湖卤水吸附法提锂的连续离子交换工艺研究

采用连续离子交换技术用于盐湖卤水的吸附法提锂。针对青海一里坪盐湖老卤体系,开发了连续离子交换吸附提锂工艺,研究了操作参数对连续离子交换系统提锂性能的影响,并在优化的工艺条件下进行了长周期的稳定性评价。结果表明,在转动步进周期为20 min、卤水进料量为3.2 BV/h、淋洗水量为2.9 BV/h、解吸水量为9.3 BV/h、解吸温度为15~25 ℃时,连续离子交换系统可以稳定获得镁锂质量浓度比（简称镁锂比）在3左右、锂质量浓度接近1.1 g/L的合格液,锂回收率为98.5%以上。     

端盖双滑块+斜顶3次复合抽芯机构注射模设计

针对塑件注射成型自动化实施困难问题， 设计了一副单点潜浇口、两板式2次开模注射模来解决这一难题。模具布局为1模2腔。模具中单腔的机构设置情况为：（1）定模侧，设计了一个油缸驱动的定模顶出机构；动模侧，设置了2个特殊的斜顶+滑块复合机构、1个万能斜顶机构、1个隧道滑块机构、及1个顶针顶出机构；（2）定模顶出机构由油缸驱动定模顶出板以驱动6根斜顶杆来对6个倒扣特征进行自动脱模；（3）2个特殊的复合机构分别为：双滑块+斜顶3次复合抽芯机构、单滑块斜顶两次抽芯机构；此2个机构的作用是，通过斜导柱驱动滑块，从而2次驱动滑块内的斜顶实施2次抽芯，来到达塑件局部区域多次多向抽芯的目的；（4）机构中，使用万能斜顶机构能有效减小模具高度尺寸；使用隧道滑块斜抽芯机构，动模一侧增加1次模板开模打开来驱动隧道滑块实施斜抽芯，能有效利用模具开模动力，降低模具制造成本。     

Functional organisation of the endomembrane network in the digestive gland of the Venus flytrap: revisiting an old story with a new microscopy toolbox

Up-to-date imaging approaches were used to address the spatiotemporal organisation of the endomembrane system in secretory cells of Dionaea muscipula. Different ‘slice and view’ methodologies were performed on resin-embedded samples to finally achieve a 3D reconstruction of the cell architecture, using ultrastructural tomography, array tomography, serial block face-scanning electron microscopy (SBF-SEM), correlation, and volume rendering at the light microscopy level. Observations of cryo-fixed samples by high-pressure freezing revealed changes of the endomembrane system that occur after trap activation and prey digestion. They provide evidence for an original strategy that adapts the secretory machinery to a specific and unique case of stimulated exocytosis in plant cells. A first secretion peak is part of a rapid response to deliver digestive fluids to the cell surface, which delivers the needed stock of digestive materials ‘on site’. The second peak of activity could then be associated with the reconstruction of the Golgi apparatus (GA), endoplasmic reticulum (ER) and vacuolar machinery, in order to prepare for a subsequent round of prey capture. Tubular continuum between ER and Golgi stacks observed on ZIO-impregnated tissues may correspond to an efficient transfer mechanism for lipids and/or proteins, especially for use in rapidly resetting the molecular GA machinery. The occurrence of one vacuolar continuum may permit continuous adjustment of cell homeostasy. The subcellular features of the secretory cells of Dionaea muscipula outline key innovations in the organisation of plant cell compartmentalisation that are used to cope with specific cell needs such as the full use of the GA as a protein factory, and the ability to create protein reservoirs in the periplasmic space. Shape-derived forces of the pleiomorphic vacuole may act as signals to accompany the sorting and entering flows of the cell.     

基于加权中智C均值算法的变压器故障诊断模型

为提高变压器故障诊断准确度,提出了一种基于加权中智C均值算法的变压器故障诊断方法。该方法利用基于样本相似度的加权方法对样本特征进行加权,再引入中智理论对样本的分布重新分配,建立起基于加权中智C均值算法的变压器故障诊断模型。研究结果表明,该方法不仅弥补了传统FCM相同权重分配的不足,有效提高了故障诊断的准确率,且诊断结果产生的中智点对故障的变化预测具有重要意义。     

磷酸脲母液制备工业级磷酸二氢铵工艺研究

湿法磷酸制备磷酸脲过程中会副产大量磷酸脲母液,母液含有金属杂质及五氧化二磷含量较高。采用溶剂萃取法回收磷酸脲母液中五氧化二磷制备工业级磷酸二氢铵（MAP）,分别考察了包括萃取、洗涤、中和、精制、结晶等工艺流程对产品收率及纯度的影响,确定了最佳工艺条件：萃取相比（有机相与水相体积比）=3:1,萃取时间为5 min,萃取温度为50 ℃,洗涤相比（有机相与洗涤剂体积比）=10:1,中和pH为4.5,复合酸性萃取剂PO8皂化率为20%,精制相比（萃取剂与水相体积比）=1:1,浓缩比为1.36,结晶温度为30 ℃。在该条件下制备的工业级MAP纯度可达99.45%,母液中五氧化二磷回收率为85.34%。该工艺对环境友好,原料中五氧化二磷回收率高,具有较高的经济效益。     

Densely connected convolutional network block based autoencoder for panorama map compression

As a novel virtual reality (VR) format, panorama maps are attracting increasing attention, while the compression of panorama images is still a concern. In this paper, a densely connected convolutional network block (dense block) based autoencoder is proposed to compress panorama maps. In the proposed autoencoder, dense blocks are specially designed to reuse feature maps and reduce redundancy of features. Meanwhile, a loss function, which imports a position-dependent weight item for each pixel, is proposed to train and adjust network parameters, in order to make the autoencoder fit to properties of panorama maps. Based on the proposed autoencoder and the weighted loss function, a greedy block-wise training scheme is also designed to avoid gradient vanishing problem and speed up training. During training process, the autoencoder is divided into several sub-nets. After each sub-net is trained separately, the whole network is fine-tuned to achieve the best performance. Experimental results demonstrate that the proposed autoencoder, compared with JPEG, saves up to 79.69 % bit rates, and obtains 7.27dB gain in BD-WS-PSNR or 0.0789 gain in BD-WS-SSIM. The proposed autoencoder also outperforms JPEG 2000, HEVC and VVC in both BD-WS-PSNR and BD-WS-SSIM. Meanwhile, subjective results show that the proposed autoencoder can recover details of panorama images, and reconstruct maps with high visual quality.