电商平台产品共同购买网络的影响因素研究

共同购买网络的推荐系统应用越加广泛，仅基于网络内生结构变量研究其共同购买链接的经济意义已有局限，故加入网络口碑这一外生变量，进行更全面的分析。采用了社会网络方法中指数随机图模型进行建模，主要围绕产品销售量、产品入度、差评率和评论数4个方面因素，探究其对共同购买网络中共同购买链接形成的影响。结果显示，销售量、产品入度和评论数对共同购买链接形成的影响呈正比关系，而差评率则会显著地降低产品共同购买的几率。该指数随机图构建出的共同购买网络为在线电商平台管理网络口碑和推荐系统优化设计提供有益参考。     

Cryptographic Lightweight Encryption Algorithm with Dimensionality Reduction in Edge Computing

Edge Computing is one of the radically evolving systems through generations as it is able to effectively meet the data saving standards of consumers, providers and the workers. Requisition for Edge Computing based items have been increasing tremendously. Apart from the advantages it holds, there remain lots of objections and restrictions, which hinders it from accomplishing the need of consumers all around the world. Some of the limitations are constraints on computing and hardware, functions and accessibility, remote administration and connectivity. There is also a backlog in security due to its inability to create a trust between devices involved in encryption and decryption. This is because security of data greatly depends upon faster encryption and decryption in order to transfer it. In addition, its devices are considerably exposed to side channel attacks, including Power Analysis attacks that are capable of overturning the process. Constrained space and the ability of it is one of the most challenging tasks. To prevail over from this issue we are proposing a Cryptographic Lightweight Encryption Algorithm with Dimensionality Reduction in Edge Computing. The t-Distributed Stochastic Neighbor Embedding is one of the efficient dimensionality reduction technique that greatly decreases the size of the non-linear data. The three dimensional image data obtained from the system, which are connected with it, are dimensionally reduced, and then lightweight encryption algorithm is employed. Hence, the security backlog can be solved effectively using this method.     

改进的多层感知机在客户流失预测中的应用

针对在传统的客户流失预测数据预处理中，使用one-hot编码处理离散属性导致数据维度增加及数据过于稀疏的问题，提出了两种基于多层感知机的改进后的客户流失预测模型。其主要思想是分别使用堆叠自编码器和实体嵌入两种方法对多层感知机进行改进，通过将离散属性的高维编码数据向低维空间映射，有效地减少了one-hot编码产生的稀疏数据，增加了离散属性值之间的关联度。在对两份公开的数据集进行交叉验证后的实验结果表明，改进后的模型既有效地提高了预测的准确度，又维持了传统多层感知机模型在并行化计算方面的优势。     

云南镇源难处理金精矿工艺矿物学研究

利用X射线衍射、X射线荧光光谱（XRF）、X射线能谱分析（EDX）和矿物解离分析（MLA）等检测手段对云南镇源难处理金精矿的化学组成、矿物组成、硫化物特征以及金的分布情况进行了详细的工艺矿物学研究。结果显示：该金矿以硫化矿、碳酸盐和硅酸盐类矿物为主，含有3.18%的有机碳和2.37%的无机碳。通过金的诊断浸出发现96.16%的金被硫化物包裹，少量金以单体形式存在。通过对主要载金矿物黄铁矿、辉锑矿和毒砂的粒度、包裹及裸露情况进行分析，得出大部分硫化矿以解离单体的形式存在，少部分与其他矿物共生。根据MLA测试及金的诊断浸出，认为大部分金被硫化矿完全包裹，处理该矿石时应先进行硫化物包裹层的氧化处理，再进行金矿的浸出。     

Bond graph modeling,design and experimental validation of a photovoltaic/fuel cell/ electrolyzer/battery hybrid power system

This work presents a complete bond graph modeling of a hybrid photovoltaic-fuel cell-electrolyzer-battery system. These are multi-physics models that will take into account the influence of temperature on the electrochemical parameters. A bond graph modeling of the electrical dynamics of each source will be introduced. The bond graph models were developed to highlight the multi-physics aspect describing the interaction between hydraulic, thermal, electrochemical, thermodynamic, and electrical fields. This will involve using the most generic modeling approach possible for managing the energy flows of the system while taking into account the viability of the system. Another point treated in this work is to propose. In this work, a new strategy for the power flow management of the studied system has been proposed. This strategy aims to improve the overall efficiency of the studied system by optimizing the decisions made when starting and stopping the fuel cell and the electrolyzer. It was verified that the simulation results of the proposed system, when compared to simulation results presented in the literature, that the hydrogen demand is increased by an average of 8%. The developed management algorithm allows reducing the fuel cell degradation by 87% and the electrolyzer degradation by 65%. As for the operating time of the electrolyzer, an increment of 65% was achieved, thus improving the quality of the produced hydrogen. The Fuel Cell's running time has been decreased by 59%. With the ambition to validate the models proposed and the associated commands, the development of this study gave rise to the creation of an experimental platform. Using this high-performance experimental platform, experimental tests were carried out and the results obtained are compared with those obtained by simulation under the same metrological conditions.     

结合句法依存信息的方面级情感分类

引入句法依存信息到原方面术语,提出一种新的方面术语表示方法,利用Glove词向量表示单词以及单词与单词之间的依存关系,构造出包含句法依存信息的依存关系邻接矩阵和依存关系表示矩阵,利用图卷积神经网络和多头注意力机制将句法依存信息融入到方面术语中,使得方面术语表达与上下文结构高度相关。将改进后的方面词术语表示替换到现有模型后,模型泛化能力得到有效提升。对比试验和分析结果表明:该方法具有有效性和泛化性。     

LinkingPark: An automatic semantic table interpretation system

In this paper, we present LinkingPark, an automatic semantic annotation system for tabular data to knowledge graph matching. LinkingPark is designed as a modular framework which can handle Cell-Entity Annotation (CEA), Column-Type Annotation (CTA), and Columns-Property Annotation (CPA) altogether. It is built upon our previous SemTab 2020 system, which won the 2nd prize among 28 different teams after four rounds of evaluations. Moreover, the system is unsupervised, stand-alone, and flexible for multilingual support. Its backend offers an efficient RESTful API for programmatic access, as well as an Excel Add-in for ease of use. Users can interact with LinkingPark in near real-time, further demonstrating its efficiency.     

一种使用多跳事实的端到端知识库实体描述生成方法

自动化实体描述生成有助于进一步提升知识图谱的应用价值,而流畅度高是实体描述文本的重要质量指标之一。该文提出使用知识库上多跳的事实来进行实体描述生成,从而贴近人工编撰的实体描述的行文风格,提升实体描述的流畅度。该文使用编码器—解码器框架,提出了一个端到端的神经网络模型,可以编码多跳的事实,并在解码器中使用关注机制对多跳事实进行表示。该文的实验结果表明,与基线模型相比,引入多跳事实后模型的BLEU-2和ROUGE-L等自动化指标分别提升约8.9个百分点和7.3个百分点。