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。     

融合情感与语义信息的情感分析方法

在使用词嵌入法进行词转向量时，两个反义词会转换成相近的向量。如果这两个词是情感词，将会导致词的情感信息的丢失，这在情感分析任务中是不合理的。为了解决这个问题，提出了一种在词嵌入的基础上增加情感向量来获取情感信息的方法。首先利用情感词典资源构建情感向量，将其与词嵌入法得到的词向量融合在一起；然后采用双向长短期记忆（BiLSTM）网络获取文本的特征；最后对文本的情感进行分类。在4个数据集上分别对该方法与未融合情感向量的方法进行了实验。实验结果表明所提方法分类准确度与F1值都高于未融合方法，说明了加入情感向量有助于提高情感分析的性能。     

{X,Y}-Cyclacene Graphs with Next Nearest Neighbor Interactions

Eigensolutions of {X( = C,B,N),Y( = C,B,N)}-cyclacene graphs with next nearest neighbor (nnn) interactions have been obtained in analytical forms by adapting n-fold rotational symmetry followed by two-fold rotational symmetry (or a plane of symmetry). Expressions of eigensolution indicate the subspectral relationship among such cyclacenes with an even number of hexagonal rings e.g., eigenvalues of {X,Y}-di-cyclacene are found in the eigenspectra of all such even cyclacenes. Total π-electron energies and highest occupied molecular orbital and lowest unoccupied molecular orbital (HOMO–LUMO) gaps are calculated using the analytical expressions obtained and are found to vary negligibly with the variation of nnn interactions in such cyclacenes. Total π-electron energy is found to increase due to increase in restriction intensity of nnn interactions, whereas the HOMO–LUMO gap of polyacenecs having the even number of hexagonal rings and with one electron at each site (atom) decreases with increase in the restriction intensity since such systems contain degenerate half-filled HOMO (bonding or nonbonding) that are much more vulnerable for perturbations imposed through nnn interactions.     

基于改进词嵌入表示和卷积神经网络的银行智能派单系统的研究

银行智能派单系统的实现和功能完善,对银行提升客户满意度、提高突发事件处理效率、降低人工处理成本等非常重要。针对现有的基于Word2vec和TextCNN模型的银行智能派单系统进行了改进,针对特征词权重表达性弱,特征词类别及位置区分性弱等问题,提出基于改进TF-IDF加权的Word2vec词嵌入表示和卷积神经网络结合的银行智能派单系统:首先利用Word2vec模型得到输入事件单的词嵌入向量;再针对经典TF-IDF方法不具备类别区分性、位置区分性,也没有考虑极端频率特征词代表性的情况,提出改进型TF-IDF算法,计算每个特征词的权重,得到基于改进TF-IDF加权的Word2vec词嵌入表示;最后在卷积神经网络模型中进行训练,通过迭代训练最终得到分类器,利用分类器可对输入事件单信息自动进行系统类别的判断。实验结果表明改进词嵌入表示的银行智能派单系统分类模型的宏查准率、宏查全率、准确率以及宏F1值都得到进一步的提高。     

基于光谱分类模型的保险杠物证无损研究

采用中红外光谱结合化学计量学的方法对车用保险杠碎片进行鉴别，分别对52个车用保险杠碎片样本的全波段光谱数据、指纹区光谱数据和主成分分析降维后的光谱数据建立Fisher判别分析和K近邻算法2种分类模型，并对分类结果进行比较。结果表明，主成分分析提取特征变量后构建的分类模型，分类的准确率更高，对聚丙烯（PP）、PP/滑石粉、PP/滑石粉/碳酸钙（CaCO₃）3种类型的样本分类准确率达到92.3 %，对PP/滑石粉类型中的10种品牌样本分类准确率达到88.9 %，分类结果理想；在构建的2种分类模型中，Fisher判别分析模型的分类率远高于K近邻算法模型，分析认为K近邻算法模型受到样本不均衡的影响；中红外光谱结合化学计量学可以实现对车用保险杠碎片的准确区分，且满足快速、无损的检验要求。     

Filling the gap between Continuous and Discrete Time Dynamics of Autoregressive Processes

Discretization of continuous time autoregressive (AR) processes driven by a Brownian motion and embedding of discrete time AR sequences driven by a Gaussian white noise are classical issues. The article aims at establishing and using such discretization and embedding formulae between extended AR continuous time processes and discrete time sequences. The continuous-time processes are driven by either Brownian or jump processes, and may have random coefficients depending on time; Lévy-driven processes are also considered. The innovation of the discrete time processes may be of many types – including Gaussian. In one way, observing the continuous time AR process at discrete times leads the AR dynamics of the discretized process to be characterized. The other way round, AR sequences can be embedded, in the almost sure sense, into continuous time AR processes with the same dynamics. Illustration is provided through many examples and simulation.     

基于最近邻与神经网络融合模型的软测量建模方法

软测量建模能够有效地解决生产过程中在线分析仪表测量滞后大、价格昂贵、维护保养复杂等问题。目前，基于数据驱动的神经网络是软测量建模的主要工具之一。而在建模数据的采集过程中，主导变量的采集相对辅助变量要困难得多，由此产生了大量缺失标签的数据。但传统的软测量建模方法却忽视了这些无标签数据，只利用少量的有标签数据建模，从而影响了模型的预测精度。为了解决标签缺失的问题，采用最近邻算法对无标签数据进行伪标记，同时设计了由卷积操作与门限循环单元神经网络（GRU）结合的网络结构来进一步利用无标签数据，提取不同时刻数据中的动态特征，提高神经网络的预测精度。最后将该方法应用于丙烯精馏塔塔顶丙烷浓度的预测，实验结果表明该模型能有效处理非线性动态系统的标签缺失问题，具有更高的预测精度。