基于图注意力网络的案件罪名预测方法:CP-GAT

案件罪名预测任务是基于文本数据去预测案件所属罪名.针对现有方法在相似罪名和长尾数据集上表现不佳的问题，提出了一种基于图注意力网络的案件罪名预测方法CP-GAT(charge prediction based on graph attention network).该方法首先使用司法文书数据集中的案例事件描述文本和案例对应的法条信息建立异质图结构数据，构建后的异质图包含两种类型的节点(词节点、案例节点)，两种类型的边(词节点与词节点相连的边，词节点与案例节点相连的边).在基于法律文本构建后的异质图上使用图注意力网络进行图特征提取，最后将得到的特征向量输入到罪名预测的分类器中，得到案例所属的罪名.在CAIL2018法律数据集上的实验结果表明，基于图注意力网络的罪名预测方法优于对比实验使用的方法，准确率和宏观F1值分别达到了95.2%和66.1，验证了提出的方法有利于提升案件罪名预测任务的性能.     

基于滑移/非滑移异质界面的动压润滑性能优化

合理布置的滑移/非滑移异质界面可以提高流体动压润滑性能,但目前滑移区和非滑移区的组合方式大多采用单一的直线拼接法,没有针对流体润滑摩擦副的各类工况设计出相应的优化方案,为此本文建立了一组离散式二次方程来描述滑移区和非滑移区拼接轨迹,并引入计算域单元的宽长比作为优化变量,分别以液膜刚度和摩擦因数作为优化目标,通过MATLAB数值仿真求解不同宽长比条件下滑移区和非滑移区的最优拼接轨迹。结果表明,与直线拼接法相比,选取二次方程所描述的抛物线作为滑移区和非滑移区拼接轨迹的方法使流体润滑摩擦副在摩擦因数和液膜刚度等性能指标上都有所改善,而且根据不同的优化目标参数可以方便地绘制出最优拼接方案,验证了本文方法在改善动压润滑性能上的可行性和普适性。     

Objectivity in confirmation: Post hoc monsters and novel predictions

The aim of this paper is to put in place some cornerstones in the foundations for an objective theory of confirmation by considering lessons from the failures of predictivism. Discussion begins with a widely accepted challenge, to find out what is needed in addition to the right kind of inferential–semantical relations between hypothesis and evidence to have a complete account of confirmation, one that gives a definitive answer to the question whether hypotheses branded as “post hoc monsters” can be confirmed. The predictivist view is then presented as a way to meet this challenge. Particular attention is paid to Worrall’s version of predictivism, as it appears to be the most sophisticated of the lot. It is argued that, despite its faults, his view turns our heads in the right direction by attempting to remove contingent considerations from confirmational matters. The demand to remove such considerations becomes the first of four cornerstones. Each cornerstone is put in place with the aim to steer clear of the sort of failures that plague various kinds of predictivism. In the process, it becomes obvious that the original challenge is wrongheaded and in need of revision. The paper ends with just such a revision.     

基于全基因组测序的粘绿木霉Gv29-8中分泌蛋白预测

粘绿木霉Gv29-8作为木霉属中重要的生防菌之一,对该菌分泌蛋白进行预测及其特征进行明确具有重要的理论意义。利用SignalP、ProtComp等预测程序对该菌中12427条蛋白质序列进行分泌蛋白找寻,并对上述分泌蛋白的氨基酸分布、信号肽长度大小及切割位点等性质进行分析。粘绿木霉含有分泌蛋白为377个,其氨基酸长度、信号肽长度与植物病原菌不同;信号肽切割位点属于A-X-A类型,与其他已经报道的植物病原真菌、卵菌中分泌蛋白信号肽切割位点一致。     

Nutch中网页更新预测研究与优化

Nutch的网页更新预测方法采用的是邻比法,相关更新参数需要人为设定,不能自适应调整,无法应对海量网页更新的差异性.为解决这个问题,提出动态选择策略对Nutch的网页更新预测方法进行改进.该策略在网页更新历史数据不足时,通过基于MapReduce的DBSCAN聚类算法来减少爬虫系统抓取网页数量,将样本网页的更新周期作为所属类其他网页的更新周期;在网页更新历史数据较多时,通过对网页更新历史数据进行泊松过程建模,较准确地预测每个网页的更新周期.最后在Hadoop分布式平台下对改进该策略测试.实验结果表明,优化后的网页更新预测方法表现更优.     

The RCT approach for cell coverage prediction (II): Experiment and early results

We study on the implementation flow of the radio computerized tomography (RCT) prediction method. A case in real cellular mobile radio (CMR) system together with the prediction results are also presented. As shown by the results, the RCT prediction method is marked for its convenience and rapidity, as well as its relative high precision even when the prediction procedure is highly simplified. Since it is developed according to the characteristics of wireless communication environments of our country and has concurrently merits from both statistical and deterministic prediction models, the RCT prediction method is in good agreement with engineering practices in cellular mobile communication in cities at home. Optimized by combining with other techniques, further improvement could be achieved in the stability and precision of the RCT prediction method which now serves as the core part of a software tool for commercial use in CMR system analysis and optimization. Biography: Yu Sheng-bing (1974-), male, Ph. D candidate, research interest: theory analysis and application development of radio propagation in wireless communication systems.     

Latent Co-interests' Relationship Prediction

With the development of the social media and Internet, discovering latent information from massive information is becoming particularly relevant to improving user experience. Research efforts based on preferences and relationships between users have attracted more and more attention. Predictive problems, such as inferring friend relationship and co-author relationship between users have been explored. However, many such methods are based on analyzing either node features or the network structures separately, few have tried to tackle both of them at the same time. In this paper, in order to discover latent co-interests’ relationship, we not only consider users’ attributes but network information as well. In addition, we propose an Interest-based Factor Graph Model (I-FGM) to incorporate these factors. Experiments on two data sets (bookmarking and music network) demonstrate that this predictive method can achieve better results than the other three methods (ANN, NB, and SVM).     

二次时变参数离散灰色模型

本文基于离散灰色模型模拟值增长率恒定的原因,通过引入二次时间项来构造了 二次时变参数离散灰色模型(quadratic time-varying parameters discrete grey model,简称为QDGM(1,1)模型).并且研究了该模型的性质.结果说明, QDGM(1,1)模型具 有白指数规律重合性,线性规律重合性,二次规律重合性,伸缩变换一致性.应用最优化方法研究QDGM(1,1)模型迭代基值问题,建立优化模型并提出求解算法.最后叙述了应用 QDGM(1,1)模型建模和预测的步骤,并通过实例比较了QDGM(1,1)模型与原离散灰色 模型及其非齐次离散模型和线性时变参数离散灰色模型的预测能力,最终结果表明本文 提出的QDGM(1,1)模型具有更高的模拟和预测精度.     

时变时滞系统的灰色预测非线性PID控制

针对时变时滞过程提出一种新的控制结构.在此控制结构中,利用遗传算法自动跟踪系统的时滞变化,由灰色预测模型根据辨识的时滞提前预测出系统的输出,而系统的预测输出与输入的偏差以及偏差变化率为非线性PID控制器的输入.仿真结果验证了这种结构能很好地满足时变时滞系统的快速动态响应和稳定性要求.     

一种参数自调整风电功率预测模型

为了提高风电功率预测精度,提出一种参数自调整风电功率预测模型.通过加权递推最小二乘(SWWRLS)方法建立预测模型,侧重当前数据对预测结果的影响,排除了历史数据对预测结果的干扰.模型通过加权递推的方法节省了存储空间,并且提高了模型对外界环境数据变化的自适应性.最后,分别采用支持向量机(SVM)方法、卡尔曼滤波(KF)方法和本文SWWRLS方法,以辽宁省某风电场的真实历史数据进行风电功率预测对比实验,实验结果表明,本文方法建立的模型具有较高的预测精度.