Novelty,coherence, and Mendeleev’s periodic table

Predictivism is the view that successful predictions of “novel” evidence carry more confirmational weight than accommodations of already known evidence. Novelty, in this context, has traditionally been conceived of as temporal novelty. However temporal predictivism has been criticized for lacking a rationale: why should the time order of theory and evidence matter? Instead, it has been proposed, novelty should be construed in terms of use-novelty, according to which evidence is novel if it was not used in the construction of a theory. Only if evidence is use-novel can it fully support the theory entailing it. As I point out in this paper, the writings of the most influential proponent of use-novelty contain a weaker and a stronger version of use-novelty. However both versions, I argue, are problematic. With regard to the appraisal of Mendeleev’ periodic table, the most contentious historical case in the predictivism debate, I argue that temporal predictivism is indeed supported, although in ways not previously appreciated. On the basis of this case, I argue for a form of so-called symptomatic predictivism according to which temporally novel predictions carry more confirmational weight only insofar as they reveal the theory’s presumed coherence of facts as real.     

网络结构特征与链路预测算法关系研究

以美国航空网络、科学家合作网络和线虫新陈代谢网络等5种实际网络为例进行了综合实验,用结果数据定量化描述了同配系数、集聚系数和网络效率等网络结构特征参数,与基于局部信息和全局信息的两类链路预测方法结果之间的关系。通过对结果的分析,得到了网络同配系数为正且聚集系数大于阈值(约0.1)时适用基于局部信息的预测方法,否则适用基于全局信息的预测方法;以及集聚系数、网络效率与局部信息预测方法的结果成正比,与全局信息预测方法成反比等结论。这些结论为通过网络特征参数进行链路预测方法的选择提供了定量化的参考依据。     

考虑车辆间交互作用的驾驶意图预测方法

准确的意图预测可以帮助智能车辆更好地了解周围环境并做出更加安全的决策，从而提高自动驾驶的安全性，促进人机协同驾驶。为了对驾驶员未来的意图做出更加精准的预测，提出了一种交互式意图预测方法。首先，通过将隐马尔可夫模型（HMM）与高斯混合模型（GMM）相结合，在充分考虑周围场景信息后建立了行为识别模型，用于对当前的驾驶行为做出准确的判断。然后，考虑到交通场景复杂多变的特点，提出基于意图的轨迹预测方法规划出一条最佳的行驶轨迹，并采用最大期望效用理论对未来的驾驶行为进行推理。由于行为识别和意图推理模型综合考虑了交通态势的演变过程和车辆之间的交互作用，所以将两个模型得到的结果相结合可得到车辆最终预测出的驾驶意图。最后，在NGSIM数据集对所提出的方法进行验证，结果表明提出的行为识别模型能够提前0.2~0.3 s识别出车辆的换道意图，结合未来意图推理模型，能够更加准确地预测出车辆未来的驾驶行为，由此可提高车辆驾驶的安全性。     

基于控制变量估计的高超声速再入滑翔目标轨迹预测算法

以高超声速再入滑翔目标为研究对象,在对目标机动控制变量进行建模分析的基础上提出了一种轨迹预测算法。首先,基于动力学建模构建了目标跟踪模型,利用气动参数对目标状态向量进行扩维并推导了对应的运动模型。其次,构造了适用于轨迹预测的目标机动控制变量,在不同机动模式下分析了控制变量的变化规律,基于控制变量设计了对应运动方程以及轨迹预测模型。最后,仿真生成了两条轨迹并对所提算法进行了仿真验证,分析了算法性能。仿真结果表明所提轨迹预测算法能够取得较好的预测效果。     

两阶段非线性Wiener过程退化建模与可靠性分析

基于性能退化数据对产品进行可靠性分析一直是可靠性工程领域研究的热点与难点。针对多阶段退化过程中存在的非线性规律,同时考虑变点位置位于测试时刻之间的一般情形且各试样变点存在个体差异性的实际情况,提出了基于Wiener过程的两阶段非线性退化模型,给出了模型参数极大似然估计方法,建立了可靠性分析和寿命预测方法。最后通过高压脉冲电容器实例的对比分析,验证了所提方法的合理性与有效性。结果表明,与多阶段线性Wiener过程方法相比,所提方法能够更加准确地描述退化过程的非线性时变特征,进而得到更为合理的寿命评估结果。     

The total cost of misclassification in credit scoring: A comparison of generalized linear models and generalized additive models

This study examines whether the evaluation of a bankruptcy prediction model should take into account the total cost of misclassification. For this purpose, we introduce and apply a validity measure in credit scoring that is based on the total cost of misclassification. Specifically, we use comprehensive data from the annual financial statements of a sample of German companies and analyze the total cost of misclassification by comparing a generalized linear model and a generalized additive model with regard to their ability to predict a company's probability of default. On the basis of these data, the validity measure we introduce shows that, compared to generalized linear models, generalized additive models can reduce substantially the extent of misclassification and the total cost that this entails. The validity measure we introduce is informative and justifies the argument that generalized additive models should be preferred, although such models are more complex than generalized linear models. We conclude that to balance a model's validity and complexity, it is necessary to take into account the total cost of misclassification.     

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.     

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.