Credal model averaging for classification: representing prior ignorance and expert opinions

Bayesian model averaging (BMA) is the state of the art approach for overcoming model uncertainty. Yet, especially on small data sets, the results yielded by BMA might be sensitive to the prior over the models. Credal model averaging (CMA) addresses this problem by substituting the single prior over the models by a set of priors (credal set). Such approach solves the problem of how to choose the prior over the models and automates sensitivity analysis. We discuss various CMA algorithms for building an ensemble of logistic regressors characterized by different sets of covariates. We show how CMA can be appropriately tuned to the case in which one is prior-ignorant and to the case in which instead domain knowledge is available. CMA detects prior-dependent instances, namely instances in which a different class is more probable depending on the prior over the models. On such instances CMA suspends the judgment, returning multiple classes. We thoroughly compare different BMA and CMA variants on a real case study, predicting presence of Alpine marmot burrows in an Alpine valley. We find that BMA is almost a random guesser on the instances recognized as prior-dependent by CMA.     

Single‐electron transfer‐living radical copolymerization of butyl methacrylate and divinylbenzene for preparation of oil‐absorbing gel

Crosslinking copolymerization of butyl methacrylate with a small amount of divinylbenzene (DVB) was carried out using single‐electron transfer‐living radical polymerization initiated with carbon tetrachloride (CCl₄) and catalyzed by Cu(0)/N‐ligand in N,N‐dimethylformamide to produce a highly oil‐absorbing gel. The polymerization, gelation process, and oil‐absorbing properties were studied in detail. Analysis of monomer conversion with reaction time showed that the polymerization followed first‐order kinetics for both linear and crosslinking polymerization before gelation. Higher levels of DVB led to earlier gelation and the influence of N‐ligand on gelation was also significant. Under optimal conditions, oil absorption of the prepared gel to chloroform could reach 42.1 g·g^?1. © 2013 Wiley Periodicals, Inc. J. Polym. Sci., Part A: Polym. Chem. 2013, 51, 3233–3239     

-950m水平中央水泵房吸水井优化设计分析

吕家坨矿业分公司-950m水平中央水泵房设计应遵循简单、合理、安全、可靠。目前采用的设计是按照传统的设计方式,布置配水巷吸水井,配水巷和水仓暗平交。实践表明该设计方法施工难度较大,工程量大,建设工期长。针对以上问题反思原设计有许多部位需要优化,减少配水巷工程量,把吸水井改为吸水槽。施工实践证明,通过优化改造降低了施工难度,减少了工程量,缩短了工期。     

Independence concepts in evidence theory

We study three conditions of independence within evidence theory framework. The first condition refers to the selection of pairs of focal sets. The remaining two ones are related to the choice of a pair of elements, once a pair of focal sets has been selected. These three concepts allow us to formalize the ideas of lack of interaction among variables and among their (imprecise) observations. We illustrate the difference between both types of independence with simple examples about drawing balls from urns. We show that there are no implication relationships between both of them. We also study the relationships between the concepts of “independence in the selection” and “random set independence”, showing that they cannot be simultaneously satisfied, except in some very particular cases.     

The maximum number of infected individuals in SIS epidemic models: Computational techniques and quasi-stationary distributions

We study the maximum number of infected individuals observed during an epidemic for a Susceptible-Infected-Susceptible (SIS) model which corresponds to a birth-death process with an absorbing state. We develop computational schemes for the corresponding distributions in a transient regime and till absorption. Moreover, we study the distribution of the current number of infected individuals given that the maximum number during the epidemic has not exceeded a given threshold. In this sense, some quasi-stationary distributions of a related process are also discussed.     

织物湿传导理论与实际的研究第三报: 液态水在织物中的吸收、传输与蒸发的研究

测试和分析了织物的润湿和吸收性能、保水能力和液态水蒸发的能力.结果表明织物的液滴吸收时间与织物孔隙率ε、接触角θ、织物厚度h等有密切关系;织物的保水能力与ε/(1-ε)成线性关系;织物的湿蒸发能力与织物表面凹坑尺寸有密切关系.     

Ramanujan theta functions and birth and death processes

This paper discusses birth and death processes that are related to the celebrated Ramanujan’s theta functions. The pertinent transient system size probabilities are calculated numerically via a truncation of continued fractions.     

鞅在考虑退保及支出的复合负二项风险模型中的应用

在离散时间的情况下,考虑到保险公司退保事件的发生,建立了一种新的带支出的符合实际运营的风险分析模型。模型中保单到达过程,退保过程及理赔过程发生均为复合负二项过程,并且应用鞅分析方法对保险公司的风险模型进行研究,得到了最终破产概率及Lundberg不等式。     

磁化处理对吸波涂层吸波性能的影响

按相同比例制备了两组掺杂Mn-Zn铁氧体复合聚苯胺吸波涂层．一组放入外磁场中磁化,一组放置在空气中,然后将两组样品分别放入3cm波导测量线中,在9．2GHz的频率点处测量其电磁参数及吸波性能．吸波涂层在外界磁场处理后,涂层获得较高的各向异性．从而影响到涂层的电磁参数及吸波性能．结果表明,经磁化处理的吸波涂层的吸波效果优于未磁化处理的吸波涂层,这给出了一种增加吸波涂层吸波效果的方法．     

掺杂聚苯胺复合材料电磁参数及吸波性能研究

采用3cm波导式测量线在8～14GHz频率范围内,用多点拟合的实验和计算方法对掺杂聚苯胺的微波吸收特性及参量进行了研究．发现浓H2SO4掺杂本征态聚苯胺(PAn)所合成材料的电损耗很小、磁损耗较大(相对于HCI—PAn)．FeCl2掺杂浓H2SO4-PAn材料可合成磁损耗较高、基本上有利于吸收微波的材料;更令人注意的是,将HCl—PAn与浓H2SO4-PAn—FeCl3按一定的比例混合,可以合成出平均衰减为13．37dB、最大衰减为26．7dB、密度为0．7g／cm^3、频宽为10．34～14GHz的很有利于吸收微波的材料．同时．比较了有机酸掺杂聚苯胺DBSA—PAn与HCI—PAn的吸波性能。