An improved ensemble learning machine for biological activity prediction of tyrosine kinase inhibitors

Boosting is one of the most important strategies in ensemble learning because of its ability to improve the stability and performance of weak learners. It is nonparametric, multivariate, fast and interpretable but is not robust against outliers. To enhance its prediction accuracy as well as immunize it against outliers, a modified version of a boosting algorithm (AdaBoost R2) was developed and called AdaBoost R3. In the sampling step, extremum samples were added to the boosting set. In the robustness step, a modified Huber loss function was applied to overcome the outlier problem. In the output step, a deterministic threshold was used to guarantee that bad predictions do not participate in the final output. The performance of the modified algorithm was investigated with two anticancer data sets of tyrosine kinase inhibitors, and the mechanism of inhibition was studied using the relative weighted variable importance procedure. Investigating the effect of base learner's strength reveals that boosting is only successful using the classification and regression tree method (a weak to moderate learner) and does not have a significant effect using the radial basis functions partial least square method (a strong base learners). Copyright © 2015 John Wiley & Sons, Ltd.     

Induction of decision trees using genetic programming for modelling ecotoxicity data: adaptive discretization of real-valued endpoints

Recent literature has demonstrated the applicability of genetic programming to induction of decision trees for modelling toxicity endpoints. Compared with other decision tree induction techniques that are based upon recursive partitioning employing greedy searches to choose the best splitting attribute and value at each node that will necessarily miss regions of the search space, the genetic programming based approach can overcome the problem. However, the method still requires the discretization of the often continuous-valued toxicity endpoints prior to the tree induction. A novel extension of this method, YAdapt, is introduced in this work which models the original continuous endpoint by adaptively finding suitable ranges to describe the endpoints during the tree induction process, removing the need for discretization prior to tree induction and allowing the ordinal nature of the endpoint to be taken into account in the models built.     

大型砂尘风洞中砂尘浓度测量与控制方法的研究

砂尘浓度指标严重影响砂尘风洞试验效果;在大型砂尘风洞中准确的测量及有效的控制砂尘浓度是砂尘风洞设备研制中的两个关键问题;针对动态试验工况环境中浓度传感器标定的问题,分析了浓度测量时标定参数与风速和浓度的关系,使用模型树算法建立了三者之间的关系模型,以此模型来预测各种动态情况下的标定参数;针对复杂环境下浓度动态控制问题,采用专家PID算法,提出了多回路控制系统结构和专家规则;工程实践表明该测量和控制方法满足了动态试验环境的需求,取得了良好效果;模型树算法和专家PID系统能有效的解决动态工况下砂尘浓度的测量与控制问题。     

非齐次树上马氏链的若干强偏差定理

通过构造适当的非负鞅,将Doob鞅收敛定理应用于几乎处处收敛的研究,给出了一类非齐次树上马氏链场加权和滑动平均的若干强偏差定理.     

Uncommon suffix tries

Common assumptions on the source producing the words inserted in a suffix trie with n leaves lead to a height and saturation level. We provide an example of a suffix trie whose height increases faster than a power of n and another one whose saturation level is negligible with respect to . Both are built from VLMC (Variable Length Markov Chain) probabilistic sources and are easily extended to families of tries having the same properties. The first example corresponds to a “logarithmic infinite comb” and enjoys a non uniform polynomial mixing. The second one corresponds to a “factorial infinite comb” for which mixing is uniform and exponential. © 2013 Wiley Periodicals, Inc. Random Struct. Alg., 46, 117–141, 2015     

Covariate model-based fault tree analysis for risk assessment in chemical process industries: A case study of a chlorine manufacturing facility

Fault tree analysis (FTA) is a promising quantitative technique for risk analysis in chemical process industries (CPIs). In FTA, a certain sequence of basic events (causes) leads to one specific Top event (critical event of interest). However, the conventional fault tree analysis has the limitations of staticity and uncertainty. The staticity in conventional FTA arises due to its inability to accommodate time-dependent characteristics of the process system. Whereas uncertainty primarily lies in the failure probability data of basic events. This paper proposes an innovative methodology that uses a time-dependent covariate model to update the failure probability values of major contributing basic events in FTA. A novel subclass of the family of phase-type distributions is used to model the covariates corresponding to the basic events. The newly developed methodology is applied for a case study in a chlorine manufacturing facility to estimate the chlorine release probability. The blockage in the pipeline was identified as the significant reason for chlorine release from expert opinion and sensitivity analysis. The results of the proposed model of FTA are compared with that of conventional FTA.     

Delocalized \begin{document}$\pi_3^6$\end{document} Bond in OX\begin{document}$_2$\end{document} (X=Halogen) Molecules

OX\begin{document}$_2$\end{document} (X=halogen) molecules was studied theoretically. Calculation results show that delocalized \begin{document}$\pi_3^6$\end{document} bonds exist in their electronic structures and O atoms adopt the sp\begin{document}$^2$\end{document} type of hybridization, which violates the prediction of the valence shell electron pair repulsion theory of sp\begin{document}$^3$\end{document} type. Delocalization stabilization energy is proposed to measure the contribution of delocalized \begin{document}$\pi_3^6$\end{document} bond to energy decrease and proves to bring extra-stability to the molecule. These phenomena can be summarized as a kind of coordinating effect.     

Enhanced Crystal Quality of Perovskite via Protonated Graphitic Carbon Nitride Added in Carbon-Based Perovskite Solar Cells

The quality of perovskite layers has a great impact on the performance of perovskite solar cells (PSCs). However, defects and related trap sites are generated inevitably in the solution-processed polycrystalline perovskite films. It is meaningful to reduce and passivate the defect states by incorporating additive into the perovskite layer to improve perovskite crystallization. Here an environmental friendly 2D nanomaterial protonated graphitic carbon nitride (p-g-C\begin{document}$_3$\end{document}N\begin{document}$_4$\end{document}) was successfully synthesized and doped into perovskite layer of carbon-based PSCs. The addition of p-g-C\begin{document}$_3$\end{document}N\begin{document}$_4$\end{document} into perovskite precursor solution not only adjusts nucleation and growth rate of methylammonium lead tri-iodide (MAPbI\begin{document}$_3$\end{document}) crystal for obtaining flat perovskite surface with larger grain size, but also reduces intrinsic defects of perovskite layer. It is found that the p-g-C\begin{document}$_3$\end{document}N\begin{document}$_4$\end{document} locates at the perovskite core, and the active groups -NH\begin{document}$_2$\end{document}/NH\begin{document}$_3$\end{document} and NH have a hydrogen bond strengthening, which effectively passivates electron traps and enhances the crystal quality of perovskite. As a result, a higher power conversion efficiency of 6.61% is achieved, compared with that doped with g-C\begin{document}$_3$\end{document}N\begin{document}$_4$\end{document} (5.93%) and undoped one (4.48%). This work demonstrates a simple method to modify the perovskite film by doping new modified additives and develops a low-cost preparation for carbon-based PSCs.     

多值测试诊断策略优化设计

针对电子系统中多值测试条件下的测试排序问题,提出了一种诊断策略优化方法。首先,以相关性矩阵模型为基础,将已有的二值测试的优化算法同多值测试问题相结合,提出了适用于多值测试的基于霍夫曼编码的启发式函数;其次,将平均测试代价最小和平均测试步骤最少作为优化目标,采用与或树启发式搜索算法生成诊断树,得到多值测试的诊断策略,并给出了诊断策略优化方法的具体实现步骤;最后,将其应用到航空设备的实例中。结果表明提出的基于霍夫曼编码的与或树启发式搜索算法是可行的,其生成的诊断树是最优的,比基于信息熵的与或树启发式搜索算法具有更小的平均测试代价和更少的平均测试步骤。     

Fabrication of Melamine/Tb3+-Intercalated Polydiacetylene Nanosheets and Their Thermochromic Reversibility

Polydiacetylene (PDA) is one kind of the conjugated polymer with layered structure, which can serve as a host to accommodate the guest components through intercalation. In these intercalated PDAs, some of them were reported to have a nearly perfect organized structure and perform completely reversible thermochromism. Till now, these reported intercalated PDAs were made by only introducing a single component for intercalation. Here, we chose 10, 12-pentacosadiynoic acid (PCDA) as the monomer, of which the carboxyl-terminal groups can interact with either Tb\begin{document}$ ^{3+} $\end{document} ions or melamines (MAs). When the feeding molar ratio of PCDA, MA, and Tb\begin{document}$ ^{3+} $\end{document} ion was 3:267:1, only Tb\begin{document}$ ^{3+} $\end{document} ions were intercalated though excess MAs existed. Such Tb\begin{document}$ ^{3+} $\end{document}-intercalated poly-PCDA exhibited completely reversible thermochromism, where almost all the carboxyl groups interacted with Tb\begin{document}$ ^{3+} $\end{document} ions to form the nearly perfect structure. When the feeding molar ratio of PCDA, MA, and Tb\begin{document}$ ^{3+} $\end{document} ion was 3:267:0.6, both Tb\begin{document}$ ^{3+} $\end{document} ions and MAs were intercalated. There existed some defects in the imperfect MA-intercalated domains and at the domain boundaries. The MA/Tb\begin{document}$ ^{3+} $\end{document}-intercalated poly-PCDA exhibits partially reversible thermochromism, where the backbones near the defects are hard to return the initial conformation, while the rest, those at nearly perfect organized domains, are still able to restore the initial conformation.