Random forests for functional covariates

We propose a form of random forests that is especially suited for functional covariates. The method is based on partitioning the functions' domain in intervals and using the functions' mean values across those intervals as predictors in regression or classification trees. This approach appears to be more intuitive to applied researchers than usual methods for functional data, while also performing very well in terms of prediction accuracy. The intervals are obtained from randomly drawn, exponentially distributed waiting times. We apply our method to data from Raman spectra on boar meat as well as near‐infrared absorption spectra. The predictive performance of the proposed functional random forests is compared with commonly used parametric and nonparametric functional methods and with a nonfunctional random forest using the single measurements of the curve as covariates. Further, we present a functional variable importance measure, yielding information about the relevance of the different parts of the predictor curves. Our variable importance curve is much smoother and hence easier to interpret than the one obtained from nonfunctional random forests.     

新有机锡化合物的合成及分子内O→Sn配位键的离解与~1HNMR相关性的研究(英文)

用具有抗癌活性的(Z) - 1-[2 - (二卤化苯基锡基乙烯基)] -环辛醇与含氮的双齿配体作用,合成了一系列新的有机锡络合物,通过IR,1HNMR,元素分析和摩尔电导值的测定对其结构、性质进行了表征,特别对有机锡化合物分子内O→Sn配位键的离解与配体中烯基质子化学位移(1HNMR)的相关性进行了讨论     

Modeling Studies of the Formation and Destruction of NO in Pulsed Barrier Discharges in Nitrogen and Air

This paper presents the results of modeling studies on the formation and destruction of NO in pulsed barrier discharges in nitrogen and air. The goals of this work are to identify the major processes involved in the formation and destruction of NO in air discharges, to distinguish between oxidative and reductive paths for NO destruction, to explore the potential importance of excited state reactions, to evaluate the role of water in such systems, and to identify the final products in the absence of heterogeneous processes. In all cases, the systems were modeled with 100×10^–4% (100 ppm) of added NO, with and without 3% added water. The focus in all of this work is chemistry in the post-pulse regime.     

基于化学史和数据探究的“化学平衡常数”教学研究

分析了“化学平衡常数”的教材内容和相关教学设计,针对实际教学中存在的2个问题：简化的数据探究难以让学生体会到科学研究的复杂性;纯粹的知识性教学难以体现科学知识的价值和意义。提出在教学中融合化学史和数据探究,能帮助学生全面深入地理解概念,促进学生进一步认识科学本质和学科价值。     

新有机锡化合物的合成及分子内O→Sn配位键的离解与—1NMR相关性的研究

用具有抗癌活性的(Z)-1-[2-(二卤化苯基锡基乙烯基)]-环辛醇与含氮的双齿配体作用,合成了一系列新的有机锡络合物,通过IR,1HNMR,元素分析和摩尔电导值的测定对其结构、性质进行了表征,特别对有机锡化合物分子内O→Sn配位键的离解与配体中烯基质子化学位移(1HNMR)的相关性进行了讨论.     

Parallelization of multireference perturbation calculations with GAMESS

The quasi‐degenerate multireference second‐order perturbation theory (MRMP2) routines in the GAMESS suite of program codes have been parallelized using a distributed data interface (DDI). Two typical kinds of molecules were chosen for examination of parallelization speedup using one to eight PCs gathered as a cluster and connected by Fast Ethernet. The first example, in which total energies of several low‐lying electronic states have been obtained for niobium monohydride, give parallelization speedup of 7.15 when eight PCs were used as a cluster. The second example is the ground‐state total energy for a medium sized molecule, 4a,4b,8a,9a‐tetrahydro‐pyridino[1′,2′‐4,3]imidazo‐lidino[1,5‐a]pyridine. When distributed memory is employed, the parallelization speedup improves to 6.84 for the MRMP2 calculations when an eight‐PC cluster is used. These results demonstrate that our efforts to achieve the parallelization of MRMP2 routines have been successful. © 2001 John Wiley & Sons, Inc. J Comput Chem 22: 1243–1251, 2001     

Über Bildung und Reaktionen der CH2Li‐Derivate von tBu2P–P=P(CH3)tBu2 und (Me3Si)tBuP–P=P(CH3)tBu2

Formation and Reactions of the CH₂Li‐Derivatives of ^tBu₂P–P=P(CH₃)^tBu₂ and (Me₃Si)^tBuP–P=P(CH₃)^tBu₂ With ⁿBuLi, (Me₃Si)^tBuP–P=P(CH₃)^tBu₂ ( 1 ) and ^tBu₂P–P=P(CH₃)^tBu₂ ( 2 ) yield (Me₃Si)^tBuP–P=P(CH₂Li)^tBu₂ ( 3 ) and ^tBu₂P–P=P(CH₂Li)^tBu₂ ( 4 ), wich react with Me₃SiCl to give (Me₃Si)^tBuP–P=P(CH₂–SiMe₃)^tBu₂ ( 5 ) and ^tBu₂P–P=P(CH₂–SiMe₃)^tBu₂ ( 6 ), respectively. With ^tBu₂P–P(SiMe₃)–P^tBuCl ( 7 ), compound 3 forms 5 as well as the cyclic products [H₂C–P(^tBu)₂=P–P(^tBu)–P^tBu] ( 8 ) and [H₂C–P(^tBu)₂=P–P(P^tBu₂)–P(^tBu)] ( 9 ). Also 3 forms 8 with ^tBuPCl₂. The cleavage of the Me₃Si–P‐bond in 1 by means of C₂Cl₆ or N‐bromo‐succinimide yields (Cl)^tBuP–P=P(CH₃)^tBu₂ ( 10 ) or (Br)^tBuP–P=P(CH₃)^tBu₂ ( 11 ), resp. With LiP(SiMe₃)₂, 10 forms (Me₃Si)₂P–P(^tBu)–P=P(CH₃)^tBu₂ ( 12 ), and Et₂P–P(^tBu)–P=P(CH₃)^tBu₂ ( 13 ) with LiPEt₂. All compounds are characterized by ³¹P NMR Data and mass spectra; the ylide 5 and the THF adduct of 4 additionally by X‐ray structure analyses.     

The multivariate N-Component resolution problem with minimum assumptions

The present state of the minimum assumption multivariate component resolution theory is outlined. Some new developments are presented: limiting function domains; the analytical expression for the limiting function; efficient algorithms for defining the FIRPOL and INNPOL hyperpolyhedrons. A very low resolution data set is analyzed.