Nonparametric estimation of distributions with categorical and continuous data

In this paper we consider the problem of estimating an unknown joint distribution which is defined over mixed discrete and continuous variables. A nonparametric kernel approach is proposed with smoothing parameters obtained from the cross-validated minimization of the estimator's integrated squared error. We derive the rate of convergence of the cross-validated smoothing parameters to their ‘benchmark’ optimal values, and we also establish the asymptotic normality of the resulting nonparametric kernel density estimator. Monte Carlo simulations illustrate that the proposed estimator performs substantially better than the conventional nonparametric frequency estimator in a range of settings. The simulations also demonstrate that the proposed approach does not suffer from known limitations of the likelihood cross-validation method which breaks down with commonly used kernels when the continuous variables are drawn from fat-tailed distributions. An empirical application demonstrates that the proposed method can yield superior predictions relative to commonly used parametric models.     

Synthesis and transition temperatures of liquid crystals incorporating a 1,4-tetrafluorophenylene unit

Two homologous series of mesogenic materials which incorporate a 1,4-tetrafluorophenylene moiety and a terminal cyano- or nitro-substituent have been synthesized by using palladiumcatalysed coupling procedures. The compounds exhibit nematic and/or smectic A phases.     

Robinson-Trautman equations and Chandrasekhar's special perturbation of the Schwarzschild metric

A perturbation wave solution of the Robinson-Trautman equations is proved to be a perturbation of the Schwarzschild black hole which describes an outgoing axial gravitational wave and corresponds to a special case of Chandrasekhar's algebraically special perturbation of the Schwarzschild metric.     

A problem in extremal quasiconformal extensions

A constantK ₀ ^(m) (h) is introduced for every quasisymmetric mappingh of the unit circle and every integerm≥4 which contains the constantK ₀(h) (indicated by the change in module of the quadrilaterals with vertices on the circle) as a special case. A necessary and sufficient condition is established forK ₀ ^(m) (h) =K ₁(h). It is shown that there are infinitely many quasisymmetric mappings of the unit circle having the property thatK ₀ ^(m) (h)<K ₁(h), wherek ₁(h) is the maximal dilatation ofh.     

非线性参数估计的极小化L∞模方法

研究了L∞模的拟凸性质，利用极大熵方法得到极小化L∞模的Q算法．这是一种具有显式搜索方向的变尺度算法，在非线性参数估计中取得较好效果．     

一个新的杆状病毒凋亡抑制基因的克隆及鉴定

缺失功能性ｐ３５基因的苜蓿尺蠖核形多角体病毒（ＡｃＮＰＶ）突变体（ｖΔＰ３５Ｋ／ｐｏｌ＋）感染草地夜蛾细胞（Ｓｆ９和Ｓｆ２１）［１］及海灰翅夜蛾细胞（ＳＬ２）［２］时，引起细胞凋亡，从而使病毒的感染流产．我们发现海灰翅夜蛾核形多角体病毒（ＳｌＮＰＶ）...     

陆生植物黑麦草(Lolium multiflorum)对富营养化水体修复的围隔实验研究——氨氮的净化效应及其动态过程

采用浮床黑麦草（Lolium multi florum）对畜禽养殖富营养水体氨氮的净化效应及动态过程进行了研究．结果表明：浮床黑麦草对富营养水体中的氨氮具有明显的净化效果．当覆盖率30％时，对氨氮的去除率最高可达到95．89％．对其去除水体氨氮的动态过程拟合表明符合三次方程曲线．该研究为冬季陆生植物修复富营养水体提供重要依据．     

光致变色多阶游程光存储研究

多阶游程存储是一种不改变光学系统而显著提高光存储容量和数据传输率的新方法.介绍了光致变色多阶游程存储原理和实验系统.提出了基于光致变色原理的多阶游程存储数学模型，该模型反映了记录符反射率与曝光功率、曝光时间之间的非线性关系，并在此基础上确定了光致变色多阶游程存储的写策略.基于650nm光致变色材料进行了4阶游程存储的动态实验.结果表明，实验中采用的650nm光致变色材料可用于多阶游程存储，采用的写策略能够有效地使记录信道线性化，利于采用适合线性系统的信号处理方法. 关键词： 多阶游程 光致变色 光存储 写策略     

Effects of Post-Thermal Treatment on Quality of SiC Grown by PVT Method

We report the effects of post-thermal treatment on the quality of 2-inch 6H-SiC wafer cut from a crystal boule grown by physical vapour transportation method. The full widths at half maximum of x-ray diffraction rocking curves measured on sites across the 2-inch wafer become narrower, indicating the quality improvement after a three-step post-thermal treatment. It is found that the most common defects such as micropipes and inclusions can be significantly reduced after the treatment. Our results show that the post-thermal treatment is an effective route to improve the quality of SiC single crystals.     

多子阵子空间拟合波达方向估计

提出了考虑阵元互耦的子空间拟合波达方向估计方法。用一带状、对称Toeplitz矩阵对均匀线阵的互耦矩阵建模。根据互耦矩阵自由度,去除部分两边阵元,研究了子空间拟合算法中ESPRIT算法的理论性能。在大快拍的情况下,均匀线阵的MCLS-ESPRIT算法的角度估计误差是一个零均值的联合高斯分布,同时给出了分布的协方差表达式。由方差的数值计算可知,在阵元数和信源数确定的情况下,存在估计标准差最小的子阵;与不存在互耦的理想情况相比,除了估计标准差少许增加外,性能接近。本文的方法已应用于高分辨率测深侧扫声呐,获得了好结果。在声呐阵阵元数增加的条件下,用本文的方法,能抑制均匀线阵的互耦的影响。