中药复杂组效关系的变结构神经网络辨识方法

针对中药复杂组效关系的辨识问题,研究了变结构多层前馈神经网络,推导出一种新型的变结构网络学习算法,成功地应用于中药川芎药效活性预测计算.该方法从一个规模较小的网络出发,当网络无法达到预定的学习精度时,自动增加隐含层神经元个数,并在原有学习结果的基础上确定新的网络参数,自适应地确定前馈神经网络结构,可用于处理复杂化学模式信息.计算机仿真实验结果表明,该方法能有效地确定多层前馈神经网络的最佳结构,提高网络学习效率和函数逼近精度,解决复杂非线性函数映射关系准确建模问题.     

EIGHT-POINT STRAIGHT-LINE-NET-DIAGRAMS OF BINARY SIX-PHASE (n+4) MULTISYSTEMS (Ⅱ)——DERIVATION FROM THEORY OF PHYSICALLY REAL NETS

Based on the theory of physically real nets, the 8- point straight-line nets of bi-nary 6- phase (n + 4) multisystems (31 in toto) have been derived directly from the l-point straight-line nets. This result is in complete agreement with that derived fromthe theory of closed nets, indicating the incorrectness of the previous conclusion thatthere is only one 8-point straight-line net which corresponds to only one 8- pointstraight-line-net-diagram for binary 6- phase multisystems.     

酮存在下烷氧基钐催化选择性还原醛

本文报道了一种选择性Meerwein-Ponndorf-Verley(MPV)型还原体系。在Sm(OCH2R)3(5%)/RCH2OH/4A molecular sieves(MS 4A) (R=CH3, CH3CH2)催化下, 该体系对醛、酮羰基具有优良的选择性还原能力, 能够选择性的还原醛羰基, 而对酮羰基的还原呈惰性。     

布里奇曼法制备KPb2Cl5单晶

在500 ℃高真空条件下,制备了KPb2Cl5原料,对原料进行了XRD分析,表明该方法能得到纯相的KPb2Cl5.利用改进的布里奇曼法进行了生长KPb2Cl5单晶的实验,得到了直径15 mm的原晶,并测试了晶体样品的基本红外透过性能.结果显示:不镀膜的情况下,3～20 μm的中红外波段,透过率约为80;,具有很好的红外光学性能.     

环戊基全取代六元瓜环与钾离子配合物的合成及其结构表征

金属与瓜环的配位化学是瓜环化学的主要研究内容之一.本文主要研究了环戊基全取代六元瓜环(CyP6 Q[6])与K+的配合物的合成,并利用X-射线单晶衍射法对其晶体结构进行了表征.结果表明:K+与CyP6 Q[6]的两个端口配位,形成了分子胶囊结构.相邻的瓜环通过与[ZnCl4]2-的偶极作用,形成平面堆积结构,最后形成三维超分子自组装实体.     

敏化条件对染料敏化太阳能电池性能的影响

通过实验方案,对影响染料敏化太阳能电池(DSSC)的敏化条件进行了优化设计,在光阳极初始默认的制作条件下,从海带中提取叶绿素,分别对影响DSSC光电性能的敏化染料溶液浓度、pH值、温度、受光时间、敏化时间、对电极背景色等影响因素逐一进行研究,最终确定了光阳极敏化的最优条件:醇水溶液的最佳稀释比为1:2,最佳敏化pH=8,最佳敏化温度为30℃,最佳敏化时间24 h,黑暗环境下敏化效果最好,且对电极采用镜面背景最佳,最终获得光电转换效率0.76;.     

双层PLS算法及其在近红外光谱分析中的应用

针对近红外光谱数据局部效应显著,变量个数多,且彼此间常存在严重的复共线性,并与样品组分含量呈非线性关系,构建了一种双层非线性偏最小二乘回归 (DNPLSR)算法。它将非线性回归和偏最小二 乘(PLS)相结合,先在外层由PLS从样本数据中提取成分,并实现每对成分间的非线性映射,再在内层实施PLS算法,将外层因变量成分的拟合误差反馈计算转换权向量的增量,进一步修正转换权向量,以使外层所提取的成分对因变量具有更优的解释能力。最后,将该法应用于80个谷物样品的水组分含量与其近红外光谱的定量关系建模,效果良好,显示出很强的学习能力,所建模型的预报性能也优于其他方法。     

Testing Regression Coefficients in High-Dimensional and Sparse Settings

In the high-dimensional setting, this article considers a canonical testing problem in multivariate analysis, namely testing coefficients in linear regression models. Several tests for highdimensional regression coefficients have been proposed in the recent literature. However, these tests are based on the sum of squares type statistics, that perform well under the dense alternatives and suffer from low power under the sparse alternatives. In order to attack this issue, we introduce a new test statistic which is based on the maximum type statistic and magnifies the sparse signals. The limiting null distribution of the test statistic is shown to be the extreme value distribution of type I and the power of the test is analysed. In particular, it is shown theoretically and numerically that the test is powerful against sparse alternatives. Numerical studies are carried out to examine the numerical performance of the test and to compare it with other tests available in the literature.