Feature Reduction via Generalized Uncorrelated Linear Discriminant Analysis

High-dimensional data appear in many applications of data mining, machine learning, and bioinformatics. Feature reduction is commonly applied as a preprocessing step to overcome the curse of dimensionality. Uncorrelated Linear Discriminant Analysis (ULDA) was recently proposed for feature reduction. The extracted features via ULDA were shown to be statistically uncorrelated, which is desirable for many applications. In this paper, an algorithm called ULDA/QR is proposed to simplify the previous implementation of ULDA. Then, the ULDA/GSVD algorithm is proposed, based on a novel optimization criterion, to address the singularity problem which occurs in undersampled problems, where the data dimension is larger than the sample size. The criterion used is the regularized version of the one in ULDA/QR. Surprisingly, our theoretical result shows that the solution to ULDA/GSVD is independent of the value of the regularization parameter. Experimental results on various types of data sets are reported to show the effectiveness of the proposed algorithm and to compare it with other commonly used feature reduction algorithms.     

Microstructure investigations of ball milled materials

HREM and FEG TEM were emphasized and extensively used to follow the most subtle changes in the structure and composition of ball-milled Cu, Fe-Cu, and thermally decomposed Fe60Cu40. Some significant results are obtained and summarized as follows: HREM shows that the deformation of ball-milled copper proceeds mainly by twinning and shear bands (SBs) formation. The nano-grains formed during ball milling (BM) contain a high density of dislocations. The grain boundaries (GBs) of nanocrystalline (NC) Cu prepared by BM are ordered, curved, and strained, but disordering, lattice distortion, and nanovoids in local regions were frequently observed. Nanoscale composition analysis on mechanically alloyed Fe16Cu84 shows that the average Fe content in both the interior of grains and the GBs is close to the designed composition, which proves that a supersaturated solid solution has really formed. However, the Fe content is rather inhomogeneous between the larger and smaller grains, which infers the inhomogeneous mixing of Fe and Cu during mechanical alloying (MA). NC structure and the mechanical force-enhanced fast diffusion are the reasons of the formation of supersaturated solid solutions in immiscible systems with positive enthalpy of mixing. HREM observations carried out with the thermally decomposed Fe60Cu40 solid solution show that the Nishiyama (N-W) or Kurdyumov-Sachs (K-S) orientation relationships exist between alpha-Fe and Cu. Energy dispersive X-ray spectra (EDXS) results show that the Cu content in these alpha-Fe grains reaches as high as 9.5 at.% even after heating to 1,400 degrees C, which is even higher than the maximum solubility of Cu in gamma-Fe at 1,094 degrees C.     

用PIXE方法研究骨折家兔骨骼微量元素的变化

用质子激发X荧光分析法测定48只家兔在挠骨骨折愈合过程中骨骼中多种微量元素含量的变化。结果表明，Fe和Sr分别呈鼓凸形和下凹形规律性变化，故Fe和Sr含量的变化可作为骨折愈合过程的指示剂。在骨折愈合过程中发现骨骼和血液中元素钙的相对含量保持不变，故无法为西医用补充钙来治疗骨折的疗法提供依据，但我们的研究结果却表明中医补充微量元素治疗骨折的疗法是有道理的。     

天然汞的全套中子数据评价

在１０￣（－５）＿ｅＶ－２０ＭｅＶ中子能量范围内对天然汞的中子核数据进行评价。评价内容包括总的、弹性、去弹、总非弹、３０条分立能级、连续非弹、（ｎ，２ｎ）、（ｎ，３ｎ，）、（ｎ，ｎ＇Ｐ）、（ｎ，ｎ＇α）、（ｎ，Ｐ）、（ｎ，α）、（ｎ，ｄ）、（ｎ，ｔ）和（ｎ，γ）截面；次级中子角分布；双微分截面（ＤＤＣＳ）；γ射线产生数据等。评价根据有效实验数据（至１９９３年）和ＵＮＦ－９２￣［１］理论计算。评价数据以ＥＮＤＦ／Ｂ６格式录入中国评价核数据库ＣＥＮＤＬ－２．１版（ＭＡＴ＝１８００），并提供核工程有关部门使用。     

ERS-1的SAR校准试验

前言欧洲遥感卫星1号(ERS-1)于1991年5月4日发射上天。合成孔径雷达(SAR)是其星载传感器的一种,自发射升空后,一直顺利运转着。SAR系全天候型传感器,由于它收集的信息不同于历来的光学传感器,所以近些年来,它是深受重视的一种仪器。SAR所观测的物理量为地表后向散射雷达的截面积,这种物理量借助地表与SAR的辐射关系便可转换成后向散射系数。为了有效利用SAR,对该物理量赋予绝对值较为重要,因此,数据的辐射校准是必要而不可缺的。     

控制棒钴吸收体的活度分布

应用单组中子微扰理论,对辐照后控制棒钴吸收体内活度分布进行理论分析,得到活度分布计算的解析表达式。对高通量工程试验堆(HFETR)首次出堆的2根控制棒钴吸收体进行数值计算。利用钴靶活度水下测量装置进行这2根钴吸收体活度分布的实验测量。计算与实验测量结果相符。通过理论计算所得到的活度分布可作为辐照后~(60)Co同位素分装依据。本文得到的控制棒相对价值曲线理论计算值与实验测量结果符合良好。     

岩石样品中铷的中子活化分析

研究了苦味酸溶液的ｐＨ变化对用１８－Ｃ－６（１８Ｃ６）的硝基苯溶液定量萃取Ｒｂ的影响及１８Ｃ６浓度变化对定量萃取Ｒｂ的影响，确定了定量反萃Ｒｂ的实验条件。作出了磷酸锆无机离子交换柱上的Ｒｂ－Ｃｓ分离曲线。测定了岩石样品的微量Ｒｂ和痕量＾８４Ｒｂ。     

Stability analysis and antiwindup design of uncertain discrete-time switched linear systems subject to actuator saturation

This paper investigates the stability analysis and antiwindup design problem for a class of discrete-time switched linear systems with time-varying norm-bounded uncertainties and saturating actuators by using the switched Lyapunov function approach.Supposing that a set of linear dynamic output controllers have been designed to stabilize the switched system without considering its input saturation,we design antiwindup compensation gains in order to enlarge the domain of attraction of the closed-loop system in the presence of saturation.Then,in terms of a sector condition,the antiwindup compensation gains which aim to maximize the estimation of domain of attraction of the closed-loop system are presented by solving a convex optimization problem with linear matrix inequality(LMI)constraints.A numerical example is given to demonstrate the effectiveness of the proposed design method.     

编译原理实验课程教学设计的改进

目前,编译原理实验课程中存在的一些问题影响了教学效果。主要原因是:学生的认识存在误区,实验内容和要求层次性不够明显,实验的组织形式比较单一。提出了改进方法:设计应用型实验提高学生的学习兴趣;重新设计实验内容和实验难度,更好地符合学生的认知规律;通过协同学习,提高学生的团队协作能力。     

混沌信号的主要测量特性分析

初步分析了混沌信号(以Logistic为例)应用于测量中的主要特性。仿真分析了Logistic信号的频谱特性、相关特性、模糊函数。说明了混沌信号在具有较高的距离速度分辨力,同时具备强抗干扰性。对比分析了混沌码和伪随机码的多普勒容限能力。初步分析Logistic信号的抗干扰特性。