基于模式搜索的连续函数寻优

模式搜索方法是求解最优化问题的一种直接搜索方法,它只根据函数值信息来进行求优。但模式搜索对起始点非常敏感,对好的起始点,模式搜索可以搜索到全局最优点,但对某些起始点,模式搜索只能搜索到局部极值点。本文提出基于模式搜索的一个新方法,实验证明,它能搜索到全局最优。     

Who is LB1? Discriminant analysis for the classification of specimens

Many problems in paleontology reduce to finding those features that best discriminate among a set of classes. A clear example is the classification of new specimens. However, these classifications are generally challenging because the number of discriminant features and the number of samples are limited. This has been the fate of LB1, a new specimen found in the Liang Bua Cave of Flores. Several authors have attributed LB1 to a new species of Homo, H. floresiensis. According to this hypothesis, LB1 is either a member of the early Homo group or a descendent of an ancestor of the Asian H. erectus. Detractors have put forward an alternate hypothesis, which stipulates that LB1 is in fact a microcephalic modern human. In this paper, we show how we can employ a new Bayes optimal discriminant feature extraction technique to help resolve this type of issues. In this process, we present three types of experiments. First, we use this Bayes optimal discriminant technique to develop a model of morphological (shape) evolution from Australopiths to H. sapiens. LB1 fits perfectly in this model as a member of the early Homo group. Second, we build a classifier based on the available cranial and mandibular data appropriately normalized for size and volume. Again, LB1 is most similar to early Homo. Third, we build a brain endocast classifier to show that LB1 is not within the normal range of variation in H. sapiens. These results combined support the hypothesis of a very early shared ancestor for LB1 and H. erectus, and illustrate how discriminant analysis approaches can be successfully used to help classify newly discovered specimens.     

QuickBird and Hyperion data analysis of an invasive plant species in the Galapagos Islands of Ecuador: Implications for control and land use management

In the Galapagos Islands of Ecuador, one of the greatest threats to the terrestrial ecosystem is the increasing number and areal extent of invasive species. Increased human presence on the islands has hastened the introduction of plant and animal species that threaten the native and endemic flora and fauna. Considerable research on invasive species in the Galapagos Islands has been conducted by the Charles Darwin Foundation. We complement that work through a spatially- and spectrally-explicit satellite assessment of an important invasive plant species (Psidium guajava — guava) on Isabela Island that integrates diverse remote sensing systems, data types, spatial and spectral resolutions, and analytical and image processing approaches. QuickBird and Hyperion satellite data are processed to characterize the areal extent and spatial structure of guava through the following approaches: (1) QuickBird data are classified through a traditional pixel-based approach (i.e., an unsupervised classification approach using the ISODATA algorithm), as well as an Object-Based Image Analysis (OBIA) approach; (2) multiple approaches for spectral “unmixing” of the Hyperion hyper-spectral data are assessed to construct spectral end-members from QuickBird data using linear and non-linear mixture modeling approaches; and (3) landscape pattern metrics are calculated and compared for the pixel-based, object-based, and spectral unmixing approaches. The spectral–spatial characteristics of guava are interpreted relative to management strategies for the control of guava and the restoration of natural ecosystems in the Galapagos National Park.     

Motif patterns in 2D

Motif patterns consisting of sequences of intermixed solid and don’t-care characters have been introduced and studied in connection with pattern discovery problems of computational biology and other domains. In order to alleviate the exponential growth of such motifs, notions of maximal saturation and irredundancy have been formulated, whereby more or less compact subsets of the set of all motifs can be extracted, that are capable of expressing all others by suitable combinations. In this paper, we introduce the notion of maximal irredundant motifs in a two-dimensional array and develop initial properties and a combinatorial argument that poses a linear bound on the total number of such motifs. The remainder of the paper presents approaches to the discovery of irredundant motifs both by offline and incremental algorithms.     

医学肝脏图像Gabor小波纹理特征研究

针对肝脏图像自身特点,研究了Gabor小波纹理特征在医学肝脏图像识别中的意义,提出一种基于Gabor小波纹理特征的医学肝脏图像识别方法.实验表明:引进Gabor小波纹理特征能较好地实现医学肝脏图像识别问题;与其它典型图像识别方法对比结果验证,新方法可以取得更高的识别率.     

CAN总线在汽车轮胎监测系统中的应用设计

针对当前独立的汽车轮胎监测系统存在的弊端提出一种新的实现方案,动态监测汽车各轮胎的参数,并把动态参数通过CAN总线传输到汽车驾驶室仪表上,实现汽车轮胎故障预警功能.该方案增加了系统的可靠性、灵活性,扩展了汽车轮胎压力监测系统的使用场合,在大型车辆的安全系统中有很高的实用价值.     

基于PSO的Fisher准则下小样本最佳鉴别变换

小样本条件下,Fisher准则中类内散布矩阵一般是奇异的,无法直接求解.本文提出利用粒子群优化理论,在无需求类内散布矩阵逆的情况下求解Fisher准则下小样本最佳鉴别变换的方法.讨论了通过粒子群优化算法的位置-速度搜索模型获取最佳鉴别投影向量的方法和步骤.实验对比类内散布矩阵非奇异时,采用计算特征向量方法和本文方法的差异.分析验证小样本条件下类内散布矩阵奇异时,通过本文方法进行最佳鉴别变换的分类效果.实验证实本文算法的有效性.     

基于k-最近邻的支持向量预选取方法

在所有的训练样本中只有支持向量(SVs)能对支持向量机分界面优化结果产生显著影响.基于七一最近邻规则.提出了一种训练样本的预选取方法.针对一些典型人工数据集、公用基准数据集以及TM遥感数据的实验结果表明.该方法能够有效减少训练样本数目.显著加快学习速度,并保证理想的分类精度.     

一种过程支持向量机及其在动态模式分类中的应用

针对一般SVM在机制上难以直接对动态模式进行分类的问题,提出了一种基于函数正交基展开的过程支持向量机.该模型的输入为时变函数,输出为模式类别.在输入函数空间中选择一组适当的正交函数基,将输入函数在该组函数基下进行有限项展开,把展开式系数作为核函数的输入.由于时变函数在基函数映射下与展开式系数一一对应,从而可利用SVM的变换机制实现动态模式分类.给出了基于SMO的求解算法,实验结果验证了模型和算法的有效性.     

黄金分割法结合UTD计算机载天线方向图

机载天线辐射特性的研究,对机载天线的一体化设计、布局以及机载电子系统的电磁兼容性(EMC)具有非常重要的意义.应用一致性几何绕射理论(UTD)分析机载天线的辐射特性,利用黄金分割法(0.618法)优化二阶射线寻迹,并考虑了遮挡的判断问题,提高了运算的速度和精度.以机载单极子天线为例.给出了机载天线远场方向图的仿真结果.结果比较令人满意,证明了方法是正确的,并对机载天线耦合分析有一定参考意义.