An evaluation of Guided Regularized Random Forest for classification and regression tasks in remote sensing

New Earth observation missions and technologies are delivering large amounts of data. Processing this data requires developing and evaluating novel dimensionality reduction approaches to identify the most informative features for classification and regression tasks. Here we present an exhaustive evaluation of Guided Regularized Random Forest (GRRF), a feature selection method based on Random Forest. GRRF does not require fixing a priori the number of features to be selected or setting a threshold of the feature importance. Moreover, the use of regularization ensures that features selected by GRRF are non-redundant and representative. Our experiments based on various kinds of remote sensing images, show that GRRF selected features provides similar results to those obtained when using all the available features. However, the comparison between GRRF and standard random forest features shows substantial differences: in classification, the mean overall accuracy increases by almost 6% and, in regression, the decrease in RMSE almost reaches 2%. These results demonstrate the potential of GRRF for remote sensing image classification and regression. Especially in the context of increasingly large geodatabases that challenge the application of traditional methods.     

Isotope hydrological study of mean transit time in the granitic Strengbach catchment (Vosges massif,France): application of the FlowPC model with modified input function

Measurements of ¹⁸O concentrations in precipitation, soil solution, spring and runoff are used to determine water transit time in the small granitic Strengbach catchment (0·8 km²; 883–1146 m above sea level) located in the Vosges Mountains of northeastern France. Water transit times were calculated by applying the exponential, exponential piston and dispersion models of the FlowPC program to isotopic input (rainfall) and output (spring and stream water) data sets during the period 1989–95. The input function of the model was modified compared with the former version of the model and estimated by a deterministic approach based on a simplified hydrological balance. The fit between observed and calculated output data showed marked improvements compared with results obtained using the initial version of the model. An exponential piston version of the model applied to spring water indicates a 38·5 month mean transit time, which suggests that the volume in the aquifer, expressed in water depth, is 2·4 m. A considerable thickness (>45 m) of fractured bedrock may be involved for such a volume of water to be stored in the aquifer. Copyright © 2005 John Wiley & Sons, Ltd.     

重庆地面最高气温与最大风速年极值的渐近分布

利用重庆1951-1990年间地面最高气温和1956-1990年间地面最大风速年极值的记录,采用韦伯分布和耿贝尔分布分别对其渐近分布进行拟合.通过统计推断,找出重庆地面最高气温和地面最大风速年极值遵循的最佳渐近分布--韦伯分布.     

AR（P）参数估计协方差方法与其改进型方法的对比研究

定性分析协方差方法及其改进型在ＡＲ（Ｐ）参数估计中的应用，提供了一种估计参数的计算机上机流程图，比较了协方差方法及其改进型谱估计结果。     

利用Lageos 1 SLR资料解算1990-2001年的地球定向参数

利用 12年的Lageos 1卫星激光测距资料 (1990 - 2 0 0 1)解算得到了地球定向参数 (EOP) ,将该序列的结果与同期的EOP(IERS)C0 4进行比较 ,其外符精度为 :极移XP— 0 .4 0mas,YP— 0 .4 2mas ,日长变化Dr— 0 .0 35ms。     

WR 7a: a V Sagittae or a qWR star?

The star WR 7a, also known as SPH 2, has a spectrum that resembles that of V Sagittae stars although no O  vi emission has been reported. The Temporal Variance Spectrum – TVS – analysis of our data shows weak but strongly variable emission of O  vi lines which is below the noise level in the intensity spectrum.
Contrary to what is seen in V Sagittae stars, optical photometric monitoring shows very little, if any, flickering. We found evidence of periodic variability. The most likely photometric period is   P _phot= 0.227(±14) d  , while radial velocities suggest a period of   P _spec= 0.204(±13) d  . One-day aliases of these periods can not be ruled out. We call attention to similarities with HD 45166 and DI Cru (= WR 46), where multiple periods are present. They may be associated to the binary motion or to non-radial oscillations.
In contrast to a previous conclusion by Pereira et al., we show that WR 7a contains hydrogen. The spectrum of the primary star seems to be detectable as the N  v 4604 Å  absorption line is visible. If so, it means that the wind is optically thin in the continuum and that it is likely to be a helium main sequence star.
Given the similarity to HD 45166, we suggests that WR 7a may be a qWR – quasi Wolf–Rayet – star. Its classification is WN4h/CE in the Smith, Shara & Moffat three-dimensional classification system.     

Influence of Ultrasonic Treatment on the Allergenic Properties of Shrimp （Penaeus vannamei ） Allergen

The present study was undertaken to determine whether high intensity ultrasound could reduce the allergic properties of shrimp allergens. Reducing the allergenic properties of these allergens will be beneficial to allergic individuals. Samples of shrimp protein extract and shrimp muscle were treated by high-intensity ultrasound with water bathing at 0 ℃ or 50 ℃ for different time periods. The treated and untreated samples were then analyzed by SDS-PAGE, Western blots and competitive inhibition ELISA （Ci-ELISA） to determine the shrimp allergenicity. The results show that high-intensity ultrasound has no effect on allergenicity when the extracts were treated at 0℃. However, a significant decrease was observed in the level of the major shrimp allergen, Pen a 1, when the samples were treated at 50 ℃. In the determination of allergenicity with CiELISA, a reduction in IgE binding was also observed.     

International program of observations of selected minor planets: first results

International programs of observations of selected minor planets have lasted about 50 years and the last one comes to the end in 2000. The main aim of these observational programs consists in obtaining the orientation of the stellar reference frame with respect to the dynamical one using observations of the bright minor planets. The observations are also useful for the orbital improvements of the asteroids themselves. They are available from the author via e-mail at the address .During the above mentioned period more than 23 000 observations of minor planets, referred to different reference star catalogues, have been obtained. The reduction procedure of observations to the PPM star catalogue is described. The orientation parameters are given and discussed.     

抗差估计的初值选择

对L1 范估计的平差值和LS估计的平差值作为抗差估计的初值进行了比较 ,指出在 ρ函数是严凸函数时 ,二者无明显的区别。因为LS估计简单且易于计算 ,因此建议用LS估计的平差值作为抗差估计的初值。     

STUDY ON GIS FOR YIELD ESTIMATION BY REMOTE SENSING IN JILIN MAIZE BELT

ＳＴＵＤＹ　ＯＮ　ＧＩＳ　ＦＯＲ　ＹＩＥＬＤ　ＥＳＴＩＭＡＴＩＯＮ　ＢＹ　ＲＥＭＯＴＥ　ＳＥＮＳＩＮＧ　ＩＮ　ＪＩＬＩＮ　ＭＡＩＺＥ　ＢＥＬＴＳＴＵＤＹＯＮＧＩＳＦＯＲＹＩＥＬＤＥＳＴＩＭＡＴＩＯＮＢＹＲＥＭＯＴＥＳＥＮＳＩＮＧＩＮＪＩＬＩＮＭＡＩＺ...