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

《International Journal of Applied Earth Observation and Geoinformation》2020

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.  相似文献   

Developing constitutive models from EPR‐based self‐learning finite element analysis          下载免费PDF全文

Ali Nassr  Akbar Javadi  Asaad Faramarzi 《国际地质力学数值与分析法杂志》2018,42(3):401-417

A constitutive model that captures the material behavior under a wide range of loading conditions is essential for simulating complex boundary value problems. In recent years, some attempts have been made to develop constitutive models for finite element analysis using self‐learning simulation (SelfSim). Self‐learning simulation is an inverse analysis technique that extracts material behavior from some boundary measurements (eg, load and displacement). In the heart of the self‐learning framework is a neural network which is used to train and develop a constitutive model that represents the material behavior. It is generally known that neural networks suffer from a number of drawbacks. This paper utilizes evolutionary polynomial regression (EPR) in the framework of SelfSim within an automation process which is coded in Matlab environment. EPR is a hybrid data mining technique that uses a combination of a genetic algorithm and the least square method to search for mathematical equations to represent the behavior of a system. Two strategies of material modeling have been considered in the SelfSim‐based finite element analysis. These include a total stress‐strain strategy applied to analysis of a truss structure using synthetic measurement data and an incremental stress‐strain strategy applied to simulation of triaxial tests using experimental data. The results show that effective and accurate constitutive models can be developed from the proposed EPR‐based self‐learning finite element method. The EPR‐based self‐learning FEM can provide accurate predictions to engineering problems. The main advantages of using EPR over neural network are highlighted.  相似文献   

GDJ人卫目视观测数据采集和处理系统的研制     

何妙婵 《天文研究与技术》1996,(1)

本文介绍了ＧＤＪ跟踪打印经纬仪在人造卫星的观测中如何应用计算机对多圈卫星的目视观测资料进行实时采集、处理等工作过程的原理和方法。  相似文献   

Polar shapelets     

Richard Massey  Alexandre Refregier 《Monthly notices of the Royal Astronomical Society》2005,363(1):197-210

  相似文献   

Simulations of multimode bolometric interferometers     

George Saklatvala  Michael P. Hobson  Stafford Withington 《Monthly notices of the Royal Astronomical Society》2006,367(3):1194-1200

We describe a procedure for the numerical modelling of astronomical interferometers, with particular relevance to far-infrared and submillimetre wavelengths. The scheme is based on identifying a set of modes that carry power from the sky to the detector. The procedure is extremely general, and can be used to model scalar or vector fields, in any state of coherence and polarization, the only limitation being that the propagation of a coherent field through the system be described by an integral transform, a constraint that is in practise always met.
We present simulations of ideal, multimode two-dimensional interferometers, and show that the modal theory reproduces the correct behaviour of both Michelson and Fizeau interferometers. We calculate simulated visibility data for a multimode bolometric Michelson interferometer, with a synthesized source, and produce a dirty map, recovering the original source with the usual artefacts associated with interferometers.  相似文献   

OSIRIS: AO-assisted integral-field spectroscopy at the Keck Observatory     

A. Quirrenbach  J. Larkin  M. Barczys  T. Gasaway  C. Iserlohe  A. Krabbe  M. McElwain  I. Song  J. Weiss  S. Wright 《New Astronomy Reviews》2006,49(10-12):639

OSIRIS (OH-Suppressing Infra-Red Integral-field Spectrograph) is a new facility instrument for the Keck Observatory. After seeing first light in February 2005, OSIRIS is currently undergoing commissioning. OSIRIS provides the capability of performing three-dimensional spectroscopy in the near-infrared z, J, H, and K bands at the resolution limit of the Keck II telescope, which is equipped with adaptive optics and a laser guide star. The science case for OSIRIS is summarized, and the instrument and associated data reduction software are described.  相似文献   

Wavelet Analysis of Space Solar Telescope Images   总被引：1，自引：0，他引：1  

Xi-An Zhu  Sheng-Zhen Jin  Jing-Yu Wang  Shu-Nian NingNational Astronomical Observatories  Chinese Academy of Science  Beijing  Department of Mechanical  Electric Engineering  China College of Mining  Technology  Beijing 《中国天文和天体物理学报》2003,3(6):587-596

The scientific satellite SST (Space Solar Telescope) is an important research project strongly supported by the Chinese Academy of Sciences. Every day, SST acquires 50 GB of data (after processing) but only 10GB can be transmitted to the ground because of limited time of satellite passage and limited channel volume. Therefore, the data must be compressed before transmission. Wavelets analysis is a new technique developed over the last 10 years, with great potential of application. We start with a brief introduction to the essential principles of wavelet analysis, and then describe the main idea of embedded zerotree wavelet coding, used for compressing the SST images. The results show that this coding is adequate for the job.  相似文献   

Correcting systematic effects in a large set of photometric light curves     

O. Tamuz  T. Mazeh  S. Zucker † 《Monthly notices of the Royal Astronomical Society》2005,356(4):1466-1470

We suggest a new algorithm to remove systematic effects in a large set of light curves obtained by a photometric survey. The algorithm can remove systematic effects, such as those associated with atmospheric extinction, detector efficiency, or point spread function changes over the detector. The algorithm works without any prior knowledge of the effects, as long as they linearly appear in many stars of the sample. The approach, which was originally developed to remove atmospheric extinction effects, is based on a lower rank approximation of matrices, an approach which has already been suggested and used in chemometrics, for example. The proposed algorithm is especially useful in cases where the uncertainties of the measurements are unequal. For equal uncertainties, the algorithm reduces to the Principal Component Analysis (PCA) algorithm. We present a simulation to demonstrate the effectiveness of the proposed algorithm and we point out its potential, in the search for transit candidates in particular.  相似文献   

An efficient technique for pre-selecting low-redshift damped Lyα systems     

Sara L. Ellison 《Monthly notices of the Royal Astronomical Society》2006,368(1):335-340

The number of z ∼ 1 damped Lyα systems (DLAs, log  N (H  i ) ≥ 20.3) per unit redshift is approximately 0.1, making them relatively rare objects. Large, blind QSO surveys for low-redshift DLAs are therefore an expensive prospect for space-borne ultraviolet telescopes. Increasing the efficiency of these surveys by pre-selecting DLA candidates based on the equivalent widths (EWs) of metal absorption lines has previously been a successful strategy. However, the success rate of DLA identification is still only ∼35 per cent when simple EW cut-offs are applied, the majority of systems having 19.0 < log  N (H  i ) < 20.3. Here, we propose a new way to pre-select DLA candidates. Our technique requires high-to-moderate-resolution spectroscopy of the Mg  ii λ2796 transition, which is easily accessible from the ground for 0.2 ≲ z ≲ 2.4. We define the D -index, the ratio of the line equivalent width to velocity spread, and measure this quantity for 19 DLAs and eight sub-DLAs in archival spectra obtained with echelle spectrographs. For the majority of absorbers, there is a clear distinction between the D -index of DLAs compared with sub-DLAs (Kolmogorov–Smirnov probability = 0.8 per cent). Based on this pilot data sample, we find that the D -index can select DLAs with a success rate of up to 90 per cent, an increase in selection efficiency by a factor of 2.5 compared with a simple EW cut. We test the applicability of the D -index at lower resolution and find that it remains a good discriminant of DLAs for full width at half-maximum (FWHM) ≲ 1.5 Å. However, the recommended D -index cut-off between DLAs and sub-DLAs decreases with poorer resolution and we tabulate the appropriate D -index values that should be used with spectra of different resolutions.  相似文献   

The Faint Sky Variability Survey – I. Goals and data reduction process     

P. J. Groot  P. M. Vreeswijk  M. E. Huber  M. E. Everett  S. B. Howell  G. Nelemans  J. van Paradijs  E. P. J. van den Heuvel  T. Augusteijn  E. Kuulkers  R. G. M. Rutten  J. Storm 《Monthly notices of the Royal Astronomical Society》2003,339(2):427-434

  相似文献