scholarly journals Estimation accuracy under covariate-adaptive randomization procedures

2017 ◽  
Vol 11 (1) ◽  
pp. 1180-1206 ◽  
Author(s):  
Alessandro Baldi Antognini ◽  
Maroussa Zagoraiou
Keyword(s):  
Estimation Accuracy ◽  
Adaptive Randomization

Experimental research of indoor navigation system based on broadcast signals

2020 ◽  
Vol 49 (5) ◽  
pp. 49-57
Author(s):  
A. V. Ksendzuk ◽  
E. A. Surmin ◽  
V. V. Kachesov ◽  
S. O. Zhdanov ◽  
K. S. Shakhalov
Keyword(s):  
Navigation System ◽  
Open Space ◽  
Position Estimation ◽  
Indoor Navigation ◽  
Estimation Accuracy ◽  
Satellite Systems ◽  
Indoor Navigation System ◽  
Point To Point ◽  
Navigation Signals ◽  
Navigation Equipment

Results of an experimental study of a local navigation system based on the processing signals from broadcast sources presented. The results of the development of processing algorithms for point-to-point coordinates estimation of the object are presented. The results of the development of algorithms for trajectories estimation are presented. In performed simulation the possibility of obtaining submeter position estimation accuracy in the proposed system is shown. Development results of the navigation module demonstrator are presented. The results of experimental work in difficult navigation conditions, in the presence of shading, reflections and other factors, are presented. It is shown that the developed navigation module allows in the open space near buildings which partially obscuring the satellite systems signals to obtain accuracy higher than the GNSS navigation equipment. In indoor environment in the absence of satellite navigation signals, the developed module shows positioning accuracy not worse than 1.5 meters and provides a measurement rate 1 Hz and better.

scholarly journals Multilayer Soil Moisture Mapping at a Regional Scale from Multisource Data via a Machine Learning Method

2019 ◽  
Vol 11 (3) ◽  
pp. 284 ◽  
Author(s):  
Linglin Zeng ◽  
Shun Hu ◽  
Daxiang Xiang ◽  
Xiang Zhang ◽  
Deren Li ◽  
...  
Keyword(s):  
Machine Learning ◽  
Soil Moisture ◽  
Regional Scale ◽  
Remotely Sensed ◽  
Temporal Variations ◽  
Training Data ◽  
Estimation Accuracy ◽  
Learning Approaches ◽  
Remotely Sensed Data ◽  
Deep Soil

Soil moisture mapping at a regional scale is commonplace since these data are required in many applications, such as hydrological and agricultural analyses. The use of remotely sensed data for the estimation of deep soil moisture at a regional scale has received far less emphasis. The objective of this study was to map the 500-m, 8-day average and daily soil moisture at different soil depths in Oklahoma from remotely sensed and ground-measured data using the random forest (RF) method, which is one of the machine-learning approaches. In order to investigate the estimation accuracy of the RF method at both a spatial and a temporal scale, two independent soil moisture estimation experiments were conducted using data from 2010 to 2014: a year-to-year experiment (with a root mean square error (RMSE) ranging from 0.038 to 0.050 m3/m3) and a station-to-station experiment (with an RMSE ranging from 0.044 to 0.057 m3/m3). Then, the data requirements, importance factors, and spatial and temporal variations in estimation accuracy were discussed based on the results using the training data selected by iterated random sampling. The highly accurate estimations of both the surface and the deep soil moisture for the study area reveal the potential of RF methods when mapping soil moisture at a regional scale, especially when considering the high heterogeneity of land-cover types and topography in the study area.

scholarly journals DEVELOPMENT OF THE MONTHLY AVERAGE DAILY SOLAR RADIATION MAP USING A-CBR, FEM, AND KRIGING METHOD

2017 ◽  
Vol 24 (2) ◽  
pp. 489-512 ◽  
Author(s):  
Choongwan KOO ◽  
Taehoon HONG ◽  
Kwangbok JEONG ◽  
Jimin KIM
Keyword(s):  
Solar Radiation ◽  
Decision Makers ◽  
Estimation Accuracy ◽  
Case Based Reasoning ◽  
Final Decision ◽  
Kriging Method ◽  
Pv System ◽  
Fem Model ◽  
Remote Sensors ◽  
Monthly Average

Photovoltaic (PV) system could be implemented to mitigate global warming and lack of energy. To maximize its effectiveness, the monthly average daily solar radiation (MADSR) should be accurately estimated, and then an accurate MADSR map could be developed for final decision-makers. However, there is a limitation in improving the accuracy of the MADSR map due to the lack of weather stations. This is because it is too expensive to measure the actual MADSR data using the remote sensors in all the sites where the PV system would be installed. Thus, this study aimed to develop the MADSR map with improved estimation accuracy using the advanced case-based reasoning (A-CBR), finite element method (FEM), and kriging method. This study was conducted in four steps: (i) data collection; (ii) estimation of the MADSR data in the 54 unmeasured locations using the A-CBR model; (iii) estimation of the MADSR data in the 89 unmeasured locations using the FEM model; and (iv) development of the MADSR map using the kriging method. Compared to the previous MADSR map, the proposed MADSR map was determined to be improved in terms of its estimation accuracy and classification level.

scholarly journals A Preprocess Method of External Disturbance Suppression for Carotid Wall Motion Estimation Using Local Phase and Orientation of B-Mode Ultrasound Sequences

2019 ◽  
Vol 2019 ◽  
pp. 1-15
Author(s):  
Qinghui Zhang ◽  
Junqiu Li ◽  
Zhenping Qiang ◽  
Libo He
Keyword(s):  
Motion Estimation ◽  
Wall Motion ◽  
Structural Information ◽  
External Disturbance ◽  
Estimation Accuracy ◽  
Ultrasound Images ◽  
Local Phase ◽  
Registration Method ◽  
Anisotropic Diffusion Filter ◽  
Disturbance Suppression

Estimating the motions of the common carotid artery wall plays a very important role in early diagnosis of the carotid atherosclerotic disease. However, the disturbances caused by either the instability of the probe operator or the breathing of subjects degrade the estimation accuracy of arterial wall motion when performing speckle tracking on the B-mode ultrasound images. In this paper, we propose a global registration method to suppress external disturbances before motion estimation. The local vector images, transformed from B-mode images, were used for registration. To take advantage of both the structural information from the local phase and the geometric information from the local orientation, we proposed a confidence coefficient to combine them two. Furthermore, we altered the speckle reducing anisotropic diffusion filter to improve the performance of disturbance suppression. We compared this method with schemes of extracting wall displacement directly from B-mode or phase images. The results show that this scheme can effectively suppress the disturbances and significantly improve the estimation accuracy.

A Strong Tracking Cubature Kalman Filter for Nonlinear Estimation

2013 ◽  
Vol 313-314 ◽  
pp. 1115-1119
Author(s):  
Yong Qi Wang ◽  
Feng Yang ◽  
Yan Liang ◽  
Quan Pan
Keyword(s):  
Kalman Filter ◽  
State Estimation ◽  
Scaling Factor ◽  
Estimation Accuracy ◽  
Nonlinear State Estimation ◽  
Cubature Kalman Filter ◽  
Novel Method ◽  
Simulation Results ◽  
Tracking Filter ◽  
Nonlinear State

In this paper, a novel method based on cubature Kalman filter (CKF) and strong tracking filter (STF) has been proposed for nonlinear state estimation problem. The proposed method is named as strong tracking cubature Kalman filter (STCKF). In the STCKF, a scaling factor derived from STF is added and it can be tuned online to adjust the filtering gain accordingly. Simulation results indicate STCKF outperforms over EKF and CKF in state estimation accuracy.

scholarly journals Fast Target Localization Method for FMCW MIMO Radar via VDSR Neural Network

2021 ◽  
Vol 13 (10) ◽  
pp. 1956
Author(s):  
Jingyu Cong ◽  
Xianpeng Wang ◽  
Xiang Lan ◽  
Mengxing Huang ◽  
Liangtian Wan
Keyword(s):  
Neural Network ◽  
Continuous Wave ◽  
Super Resolution ◽  
Mimo Radar ◽  
Target Localization ◽  
Estimation Accuracy ◽  
Low Resolution ◽  
Range Estimation ◽  
Resolution Image ◽  
Resolution Imaging

The traditional frequency-modulated continuous wave (FMCW) multiple-input multiple-output (MIMO) radar two-dimensional (2D) super-resolution (SR) estimation algorithm for target localization has high computational complexity, which runs counter to the increasing demand for real-time radar imaging. In this paper, a fast joint direction-of-arrival (DOA) and range estimation framework for target localization is proposed; it utilizes a very deep super-resolution (VDSR) neural network (NN) framework to accelerate the imaging process while ensuring estimation accuracy. Firstly, we propose a fast low-resolution imaging algorithm based on the Nystrom method. The approximate signal subspace matrix is obtained from partial data, and low-resolution imaging is performed on a low-density grid. Then, the bicubic interpolation algorithm is used to expand the low-resolution image to the desired dimensions. Next, the deep SR network is used to obtain the high-resolution image, and the final joint DOA and range estimation is achieved based on the reconstructed image. Simulations and experiments were carried out to validate the computational efficiency and effectiveness of the proposed framework.

Sign in / Sign up

Export Citation Format

Share Document