• Journal of Korea Water Resources Association
• /
• v.56 no.3
• /
• pp.211-224
• /
• 2023

In this study, a soil moisture estimation was performed using the Water Cloud Model (WCM), a backscatter model that considers vegetation based on SAR (Synthetic Aperture Radar). Sentinel-1 SAR and Sentinel-2 MSI (Multi-Spectral Instrument) images of a 40 × 50 km² area including the Yongdam Dam watershed of the Geum River were collected for this study. As vegetation descriptor of WCM, Sentinel-1 based vegetation index RVI (Radar Vegetation Index), depolarization ratio (DR), and Sentinel-2 based NDVI (Normalized Difference Vegetation Index) were used, respectively. Forward modeling of WCM was performed by 3 groups, which were divided by the characteristics between backscattering coefficient and soil moisture. The clearer the linear relationship between soil moisture and the backscattering coefficient, the higher the simulation performance. To estimate the soil moisture, the simulated backscattering coefficient was inverted. The simulation performance was proportional to the forward modeling result. The WCM simulation error showed an increasing pattern from about -12dB based on the observed backscattering coefficient.

• Korean Journal of Remote Sensing
• /
• v.36 no.4
• /
• pp.515-525
• /
• 2020

This study investigates the potential of bidirectional long short-term memory (Bi-LSTM) for efficient modeling of temporal information in crop classification using multitemporal remote sensing images. Unlike unidirectional LSTM models that consider only either forward or backward states, Bi-LSTM could account for temporal dependency of time-series images in both forward and backward directions. This property of Bi-LSTM can be effectively applied to crop classification when it is difficult to obtain full time-series images covering the entire growth cycle of crops. The classification performance of the Bi-LSTM is compared with that of two unidirectional LSTM architectures (forward and backward) with respect to different input image combinations via a case study of crop classification in Anbadegi, Korea. When full time-series images were used as inputs for classification, the Bi-LSTM outperformed the other unidirectional LSTM architectures; however, the difference in classification accuracy from unidirectional LSTM was not substantial. On the contrary, when using multitemporal images that did not include useful information for the discrimination of crops, the Bi-LSTM could compensate for the information deficiency by including temporal information from both forward and backward states, thereby achieving the best classification accuracy, compared with the unidirectional LSTM. These case study results indicate the efficiency of the Bi-LSTM for crop classification, particularly when limited input images are available.

• Geophysics and Geophysical Exploration
• /
• v.10 no.2
• /
• pp.111-123
• /
• 2007

Unlike the conventional reverse time migration method which is implemented by simply extrapolating wavefield in reverse time, this paper presents a derivation of another reverse time migration operator as the exact adjoint of the presumed forward wavefield extrapolation operator. The adjoint operator is obtained by formulating the forward time extrapolation operator in an explicit matrix equation form and then taking the adjoint to this matrix equation followed by determining the corresponding operator. The reverse time migration operator as the exact adjoint to the implied forward operator can be used not only as a migration algorithm but also as an adjoint operator which is required in the imaging through an inversion such as least-squares migration.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.772-779
• /
• 2006

The new model proposed in this paper is the hidden Markov mesh model or the 2D HMM with the causality of top-down and left-right direction. With the addition of the causality constraint, two algorithms for the evaluation of a model and the maximum likelihood estimation of model parameters have been developed theoretically which are based on the forward-backward algorithm. It is a more natural extension of the 1D HMM than other 2D models. The proposed method will provide a useful way of modeling highly variable image patterns such as offline cursive characters.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.724-727
• /
• 1997

In this paper, we developed a Windows 95 version Off-Line Programming System which can simulate a Robot model in 3D Graphic space. 4 axes SCARA Robot (especially FARA SM5)was adopted as an objective model. Forward kinematics, inverse kinematics and robot dynamics modeling were included in the developed program. The interface between users and the OLP system in the Windows 95's GUI environment was also studied. The developing language is Microsoft Visual C++. Graphic libraries, OpenGL, by Silicon Graphics, Inc. were utilized for 3D Graphics.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2013.05a
• /
• pp.1437-1438
• /
• 2013

• Proceedings of the KIEE Conference
• /
• 1991.07a
• /
• pp.805-808
• /
• 1991

In this paper, dynamical model and control architecture are developed for the closed chain motion of two N-joint manipulators holding a rigid object. Controller consist of forward controller which is reduced order model and compensator that compensates for modeling error. Control laws are determined so as to decouple the force and position controlled degree of freedom(DOF) during motion of the system.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1998.03a
• /
• pp.227-232
• /
• 1998

We developed a Off-Line Graphic Simulator which can simulate a robot model in 3D graphics space in Windows 95 version. 4 axes SCARA robot was adopted as an objective model. Forward kinematics, inverse kinematics and robot dynamics modeling were included in the developed program. The interface between users and the off-line program system in the Windows 95's graphic user interface environment was also studied. The developing language is Microsoft Visual C++. Graphic libraries, OpenGL, by Silicon Graphics, Inc. were utilized for 3D graphics.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10a
• /
• pp.218-223
• /
• 1992

This paper describes a learning method of neural network controllers. The learning method improves the performance of indirect learning mechanism in the neuro-control of nonlinear systems. To precisely identify dynamic characteristics of the plant by utilizing a limited prior information we propose a new energy function which takes advantage of the proportional relationship between outputs of the plant and those of neural networks.

• The Bulletin of The Korean Astronomical Society
• /
• v.35 no.1
• /
• pp.81.1-81.1
• /
• 2010

We present a detailed description of the blast-wave modeling technique for a very general class of GRB explosions. Providing a simple method of evaluating the blast energy, we demonstrate that a common approximation of pressure balance for the blast wave violates the energy-conservation law significantly for adiabatic blast waves. We show that the energy-violation problem is successfully resolved by the "mechanical model" that we developed. GRB afterglow lightcurves that are produced by the forward and reverse shock waves of the blast wave are presented.