• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.429-431
• /
• 2003

The induced learning retardation method involves the temporary inhibition of the artificial neural network’s active units from participating in the error reduction process during training. This stimulates the less active units to contribute significantly to reduce the network error. However, some less active units are not sensitive to stimulation making them almost useless. The network can then be pruned by removing the less active units to make it smaller and more efficient. This study focuses on making the network more efficient and accurate by developing the induced learning retardation and pruning sequence training method. The developed procedure results to faster learning and more accurate artificial neural network for satellite image classification.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.120-120
• /
• 2020

Spatial precipitation data is one of the essential components in modeling hydrological problems. The estimation of these data has achieved significant achievements own to the recent advances in remote sensing technology. However, there are still gaps between the satellite-derived rainfall data and observed data due to the significant dependence of rainfall on spatial and temporal characteristics. An effective approach based on the Convolutional Neural Network (CNN) model to correct the satellite-derived rainfall data is proposed in this study. The Mekong River basin, one of the largest river system in the world, was selected as a case study. The two gridded precipitation data sets with a spatial resolution of 0.25 degrees used in the CNN model are APHRODITE (Asian Precipitation - Highly-Resolved Observational Data Integration Towards Evaluation) and PERSIANN-CDR (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks). In particular, PERSIANN-CDR data is exploited as satellite-based precipitation data and APHRODITE data is considered as observed rainfall data. In addition to developing a CNN model to correct the satellite-based rain data, another statistical method based on standard deviations for precipitation bias correction was also mentioned in this study. Estimated results indicate that the CNN model illustrates better performance both in spatial and temporal correlation when compared to the standard deviation method. The finding of this study indicated that the CNN model could produce reliable estimates for the gridded precipitation bias correction problem.

• Journal of the Korean Geographical Society
• /
• v.46 no.3
• /
• pp.319-330
• /
• 2011

In this study, a soil moisture estimation model was proposed using the ground observation data of soil moisture, precipitation, surface temperature, MODIS NDVI and artificial neural networks. The model was calibrated and verified on the Yongdam dam watershed which has reliable ground soil moisture networks. The test statistics of calibration sites, Jucheon, Bugui, Sangjeon, showed that the correlation coefficients between observations and estimations are about 0.9353 and RMSE is about 1.4957%. Also that of the verification site, Cheoncheon2, showed that the correlation coefficient is about 0.8215 and RMSE is about 4.2077%. The soil moisture estimation model was applied to estimate the spatial distribution of soil moisture in the Yongdam dam watershed and results showed improved spatial soil moisture distribution since the model used satellite information of NDVI and artificial neural networks which can represent the nonlinear relationships between data well. The model should be useful to estimate wide range soil moisture information.

• Korean Journal of Remote Sensing
• /
• v.35 no.3
• /
• pp.447-455
• /
• 2019

Since the forest type map in Korea has been mostly constructed every five years, the forest information from the map lacks up-to-date information. Forest research has been carried out by aerial photogrammetry and field surveys, and hence it took a lot of times and money. The vertical structure of forests is an important factor in evaluating forest diversity and environment. The vertical structure is essential information, but the observation of the vertical structure is not easy because the vertical structure indicates the internal structure of forests. In this study, the index map and texture map produced from KOMPSAT-3/3A/5 satellite images and the canopy information generated by the difference between DSM (Digital Surface Model) and DTM (Digital Terrain Model) were classified using the artificial neural network. The vertical structure of forests of single and multi-layer forests was classified to identify 81.59% of the final classification result.

• The Korean Journal of Air & Space Law and Policy
• /
• v.15
• /
• pp.146-181
• /
• 2002

• Journal of Astronomy and Space Sciences
• /
• v.5 no.1
• /
• pp.45-51
• /
• 1988

Most of all methods of determining the preliminary orbit of an artificial Earth satellite are reviewed. The preliminary orbits of the methorological satellite NOAA-10 are determined using the studied methods and are compared with mean orbital elements determined at NASA. Through the comparision the preliminary orbital elements determined with Gauss type methods are more approximate to those of NASA than those calculated with Laplacian type ones. Our results indicate that Taff(1984)'s criticism on the Gauss method must be abandoned and Marsden (1985)'s analysis on the method is correct.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.10a
• /
• pp.497-500
• /
• 2002

When one is interested in the dynamics of a mechanical system with electric motors, the force generated by the motor is generally considered as only an applied torque or force independent of mechanical state variables such as velocity. For a system operated in non-steady dynamic conditions, however, the usual analysis approach may fail to predict some characteristics in the dynamic behaviors because of electromechanical coupling effects. In this paper, we propose dynamics analysis model in which dc motor dynamics with the electromechanical coupling effects are embedded to mechanical dynamics models. The do motor is modeled based on its equivalent circuit model and included in the dynamics solving algorithm which we developed before, called generalized recursive dynamics formula. The developed dynamic analysis model is effective and realistic for analysis of electromechanical dynamics of a system with do motors. The developed model is evaluated by constructing and simulating the flexible antennas of an artificial satellite driven by do motors.

• Journal of Satellite, Information and Communications
• /
• v.12 no.2
• /
• pp.11-14
• /
• 2017

In this paper, we introduce a method of light focusing effect using prism structure to solve optical discontinuity of conventional external signage LED panels. The prims structures were patterned on a transparent polycarbonate substrate with MEMS and femto-second laser process. We have confirmed that the patterned prism structures on the substrate made artificial LED lights on empty space between the panels by light guide effect of the structure. The artificial light's lateral positions were controlled by thickness of polycarbonate substrate. This cost effective prim patterned transparent film can be utilized on digital signage LED panels to achieve good optical communication.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.294-297
• /
• 2004

The purpose of this study was to develop landslide susceptibility analysis techniques using artificial neural networks and then to apply these to the selected study area of Janghung in Korea. We aimed to verify the effect of data selection on training sites. Landslide locations were identified from interpretation of satellite images and field survey data, and a spatial database of the topography, soil, forest, and land use was constructed. Thirteen landslide-related factors were extracted from the spatial database. Using these factors, landslide susceptibility was analyzed using an artificial neural network. The weights of each factor were determined by the back-propagation training method. Five different training datasets were applied to analyze and verify the effect of training. Then, the landslide susceptibility indices were calculated using the trained back-propagation weights and susceptibility maps were constructed from Geographic Information System (GIS) data for the five cases. The results of the landslide susceptibility maps were verified and compared using landslide location data. GIS data were used to efficiently analyze the large volume of data, and the artificial neural network proved to be an effective tool to analyze landslide susceptibility.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2003.04a
• /
• pp.77-82
• /
• 2003

The purpose of this study is to develop landslide susceptibility analysis techniques using artificial neural network and to apply the developed techniques to the study area of janghung in Korea. Landslide locations were identified in the study area from interpretation of satellite image and field survey data, and a spatial database of the topography, soil, forest and land use were consturced. The 13 landslide-related factors were extracted from the spatial database. Using those factors, landslide susceptibility was analyzed by artificial neural network methods, and the susceptibility map was made with a e15 program. For this, the weights of each factor were determinated in 5 cases by the backpropagation method, which is a type of artificial neural network method. Then the landslide susceptibility indexes were calculated using the weights and the susceptibility maps were made with a GIS to the 5 cases. A GIS was used to efficiently analyze the vast amount of data, and an artificial neural network was turned out be an effective tool to analyze the landslide susceptibility.