• Korean Journal of Remote Sensing
• /
• v.37 no.5_3
• /
• pp.1405-1423
• /
• 2021

Precipitation is one of the main factors that affect water and energy cycles, and its estimation plays a very important role in securing water resources and timely responding to water disasters. Satellite-based quantitative precipitation estimation (QPE) has the advantage of covering large areas at high spatiotemporal resolution. In this study, machine learning-based rainfall intensity models were developed using Himawari-8 Advanced Himawari Imager (AHI) water vapor channel (6.7 ㎛), infrared channel (10.8 ㎛), and weather radar Column Max (CMAX) composite data based on random forest (RF). The target variables were weather radar reflectivity (dBZ) and rainfall intensity (mm/hr) converted by the Z-R relationship. The results showed that the model which learned CMAX reflectivity produced the Critical Success Index (CSI) of 0.34 and the Mean-Absolute-Error (MAE) of 4.82 mm/hr. When compared to the GeoKompsat-2 and Precipitation Estimation from Remotely Sensed Information Using Artificial Neural Networks (PERSIANN)-Cloud Classification System (CCS) rainfall intensity products, the accuracies improved by 21.73% and 10.81% for CSI, and 31.33% and 23.49% for MAE, respectively. The spatial distribution of the estimated rainfall intensity was much more similar to the radar data than the existing products.

• Geophysics and Geophysical Exploration
• /
• v.25 no.2
• /
• pp.59-70
• /
• 2022

Recent studies demonstrate that machine learning has expanded in the field of seismic interpretation. Many convolutional neural networks have been developed for seismic sequence identification, which is important for seismic interpretation. However, expense and time limitations indicate that there is insufficient data available to provide a sufficient dataset to train supervised machine learning programs to identify seismic sequences. In this study, patch division and data augmentation are applied to mitigate this lack of data. Furthermore, to obtain spatial information that could be lost during patch division, an artificial channel is added to the original data to indicate depth. Seismic sequence identification is performed using a U-Net network and the Netherlands F3 block dataset from the dGB Open Seismic Repository, which offers datasets for machine learning, and the predicted results are evaluated. The results show that patch-based U-Net seismic sequence identification is improved by data augmentation and the addition of an artificial channel.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3567-3582
• /
• 2020

Human activities are often affected by weather conditions. Automatic weather recognition is meaningful to traffic alerting, driving assistance, and intelligent traffic. With the boost of deep learning and AI, deep convolutional neural networks (CNN) are utilized to identify weather situations. In this paper, a three-channel convolutional neural network (3C-CNN) model is proposed on the basis of ResNet50.The model extracts global weather features from the whole image through the ResNet50 branch, and extracts the sky and ground features from the top and bottom regions by two CNN5 branches. Then the global features and the local features are merged by the Concat function. Finally, the weather image is classified by Softmax classifier and the identification result is output. In addition, a medium-scale dataset containing 6,185 outdoor weather images named WeatherDataset-6 is established. 3C-CNN is used to train and test both on the Two-class Weather Images and WeatherDataset-6. The experimental results show that 3C-CNN achieves best on both datasets, with the average recognition accuracy up to 94.35% and 95.81% respectively, which is superior to other classic convolutional neural networks such as AlexNet, VGG16, and ResNet50. It is prospected that our method can also work well for images taken at night with further improvement.

• Journal of Korea Water Resources Association
• /
• v.41 no.10
• /
• pp.1035-1044
• /
• 2008

It is critical to study on data charateristics analysis and prediction for the flood disaster prevention and water quality monitoring because discharge and TOC data in a river channel are strongly nonlinear. Therefore, in the present study, prediction models for discharge, TOC, and TOC load data were developed using approximation component in the last level and detail components segregated by wavelet transform. The results show that the developed model overcame the persistence phenomenon which could be seen from previous models and improved the prediciton accuracy comparing with the previous models. It might be expected that the results from the present study can mitigate flood disaster damage and construct active alternatives to various water quality problems in the future.

• Journal of Korea Water Resources Association
• /
• v.52 no.spc2
• /
• pp.835-844
• /
• 2019

This study dealt with a systematic approach for sediment replenishment works which defines the artificial supply of coarse sediment to downstream river channels of dams. That is an increasing practice in Japanese, American and European rivers for the purpose of compensating sediment deficits downstream and rehabilitating geomorphological habitats below dams. We introduced five main objectives of the sediment replenishment, simply from construction of artificial spawning redds for anadromous fish to restoration of fluvial geomorphological process of river system. Then we suggested determination of sediment size distribution and quantity of coarse sediment as well as selecting an effective implementation method in corresponding to specific objectives and local restrictions in the basin, reservoir and river.

• Journal of Korea Water Resources Association
• /
• v.52 no.spc2
• /
• pp.791-799
• /
• 2019

This study explained the historical changes in the habitat structures based on the aerial photographs (1948, 1967, 1973, 1989 and 2010) of the mid-stream reach of the Mangyeong River. The habitat structure was divided into landforms and aquatic habitats. The landform was classified into bare land, vegetated land, water surface, farmland and artificial land. The aquatic habitat was classified into natural riffle, artificial riffle, run, head wando, tail wando, mid wando, pond and chute channel. The ratio of bareland decreased, and water surface and vegetated land increased after the excavation in 1970s and since the construction of weir in 1980s. As historical changes of aquatic habitat, ratio of run decreased sharply while mid wando increased sharply. aquatic habitats such as head wando, tail wando, and pond located on bars decreased dramatically.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.51-57
• /
• 2021

In this paper, we propose a method to find the DoF(Depth of field) that is blurred in an image by focusing and out-focusing the camera through a efficient convolutional neural network. Our approach uses the RGB channel-based cross-correlation filter to efficiently classify the DoF region from the image and build data for learning in the convolutional neural network. A data pair of the training data is established between the image and the DoF weighted map. Data used for learning uses DoF weight maps extracted by cross-correlation filters, and uses the result of applying the smoothing process to increase the convergence rate in the network learning stage. The DoF weighted image obtained as the test result stably finds the DoF region in the input image. As a result, the proposed method can be used in various places such as NPR(Non-photorealistic rendering) rendering and object detection by using the DoF area as the user's ROI(Region of interest).

• Journal of Biomedical Engineering Research
• /
• v.43 no.3
• /
• pp.170-176
• /
• 2022

Cell separation from a heterogenous mixture sample is an essential process for downstream analysis in biological, chemical, and clinical applications. This study demonstrates an integrated hybrid device of the viscoelastic focusing in a straight rectangular channel and subsequent size-based separation using acoustophoresis to attain high efficiency and separation tunability. For particle pre-alignment in a viscoelastic fluid, the flow rate higher than 10 μl/min was required. Surface acoustic wave-based lateral migration of particles with different sizes (13 and 27 ㎛) was examined at various applied voltages and flow rate conditions. Therefore, the flow rate of 100 μl/min and the applied voltage of 20 V_pp can be used for size-based particle separation.

• Journal of Korea Water Resources Association
• /
• v.38 no.7 s.156
• /
• pp.527-535
• /
• 2005

The computation of normal depth is very important for the design of channel and the analysis of water flow. Drainage pipe generally has the shape of curvature like circular or U-type, which is different from artificial triangular or rectangular channel. In this case, the computation of normal depth or the derivation of equations is very difficult because the change of hydraulic radius and area versus depth is not simple. If the ratio of the area to the diameter, or the hydraulic radius to the diameter of pipe is expressed as the water depth to the diameter of pipe by power law, however, the process of computing normal depth becomes relatively simple, and explicit equations can be obtained. In the present study, developed are the explicit normal depth equations for circular and U-type pipes, and the normal depth equation associated with Hagen (Manning) equation and friction factor equation of smooth turbulent flow by power law is also proposed because of its wide usage in engineering design.

• Korean Journal of Human Ecology
• /
• v.17 no.1
• /
• pp.57-80
• /
• 2008

The contemporary consumers have insatiable desires for material and outward appearance. In terms of the desire for outward appearance, people recognize that a beautiful outward appearance can be made by an artificial effort. Subsequently, the interest in a beauty and fashion has been increased. In addition, a cable TV shows a beauty and fashion program targeted for women in 20s to 30s. This study tried to examine the stories on experience of consumption by consumers watching a beauty and fashion program in a women specialized channel of a cable TV. The total number of narrators who participated in this study was 11. Among them, we formed 26 narrative plots on the basis of interviews for 7 persons who could use Labov's structural analysis. The result of analyzing narrators' narrative plots was as follows: First, although narrators received the information on beauty and fashion through a channel which became the target of this study, they applied such information into an ordinary life by transforming such information. Second, narrators thought that their confidence and superiority could be expressed through a beauty and fashion. Third, narrators' consuming life showed a showing off-type consumption and an objective consumption. Fourth, narrators have a gap between the behavior orientation and real actions. And they experiences various trobles on consumption life. Fifth, through the interview for narrators, a trend of reconsidering their consuming life was found out.