• Journal of Korea Water Resources Association
• /
• v.53 no.12
• /
• pp.1159-1172
• /
• 2020

This study applied deep convolution neural network based on U-Net and SegNet using long period weather radar data to very short-term rainfall prediction. And the results were compared and evaluated with the translation model. For training and validation of deep neural network, Mt. Gwanak and Mt. Gwangdeoksan radar data were collected from 2010 to 2016 and converted to a gray-scale image file in an HDF5 format with a 1km spatial resolution. The deep neural network model was trained to predict precipitation after 10 minutes by using the four consecutive radar image data, and the recursive method of repeating forecasts was applied to carry out lead time 60 minutes with the pretrained deep neural network model. To evaluate the performance of deep neural network prediction model, 24 rain cases in 2017 were forecast for rainfall up to 60 minutes in advance. As a result of evaluating the predicted performance by calculating the mean absolute error (MAE) and critical success index (CSI) at the threshold of 0.1, 1, and 5 mm/hr, the deep neural network model showed better performance in the case of rainfall threshold of 0.1, 1 mm/hr in terms of MAE, and showed better performance than the translation model for lead time 50 minutes in terms of CSI. In particular, although the deep neural network prediction model performed generally better than the translation model for weak rainfall of 5 mm/hr or less, the deep neural network prediction model had limitations in predicting distinct precipitation characteristics of high intensity as a result of the evaluation of threshold of 5 mm/hr. The longer lead time, the spatial smoothness increase with lead time thereby reducing the accuracy of rainfall prediction The translation model turned out to be superior in predicting the exceedance of higher intensity thresholds (> 5 mm/hr) because it preserves distinct precipitation characteristics, but the rainfall position tends to shift incorrectly. This study are expected to be helpful for the improvement of radar rainfall prediction model using deep neural networks in the future. In addition, the massive weather radar data established in this study will be provided through open repositories for future use in subsequent studies.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.4C
• /
• pp.514-523
• /
• 2004

In this paper, a new intelligent moving target tracking and surveillance system basing on the pan/tilt-embedded stereo camera system is suggested and implemented. In the proposed system, once the face area of a target is detected from the input stereo image by using a YCbCr color model and then, using this data as well as the geometric information of the tracking system, the distance and 3D information of the target are effectively extracted in real-time. Basing on these extracted data the pan/tilted-embedded stereo camera system is adaptively controlled and as a result, the proposed system can track the target adaptively under the various circumstance of the target. From some experiments using 80 frames of the test input stereo image, it is analyzed that standard deviation of the position displacement of the target in the horizontal and vertical directions after tracking is kept to be very low value of 1.82, 1.11, and error ratio between the measured and computed 3D coordinate values of the target is also kept to be very low value of 0.5% on average. From these good experimental results a possibility of implementing a new real-time intelligent stereo target tracking and surveillance system using the proposed scheme is finally suggested.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.2
• /
• pp.189-194
• /
• 2010

In the recommendation system that recommends services to a specific user by using the estimation value of other users for users' recommendation service, collaborative filtering methods are widely used. But such recommendation systems have problems that exact classification is not possible because a specific user is classified to already classified group in the course of clustering and inexact result can be recommended in case of big errors in users' estimation values. In this paper, in order to increase estimation accuracy, the researchers suggest a recommendation system that applies collaborative filtering after reclassifying on the basis of a specific user's classification items and then finding and correcting the estimation values of the users beyond the critical value of time. This system uses a method where a specific user is not classified to already classified group in the course of clustering but a group is reorganized on the basis of the specific user. In addition, the researchers correct estimation information by cutting off the subordinate 10% from the trimmed mean of samples and then applies weight over time to the remaining data. As the result of an experiment, the suggested method demonstrated about 14.9%'s more accurate estimation result in case of using MAE than general collaborative filtering method.

• Journal of Advanced Navigation Technology
• /
• v.21 no.6
• /
• pp.585-592
• /
• 2017

Recently, as the air traffic volume has been explosively increased, various studies are being conducted to increase the air passenger capacity. In order to compensate the limitation of the separation distance on the aerodrome established on the basis of existing VOR / DME equipment, GNSS utilizing satellite is considered. In addition, we are trying to obtain more precise location information by using SBAS, a system that can correct GNSS error. ICAO recommends introducing SBAS until 2025, and Korea has also started to develop KASS, a Korean SBAS since 2014. Therefore, in this paper, we analyze the interference threshold for the measurement items and the receiving antenna gain according to the elevation angle of the satellite receiving antenna.

• Journal of the Korean earth science society
• /
• v.38 no.7
• /
• pp.535-545
• /
• 2017

Maritime accidents around the Korean Peninsula are increasing, and the ship detection research using remote sensing data is consequently becoming increasingly important. This study presented a new ship detection algorithm using hyperspectral images that provide the spectral information of several hundred channels in the ship detection field, which depends on high resolution optical imagery. We applied a spectral matching algorithm between the reflection spectrum of the ship deck obtained from two field observations and the ship and seawater spectrum of the hyperspectral sensor of an airborne visible/infrared imaging spectrometer. A total of five detection algorithms were used, namely spectral distance similarity (SDS), spectral correlation similarity (SCS), spectral similarity value (SSV), spectral angle mapper (SAM), and spectral information divergence (SID). SDS showed an error in the detection of seawater inside the ship, and SAM showed a clear classification result with a difference between ship and seawater of approximately 1.8 times. Additionally, the present study classified the vessels included in hyperspectral images by presenting the adaptive thresholds of each technique. As a result, SAM and SID showed superior ship detection abilities compared to those of other detection algorithms.

• Journal of KIISE:Databases
• /
• v.33 no.3
• /
• pp.283-298
• /
• 2006

The TPR-tree is the time-parameterized indexing scheme that supports the querying of the current and projected future positions of such moving objects by representing the locations of the objects with their coordinates and velocity vectors. If this index is, however, used in environments that directions and velocities of moving objects, such as vehicles, are very often changed, it increases the communication cost between the server and moving objects because moving objects report their position to the server frequently when the direction and the velocity exceed a threshold value. To preserve the communication cost regularly, there can be used a manner that moving objects report their position to the server periodically. However, the periodical position report also has a problem that lineal time functions of the TPR-tree do not guarantee the accuracy of the object's positions if moving objects change their direction and velocity between position reports. To solve this problem, we propose the query processing scheme and the data structure using road networks for predicting uncertainty positions of moving objects, which is reported to the server periodically. To reduce an uncertainty of the query region, the proposed scheme restricts moving directions of the object to directions of road network's segments. To remove an uncertainty of changing the velocity of objects, it puts a maximum speed of road network segments. Experimental results show that the proposed scheme improves the accuracy for predicting positions of moving objects than other schemes based on the TPR-tree.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.10 no.1
• /
• pp.1-8
• /
• 2008

The concept of growing degree-days (GDD) is widely accepted as a tool to relate plant growth, development, and maturity to temperature. Information on GDD can be used to predict the yield and quality of several crops, flowering date of fruit trees, and insect activity related to agriculture and forestry. When GDD is expressed on a spatial basis, it helps identify the limits of geographical areas suitable for production of various crops and to evaluate areas agriculturally suitable for new or nonnative plants. The national digital climate maps (NDCM, the fine resolution, gridded climate data for climatological normal years) are not provided on a daily basis but on a monthly basis, prohibiting GDD calculation. We applied a widely used GDD estimation method based on monthly data to a part of the NDCM (for Hapcheon County) to produce the spatial GDD data for each month with three different base temperatures (0, 5, and $10^{\circ}C$). Synthetically generated daily temperatures from the NCDM were used to calculate GDD over the same area and the deviations were calculated for each month. The monthly-data based GDD was close to the reference GDD using daily data only for the case of base temperature $0^{\circ}C$. There was a consistent overestimation in GDD with other base temperatures. Hence, we estimated spatial GDD with base temperature $0^{\circ}C$ over the entire nation for the current (1971-2000, observed) and three future (2011-2040, 2041-2070, and 2071-2100, predicted) climatological normal years. Our estimation indicates that the annual GDD in Korea may increase by 38% in 2071-2100 compared with that in 1971-2000.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.4
• /
• pp.1-9
• /
• 2012

As we are turnning into the aged society, accidents by falling down are increasing in the aged people's group. In this paper, we design the system with the 3-Axis acceleration sensor which is composed by a single chip. The body activity signal is measured with the signal detector and RF communicator in this proposed system and the and falling by the entering signal pattern analysis with 3-Axis acceleration sensor. For the RF communication, we are using nRF24L01p and 8bits ATmega uC for the processor. The error of energy expenditure estimation between motor driven treadmill and proposed a body activity module was 7.8% respectively. Human activities and falling is monitored according to analyze and judge the critical value of the Signal Vector. as falled down if they don't turn off the alarm after specific period and the aged person's after falling down activities are their position and more.

• Journal of fish pathology
• /
• v.26 no.2
• /
• pp.65-75
• /
• 2013

Population growth equation of scuticociliate Miamiensis avidus was obtained from the experimental results of in vitro culture condition to estimate the growth rate and carrying capacity from the growth equation. In addition, intraperitoneal infections into olive flounder Paralichthys olivaceus were carried out into 2 different conditions: different concentrations of M. avidus in same water temperature and same concentration of M. avidus in different water temperatures. Olive flounder mortality was threshold dependent with both the temperature and M. avidus density parameters. In this paper, we propose a mathematical model to study M. avidus growth in olive flounder based upon the interactions between parasite and host. The mathematical model was logistic growth differential equation (1.2). The parameters were found with Matlab program through the Levenberge-Marquardt method. In theorem, equilibrium values between the infected fish population and dead population could found. Our equilibrium points were a stable equilibrium and an unstable equilibrium. From the equation (1.6), it was possible to predict the amount of cumulative mortality of olive flounder along with the time after M. avidus infection.

• Proceedings of the Korea Society for Energy Engineering kosee Conference
• /
• 2008.04a
• /
• pp.69-75
• /
• 2008

기포반응도는 월성발전소를 비롯한 CANDU형 원자로의 주된 안전성 쟁점사안으로 끊임없이 논의되어 왔다. 이는 설계기준사고가 노심에서 열에너지 불균형이 원인이 되어 기준이상의 핵연료 파손과 방사성물질 누출로 발전할 위험이 있는 사건들로 정의될 때, 사건 진행 과정에 기포반응도 증가는 조기에 운전중단을 실패할 경우 출력폭주로 이어지므로 사건의 결말이 중대사고로 전환될 위험이 크기 때문이다. 본 연구는 공개된 최신 핵자료인 ENDF/B-VII.0를 NJOY.99로 처리한 연속에너지 반응단면적 라이브러리를 구축하고 MCNP-4C에 접속하여 37봉 천연우라늄 핵연료다발의 표준노심격자에 대한 기포반응도를 시뮬레이션하여, 지금까지 각종문헌에 제시된 값들과 비교, 종합하므로 내제된 불확실성을 추정하는 내용이다. ENDF/B-VII.0 기반 MCNP-4C의 CANDU 노심격자 모델은 동일한 핵자료와 핵종농도를 사용한 WIMS-IAEA 모델과 비교할 때, 초기 노심의 임계도 오차 약 3.51mk가 연소 진행에 따라 $7.5\times10^{-4}mk$/MWD/teU의 비율로 감소하는 것으로 나타났다. 또한 MCNP-4C 예측기포반응도는 초기노심에서 기포율 50% 및 100%에 대해 각각 8.38 및 15.96mk, 평형노심에서 7.68 및 14.72mk로 계산된다. 이는 월성 2, 3, 4 FSAR의 초기노심 및 평형노심에서 100% 기포상태에 대한 값, 약15.0 및 10.6mk와 비교할 때, 초기노심은 약 1.0mk 평형노심은 약4, 1mk 보수적이지만, 다른 연구결과들과는 최대오차 ${\pm}1{\sim}2mk$ 이내에서 잘 일치하는 것으로 평가되었다. 본 연구는 CANDU 노심의 기포반응도 불확실성 요인의 규명 및 영향평가를 위한 노력의 일부로서 앞으로 감속재의 붕산농도 변화, 감속재 및 냉각재의 중수 순도 변화, 기기노화에 의한 격자 구조 및 물성 변화, 중성자속 및 출력 분포 불균형, 반응도조절장치의 위치, 등 주요 설계변수의 변화에 대한 반응도영향 분석연구를 계속할 계획이다.