• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.230-230
• /
• 2023

딥러닝 알고리즘 중 과거의 정보를 저장하는 문제(장기종속성 문제)가 있는 단순 RNN(Simple Recurrent Neural Network)의 단점을 해결한 LSTM(Long short-term memory)이 등장하면서 특정한 유역의 강우-유출 모형을 구축하는 연구가 증가하고 있다. 그러나 하나의 모형으로 모든 유역에 대한 유출을 예측하는 지역화 강우-유출 모형은 서로 다른 유역의 식생, 지형 등의 차이에서 발생하는 수문학적 행동의 차이를 학습해야 하므로 모형 구축에 어려움이 있다. 따라서, 본 연구에서는 국내 12개의 유역에 대하여 LSTM 기반 분포형 지역화 강우-유출 모형을 구축한 이후 강우 이외의 보조 자료에 따른 정확도를 살펴보았다. 국내 12개 유역의 7년 (2012.01.01-2018.12.31) 동안의 49개 격자(4km²)에 대한 10분 간격 레이더 강우, MODIS 위성 이미지 영상을 활용한 식생지수 (Normalized Difference Vegetation Index), 10분 간격 기온, 유역 평균 경사, 단순 하천 경사를 입력자료로 활용하였으며 10분 간격 유량 자료를 출력 자료로 사용하여 LSTM 기반 분포형 지역화 강우-유출 모형을 구축하였다. 이후 구축된 모형의 성능을 검증하기 위해 학습에 사용되지 않은 3개의 유역에 대한 자료를 활용하여 Nash-Sutcliffe Model Efficiency Coefficient (NSE)를 확인하였다. 식생지수를 보조 자료를 활용하였을 경우 제안한 모형은 3개의 검증 유역에 대하여 하천 흐름을 높은 정확도로 예측하였으며 딥러닝 모형이 위성 자료를 통하여 식생에 의한 차단 및 토양 침투와 같은 동적 요소의 학습이 가능함을 나타낸다.

• International Journal of Computer Science & Network Security
• /
• v.23 no.8
• /
• pp.9-16
• /
• 2023

Speech can actively elicit feelings and attitudes by using words. It is important for researchers to identify the emotional content contained in speech signals as well as the sort of emotion that resulted from the speech that was made. In this study, we studied the emotion recognition system using a database in Arabic, especially in the Saudi dialect, the database is from a YouTube channel called Telfaz11, The four emotions that were examined were anger, happiness, sadness, and neutral. In our experiments, we extracted features from audio signals, such as Mel Frequency Cepstral Coefficient (MFCC) and Zero-Crossing Rate (ZCR), then we classified emotions using many classification algorithms such as machine learning algorithms (Support Vector Machine (SVM) and K-Nearest Neighbor (KNN)) and deep learning algorithms such as (Convolution Neural Network (CNN) and Long Short-Term Memory (LSTM)). Our Experiments showed that the MFCC feature extraction method and CNN model obtained the best accuracy result with 95%, proving the effectiveness of this classification system in recognizing Arabic spoken emotions.

• Smart Structures and Systems
• /
• v.32 no.2
• /
• pp.83-99
• /
• 2023

The temperature prediction approaches of three important locations in an operational longitudinal slab track-bridge structure by using three typical neural network methods based on the field measuring platform of four meteorological factors and internal temperature. The measurement experiment of four meteorological factors (e.g., ambient temperature, solar radiation, wind speed, and humidity) temperature in the three locations of the longitudinal slab and base plate of three important locations (e.g., mid-span, beam end, and Wide-Narrow Joint) were conducted, and then their characteristics were analyzed, respectively. Furthermore, temperature prediction effects of three locations under five various meteorological conditions are tested by using three neural network methods, respectively, including the Artificial Neural Network (ANN), the Long Short-Term Memory (LSTM), and the Convolutional Neural Network (CNN). More importantly, the predicted effects of solar radiation in four meteorological factors could be identified with three indicators (e.g., Root Means Square Error, Mean Absolute Error, Correlation Coefficient of R2). In addition, the LSTM method shows the best performance, while the CNN method has the best prediction effect by only considering a single meteorological factor.

• Journal of Korean Vacuum Science & Technology
• /
• v.6 no.1
• /
• pp.12-15
• /
• 2002

The physical properties, including magneto-optical and transport ones, of Ni$_2$MnG$_2$ alloy in the martensitic and austenitic states were investigated. The dependence of the temperature coefficient of resistivity on temperature shows kinks at the structural and ferro-para magnetic transitions. Electron-magnon and electron-phonon scattering are analyzed to be the dominant scattering mechanisms of the Ni$_2$MnG$_2$ alloy in the martensitic and austenitic states, respectively. The experimental real parts of the off-diagonal components of the dielectric function present two sharp peaks, one at 1.9 eV and the other at 3.2 eV, and a broad shoulder at 3.5 eV, all are identified by the band-structure calculations. These peak positions are coincident with those in the corresponding optical-conductivity spectrum, which is thought to originate from the single-spin state in Ni$_2$MnG$_2$ alloy.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.66 no.4
• /
• pp.51-57
• /
• 2024

This study was conducted on how to simulate runoff, which was done using existing physical models, using an LSTM (Long Short-Term Memory) model based on deep learning. Tancheon, the first tributary of the Han River, was selected as the target area for the model application. To apply the model, one water level observatory and four rainfall observatories were selected, and hourly data from 2020 to 2023 were collected to apply the model. River water level of the outlet of the Tancheon basin was simulated by inputting precipitation data from four rainfall observation stations in the basin and average preceding 72-hour precipitation data for each hour. As a result of water level simulation using 2021 to 2023 data for learning and testing with 2020 data, it was confirmed that reliable simulation results were produced through appropriate learning steps, reaching a certain mean absolute error in a short period time. Despite the short data period, it was found that the mean absolute percentage error was 0.5544~0.6226%, showing an accuracy of over 99.4%. As a result of comparing the simulated and observed values of the rapidly changing river water level during a specific heavy rain period, the coefficient of determination was found to be 0.9754 and 0.9884. It was determined that the performance of LSTM, which aims to simulate river water levels, could be improved by including preceding precipitation in the input data and using precipitation data from various rainfall observation stations within the basin.

• Korean Journal of Remote Sensing
• /
• v.38 no.3
• /
• pp.265-282
• /
• 2022

Sea surface temperature (SST) is a factor that greatly influences ocean circulation and ecosystems in the Earth system. As global warming causes changes in the SST near the Korean Peninsula, abnormal water temperature phenomena (high water temperature, low water temperature) occurs, causing continuous damage to the marine ecosystem and the fishery industry. Therefore, this study proposes a methodology to predict the SST near the Korean Peninsula and prevent damage by predicting abnormal water temperature phenomena. The study area was set near the Korean Peninsula, and ERA5 data from the European Center for Medium-Range Weather Forecasts (ECMWF) was used to utilize SST data at the same time period. As a research method, Long Short-Term Memory (LSTM) algorithm specialized for time series data prediction among deep learning models was used in consideration of the time series characteristics of SST data. The prediction model predicts the SST near the Korean Peninsula after 1- to 7-days and predicts the high water temperature or low water temperature phenomenon. To evaluate the accuracy of SST prediction, Coefficient of determination (R²), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE) indicators were used. The summer (JAS) 1-day prediction result of the prediction model, R²=0.996, RMSE=0.119℃, MAPE=0.352% and the winter (JFM) 1-day prediction result is R²=0.999, RMSE=0.063℃, MAPE=0.646%. Using the predicted SST, the accuracy of abnormal sea surface temperature prediction was evaluated with an F1 Score (F1 Score=0.98 for high water temperature prediction in summer (2021/08/05), F1 Score=1.0 for low water temperature prediction in winter (2021/02/19)). As the prediction period increased, the prediction model showed a tendency to underestimate the SST, which also reduced the accuracy of the abnormal water temperature prediction. Therefore, it is judged that it is necessary to analyze the cause of underestimation of the predictive model in the future and study to improve the prediction accuracy.

• Journal of Korean Clinical Nursing Research
• /
• v.18 no.2
• /
• pp.284-295
• /
• 2012

Purpose: This study was done to clarify effects of bispectral index monitoring sedative administration, compared to MOAA/S (Modified Observer's Assessment of Alertness and Sedation), on conscious sedation, physiological stability and recovery time for patients undergoing endoscopic submucosal dissection. Methods: Participants In this study were patients who underwent endoscopic submucosal dissection because of early gastric cancer. Participants were assigned randomly to an experimental group receiving sedatives based on bispectral index monitoring or to a control group with the MOAA/S instrument. Movements, belching, memory, pain, discomfort, physiological stability (MBP, PR, $SpO_2$), and recovery time were measured during the treatment and recovery. Data were analyzed using Spearman partial correlation coefficient analysis, Mixed model and Wilcoxon rank sum test to determine differences in the parameters. Results: There were no statistically significant differences between the two groups for conscious sedation(movement, belching, memory, pain, or discomfort), physiological stability and recovery time. Conclusion: The results of this study indicate that no differences were found between the two types of monitoring. Thus, use of a bispectral index monitor in clinical practice enabling medical staff to readily assess the conscious sedation of for these patients is expected to be increasingly used as an objective assessment tool for conscious sedation for patient safety.

• Korean Journal of Materials Research
• /
• v.11 no.3
• /
• pp.197-202
• /
• 2001

M $g_{1-x}$ Z $n_{x}$O thin films with various composition x of ZnO were fabricated by a RF magnetron sputtering method, which is expected to improve the electro-optical properties of the conventional MgO protective layer for AC-PDP. Test panels with the $Mg_{1-x}$Z $n_{x}$O protective layer have been fabricated in order to investigate the effects of ZnO doping on the electrical characteristics of devices such as the discharge voltages and the memory gain. Experimental results revealed that test panels with the $Mg_{1-x}$Z $n_{x}$O(x=0.5at%) protective layer show lower firing and sustain voltages than those seen in panels with MgO protective layer by 20V. resulting in an increasement of the memory coefficient. In addition, it was found that test panels with the $Mg_{1-x}$Z $n_{x}$O protective layer show higher discharge intensity, i. e., higher plasma density, compared with panels with MgO protective layer.ve layer.layer.

• Journal of the Korean Society of Radiology
• /
• v.8 no.4
• /
• pp.163-170
• /
• 2014

This study is to investigate neuro-anatomical correlation between neuropsychological results and cerebral cortex thickness of cognitive ability in the brain MRI targeting the patients with mild cognitive impairment. It was that 78 people who were diagnosed as first Parkinson's disease followed by neuropsychological screening battery(Parkinson's disease with mild cognitive impairment: 39 people; Parkinson's disease with normal cognition: 39 people) and 32 people of normal group were selected. Correlation between mild cognitive impairment and normal cognitive impairment and correlation between neuropsychological screening battery and cerebral cortex thickness in the brain MRI were performed by independent sample t-test or Pearson correlation coefficient and then level of significance of collected data was verified in p<0.05. As a result, cerebral cortex thickness of the Parkinson's disease with mild cognitive impairment in both side precuneas and right inferiortemporal lobe had statistically significant decrease. In addition, function of visuospatial ability, verbal and visual memory was reduced in neuropsychological screening battery for cognitive assessment. Especially, there was correlation between neuropsychological screening battery of verbal and visual memory anatomical left precuneus.

• Journal of Korean Society of Disaster and Security
• /
• v.13 no.4
• /
• pp.75-92
• /
• 2020

In most cases of the water balance analysis, the return flow ratio for each water supply was uniformly determined and applied, so it has been contained a problem that the volume of available water would be incorrectly calculated. Therefore, sewage and wastewater among the return water were focused in this study and the data-driven model was developed to forecast the outflow from the sewage treatment plant. The forecasting results of LSTM (Long Short-Term Memory), GRU (Gated Recurrent Units), and SVR (Support Vector Regression) models, which are mainly used for forecasting the time series data in most fields, were compared with the observed data to determine the optimal model parameters for forecasting outflow. As a result of applying the model, the root mean square error (RMSE) of the GRU model was smaller than those of the LSTM and SVR models, and the Nash-Sutcliffe coefficient (NSE) was higher than those of others. Thus, it was judged that the GRU model could be the optimal model for forecasting the outflow in sewage treatment plants. However, the forecasting outflow tends to be underestimated and overestimated in extreme sections. Therefore, the additional data for extreme events and reducing the minimum time unit of input data were necessary to enhance the accuracy of forecasting. If the water use of the target site was reviewed and the additional parameters that could reflect seasonal effects were considered, more accurate outflow could be forecasted to be ready for climate variability in near future. And it is expected to use as fundamental resources for establishing a reasonable river water management system based on the forecasting results.