• Journal of Korea Water Resources Association
• /
• v.57 no.7
• /
• pp.437-449
• /
• 2024

Rainfall-runoff prediction studies using deep learning while considering catchment attributes have been gaining attention. In this study, we selected two models: the Transformer model, which is suitable for large-scale data training through the self-attention mechanism, and the LSTM-based multi-state-vector sequence-to-sequence (LSTM-MSV-S2S) model with an encoder-decoder structure. These models were constructed to incorporate catchment attributes and predict the inflow of 10 multi-purpose dam watersheds in South Korea. The experimental design consisted of three training methods: Single-basin Training (ST), Pretraining (PT), and Pretraining-Finetuning (PT-FT). The input data for the models included 10 selected watershed attributes along with meteorological data. The inflow prediction performance was compared based on the training methods. The results showed that the Transformer model outperformed the LSTM-MSV-S2S model when using the PT and PT-FT methods, with the PT-FT method yielding the highest performance. The LSTM-MSV-S2S model showed better performance than the Transformer when using the ST method; however, it showed lower performance when using the PT and PT-FT methods. Additionally, the embedding layer activation vectors and raw catchment attributes were used to cluster watersheds and analyze whether the models learned the similarities between them. The Transformer model demonstrated improved performance among watersheds with similar activation vectors, proving that utilizing information from other pre-trained watersheds enhances the prediction performance. This study compared the suitable models and training methods for each multi-purpose dam and highlighted the necessity of constructing deep learning models using PT and PT-FT methods for domestic watersheds. Furthermore, the results confirmed that the Transformer model outperforms the LSTM-MSV-S2S model when applying PT and PT-FT methods.

• Journal of the Korean Vacuum Society
• /
• v.10 no.4
• /
• pp.403-410
• /
• 2001

Acceleration in integration density and speed performance of ULSI circuits require miniaturization of CMOS and interconnections as well as higher current density capabilities for transistors. A leading candidate to substitute Al-alloy is Cu, which has lower resistivity and higher melting point. So we can expect much higher electromigration resistance. In this paper, we are going to explain the major features of EM for MOCVD Cu according to variant conditions. We compared the life time and activation energy of MOCVD Cu with those of I-beam Cu and AA in the same conditions. The electromigration experiments were performed with Cu/Al/TiN multilayer. Experimental results shows that the deposition rate and electromigration characteristics of Cu thin film were improved by the Al interlayer.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.649-652
• /
• 2015

Previous marking policy for the AF service of TCP traffic in the Diffserv network have no sufficient consideration on the effect of RTT and target rate. In this paper, in order to improve fairness Index by the effect RTT difference of TCP traffic, we propose the modified TSW3CDM(Time Sliding Window Three Color Dynamic Marker) based on average transfer rate estimation and the flow state. The proposed algorithm is dynamic marking policy that do allocate band width in proportion to transmission rate. To evaluate the performance of the proposed algorithm, We accomplished a computer simulation using NS-2. From simulation results, the proposed TSW3CDM algorithm improves fairness index by comparison with TSW3CM.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.103-103
• /
• 2020

Drying Stream Assessment Tool and Water Flow Tracking (DrySAT-WFT)은 하천건천화 평가 및 예측을 위해 개발된 물수지 기반의 분포형 수문모형이다. 그러나 물수지 모형의 특성상 토양층 사이를 이동하는 수직적인 물의 거동은 파악하기 용이하나, 하천 및 지표를 따라 이동하는 물의 수평적인 거동 추적에는 한계가 있다. 본 연구에서는 DrySAT-WFT 모형에 댐·보 방류량을 고려한 하도 갈수량 추적 알고리즘을 적용하여 유출 모의 성능을 개선하고, 개선된 유출 모형을 금강 유역(9,915.5 ㎢)에 적용하여 건천화 원인 추적 및 평가를 수행하였다. 하천건천화 원인 추적을 위한 영향요소로 1976년부터 2015년까지 구축한 산림높이, 도로망, 지하수 이용량, 토지이용, 토심, 기상 자료를 활용하였다. 건천화 영향요소를 적용하기 전 기상자료만을 활용해 모의한 유출결과를 기준 시나리오로 설정하고 댐·보 지점을 대상으로 검보정을 진행하였다. 이후 각 건천화 영향요소를 적용한 유출 시나리오별 유량의 감소 비율과 건천화 기여 비율을 산정하여 영향평가를 수행하였다.

• Journal of Korea Water Resources Association
• /
• v.48 no.5
• /
• pp.409-423
• /
• 2015

In this study the very short-term rainfall forecasting and storm water forecasting using the weather radar data were implemented in an urban stream basin. As forecasting time increasing, the very short-term rainfall forecasting results show that the correlation coefficient was decreased and the root mean square error was increased and then the forecasting model accuracy was decreased. However, as a result of the correlation coefficient up to 60-minute forecasting time is maintained 0.5 or higher was obtained. As a result of storm water forecasting in an urban area, the reduction in peak flow and outflow volume with increasing forecasting time occurs, the peak time was analyzed that relatively matched. In the application of storm water forecasting by radar rainfall forecast, the errors has occurred that we determined some of the external factors. In the future, we believed to be necessary to perform that the continuous algorithm improvement such as simulation of rapid generation and disappearance phenomenon by precipitation echo, the improvement of extreme rainfall forecasting in urban areas, and the rainfall-runoff model parameter optimizations. The results of this study, not only urban stream basin, but also we obtained the observed data, and expand the real-time flood alarm system over the ungaged basins. In addition, it is possible to take advantage of development of as multi-sensor based very short-term rainfall forecasting technology.

• Journal of Digital Convergence
• /
• v.17 no.8
• /
• pp.249-255
• /
• 2019

Type 2 diabetes mellitus(T2DM) is included in metabolic disorders characterized by hyperglycemia, which causes many complications, and requires long-term treatment resulting in massive medical expenses each year. There have been many studies to solve this problem, but the existing studies have not been accurate by learning and predicting the data at specific time point. Thus, this study proposed a model using RNN to increase the accuracy of prediction of T2DM. This work propose a T2DM prediction model based on Korean Genome and Epidemiology study(Ansan, Anseong Korea). We trained all of the data over time to create prediction model of diabetes. To verify the results of the prediction model, we compared the accuracy with the existing machine learning methods, LR, k-NN, and SVM. Proposed prediction model accuracy was 0.92 and the AUC was 0.92, which were higher than the other. Therefore predicting the onset of T2DM by using the proposed diabetes prediction model in this study, it could lead to healthier lifestyle and hyperglycemic control resulting in lower risk of diabetes by alerted diabetes occurrence.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.246-246
• /
• 2021

본 연구는 강우 발생시 유량을 추정하는 것에 목적이 있다. 이를 위해 본 연구는 선행연구의 모형 개발방법론에서 벗어나 딥러닝 알고리즘 중 하나인 합성곱 신경망 (convolution neural network)과 수문학적 이미지 (hydrological image)를 이용하여 강우 발생시 유량을 추정하였다. 합성곱 신경망은 일반적으로 분류 문제 (classification)을 해결하기 위한 목적으로 개발되었기 때문에 불특정 연속변수인 유량을 모의하기에는 적합하지 않다. 이를 위해 본 연구에서는 합성곱 신경망의 완전 연결층 (Fully connected layer)를 개선하여 연속변수를 모의할 수 있도록 개선하였다. 대부분 합성곱 신경망은 RGB (red, green, blue) 사진 (photograph)을 이용하여 해당 사진이 나타내는 것을 예측하는 목적으로 사용하지만, 본 연구의 경우 일반 RGB 사진을 이용하여 유출량을 예측하는 것은 경험적 모형의 전제(독립변수와 종속변수의 관계)를 무너뜨리는 결과를 초래할 수 있다. 이를 위해 본 연구에서는 임의의 유역에 대해 2차원 공간에서 무차원의 수문학적 속성을 갖는 grid의 집합으로 정의되는 수문학적 이미지는 입력자료로 활용했다. 합성곱 신경망의 구조는 Convolution Layer와 Pulling Layer가 5회 반복하는 구조로 설정하고, 이후 Flatten Layer, 2개의 Dense Layer, 1개의 Batch Normalization Layer를 배열하고, 다시 1개의 Dense Layer가 이어지는 구조로 설계하였다. 마지막 Dense Layer의 활성화 함수는 분류모형에 이용되는 softmax 또는 sigmoid 함수를 대신하여 회귀모형에서 자주 사용되는 Linear 함수로 설정하였다. 이와 함께 각 층의 활성화 함수는 정규화 선형함수 (ReLu)를 이용하였으며, 모형의 학습 평가 및 검정을 판단하기 위해 MSE 및 MAE를 사용했다. 또한, 모형평가는 NSE와 RMSE를 이용하였다. 그 결과, 모형의 학습 평가에 대한 MSE는 11.629.8 m3/s에서 118.6 m3/s로, MAE는 25.4 m3/s에서 4.7 m3/s로 감소하였으며, 모형의 검정에 대한 MSE는 1,997.9 m3/s에서 527.9 m3/s로, MAE는 21.5 m3/s에서 9.4 m3/s로 감소한 것으로 나타났다. 또한, 모형평가를 위한 NSE는 0.7, RMSE는 27.0 m3/s로 나타나, 본 연구의 모형은 양호(moderate)한 것으로 판단하였다. 이에, 본 연구를 통해 제시된 방법론에 기반을 두어 CNN 모형 구조의 확장과 수문학적 이미지의 개선 또는 새로운 이미지 개발 등을 추진할 경우 모형의 예측 성능이 향상될 수 있는 여지가 있으며, 원격탐사 분야나, 위성 영상을 이용한 전 지구적 또는 광역 단위의 실시간 유량 모의 분야 등으로의 응용이 가능할 것으로 기대된다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.1
• /
• pp.146-157
• /
• 2018

Over the last 10 years, the number of disasters has been increasing in Korea. As a result, the need for temporary residences or shelters for disaster conditions is increasing. In this study, post-disaster refugees housing was developed using lightweight composite panels that are lighter than the materials that make up the existing shelter. To accomplish this, the structural performance of the lightweight composite panel was validated. Among the performance tests on the panels, the transverse load test was conducted according to the ASTM E 72 criteria. As a result of the experiment, when each specimen was subjected to a uniformly distributed load, the allowable load was determined according to the span. All the experiments were ended due to a loss of adhesive at the junction of the skin and core. Further analysis was conducted to calculate the shear stress when the junction was dropped. The mean shear stress at the adhesive surface of a specimen, 150 mm and 200 mm in thickness, was 0.0170MPa and 0.0156MPa, respectively. This suggests that similar values were obtained from panels of equal thickness. In addition, this stress provides a criterion of judgment that could be used to inspect the structural performance of the panels. The performance of the panel was evaluated based on the allowable load, but it may be possible to increase the strength of the lightweight composite panel by improving the joining method to avoid separation from the junction.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.103-128
• /
• 2021

Recently, investors' interest and the influence of stock-related information dissemination are being considered as significant factors that explain stock returns and volume. Besides, companies that develop, distribute, or utilize innovative new technologies such as artificial intelligence have a problem that it is difficult to accurately predict a company's future stock returns and volatility due to macro-environment and market uncertainty. Market uncertainty is recognized as an obstacle to the activation and spread of artificial intelligence technology, so research is needed to mitigate this. Hence, the purpose of this study is to propose a machine learning model that predicts the volatility of a company's stock price by using the internet search volume of artificial intelligence-related technology keywords as a measure of the interest of investors. To this end, for predicting the stock market, we using the VAR(Vector Auto Regression) and deep neural network LSTM (Long Short-Term Memory). And the stock price prediction performance using keyword search volume is compared according to the technology's social acceptance stage. In addition, we also conduct the analysis of sub-technology of artificial intelligence technology to examine the change in the search volume of detailed technology keywords according to the technology acceptance stage and the effect of interest in specific technology on the stock market forecast. To this end, in this study, the words artificial intelligence, deep learning, machine learning were selected as keywords. Next, we investigated how many keywords each week appeared in online documents for five years from January 1, 2015, to December 31, 2019. The stock price and transaction volume data of KOSDAQ listed companies were also collected and used for analysis. As a result, we found that the keyword search volume for artificial intelligence technology increased as the social acceptance of artificial intelligence technology increased. In particular, starting from AlphaGo Shock, the keyword search volume for artificial intelligence itself and detailed technologies such as machine learning and deep learning appeared to increase. Also, the keyword search volume for artificial intelligence technology increases as the social acceptance stage progresses. It showed high accuracy, and it was confirmed that the acceptance stages showing the best prediction performance were different for each keyword. As a result of stock price prediction based on keyword search volume for each social acceptance stage of artificial intelligence technologies classified in this study, the awareness stage's prediction accuracy was found to be the highest. The prediction accuracy was different according to the keywords used in the stock price prediction model for each social acceptance stage. Therefore, when constructing a stock price prediction model using technology keywords, it is necessary to consider social acceptance of the technology and sub-technology classification. The results of this study provide the following implications. First, to predict the return on investment for companies based on innovative technology, it is most important to capture the recognition stage in which public interest rapidly increases in social acceptance of the technology. Second, the change in keyword search volume and the accuracy of the prediction model varies according to the social acceptance of technology should be considered in developing a Decision Support System for investment such as the big data-based Robo-advisor recently introduced by the financial sector.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.9
• /
• pp.3141-3147
• /
• 2010

The most important cause for shortening LED lighting efficiency and life is the junction temperature rises and, to solve this problem, various studies such as thermally efficient packaging, highly conductive material development, contact resistance improvement or heat sink optimization have been studied. However, most studies so far assumed that the LED lights are in the atmosphere, and thermal performance has not been therefore reported when the LED lights are mounted on the ceiling with ceiling unit. Thus, this study investigates the variation of junction temperature of the MR16 LED light under actual installation conditions and more accurate thermal design for the efficiency and life of LED lights is therefore achieved.