• 한국방재안전학회논문집
• /
• 제14권4호
• /
• pp.17-27
• /
• 2021

유량예측은 효과적인 홍수관리 및 수자원 계획을 위한 매우 중요한 재난방지 접근법이다. 현재 기후변화로 인한 집중호우가 나날이 증가하고 있어 막대한 기반시설 손실과 재산, 인명 피해가 발생하고 있다. 본 연구는 미국 테네시주 Hickman County의 Vernon에 있는 Piney Resort의 최근 홍수사례분석을 통해 최대 강우 시나리오에서 유량예측에 대한 강우의 기여도를 측정했다. Piney River 유역내 USGS 두개의 관측소(03602500, 03599500)에서 20년(2000-2019) 동안의 일별 하천 유량, 수위 및 강우 데이터를 수집했고, Long Short Term Memory(LSTM)을 사용하였다. 또한, Tensorflow, Keras Machine learning frameworks, Python을 이용하여 14일로 구별된 유량 값을 예측하였다. 또한, 모델이 2021년 8월 21일의 범람 이벤트를 예측할 수 있었는지를 결정하는 데 사용되었다. 전체 데이터(수위, 유량 및 강우량)가 포함된 LSTM 모델은 일부 강우 모델을 제외하고 지속성 모델보다 우수한 성능을 보였으며, 강우자료만 이용하여 유량예측을 하는 것은 충분하지 않음을 나타냈다. 결과는 LSTM 모델은 0.68 및 13.84m³/s의 최적 NSE 및 RMSE 값을 나타냈고, 가장 낮은 예측 오차로 예측 최대유량은 94m³/s로 나타났다. 향후 강우 패턴에 대한 다양한 분석이 이루어진다면 효율적인 홍수 경보 시스템 및 정책을 설계하는 관련 연구에 도움을 줄 것으로 판단된다.

• Journal of Astronomy and Space Sciences
• /
• 제35권4호
• /
• pp.227-233
• /
• 2018

This study presents the generation and accuracy assessment of predicted orbital ephemeris based on satellite laser ranging (SLR) for geostationary Earth orbit (GEO) satellites. Two GEO satellites are considered: GEO-Korea Multi-Purpose Satellite (KOMPSAT)-2B (GK-2B) for simulational validation and Compass-G1 for real-world quality assessment. SLR-based orbit determination (OD) is proactively performed to generate orbital ephemeris. The length and the gap of the predicted orbital ephemeris were set by considering the consolidated prediction format (CPF). The resultant predicted ephemeris of GK-2B is directly compared with a pre-specified true orbit to show 17.461 m and 23.978 m, in 3D root-mean-square (RMS) position error and maximum position error for one day, respectively. The predicted ephemeris of Compass-G1 is overlapped with the Global Navigation Satellite System (GNSS) final orbit from the GeoForschungsZentrum (GFZ) analysis center (AC) to yield 36.760 m in 3D RMS position differences. It is also compared with the CPF orbit from the International Laser Ranging Service (ILRS) to present 109.888 m in 3D RMS position differences. These results imply that SLR-based orbital ephemeris can be an alternative candidate for improving the accuracy of commonly used radar-based orbital ephemeris for GEO satellites.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2018년도 추계학술대회
• /
• pp.11-14
• /
• 2018

The aim of this study is to rectify the misclassified image features and enhance the performance of image classification tasks by incorporating a channel- coding technique, widely used in telecommunication. Specifically, the proposed algorithm employs the error - correcting mechanism of convolutional coding combined with the convolutional neural networks (CNNs) that are the state - of- the- arts image classifier s. We develop an encoder and a decoder to employ the error - correcting capability of the convolutional coding. In the encoder, the label values of the image data are converted to convolutional codes that are used as target outputs of the CNN, and the network is trained to minimize the Euclidean distance between the target output codes and the actual output codes. In order to correct misclassified features, the outputs of the network are decoded through the trellis structure with Viterbi algorithm before determining the final prediction. This paper demonstrates that the proposed architecture advances the performance of the neural networks compared to the traditional one- hot encoding method.

• 대기
• /
• 제16권4호
• /
• pp.303-318
• /
• 2006

A parameterization of gravity wave drag induced by cumulus convection (GWDC) proposed by Chun and Baik is implemented in the KMA operational global NWP model (GDAPS), and effects of the GWDC on the forecast for July 2005 by GDAPS are investigated. The forecast result is compared with NCEP final analyses data (FNL) and model's own analysis data. Cloud-top gravity wave stresses are concentrated in the tropical region, and the resultant forcing by the GWDC is strong in the tropical upper troposphere and lower stratosphere. Nevertheless, the effect of the GWDC is strong in the mid- to high latitudes of Southern Hemisphere and high latitudes of Northern Hemisphere. By examining the effect of the GWDC on the amplitude of the geopotential height perturbation with zonal wavenumbers 1-3, it is found that impact of the GWDC is extended to the high latitudes through the change of planetary wave activity, which is maximum in the winter hemisphere. The GWDC reduces the amplitude of zonal wavenumber 1 but increases wavenumber 2 in the winter hemisphere. This change alleviates model biases in the zonal wind not only in the lower stratosphere where the GWDC is imposed, but also in the whole troposphere, especially in the mid- to high latitudes of Southern Hemisphere. By examining root mean square error, it is found that the GWDC parameterization improves GDAPS forecast skill in the Southern Hemisphere before 7 days and partially in the Northern Hemisphere after about 5 days.

• 산업경영시스템학회지
• /
• 제46권1호
• /
• pp.105-111
• /
• 2023

Recently, research on prediction algorithms using deep learning has been actively conducted. In addition, algorithmic trading (auto-trading) based on predictive power of artificial intelligence is also becoming one of the main investment methods in stock trading field, building its own history. Since the possibility of human error is blocked at source and traded mechanically according to the conditions, it is likely to be more profitable than humans in the long run. In particular, for the virtual currency market at least for now, unlike stocks, it is not possible to evaluate the intrinsic value of each cryptocurrencies. So it is far effective to approach them with technical analysis and cryptocurrency market might be the field that the performance of algorithmic trading can be maximized. Currently, the most commonly used artificial intelligence method for financial time series data analysis and forecasting is Long short-term memory(LSTM). However, even t4he LSTM also has deficiencies which constrain its widespread use. Therefore, many improvements are needed in the design of forecasting and investment algorithms in order to increase its utilization in actual investment situations. Meanwhile, Prophet, an artificial intelligence algorithm developed by Facebook (META) in 2017, is used to predict stock and cryptocurrency prices with high prediction accuracy. In particular, it is evaluated that Prophet predicts the price of virtual currencies better than that of stocks. In this study, we aim to show Prophet's virtual currency price prediction accuracy is higher than existing deep learning-based time series prediction method. In addition, we execute mock investment with Prophet predicted value. Evaluating the final value at the end of the investment, most of tested coins exceeded the initial investment recording a positive profit. In future research, we continue to test other coins to determine whether there is a significant difference in the predictive power by coin and therefore can establish investment strategies.

• 한국생산제조학회지
• /
• 제8권5호
• /
• pp.70-75
• /
• 1999

Adaptive control in the robotic GMA(Gas Metal Arc) welding is employed to monitor the information about weld characteristics and process paramters as well as modification of those parameters to hold weld quality within the acceptable limits. Typical characteristics are the bead geometry composition micrrostructure appearance and process parameters which govern the quality of the final weld. The main objectives of this paper are to realize the mapping characteristicso f penetration through the learning. After learning the neural network can predict the pene-traition desired from the learning mapping characteristic. The design parameters of the neural network estimator(the number of hidden layers and the number of nodes in a layer) were chosen from an error analysis. partial-penetration single-pass bead-on-plate welds were fabricated in 12mm mild steel plates in order to verify the performance of the neural network estimator. The experimental results show that the proposed neural network estimator can predict the penetration with reasonable accuracy and gurarantee the uniform weld quality.

• 한국생산제조학회지
• /
• 제7권6호
• /
• pp.57-63
• /
• 1998

An adaptive control in the robotic GMA welding is employed to monitor information about weld characteristics and process parameters as well as to modify those parameters to hold weld quality within acceptable limits. Typical characteristics are the bead geometry, composition, microstructure, appearance, and process parameters which govern the quality of the final weld. The main objectives of this thesis are to realize the mapping characteristics of bead width through learning. After learning, the neural estimation can estimate the bead width desired form the learning mapping characteristic. The design parameters of the neural network estimator(the number of hidden layers and the number of nodes in a layer) are chosen from an estimation error analysis. A series of bead of bead-on-plate GMA welding experiments was carried out in order to verify the performance of the neural network estimator. The experimental results show that the proposed neural network estimator can predict the bead width with reasonable accuracy and guarantee the uniform weld quality.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2003년도 춘계학술대회논문집
• /
• pp.443-447
• /
• 2003

The BEM (Boundary Element Method) is a computational technique for the approximate solution of problems in continuum mechanics. In the BEM both volume and surface integrals transformed into boundary integral equations. So, we applied the ECM (Electrochemical Machining) process to boundary problem, because our focus is only deformed shape. The ECM process is modeled as a two-dimensional problem assuming constant properties of electrolyte, and an incremental formulation is used with automatic mesh regeneration. As a result the final shape is roughly agreed with experimental shape. But, it has an error of exact shape, because a chemically factor is not considered

• 한국자동차공학회논문집
• /
• 제1권3호
• /
• pp.55-62
• /
• 1993

Autoregressive moving average(ARMA) model which is a time domain parametric modeling method is implemented for modeling and reproducing characteristics of exhaust noise of an automobile in various RPM range. Experiments have been carried out using 9 set of exhaust noise signals measured at 1,000-3,000 RPM range. Characteristics of sampled signals were estimated using ARMA modeling and Akaike's FPE(final prediction error) criterion to define exact model structure and for model validation. The digital filter consisted of the esitmated ARMA(70,1) model parameters was programed to reproduce exhaust noise. The spectral analysis of reproduced noise is very close to original. The results show that our approaching technique for reproducing acoustic characteristics is valid and feasible to apply in the field of noise quality control.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권11호
• /
• pp.3145-3162
• /
• 2023

As an important technology of the internetwork, wireless sensor network technique plays an important role in indoor localization. Non-line-of-sight (NLOS) problem has a large effect on indoor location accuracy. A location algorithm based on improved particle filter and directional probabilistic data association (IPF-DPDA) for WSN is proposed to solve NLOS issue in this paper. Firstly, the improved particle filter is proposed to reduce error of measuring distance. Then the hypothesis test is used to detect whether measurements are in LOS situations or NLOS situations for N different groups. When there are measurements in the validation gate, the corresponding association probabilities are applied to weight retained position estimate to gain final location estimation. We have improved the traditional data association and added directional information on the original basis. If the validation gate has no measured value, we make use of the Kalman prediction value to renew. Finally, simulation and experimental results show that compared with existing methods, the IPF-DPDA performance better.