• 대한원격탐사학회지
• /
• 제38권6_1호
• /
• pp.1047-1056
• /
• 2022

지구 온난화의 중요한 지시자인 북극의 바다 얼음인 해빙은 기후 시스템, 선박의 항로 안내, 어업 활동 등에서의 중요성으로 인해 다양한 학문 분야에서 관심을 받고 있다. 최근 자동화와 효율적인 미래 예측에 대한 요구가 커지면서 인공지능을 이용한 새로운 해빙 예측 모델들이 전통적인 수치 및 통계 예측 모델을 대체하기 위해 개발되고 있다. 본 연구에서는 북극 해빙의 전역적, 지역적 특징을 학습할 수 있는 two-stream convolutional long- and short-term memory (TS-ConvLSTM) 인공지능 모델의 북극 해빙 면적이 최저를 보이는 9월에 대해 2001년부터 2021년까지 장기적인 성능 검증을 통해 향후 운용 가능한 시스템으로써의 가능성을 살펴보고자 한다. 장기 자료를 통한 검증 결과 TS-ConvLSTM 모델이 훈련자료의 양이 증가하면서 향상된 예측 성능을 보여주고 있지만, 최근 지구 온난화로 인한 단년생 해빙의 감소로 인해 해빙 농도 5-50% 구간에서는 예측력이 저하되고 있음을 보여주었다. 반면 TS-ConvLSTM에 의해 예측된 해빙 면적과 달리 Sea Ice Prediction Network에 제출된 Sea Ice Outlook (SIO)들의 해빙 면적 중간값의 경우 훈련자료가 늘어나더라도 눈에 띄는 향상을 보이지 않았다. 본 연구를 통해 TS-ConvLSTM 모델의 향후 북극 해빙 예측 시스템의 운용 가능 잠재성을 확인하였으나, 향후 연구에서는 예측이 어려운 자연 환경에서 더욱 안정성 있는 예측 시스템 개발을 위해 더 많은 시공간 변화 패턴을 학습할 수 있는 방안을 고려해야 할 것이다.

• Journal of Electrical Engineering and Technology
• /
• 제13권5호
• /
• pp.1841-1851
• /
• 2018

For the safe and stable operation of the power system, accurate wind power prediction is of great significance. A wind power prediction method based on empirical mode decomposition and improved extreme learning machine is proposed in this paper. Firstly, wind power time series is decomposed into several components with different frequency by empirical mode decomposition, which can reduce the non-stationary of time series. The components after decomposing remove the long correlation and promote the different local characteristics of original wind power time series. Secondly, an improved extreme learning machine prediction model is introduced to overcome the sample data updating disadvantages of standard extreme learning machine. Different improved extreme learning machine prediction model of each component is established. Finally, the prediction value of each component is superimposed to obtain the final result. Compared with other prediction models, the simulation results demonstrate that the proposed prediction method has better prediction accuracy for wind power.

• 한국전자통신학회논문지
• /
• 제16권6호
• /
• pp.1239-1248
• /
• 2021

본 논문은 학문적인 이해를 기반을 둔 예측을 수행하기 위해 FDNN(: Flood drought index neural network) 알고리즘을 제시한다. 데이터에 의존한 예측이 아닌 학문적인 이해를 기반을 둔 예측을 딥러닝에 적용하기 위해, 알고리즘을 수리, 수문학을 기반으로 구성하였다. 강수량의 입력으로 하천의 유량을 예측하는 모델을 구성하여 K-교차검증을 통해 모델의 성능을 측정한다. 제시한 알고리즘의 성능을 증명하기 위해 시계열 예측에서 가장 많이 사용되는 LSTM(: Long short term memory) 알고리즘의 예측 성능과 비교하여 제시한 알고리즘의 우수성을 나타낸다.

• 전기학회논문지
• /
• 제59권12호
• /
• pp.2202-2211
• /
• 2010

The wind power prediction system is composed of a meteorological forecasting module, calculation module of wind power output and HMI(Human Machine Interface) visualization system. The final information from this system is a short-term (6hr ahead) and mid-term (48hr ahead) wind power prediction value. The meteorological forecasting module for wind speed and direction forecasting is a combination of physical and statistical model. In this system, the WRF(Weather Research and Forecasting) model, which is a three-dimensional numerical weather model, is used as the physical model and the GFS(Global Forecasting System) models is used for initial condition forecasting. The 100m resolution terrain data is used to improve the accuracy of this system. In addition, optimization of the physical model carried out using historic weather data in Jeju. The mid-term prediction value from the physical model is used in the statistical method for a short-term prediction. The final power prediction is calculated using an optimal adjustment between the currently observed data and data predicted from the power curve model. The final wind power prediction value is provided to customs using a HMI visualization system. The aim of this study is to further improve the accuracy of this prediction system and develop a practical system for power system operation and the energy market in the Smart-Grid.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제9권4호
• /
• pp.327-332
• /
• 2009

This paper proposes a method to improve the accuracy of a short-term electrical load forecasting (STLF) system based on neuro-fuzzy models. The proposed method compensates load forecasts based on the error obtained during the previous prediction. The basic idea behind this approach is that the error of the current prediction is highly correlated with that of the previous prediction. This simple compensation scheme using error information drastically improves the performance of the STLF based on neuro-fuzzy models. The viability of the proposed method is demonstrated through the simulation studies performed on the load data collected by Korea Electric Power Corporation (KEPCO) in 1996 and 1997.

• ETRI Journal
• /
• 제45권2호
• /
• pp.329-337
• /
• 2023

For safe last-mile autonomous robot delivery services in complex environments, rapid and accurate collision prediction and detection is vital. This study proposes a suitable neural network model that relies on multiple navigation sensors. A light detection and ranging technique is used to measure the relative distances to potential collision obstacles along the robot's path of motion, and an accelerometer is used to detect impacts. The proposed method tightly couples relative distance and acceleration time-series data in a complementary fashion to minimize errors. A long short-term memory, fully connected layer, and SoftMax function are integrated to train and classify the rapidly changing collision countermeasure state during robot motion. Simulation results show that the proposed method effectively performs collision prediction and detection for various obstacles.

• Journal of Information Processing Systems
• /
• 제14권6호
• /
• pp.1508-1520
• /
• 2018

In this paper, we propose an improved model to provide users with a better long-term prediction of waterworks operation data. The existing prediction models have been studied in various types of models such as multiple linear regression model while considering time, days and seasonal characteristics. But the existing model shows the rate of prediction for demand fluctuation and long-term prediction is insufficient. Particularly in the deep running model, the long-short-term memory (LSTM) model has been applied to predict data of water purification plant because its time series prediction is highly reliable. However, it is necessary to reflect the correlation among various related factors, and a supplementary model is needed to improve the long-term predictability. In this paper, convolutional neural network (CNN) model is introduced to select various input variables that have a necessary correlation and to improve long term prediction rate, thus increasing the prediction rate through the LSTM predictive value and the combined structure. In addition, a multiple linear regression model is applied to compile the predicted data of CNN and LSTM, which then confirms the data as the final predicted outcome.

• 한국공간구조학회논문집
• /
• 제14권3호
• /
• pp.93-100
• /
• 2014

Ethylene Tetrafluoroethylene (ETFE) has been widely used in long-span buildings because of its light weight and high transparency. This paper studies the short and long term creep behaviour of ETFE foil. A series of short-term creep and recovery tests were performed, in which the residual strain was observed. A long-term creep test of the ETFE foil was also performed over 110 days. A viscoelastic-plastic model was then established to describe the short-term creep and recovery behaviour. The model contains a traditional multi-Kelvin part and an added steady-flow component to represent the viscoelastic and viscoplastic behaviour, respectively. The model successfully fit the data for three stresses and six temperatures. Additionally, time-temperature equivalency was adopted to predict the long-term creep behaviour of ETFE foil. Horizontal shifting factors were determined from the process of shifting creep-curves at six temperatures. The long-term creep behaviours at three temperatures were predicted. Finally, the long-term creep test showed that the short-term creep test at identical temperatures insufficiently predicted additional creep behaviour, and the long-term test verified the horizontal shifting factors derived from the time-temperature equivalency.

• 지능정보연구
• /
• 제29권1호
• /
• pp.377-396
• /
• 2023

암호화폐시장이 지속해서 성장함에 따라 하나의 새로운 금융시장으로 발전하였다. 이러한 암호화폐시장에 관한 투자전략 연구의 필요성 또한 대두되고 있다. 본 연구에서는 단기매매전략과 딥러닝을 결합한 암호화폐 투자 방법론에 대해 실증분석을 진행하였다. 투자 대상의 암호화폐를 이더리움으로 설정하고, 과거 데이터를 기반으로 최적의 파라미터를 찾아 이를 활용하여 실험 모델의 투자 성과를 분석하였다. 실험 모델은 변동성돌파전략, LSTM(Long Short Term Memory)모델, 이동평균 교차 전략, 그리고 단일 모델들을 결합한 결합 모델이다. 변동성돌파전략은 일 단위로 변동성이 크게 상승할 때 매수하고 당일 종가에 매도하는 단기매매전략이며, LSTM모델은 시계열 데이터에 적합한 딥러닝 모델인 LSTM을 활용하여 얻은 예측 종가를 이용한 매매방법이다. 이동평균 교차 전략은 단기 이동평균선이 교차할 때 매매를 결정하는 방법이다. 결합 모델은 변동성돌파전략의 매수 조건과 변동성돌파전략의 목표 매수가보다 LSTM의 예측 종가가 큰 경우 매수하는 조건이 동시에 만족하면 매수하는 규칙이다. 결합 모델은 변동성돌파전략과 LSTM모델의 파생 변수를 활용해 매수 조건에 AND와 OR를 사용하여 만든 매매 규칙이다. 실험 결과, 단일 모델보다 결합 모델에서 투자 성과가 우수함을 확인하였다. 특히, 데일리 트레이딩과 매수 후 보유의 누적수익률은 -50%이하인 것에 비해 결합 모델은 +11.35%의 높은 누적수익률을 달성하여 하락이 지속되던 투자 기간에도 기술적으로 방어하며 수익을 낼 수 있음을 확인하였다. 본 연구는 기존의 딥러닝기반 암호화폐 가격 예측에서 나아가 변동성이 큰 암호화폐시장에서 딥러닝과 단기매매전략을 결합하여 투자 성과를 개선하였다는 점에서 학술적 의의가 있으며, 실제 투자 시 적용 가능성을 보여주었다는 점에서 실무적 의의가 있다.

• 대한안전경영과학회지
• /
• 제6권2호
• /
• pp.211-229
• /
• 2004

The basis of cyber trading has been sufficiently developed with innovative advancement of Internet Technology and the tendency of stock market investment has changed from long-term investment, which estimates the value of enterprises, to short-term investment, which focuses on getting short-term stock trading margin. Hence, this research shows a Short-term Stock Price Forecasting System on Learning Agent System using DTA(Decision Tree Algorithm) ; it collects real-time information of interest and favorite issues using Agent Technology through the Internet, and forms a decision tree, and creates a Rule-Base Database. Through this procedure the Short-term Stock Price Forecasting System provides customers with the prediction of the fluctuation of stock prices for each issue in near future and a point of sales and purchases. A Human being has the limitation of analytic ability and so through taking a look into and analyzing the fluctuation of stock prices, the Agent enables man to trace out the external factors of fluctuation of stock market on real-time. Therefore, we can check out the ups and downs of several issues at the same time and figure out the relationship and interrelation among many issues using the Agent. The SPFA (Stock Price Forecasting System) has such basic four phases as Data Collection, Data Processing, Learning, and Forecasting and Feedback.