• 전력전자학회논문지
• /
• 제27권4호
• /
• pp.316-324
• /
• 2022

This paper uses seasonal auto-regressive integrated moving average (S-ARIMA), which is efficient in seasonality between time-series models, to predict the degradation tendency for lithium-ion batteries and study a method for improving the predictive performance. The proposed method analyzes the degradation tendency and extracted factors through an electrical characteristic experiment of lithium-ion batteries, and verifies whether time-series data are suitable for the S-ARIMA model through several statistical analysis techniques. Finally, prediction of battery aging is performed through S-ARIMA, and performance of the model is verified through error comparison of predictions through mean absolute error.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 추계종합학술대회 논문집
• /
• pp.1281-1284
• /
• 1998

This paper proposes an efficient time series prediction of the nonlinear dynamical discrete-time systems using multilayer neural networks of a hybrid learning algorithm. The proposed learning algorithm is a hybrid backpropagation algorithm based on the steepest descent for high-speed optimization and the dynamic tunneling for global optimization. The proposed algorithm has been applied to the y00 samples of 700 sequences to predict the next 100 samples. The simulation results shows that the proposed algorithm has better performances of the convergence and the prediction, in comparision with that using backpropagation algorithm based on the gradient descent for multilayer neural network.

• 한국수자원학회논문집
• /
• 제55권8호
• /
• pp.565-575
• /
• 2022

최근의 수자원공학 분야는 4차산업혁명과 더불어 비약적으로 발전된 딥러닝 기술을 활용한 시계열 수위 및 유량의 예측에 대한 관심이 높아지고 있다. 또한 시계열 자료의 예측이 가능한 LSTM 모형과 GRU 모형을 활용하여 수위 및 유량 예측을 수행하고 있지만 시간 변동성이 매우 큰 하천에서의 유량 예측 정확도는 수위 예측 정확도에 비해 낮게 예측되는 경향이 있다. 본 연구에서는 유량변동이 크고 하구에서의 조석의 영향이 거의 없는 한강의 팔당대교 관측소를 선택하였다. 또한, LSTM 모형과 GRU 모형의 입력 및 예측 자료로 활용될 유량변동이 큰 시계열 자료를 선택하였고 총 자료의 길이는 비교적 짧은 2년 7개월의 수위 자료 및 유량 자료를 수집하였다. 시간변동성이 큰 시계열 수위를 2개의 모형에서 학습할 경우, 2개의 모형 모두에서 예측되는 수위 결과는 관측 수위와 비교하여 적정한 정확도가 확보되었으나 변동성이 큰 유량 자료를 2개의 모형에서 직접 학습시킬 경우, 예측되는 유량 자료의 정확도는 악화되었다. 따라서, 본 연구에서는 급변하는 유량을 정확히 예측하기 위하여 2개 모형으로 예측된 수위 자료를 수위-유량관계곡선의 입력자료로 활용하여 유량의 예측 정확도를 크게 향상시킬 수 있었다. 마지막으로 본 연구성과는 수문자료의 별도 가공없이 관측 길이가 상대적으로 충분히 길지 않고 유출량이 급변하는 도시하천에서의 홍수예경보 자료로 충분히 활용할 수 있을 것으로 기대된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권10호
• /
• pp.3851-3866
• /
• 2015

The dynamic nature of opportunistic networks results in long delays, low rates of success for deliveries, etc. As such user experience is limited, and the further development of opportunistic networks is constrained. This paper proposes a prediction-based routing method for opportunistic networks (PB-OppNet). Firstly, using an ARIMA model, PB-OppNet describes the historical contact information between a node pair as a time series to predict the average encounter time interval of the node pair. Secondly, using an optimal stopping rule, PB-OppNet obtains a threshold for encounter time intervals as forwarding utility. Based on this threshold, a node can easily make decisions of stopping observing, or delivering messages when potential forwarding nodes enter its communication range. It can also report different encounter time intervals to the destination node. With the threshold, PB-OppNet can achieve a better compromise of forwarding utility and waiting delay, so that delivery delay is minimized. The simulation experiment result presented here shows that PB-OppNet is better than existing methods in prediction accuracy for links, delivery delays, delivery success rates, etc.

• 지식경영연구
• /
• 제22권2호
• /
• pp.1-17
• /
• 2021

본 연구에서는 한국과 미국의 대표적인 거래소인 빗썸과 코인베이스의 비트코인 가격을 ARIMA와 순환 신경망(Recurrent Neural Network)을 이용해 예측하고, 이후 각 국가의 뉴스 기사를 이용해 분리 학습에 기반한 separated RNN 모형을 제안한다. separated RNN 모형은 학습 데이터를 가격의 추세 변화 점을 기준으로 분리해 학습시킨 후, 추세 변화점 별 뉴스 데이터를 활용해 용어 기반 사전을 구축한다. 이후 용어 기반 사전과 평가 데이터 기간의 뉴스 데이터를 이용해 예측할 데이터의 가격 추세 변화 점을 찾아낸 후, 매칭되는 모형을 적용해 예측 결과를 산출한다. 2017년 5월 22일부터 2020년 9월 16일까지의 가격 데이터를 사용해 분석한 결과, 제안된 separated RNN을 이용해 예측한 결과가 한국과 미국의 비트코인 가격 예측 모두에서 순환 신경망(RNN)을 이용해 예측한 결과보다 높은 예측 성과를 보였다. 본 연구는 시계열 예측 기법의 한계를 뉴스 데이터를 이용한 추세 변화 점 탐색을 통해 극복할 수 있고, 성과 향상을 위한 추후 다양한 시계열 예측 기법 및 추세 변화 점 탐색을 위한 다양한 텍스트 마이닝 기법을 적용해볼 필요가 있음을 시사한다.

• Communications for Statistical Applications and Methods
• /
• 제7권1호
• /
• pp.87-96
• /
• 2000

Nonlinear time series prediction is derived and compared between statistic of modeling and neural network method. In particular mean squared errors of predication are obtained in generalized random coefficient model and generalized autoregressive conditional heteroscedastic model and compared with them by neural network forecasting.

• Communications for Statistical Applications and Methods
• /
• 제29권6호
• /
• pp.709-719
• /
• 2022

Recently, as the importance of environmental protection has emerged, interest in new and renewable energy is also increasing worldwide. In particular, the solar energy sector accounts for the highest production rate among new and renewable energy in Korea due to its infinite resources, easy installation and maintenance, and eco-friendly characteristics such as low noise emission levels and less pollutants during power generation. However, although climate prediction is essential since solar power is affected by weather and climate change, solar radiation, which is closely related to solar power, is not currently forecasted by the Korea Meteorological Administration. Solar radiation prediction can be the basis for establishing a reasonable new and renewable energy operation plan, and it is very important because it can be used not only in solar power but also in other fields such as power consumption prediction. Therefore, this study was conducted for the purpose of improving the accuracy of solar radiation. Solar radiation was predicted by a total of three weather variables, temperature, humidity, and cloudiness, and solar radiation outside the atmosphere, and the results were compared using various models. The CatBoost model was best obtained by fitting and comparing the Boosting series (XGB, CatBoost) and RNN series (Simple RNN, LSTM, GRU) models. In addition, the results were further improved through Time series cross-validation.

• 생태와환경
• /
• 제43권1호
• /
• pp.161-167
• /
• 2010

In this study, we implemented an experimental approach of ecological model development in order to emphasize the importance of input variable selection with respect to time-delayed arrangement between input and output variables. Time-series modeling requires relevant input variable selection for the prediction of a specific output variable (e.g. density of a species). Inadequate variable utility for input often causes increase of model construction time and low efficiency of developed model when applied to real world representation. Therefore, for future prediction, researchers have to decide number of time-delay (e.g. months, weeks or days; t-n) to predict a certain phenomenon at current time t. We prepared a total of 3,900 equation models produced by Time-Series Optimized Genetic Programming (TSOGP) algorithm, for the prediction of monthly averaged density of a potamic phytoplankton species Stephanodiscus hantzschii, considering future prediction from 0- (no future prediction) to 12-months ahead (interval by 1 month; 300 equations per each month-delay). From the investigation of model structure, input variable selectivity was obviously affected by the time-delay arrangement, and the model predictability was related with the type of input variables. From the results, we can conclude that, although Machine Learning (ML) algorithms which have popularly been used in Ecological Informatics (EI) provide high performance in future prediction of ecological entities, the efficiency of models would be lowered unless relevant input variables are selectively used.

• Communications for Statistical Applications and Methods
• /
• 제18권3호
• /
• pp.319-331
• /
• 2011

In this paper, we propose automatic procedures for the model selection of various univariate time series data. Automatic model selection is important, especially in data mining with large number of time series, for example, the number (in thousands) of signals accessing a web server during a specific time period. Several methods have been proposed for automatic model selection of time series. However, most existing methods focus on linear time series models such as exponential smoothing and autoregressive integrated moving average(ARIMA) models. The key feature that distinguishes the proposed procedures from previous approaches is that the former can be used for both linear time series models and nonlinear time series models such as threshold autoregressive(TAR) models and autoregressive moving average-generalized autoregressive conditional heteroscedasticity(ARMA-GARCH) models. The proposed methods select a model from among the various models in the prediction error sense. We also provide an R package autots that implements the proposed automatic model selection procedures. In this paper, we illustrate these algorithms with the artificial and real data, and describe the implementation of the autots package for R.

• 전기학회논문지
• /
• 제59권1호
• /
• pp.184-191
• /
• 2010

Many researchers have been considering genetic algorithms to system optimization problems. Especially, real-coded genetic algorithms are very effective techniques because they are simpler in coding procedures than binary-coded genetic algorithms and can reduce extra works that increase the length of chromosome for wide search space. Thus, this paper presents a fuzzy system design technique to improve the performance of the fuzzy system. The proposed system consists of two procedures. The primary tuning procedure coarsely tunes fuzzy sets of the system using the k-means clustering algorithm of which the structure is very simple, and then the secondary tuning procedure finely tunes the fuzzy sets using enhanced real-coded genetic algorithms based on the primary procedure. In addition, this paper constructs multiple fuzzy systems using a data preprocessing procedure which is contrived for reflecting various characteristics of nonlinear data. Finally, the proposed fuzzy system is applied to the field of time series prediction and the effectiveness of the proposed techniques are verified by simulations of typical time series examples.