• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2001년도 추계학술발표논문집 (상)
• /
• pp.535-538
• /
• 2001

Since 1990s, many literatures have shown that connectionist models, such as back propagation, recurrent network, and RBF (Radial Basis Function) outperform the traditional models, MA (Moving Average), AR (Auto Regressive), and ARIMA (Auto Regressive Integrated Moving Average) in time series prediction. Neural based approaches to time series prediction require the enough length of historical measurements to generate the enough number of training patterns. The more training patterns, the better the generalization of MLP is. The researches about the schemes of generating artificial training patterns and adding to the original ones have been progressed and gave me the motivation of developing VTG schemes in 1996. Virtual term is an estimated measurement, X(t+0.5) between X(t) and X(t+1), while the given measurements in the series are called actual terms. VTG (Virtual Tern Generation) is the process of estimating of X(t+0.5), and VTG schemes are the techniques for the estimation of virtual terms. In this paper, the alternative VTG schemes to the VTG schemes proposed in 1996 will be proposed and applied to multivariate time series prediction. The VTG schemes proposed in 1996 are called deterministic VTG schemes, while the alternative ones are called stochastic VTG schemes in this paper.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제54권6호
• /
• pp.390-395
• /
• 2005

Sunspots are dark areas that grow and decay on the lowest level of the sun that is visible from the Earth. Shot-term predictions of solar activity are essential to help plan missions and to design satellites that will survive for their useful lifetimes. This paper presents a parallel-structure fuzzy system(PSFS) for prediction of sunspot number time series. The PSFS consists of a multiple number of component fuzzy systems connected in parallel. Each component fuzzy system in the PSFS predicts future data independently based on its past time series data with different embedding dimension and time delay. An embedding dimension determines the number of inputs of each component fuzzy system and a time delay decides the interval of inputs of the time series. According to the embedding dimension and the time delay, the component fuzzy system takes various input-output pairs. The PSFS determines the final predicted value as an average of all the outputs of the component fuzzy systems in order to reduce error accumulation effect.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제8권1호
• /
• pp.31-36
• /
• 2008

This paper presents adaptive learning data of evolvable neural networks (ENNs) for time series prediction of nonlinear dynamic systems. ENNs are a special class of neural networks that adopt the concept of biological evolution as a mechanism of adaptation or learning. ENNs can adapt to an environment as well as changes in the enviromuent. ENNs used in this paper are L-system and DNA coding based ENNs. The ENNs adopt the evolution of simultaneous network architecture and weights using indirect encoding. In general just previous data are used for training the predictor that predicts future data. However the characteristics of data and appropriate size of learning data are usually unknown. Therefore we propose adaptive change of learning data size to predict the future data effectively. In order to verify the effectiveness of our scheme, we apply it to chaotic time series predictions of Mackey-Glass data.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 추계학술대회 논문집 학회본부 D
• /
• pp.666-668
• /
• 2000

In this paper, a fuzzy prediction method is proposed for time series data having uncertainty and non-stationary characteristics. Conventional methods, which use past data directly in prediction procedure, cannot properly handle non-stationary data whose long-term mean is floating. To cope with this problem, a data preprocessing technique utilizing the differences of original time series data is suggested. The difference sets are established from data. And the optimal difference set is selected for input of fuzzy predictor. The proposed method based the Takigi-Sugeno-Kang(TSK or TS) fuzzy rule. Computer simulations show improved results for various time series.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.920-924
• /
• 2005

This paper presents adaptive learning data of evolvable neural networks (ENNs) for time series prediction of nonlinear dynamic systems. ENNs are a special class of neural networks that adopt the concept of biological evolution as a mechanism of adaptation or learning. ENNs can adapt to an environment as well as changes in the environment. ENNs used in this paper are L-system and DNA coding based ENNs. The ENNs adopt the evolution of simultaneous network architecture and weights using indirect encoding. In general just previous data are used for training the predictor that predicts future data. However the characteristics of data and appropriate size of learning data are usually unknown. Therefore we propose adaptive change of learning data size to predict the future data effectively. In order to verify the effectiveness of our scheme, we apply it to chaotic time series predictions of Mackey-Glass data.

• 산업기술연구
• /
• 제28권B호
• /
• pp.101-109
• /
• 2008

In general, non-stationary or chaos time series forecasting is very difficult since there exists a drift and/or nonlinearities in them. To overcome this situation, we suggest a new prediction method based on multiple model TS fuzzy predictors combined with preprocessing of time series data, where, instead of time series data, the differences of them are applied to predictors as input. In preprocessing procedure, the candidates of optimal difference interval are determined by using con-elation analysis and corresponding difference data are generated. And then, for each of them, TS fuzzy predictor is constructed by using k-means clustering algorithm and least squares method. Finally, the best predictor which minimizes the performance index is selected and it works on hereafter for prediction. Computer simulation is performed to show the effectiveness and usefulness of our method.

• 응용통계연구
• /
• 제16권2호
• /
• pp.293-303
• /
• 2003

개입효과가 포함된 시계열 자료에 대한 여러 시계열 모형에 의한 예측 방법들이 비교 분석된다. 개입이 있는 선형 ARIMA 모형, 비선형 ARCH 모형 및 개입이 있는 비선형 ARCH 모형 그리고 TONG 이 제안한 결합예측방법들이 소개되고, 실증분석으로 개입이 있다고 생각되는 한국건축허가면적 자료로부터 그 예측 수월성이 비교된다.

• 품질경영학회지
• /
• 제47권3호
• /
• pp.497-508
• /
• 2019

Purpose: The purpose of this study is to overcome limitations of conventional studies that to predict Baltic Dry Index (BDI). The study proposed applications of Artificial Neural Network (ANN) named Long Short-Term Memory (LSTM) to predict BDI. Methods: The BDI time-series prediction was carried out through eight variables related to the dry bulk market. The prediction was conducted in two steps. First, identifying the goodness of fitness for the BDI time-series of specific ANN models and determining the network structures to be used in the next step. While using ANN's generalization capability, the structures determined in the previous steps were used in the empirical prediction step, and the sliding-window method was applied to make a daily (one-day ahead) prediction. Results: At the empirical prediction step, it was possible to predict variable y(BDI time series) at point of time t by 8 variables (related to the dry bulk market) of x at point of time (t-1). LSTM, known to be good at learning over a long period of time, showed the best performance with higher predictive accuracy compared to Multi-Layer Perceptron (MLP) and Recurrent Neural Network (RNN). Conclusion: Applying this study to real business would require long-term predictions by applying more detailed forecasting techniques. I hope that the research can provide a point of reference in the dry bulk market, and furthermore in the decision-making and investment in the future of the shipping business as a whole.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 하계종합학술대회 논문집(3)
• /
• pp.5-8
• /
• 2000

In this paper, we propose new algorithms for the partition of input space and the generation of fuzzy control rules. The one consists of Shannon and extended fuzzy entropy function, the other consists of adaptive fuzzy neural system with back propagation teaming rule. The focus of this scheme is to realize the optimal fuzzy rule base with the minimal number of the parameters of the rules, reducing the complexity of the system. The proposed algorithm is tested with the time series prediction problem using Mackey-Glass chaotic time series.

• 한국정보시스템학회지:정보시스템연구
• /
• 제31권3호
• /
• pp.197-220
• /
• 2022

Purpose The purpose of this study is to identifies the demand pattern categorization of repair parts of Automotive After-sales Service(A/S) and proposes a demand prediction model for Auto repair parts using Long Short-Term Memory (LSTM) of artificial neural networks (ANN). The optimal parts inventory quantity prediction model is implemented by applying daily, weekly, and monthly the parts demand data to the LSTM model for the Lumpy demand which is irregularly in a specific period among repair parts of the Automotive A/S service. Design/methodology/approach This study classified the four demand pattern categorization with 2 years demand time-series data of repair parts according to the Average demand interval(ADI) and coefficient of variation (CV²) of demand size. Of the 16,295 parts in the A/S service shop studied, 96.5% had a Lumpy demand pattern that large quantities occurred at a specific period. lumpy demand pattern's repair parts in the last three years is predicted by applying them to the LSTM for daily, weekly, and monthly time-series data. as the model prediction performance evaluation index, MAPE, RMSE, and RMSLE that can measure the error between the predicted value and the actual value were used. Findings As a result of this study, Daily time-series data were excellently predicted as indicators with the lowest MAPE, RMSE, and RMSLE values, followed by Weekly and Monthly time-series data. This is due to the decrease in training data for Weekly and Monthly. even if the demand period is extended to get the training data, the prediction performance is still low due to the discontinuation of current vehicle models and the use of alternative parts that they are contributed to no more demand. Therefore, sufficient training data is important, but the selection of the prediction demand period is also a critical factor.