• Journal of Intelligence and Information Systems
• /
• v.19 no.1
• /
• pp.1-17
• /
• 2013

In this article, several types of hybrid forecasting models are suggested. In particular, hybrid models using the generalized additive model (GAM) are newly suggested as an alternative to those using neural networks (NN). The prediction performances of various hybrid and non-hybrid models are evaluated using simulated time series data. Five different types of seasonal time series data related to an additive or multiplicative trend are generated over different levels of noise, and applied to the forecasting evaluation. For the simulated data with only seasonality, the autoregressive (AR) model and the hybrid AR-AR model performed equivalently very well. On the other hand, if the time series data employed a trend, the SARIMA model and some hybrid SARIMA models equivalently outperformed the others. In the comparison of GAMs and NNs, regarding the seasonal additive trend data, the SARIMA-GAM evenly performed well across the full range of noise variation, whereas the SARIMA-NN showed good performance only when the noise level was trivial.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.3
• /
• pp.176-182
• /
• 2024

In this study, we compared and analyzed various methods of missing data handling to build a machine learning model that can effectively analyze and predict time series data with a high percentage of missing values. For this purpose, Predictive State Model Filtering (PSMF), MissForest, and Imputation By Feature Importance (IBFI) methods were applied, and their prediction performance was evaluated using LightGBM, XGBoost, and Explainable Boosting Machines (EBM) machine learning models. The results of the study showed that MissForest and IBFI performed the best among the methods for handling missing values, reflecting the nonlinear data patterns, and that XGBoost and EBM models performed better than LightGBM. This study emphasizes the importance of combining nonlinear imputation methods and machine learning models in the analysis and prediction of time series data with a high percentage of missing values, and provides a practical methodology.

• 제어로봇시스템학회:학술대회논문집
• /
• 1986.10a
• /
• pp.108-112
• /
• 1986

Several algorithms for bivariate time series modeling are reviewed : linear least square, nonlinear least squares, generalized least square, and multi-stage least square methods. Estimation results of simulated data by the above methods are discussed.

• Journal of the Society of Naval Architects of Korea
• /
• v.57 no.5
• /
• pp.305-311
• /
• 2020

This study presents a probabilistic time series forecast of ship structural response using Bayesian inference combined with Volterra linear model. The structural response of a ship exposed to irregular wave excitation was represented by a linear Volterra model and unknown uncertainties were taken care by probability distribution of time series. To achieve the goal, Volterra series of first order was expanded to a linear combination of Laguerre functions and the probability distribution of Laguerre coefficients is estimated using the prepared data by treating Laguerre coefficients as random variables. In order to check the validity of the proposed methodology, it was applied to a linear oscillator model containing damping uncertainties, and also applied to model test data obtained by segmented hull model of 400,000 DWT VLOC as a practical problem.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.17 no.4
• /
• pp.183-189
• /
• 2024

In order to effectively predict time series data, this study proposed a hybrid prediction model that decomposes the data into trend, seasonality, and residual components using Seasonal-Trend Decomposition on Loess, and then applies ARIMA to the trend component, Fourier Series Regression to the seasonality component, and XGBoost to the remaining components. In addition, performance comparison experiments including ARIMA, XGBoost, LSTM, EMD-ARIMA, and CEEMDAN-LSTM models were conducted to evaluate the prediction performance of each model. The experimental results show that the proposed hybrid model outperforms the existing single models with the best performance indicator values in MAPE(3.8%), MAAPE(3.5%), and RMSE(0.35) metrics.

• Journal of the Korean Solar Energy Society
• /
• v.30 no.3
• /
• pp.25-32
• /
• 2010

A real-time monitoring system was developed for transfer, receive, backup and analysis of wind power data at three wind farm(Hang won, Hankyung and Sung san) in Jeju. For this monitoring system a communication system analysis, a collection of data and transmission module development, data base construction and data analysis and management module was developed, respectively. These modules deal with mechanical, electrical and environmental problem. Especially, time series graphic is supported by the data analysis and management module automatically. The time series graphic make easier to raw data analysis. Also, the real-time monitoring system is connected with wind power forecasting system through internet web for data transfer to wind power forecasting system's data base.

• Proceedings of the Korea Association of Information Systems Conference
• /
• 2000.11a
• /
• pp.36-44
• /
• 2000

The purpose of this study is to introduce a more efficient forecasting technique, which could help result the reduction of cost in removing the waste of airline in-flight meals. We will use a neural network approach known to many researchers as the “Outstanding Forecasting Technique”. We employed a multi-layer perceptron neural network using a backpropagation algorithm. We also suggested using other related information to improve the forecasting performances of neural networks. We divided the data into three sets, which are training data set, cross validation data set, and test data set. Time lag variables are still employed in our model according to the general view of time series forecasting. We measured the accuracy of our model by “Mean Square Error”(MSE). The suggested model proved most excellent in serving economy class in-flight meals. Forecasting the exact amount of meals needed for each airline could reduce the waste of meals and therefore, lead to the reduction of cost. Better yet, it could enhance the cost competition of each airline, keep the schedules on time, and lead to better service.

• Journal of Mechanical Science and Technology
• /
• v.20 no.7
• /
• pp.950-960
• /
• 2006

An output time delay always exists in practical systems. Analysis of the delay phenomenon in a continuous-time domain is sophisticated. It is appropriate to obtain its corresponding discrete-time model for implementation via a digital computer. A new method for the discretization of nonlinear systems using Taylor series expansion and the zero-order hold assumption is proposed in this paper. This method is applied to the sampled-data representation of a nonlinear system with a constant output time-delay. In particular, the effect of the time-discretization method on key properties of nonlinear control systems, such as equilibrium properties and asymptotic stability, is examined. In addition, 'hybrid' discretization schemes resulting from a combination of the 'scaling and squaring' technique with the Taylor method are also proposed, especially under conditions of very low sampling rates. A performance of the proposed method is evaluated using two nonlinear systems with time-delay output.

• Journal of Korean Society of Transportation
• /
• v.29 no.4
• /
• pp.95-101
• /
• 2011

This study proposes the accident estimation model developed based on the time-series cross-sectional data at 50 intersections in Cheongju. The data were collected repeatedly and accumulated from 2004 to 2007. This study focused on deriving the optimal among the various models including TSCSREG(Time Series Cross Section Regression). Four different models utilizing various elements affecting accidents were developed. Through a statistical test, it was found that the t values of independent variables of the fixed effect models were less than those of the random effect models. Two variables were then found to be positive to the accidents: the number of crosswalks at an intersection and the number of intersections.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.2
• /
• pp.121-125
• /
• 2021

Cloud service has the characteristic that it must be always available and that it must be able to respond immediately to user requests. This study suggests a method for constructing a proactive and autonomous quality and performance management system to meet these characteristics of cloud services. To this end, we identify quantitative measurement factors for cloud service quality and performance management, define a structure for applying a time series framework to cloud service application quality and performance management for proactive management, and then use big data and artificial intelligence for autonomous management. The flow of data processing and the configuration and flow of big data and artificial intelligence platforms were defined to combine intelligent technologies. In addition, the effectiveness was confirmed by applying it to the cloud service quality and performance management system through a case study. Using the methodology presented in this study, it is possible to improve the service management system that has been managed artificially and retrospectively through various convergence. However, since it requires the collection, processing, and processing of various types of data, it also has limitations in that data standardization must be prioritized in each technology and industry.