• Journal of Intelligence and Information Systems
• /
• v.1 no.1
• /
• pp.135-148
• /
• 1995

Neural Networks have been advocated as an alternative to statistical forecasting methods. However, the empirical evidences are not consistent. In the present experiments, multi-layered perceptron (MLP) are adopted as approximator to the time series generating processes. To prevent the MLP from being overfitted to the given time series, the information obtained from ARMA modeling is used to determine the architecture of MLP. The proposed approach was tested empirically using the subsamples of the 111 time series used in the first Markridakis Competition. The forecasting results were analyzed to find out the factors that affect the performance of MLP. The experimental results show that the proposed approach outperforms ARMA models in terms of fitting and forecasting accuracy. In addition, it is found that the use of deseasonalized data improves the forecasting accuracy of MLP.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.4
• /
• pp.131-135
• /
• 2023

Neural network-based time series models called time series neural networks (TSNNs) are trained by the error backpropagation algorithm and used to predict process shifts of parameters such as gas flow, RF power, and chamber pressure in reactive ion etching (RIE). The training data consists of process conditions, as well as principal components (PCs) of optical emission spectroscopy (OES) data collected in-situ. Data are generated during the etching of benzocyclobutene (BCB) in a SF₆/O₂ plasma. Combinations of baseline and faulty responses for each process parameter are simulated, and a moving average of TSNN predictions successfully identifies process shifts in the recipe parameters for various degrees of faults.

• Proceedings of the Korean Environmental Sciences Society Conference
• /
• 2007.05a
• /
• pp.218-222
• /
• 2007

• Journal of the Korean earth science society
• /
• v.32 no.3
• /
• pp.249-264
• /
• 2011

A multi-Gaussian kriging approach extended to space-time domain is presented for uncertainty modeling as well as time-series mapping of environmental variables. Within a multi-Gaussian framework, normal score transformed environmental variables are first decomposed into deterministic trend and stochastic residual components. After local temporal trend models are constructed, the parameters of the models are estimated and interpolated in space. Space-time correlation structures of stationary residual components are quantified using a product-sum space-time variogram model. The ccdf is modeled at all grid locations using this space-time variogram model and space-time kriging. Finally, e-type estimates and conditional variances are computed from the ccdf models for spatial mapping and uncertainty analysis, respectively. The proposed approach is illustrated through a case of time-series Particulate Matter 10 ($PM_{10}$) concentration mapping in Incheon Metropolitan city using monthly $PM_{10}$ concentrations at 13 stations for 3 years. It is shown that the proposed approach would generate reliable time-series $PM_{10}$ concentration maps with less mean bias and better prediction capability, compared to conventional spatial-only ordinary kriging. It is also demonstrated that the conditional variances and the probability exceeding a certain thresholding value would be useful information sources for interpretation.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2008.05a
• /
• pp.694-698
• /
• 2008

In hydrology, it is a difficult task to deal with multivariate time series such as modeling streamflows of an entire complex river system. Normal distribution based model such as MARMA (Multivariate Autorgressive Moving average) has been a major approach for modeling the multivariate time series. There are some limitations for the normal based models. One of them might be the unfavorable data-transformation forcing that the data follow the normal distribution. Furthermore, the high dimension multivariate model requires the very large parameter matrix. As an alternative, one might be decomposing the multivariate data into independent components and modeling it individually. In 1985, Lins used Principal Component Analysis (PCA). The five scores, the decomposed data from the original data, were taken and were formulated individually. The one of the five scores were modeled with AR-2 while the others are modeled with AR-1 model. From the time series analysis using the scores of the five components, he noted "principal component time series might provide a relatively simple and meaningful alternative to conventional large MARMA models". This study is inspired from the researcher's quote to develop a multivariate simulation model. The multivariate simulation model is suggested here using Principal Component Analysis (PCA) and Independent Component Analysis (ICA). Three modeling step is applied for simulation. (1) PCA is used to decompose the correlated multivariate data into the uncorrelated data while ICA decomposes the data into independent components. Here, the autocorrelation structure of the decomposed data is still dominant, which is inherited from the data of the original domain. (2) Each component is resampled by block bootstrapping or K-nearest neighbor. (3) The resampled components bring back to original domain. From using the suggested approach one might expect that a) the simulated data are different with the historical data, b) no data transformation is required (in case of ICA), c) a complex system can be decomposed into independent component and modeled individually. The model with PCA and ICA are compared with the various statistics such as the basic statistics (mean, standard deviation, skewness, autocorrelation), and reservoir-related statistics, kernel density estimate.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.26 no.6
• /
• pp.71-78
• /
• 1989

The imput-output relations for nonlinear systems can be explicitly represented by the Volterra series and they can be characterized by the Volterra kernels. This study is concerned with modeling an elastomer force-displacement relation due to step inputs by utilizing the truncated Volterra series. Since it is practically impossible to apply step inputs that have infinite slope at zero time, the loads due to constant penetration(displacement) rate followed by constant penetration inputs are measured as an alternative approach and estimated for step inputs and then utilized for the truncated Volterra series models. One second order and one third order truncated Volterra series models have been employed to model the force-displacement relation which is one of the prominent properties to characterize the viscoelastic material. The third order truncated Volterra series model has better results, compared with those of the second order truncated Volterra series model.

• 제어로봇시스템학회:학술대회논문집
• /
• 1988.10a
• /
• pp.264-267
• /
• 1988

One of the major reasons of Adaptive Control is to control time varying systems. In this paper new adaptive algorithms are suggested for a class of linear time varying systems that satisfy certain assumptions. These algorithms consist of three modules, modeling, parameter estimation and control. The key feature of this paper is that power series of time varying parameters are used for estimation.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.113-116
• /
• 2001

This paper describes an analysis of the music as a time series and the fuzzy logic-based modeling of it. All music is made up of a finite number of musical notations known as the musical symbols, such as clefs, staff, tine signature, notes, rests, etc. . The musical score uses musical symbols to present various characteristics, such as rhythm, melody, chord, etc,. for interpreting the music. In this paper, it is possible to transform the beat and pitch in the musical into time series from the viewpoint of recognizing beat and pitch of sounding tone at each time. On the basis of the identified features of the musical score, a musical score is represented as a time series and then is constructed to fuzzy logic-based model for predicting them. Examples are presented to illustrate the validity of the proposed method.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.5
• /
• pp.829-837
• /
• 2011

Since Harvey (1989), many approaches for applying unobserved components (UC) models to both univariate and multivariate time series analysis have been developed. However, practitioners still tend to use traditional methods such as exponential smoothing or ARIMA models for modeling and predicting time series data. It is well known that the UC model combines the flexibility of ARIMA models and the easy interpretability of exponential smoothing models by using unobserved components such as trend, cycle, season, and irregular components. This study reviews the UC model and compares its relative performances with those of the other models in modeling and predicting the real gross domestic products (GDP) in Korea. We conclude that the optimal model is the UC model on basis of root mean squared error.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.5
• /
• pp.423-432
• /
• 2022

This paper analyzes a total of 10,599 papers related to COVID-19 from January 2020 to July 2022 collected from the KCI site using LDA topic modeling so that academic researchers can understand the overall research trend. The results of LDA topic modeling are analyzed by major research categories so that academic researchers can easily figure out topics in their research fields. Then, the detailed research category information in which a lot of research is done by topic is analyzed. It is very important for academic researchers to understand the trend of research topics over time. Therefore, in this paper, the trend of topics is analyzed and presented using time series decomposition.