• Communications for Statistical Applications and Methods
• /
• v.17 no.5
• /
• pp.697-712
• /
• 2010

This paper is concerned with the statistical analysis and development of stochastic models for the demand for life insurance policy loans. For these, firstly the characteristics of the regression trend, periodicity and dependence of the monthly demand for life insurance policy loans are investigated by a statistical analysis of the monthly demand data for the years 1999 through 2008. Secondly, the causal relationships between the demand for life insurance policy loans and the economic variables including unemployment rate and inflation rate for the period are investigated. The results show that inflation rate is main factor influencing policy loan demands. The overall evidence, however, failed to establish unidirectional causality relationships between the demand series and the other variables under study. Finally, based on these, univariate time series model and transfer function model where the demand series is related to one input series are derived, respectively, for the prediction of the demand for life insurance policy loans. A statistical procedure for using the model to predict the demand for life insurance policy loans is also proposed.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.31 no.4
• /
• pp.31-49
• /
• 1989

It is of the most urgent necessity to get hydrological time series of long duration for the establishment of rational design and operation criterion for the Agricultural hydraulic structures. This study was conducted to select best fitted frequency distribution for the monthly runoff and to simulate long series of generated flows by multi-season first order Markov model with comparison of statistical parameters which are derivated from observed and sy- nthetic flows in the five watersheds along Geum river basin. The results summarized through this study are as follows. 1. Both two parameter gamma and two parameter lognormal distribution were judged to be as good fitted distributions for monthly discharge by Kolmogorov-Smirnov method for goodness of fit test in all watersheds. 2. Statistical parameters were obtained from synthetic flows simulated by two parameter gamma distribution were closer to the results from observed flows than those of two para- meter lognormal distribution in all watersheds. 3. In general, fluctuation for the coefficient of variation based on two parameter gamma distribution was shown as more good agreement with the observed flow than that of two parameter lognormal distribution. Especially, coefficient of variation based on two parameter lognormal distribution was quite closer to that of observed flow during June and August in all years. 4. Monthly synthetic flows based on two parameter gamma distribution are considered to give more reasonably good results than those of two parameter lognormal distribution in the multi-season first order Markov model in all watersheds. 5. Synthetic monthly flows with 100 years for eack watershed were sjmulated by multi- season first order Markov model based on two parameter gamma distribution which is ack- nowledged to fit the actual distribution of monthly discharges of watersheds. Simulated sy- nthetic monthly flows may be considered to be contributed to the long series of discharges as an input data for the development of water resources. 6. It is to be desired that generation technique of synthetic flow in this study would be compared with other simulation techniques for the objective time series.

• Journal of the Korean Society for Railway
• /
• v.14 no.5
• /
• pp.470-476
• /
• 2011

This study proposed the intervention ARIMA model as a way to forecast the KTX passenger demand. The second phase of the Gyeongbu high-speed rail project and the financial crisis in 2008 were analyzed in order to determine the effect of time series on the opening of a new line and economic impact. As a result, the financial crisis showed that there is no statistically significant impact, but the second phase of the Gyeongbu high-speed rail project showed that the weekday trips increased about 17,000 trips/day and the weekend trips increased about 26,000 trips/day. This study is meaningful in that the intervention explained the phenomena affecting the time series of KTX trip and analyzed the impact on intervention of time series quantitatively. The developed model can be used to forecast the outline of the overall KTX demand and to validate the KTX O/D forecasting demand.

• Journal of Digital Convergence
• /
• v.13 no.7
• /
• pp.169-175
• /
• 2015

An effective way to understand the dynamic and time series that follows the passage of time, as valuation is to establish a model to analyze the phenomena of the system. Model of the decision process is efficient clustering information of the total mass of the time series data of the relevant population been collected in a particular number of sub-groups than to look at all a time to an understand of the overall data through each community-specific model determination. In this study, a sub-grouping of the group and the first of the two process model of each cluster by determining, in the following in sub-population characterized by a fusion with heuristic Bayesian clustering techniques proposed a process which can reduce calculation time and cost was confirmed by experiments using actual effectiveness valuation.

• 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.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.5 no.3
• /
• pp.36-42
• /
• 2006

The analytical realization of uncoupled system was introduced in this study using times series and its spectrum analysis. The ARMAX spectra of time series methods were compared with the conventional FFT spectrum. Also, the response of second order system uncoupled was solved using the Runge-Kutta Gill method. In this numerical analysis, the displacement, velocity and acceleration were calculated. The displacement response among them was used for the power spectrum analysis. The ARMAX algorithm in time series was proved to be appropriate for the mode estimation and spectrum analysis. Using the separate response of first and second mode, each modes were calculated separately and the response of mixed modes was also analyzed for the mode estimation using several time series methods.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.2
• /
• pp.113-120
• /
• 2015

Technology analysis is to analyze technological data such as patent and paper for a given technology field. From the results of technology analysis, we can get novel knowledge for R&D planing and management. For the technology analysis, we can use diverse methods of statistics. Time series analysis is one of efficient approaches for technology analysis, because most technologies have researched and developed depended on time. So many technological data are time series. Time series data are occurred through time. In this paper, we propose a methodology of technology forecasting using the dynamic time warping (DTW) of time series analysis. To illustrate how to apply our methodology to real problem, we perform a case study of patent documents in target technology field. This research will contribute to R&D planning and technology management.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.890-892
• /
• 1996

This paper presents a method for optimal placement of series condenser in order to improve the power system transient stability using genetic algorithms(GAs). In applying GAs, this approach utilizes two kinds of strings, one is coded by a binary finite-length for the selection of lines to install series condenser, the other is coded by a real value for the determination of injected condenser capacitance. For the formulation. this paper considers multi-objective function which is the critical energy as decelerating energy in power systems and the total injected condenser capacitance. The proposed method is applied to 9-bus, 18-line, 3-machine model system to show its effectiveness in determining the locations to install series condenser and the series condenser capacitance to be injected, simultaneously.

• Annual Conference of KIPS
• /
• 2023.05a
• /
• pp.377-379
• /
• 2023

Concept drift detection on data stream is the major issue to maintain the performance of the machine learning model. Since the online stream is to be a function of time, the classical statistic methods are hard to apply. In particular case of seasonal time series, a novel window strategy with Fourier analysis however, gives a chance to adapt the classical methods on the series. We explore the KS-test for an adaptation of the periodic time series and show that this strategy handles a complicate time series as an ordinary tabular dataset. We verify that the detection with the strategy takes the second place in time delay and shows the best performance in false alarm rate and detection accuracy comparing to that of arbitrary window sizes.

• The Korean Journal of Applied Statistics
• /
• v.29 no.3
• /
• pp.525-537
• /
• 2016

The paper considers a hybrid model to analyze and forecast time series data based on an empirical mode decomposition (EMD) that accommodates complex characteristics of time series such as nonstationarity and nonlinearity. We aggregate IMFs using the concept of cumulative energy to improve the interpretability of intrinsic mode functions (IMFs) from EMD. We forecast aggregated IMFs and residue with a hybrid model that combines the ARIMA model and an exponential smoothing method (ETS). The proposed method is applied to forecast KOSPI time series and is compared to traditional forecast models. Aggregated IMFs and residue provide a convenience to interpret the short, medium and long term dynamics of the KOSPI. It is also observed that the hybrid model with ARIMA and ETS is superior to traditional and other types of hybrid models.