• The Korean Journal of Applied Statistics
• /
• v.29 no.1
• /
• pp.193-203
• /
• 2016

This paper forecasts electricity demand as a critical element of a demand management system in Smart Grid environment. We present a prediction method of using a combination of predictive values by time series clustering. Periodogram-based normalized clustering, predictive analysis clustering and dynamic time warping (DTW) clustering are proposed for time series clustering methods. Double Seasonal Holt-Winters (DSHW), Trigonometric, Box-Cox transform, ARMA errors, Trend and Seasonal components (TBATS), Fractional ARIMA (FARIMA) are used for demand forecasting based on clustering. Results show that the time series clustering method provides a better performances than the method using total amount of electricity demand in terms of the Mean Absolute Percentage Error (MAPE).

• Journal of the Korean Data and Information Science Society
• /
• v.10 no.2
• /
• pp.485-500
• /
• 1999

The systematic forecast of interest rates with liberalization was on the rise to important problems in the money market. Liberalization and globalization of the money market produced a seriously change as a compatition among the money market. Profits of an organ of monetary circulation are, also, definitively influenced by a change of interest rates. Hence most of the organ of monetary circulation studied to a scientific and systematic analysis for deterministic factors which have an effect on interest rates and progress development of a forecasting model of interest rates. In this paper, we develope the forecasting system which has highly forecasting performance based on a number of time series models for interest rates and discuss practical use of this system.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.9
• /
• pp.2470-2478
• /
• 1999

In this paper, algorithm is proposed to forecast line utilization using SNMP MIB-II. We calculate line utilization using SNMP MIB-II on TCP/IP based Internet and suggest a method for forecasting a line utilization on the basis of past line utilization. We use a MA model taking difference transform among ARIMA methods. A system for orecasting is proposed. To show availability of this algorithm, some results are shown and analyzed about routers on real environments. We get a future line utilization using this algorithm and compare it ot real data. Correct results are obtained in case of being few data deviating from mean value. This algorithm for forecasting line utilization can give effect to line c-apacity plan for a manager by forecasting the future status of TCP/IP network. This will also help a network management of decision making of performance upgrade.

• Convergence Security Journal
• /
• v.24 no.2
• /
• pp.151-160
• /
• 2024

In recent years with high interest rates and inflations, which worsen people's lives, voice phishing crimes also increase along with damage. Voice phishing that becomes more evolved by technology developments causes serious financial and mental damage to victims. This work aims to study time series models for its accurate prediction. ARIMA, SARIMA and SARIMAX models are compared. As exogenous variables, the amount of damages and the numbers of arrests and criminals are adopted. Forecasting performances are evaluated. Prediction intervals are constructed along with empirical coverages, which justify the superiority of the model. Finally, the numbers of voice phishing up to December 2024 are predicted, through which we expect the establishment of future prevention strategies for voice phishing.

• Journal of Urban Science
• /
• v.7 no.1
• /
• pp.45-54
• /
• 2018

The purpose of this study is to find the factors that reduce prediction error in traffic volume using highway traffic volume data. The ARIMA model was used to predict the day, and it was confirmed that weekday and weekly characteristics were distinguished by prediction error. The forecasting results showed that weekday characteristics were prominent on Tuesdays, Wednesdays, and Thursdays, and forecast errors including MAPE and MAE on Sunday were about 15% points and about 10 points higher than weekday characteristics. Also, on Friday, the forecast error was high on weekdays, similar to Sunday's forecast error, unlike Tuesday, Wednesday, and Thursday, which had weekday characteristics. Therefore, when forecasting the time series belonging to Friday, it should be regarded as a weekly characteristic having characteristics similar to weekend rather than considering as weekday.

• Nuclear Engineering and Technology
• /
• v.52 no.6
• /
• pp.1334-1339
• /
• 2020

This paper presents an empirical and comprehensive forecasting analysis of the uranium price. Prices are generally difficult to forecast, and the uranium price is not an exception because it is affected by many external factors, apart from imbalances between demand and supply. Therefore, a systematic analysis of multiple forecasting methods and combinations of them along repeated forecast origins is a way of discerning which method is most suitable. Results suggest that i) some sophisticated methods do not improve upon the Naïve's (horizontal) forecast and ii) Unobserved Components methods are the most powerful, although the gain in accuracy is not big. These two facts together imply that uranium prices are undoubtedly subject to many uncertainties.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.35 no.2
• /
• pp.106-112
• /
• 2012

Real-life time series characteristic data has significant amount of non-stationary components, especially periodic components in nature. Extracting such components has required many ad-hoc techniques with external parameters set by users in case-by-case manner. In our study, we evaluate whether Hilbert-Huang Transform, a new tool of time-series analysis can be used for effective analysis of such data. It is divided into two points : 1) how effective it is in finding periodic components, 2) whether we can use its results directly in detecting values outside control limits, for which a traditional method such as ARIMA had been used. We use glass furnace temperature data to illustrate the method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.7
• /
• pp.625-637
• /
• 2020

In order to decide the naval ship weapon system acquisition for national policy/market economy activities, the decision makers can determine policy based on current technology level/concentration/utilization. For this, the decision makers apply the major common technology field analysis using patents data. As a method for collecting patent data, we can collect patent data of domestic mobile carriers through the Korea Intellectual Property Rights Information System of Korean Intellectual Property Office. As a result, we collected 14,964 patents/352 International Patent Classification(IPC) types. Based on these data, we performed three analysis processes (SNA, PCA, ARIMA, Text Mining) and got each result from extracting 58 IPC types of SNA and 7 IPC types of PCA. Based on the analysis results, we have confirmed that 7 IPC(B63B, H01M, F03D, B01D, H02K, B23K, H01H) types are the Major Common Technology Distribution of domestic Defense Companies.

• Journal of the military operations research society of Korea
• /
• v.37 no.1
• /
• pp.39-48
• /
• 2011

To predict the shelf-life of ammunition stockpiled in intermediate have practical meaning as a core value of combat support. This research is to Predict the shelf-life of ammunition by applying time series analysis based on report from ASRP of the 155mm, KD541 performed for 6 years. This study applied time series analysis using 'Mini-tab program' to measure the amount of stabilizer as time passes by is different from the other one that uses regression analysis. The average shelf-life of KD541 drawn by time series analysis was 43 years and the lowest shelf-life assessed on the 95% confidence level was 35 years.

• The Korean Journal of Applied Statistics
• /
• v.32 no.1
• /
• pp.149-160
• /
• 2019

The electricity consumption time series data of 'A' University from July 2016 to June 2017 is analyzed via nonparametric functional data clustering since the time series data can be regarded as realization of continuous functions with dependency structure. We use a Bouveyron and Jacques (Advances in Data Analysis and Classification, 5, 4, 281-300, 2011) method based on model-based functional clustering with an FEM algorithm that assumes a Gaussian distribution on functional principal components. Clusterwise analysis is provided with cluster mean functions, densities and cluster profiles.