• Communications for Statistical Applications and Methods
• /
• v.18 no.3
• /
• pp.319-331
• /
• 2011

In this paper, we propose automatic procedures for the model selection of various univariate time series data. Automatic model selection is important, especially in data mining with large number of time series, for example, the number (in thousands) of signals accessing a web server during a specific time period. Several methods have been proposed for automatic model selection of time series. However, most existing methods focus on linear time series models such as exponential smoothing and autoregressive integrated moving average(ARIMA) models. The key feature that distinguishes the proposed procedures from previous approaches is that the former can be used for both linear time series models and nonlinear time series models such as threshold autoregressive(TAR) models and autoregressive moving average-generalized autoregressive conditional heteroscedasticity(ARMA-GARCH) models. The proposed methods select a model from among the various models in the prediction error sense. We also provide an R package autots that implements the proposed automatic model selection procedures. In this paper, we illustrate these algorithms with the artificial and real data, and describe the implementation of the autots package for R.

• Journal of Positioning, Navigation, and Timing
• /
• v.9 no.2
• /
• pp.89-98
• /
• 2020

Prediction of clock behaviors is necessary to generate very high stable system time which is essential for a satellite navigation system. For the purpose, we applied the Auto-Regressive Integrated Moving Average (ARIMA) model to the prediction of two hydrogen masers' behaviors with respect to the rapid Coordinated Universal Time (UTCr). Using the packaged programming language R, we made an analysis and prediction of time series data of [UTCr - clocks]. The maximum variation width of the residuals which were obtained by the difference between the predicted and measured values, was 6.2 ns for 106 days. This variation width was just one-sixth of [UTCr-UTC (KRIS)] published by the BIPM for the same period. Since the two hydrogen masers were found to be strongly correlated, we applied the Vector Auto-Regressive Moving Average (VARMA) model for more accurate prediction. The result showed that the prediction accuarcy was improved by two times for one hydrogen maser.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.7
• /
• pp.711-717
• /
• 2007

Location information will become increasingly important for future Pervasive Computing applications. Location tracking system of a moving device can be classified into two types of architectures: an active mobile architecture and a passive mobile architecture. In the former, a mobile device actively transmits signals for estimating distances to listeners. In the latter, a mobile device listens signals from beacons passively. Although the passive architecture such as Cricket location system is inexpensive, easy to set up, and safe, it is less precise than the active one. In this paper, we present a passive location system using Cricket Mote sensors which use RF and ultrasonic signals to estimate distances. In order to improve accuracy of the passive system, the transmission speed of ultrasound was compensated according to air temperature at the moment. Upper and lower bounds of a distance estimation were set up through measuring minimum and maximum distances that ultrasonic signal can reach to. Distance estimations beyond the upper and the lower bounds were filtered off as errors in our scheme. With collecting distance estimation data at various locations and comparing each distance estimation with real distance respectively, we proposed an equation to compensate the deviation at each point. Equations for proposed algorithm were derived to calculate relative coordinates of a moving device. At indoor and outdoor tests, average location error and average location tracking period were 3.5 cm and 0.5 second, respectively, which outperformed Cricket location system of MIT.

• The Journal of Information Systems
• /
• v.12 no.2
• /
• pp.1-20
• /
• 2003

This paper deals with the application of the genetic algorithm to the technical trading rule of the stock market. MACD(Moving Average Convergence & Divergence) and the Stochastic techniques are widely used technical trading rules in the financial markets. But, it is necessary to determine the parameters of these trading rules in order to use the trading rules. We use the genetic algorithm to obtain the appropriate values of the parameters. We use the daily KOSPI data of eight years during January 1995 and October 2002 as the experimental data. We divide the total experimental period into learning period and testing period. The genetic algorithm determines the values of parameters for the trading rules during the teaming period and we test the performance of the algorithm during the testing period with the determined parameters. Also, we compare the return of the genetic algorithm with the returns of buy-hold strategy and risk-free asset. From the experiment, we can see that the genetic algorithm outperforms the other strategies. Thus, we can conclude that genetic algorithm can be used successfully to the technical trading rule.

• Nuclear Engineering and Technology
• /
• v.49 no.4
• /
• pp.825-837
• /
• 2017

Due to the severe impacts of recent earthquakes, the use of seismic isolation is paramount for the safety of nuclear structures. The diversity observed in seismic events demands ongoing research to analyze the devastating attributes involved, and hence to enhance the sustainability of base-isolated nuclear power plants. This study reports the seismic performance of a seismically-isolated nuclear reactor containment building (NRCB) under strong short-period ground motions (SPGMs) and long-period ground motions (LPGMs). The United States Nuclear Regulatory Commission-based design response spectrum for the seismic design of nuclear power plants is stipulated as the reference spectrum for ground motion selection. Within the period range(s) of interest, the spectral matching of selected records with the target spectrum is ensured using the spectral-compatibility approach. NRC-compliant SPGMs and LPGMs from the mega-thrust Tohoku earthquake are used to obtain the structural response of the base-isolated NRCB. To account for the lack of earthquakes in low-to-moderate seismicity zones and the gap in the artificial synthesis of long-period records, wavelet-decomposition based autoregressive moving average modeling for artificial generation of real ground motions is performed. Based on analysis results from real and simulated SPGMs versus LPGMs, the performance of NRCBs is discussed with suggestions for future research and seismic provisions.

• Physical Therapy Korea
• /
• v.3 no.1
• /
• pp.73-79
• /
• 1996

Photochemotherapy(UVA with 8-methoxypsoralen) was given to 30 patients with systemic psoriasis. The results of clearing and long-term(6-month) interval maintenance were reported. Clearing requirements were in general similar to these reported by Melski and Burger. The skin of the 14 patients (46.6%) recovered good skin condition by a once weekly maintenance dose. This result was better than that reported by other authors. 1. During initial treatment period, average number of treatment was 27.3 and average duration treatment was 24.8 weeks. 2. The factors to quit treatment were motion decrease, moving to the remote area, complications, etc. 3. Number of patient who received maintenance treatment was 14. 4. The complications reported from the patients were hyperpigmentation, nausea, headache, pruritis, vomiting, gastritis.

• Journal of Intelligence and Information Systems
• /
• v.1 no.2
• /
• pp.103-121
• /
• 1995

This study proposes a artificial neural network method to predict the time to buy and sell the stocks listed on the Korea Composite Stock Price Index(KOSPI). Four types (NN1, NN2, NN3, NN4) of independent networks were developed to predict KOSPIs up/down direction after four weeks. These networks have a difference only in the length of learning period. NN5 - arithmetic average of four networks outputs - shows an higher accuracy than other network types and Multiple Linear Regression (MLR), and buying and selling simulation using systems outputs produces higher reture than buy-and-hold strategy.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.12 no.1
• /
• pp.799-809
• /
• 2020

In this study, the supercavitating flow of a high-velocity moving body near air-water surface is calculated and analyzed based on a commercial CFD software ANSYS Fluent. The effect of regular wave parameters including both wave height and wavelength on the cavitating flow and force characteristics of a body at different velocities is investigated. It is found that the cavity shape, lift coefficient and drag coefficient of the body vary periodically with wave fluctuation, and the variation period is basically consistent with wave period. When the wavelength is much greater than the cavity length, the effect of wave on supercavitation is the alternating effect of axial compression and radial compression. However, when the wavelength varies around the cavity length, the cavity often crosses two adjacent troughs and is compressed periodically by the two wave troughs. With the variation of wavelength, the average area of cavity shows a different trend with the change of wave height.

• Journal of Korea Water Resources Association
• /
• v.39 no.2 s.163
• /
• pp.121-126
• /
• 2006

Snowmelt effect is identified from the analysis of the relationship between precipitation and groundwater level(GWL) data and Severe drawdown of GWL is observed in drought. Groundwater dam Operation Index (GOI), which is developed for the optimal operation of groundwater dam, is calculated by taking common logarithm of the moving average(MA) of precipitation data for a certain period. The period can vary from watershed to watershed because the period is decided by picking the maximum correlation coefficient between GWL and GOI of several MAs of precipitation. For Ssangchun watershed, the correlation was the strongest when we apply 70 day MA for GOI calculation. Snowmelt effect is considered by applying the temperature change by elevation($0.5^{\circ}C$ decrease per 100m) and examining the areal distribution of the watershed by elevation. Snow event is assumed when the daily average temperature is below $0^{\circ}C$ and snowmelt is assumed when the temperature is above zero degree Celsius. Total snowmelt is assumed for the day. When the snow event is occurred the precipitation data is separated into two components, snow and rainfall. The areal distribution by elevation is used for the calculation in the separation. The correlation between GWL and GOI is higher when we consider snowmelt effect than we neglected it.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.1B
• /
• pp.21-27
• /
• 2011

When execute runoff forecasting, can not remove perfectly uncertainty of forecasting results. But, reduce uncertainty by various techniques analysis. This study applied various forecasting techniques for runoff prediction's accuracy elevation in Gongju basin. statics techniques is ESP, Period Average & Moving average, Exponential Smoothing, Winters, Auto regressive moving average process. Authoritativeness estimation with results of runoff forecasting by each techniques used MAE (Mean Absolute Error), RMSE (Root Mean Squared Error), RRMSE (Relative Root Mean Squared Error), Mean Absolute Percentage Error (MAPE), TIC (Theil Inequality Coefficient). Result that use MAE, RMSE, RRMSE, MAPE, TIC and confirm improvement effect of runoff forecasting, ESP techniques than the others displayed the best result.