• 물과 미래
• /
• 제12권2호
• /
• pp.63-69
• /
• 1979

The sequences of monthly streamflows constitute a non-statonary time series. The purely stochastic model has been applied to data generation of non-stationary time series. Tow different mothods--single site and multisite generation--have been used on the hydrologic time series. In this study the synthetic generation method by bivariate analysis, studied by Thomas Fiering, one of multi-site models, has been applied to the historical data on monthly streamflows at two sites in Nakdong River, and also for validity of this model the single site Thomas Fiering model applied. Through statistical analysis it has been shown that the performance of bivariate Thomas Fiering model was better than that of the other. By comparison of mean and standard deviaion between the historical and the generated, and cross correlogram interpretation, it has been known that the model used herein has good performance to simultaneously generate the monthly streamflows at two sites in a river hasin.

• 한국산업정보학회논문지
• /
• 제15권5호
• /
• pp.63-69
• /
• 2010

게임접속 시간의 예측은 서버접속의 폭주와 렉 현상의 예측을 통한 게임서비스 향상과 게임 매출의 예측에 매우 중요한 정보를 제공한다. 본 논문에서는 대표적 온라인 게임인 "아이온"과 "서든어택"의 2009년 PC방 접속시간 자료를 대상으로 다양한 시계열 분석 방법을 적용하여 접속시간 예측을 실험하였다. 실험결과 평균 게임접속시간의 예측에는 분해법이 실제 접속시간 데이터와 가장 유사한 결과를 보였다.

• 지능정보연구
• /
• 제5권1호
• /
• pp.103-123
• /
• 1999

Input filtering as a preprocessing method is so much crucial to get good performance in time series forecasting. There are a few preprocessing methods (i.e. ARMA outputs as time domain filters, and Fourier transform or wavelet transform as time-frequency domain filters) for handling time series. Specially, the time-frequency domain filters describe the fractal structure of financial markets better than the time domain filters due to theoretically additional frequency information. Therefore, we, first of all, try to describe and analyze specially some issues on the effectiveness of different filtering methods from viewpoint of the performance of a neural network based forecasting. And then we discuss about neural network model architecture issues, for example, what type of neural network learning architecture is selected for our time series forecasting, and what input size should be applied to a model. In this study an input selection problem is limited to a size selection of the lagged input variables. To solve this problem, we simulate on analyzing and comparing a few neural networks having different model architecture and also use an embedding dimension measure as chaotic time series analysis or nonlinear dynamic analysis to reduce the dimensionality (i.e. the size of time delayed input variables) of the models. Throughout our study, experiments for integration methods of joint time-frequency analysis and neural network techniques are applied to a case study of daily Korean won / U. S dollar exchange returns and finally we suggest an integration framework for future research from our experimental results.

• 전자통신동향분석
• /
• 제36권4호
• /
• pp.145-153
• /
• 2021

Data imputation is a crucial issue in data analysis because quality data are highly correlated with the performance of AI models. Particularly, it is difficult to collect quality time-series data for uncertain situations (for example, electricity blackout, delays for network conditions). Thus, it is necessary to research effective methods of time-series data imputation. Many studies on time-series data imputation can be divided into 5 parts, including statistical based, matrix-based, regression-based, deep learning (RNN and GAN) based methodologies. This study reviews and organizes these methodologies. Recently, deep learning-based imputation methods are developed and show excellent performance. However, it is associated to some computational problems that make it difficult to use in real-time system. Thus, the direction of future work is to develop low computational but high-performance imputation methods for application in the real field.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.952-954
• /
• 2003

In this paper, we present the different characteristics of NDVI fluctuation pattern between irrigated and non-irrigated area in Suphanburi province, in Central Thailand. For non-irrigated rice cultivation area, there is a strong correlation between NDVI fluctuation and peak rainfall, while there is a lower correlation with irrigated area. In this study, the 'peak detector' classifier was developed to identify the area of non-irrigated and irrigated cropping and its cropping intensity (number of crops per year). This classifier was created based on cropping characteristics such as number of crops, time or planting period of each crop and its relationship with the peak of rainfall. The classified result showed good accuracy in identification irrigated and nonirrigated rice cultivation areas.

• 한국가시화정보학회:학술대회논문집
• /
• 한국가시화정보학회 2002년도 추계학술대회 논문집
• /
• pp.77-80
• /
• 2002

The recent 3D visualization such as volume rendering, iso-surface rendering or stream line visualization gives more understanding about structures or distribution of data in a space and, moreover, the real-time rendering of a scene enables the animation of time-series data. Because the meteorological data is frequently formed as multi-variables, 3-dimensional and time-series data, the spatial analysis, time-series analysis, vector display, and animation techniques can do important roles to get more understanding about data. In this research, our aim is to develop the 3-dimensional visualization techniques for meteorological data in the PC environment by using IDL. The visualization technology from :his research will be used as basic technology not only for the deeper understanding and the more exact prediction about meteorological environments but also for the scientific and spatial data visualization research in any field from which three-dimensional data comes out such as oceanography, earth science, or aeronautical engineering.

• 한국수자원학회논문집
• /
• 제39권3호
• /
• pp.253-259
• /
• 2006

기존의 거의 모든 수문학적 연구에 있어서, 시스템의 특성을 파악한 뒤 예측을 실시하는 표준접근법이 채택되어왔다. 그러나 최근 들어 시스템의 특성분석에 앞서 예측을 실시하고, 상태공간 매개변수가 시스템의 특성분석단계가 아닌 예측단계에서 평가되는 가역접근법이 제안되었다. 본 연구에서는 최근에 제안된 가역접근법과 기존에 널리 적용되어온 표준접근법을 이론적 카오스 시계열과 Idaho주 Bear강의 일유출량 자료에 적용함으로써, 가역접근법의 적용성을 검토하고 카오스 시계열의 특성을 알아보았으며, 카오스이론이 적용된 비선형 예측기법으로는 부분근사화 기법을 이용하였다. 카오스 특성 분석을 통해, 이론적 카오스 시계열과 Idaho주 Bear강의 일유출량 시계열 자료 모두에서 카오스 특성이 나타남을 알 수 있었다. 200일에 대한 1, 3, 5일 예측 결과, 가역접근법이 표준접근법에 비해 우수함을 알 수 있었다.

• 대한치과교정학회지
• /
• 제47권5호
• /
• pp.298-305
• /
• 2017

Objective: This paper describes changes in the characteristics of patients seeking orthodontic treatment over the past decade and the treatment they received, to identify any seasonal variations or trends. Methods: This single-center retrospective cohort study included all patients who presented to Seoul National University Dental Hospital for orthodontic diagnosis and treatment between January 1, 2005 and December 31, 2015. The study analyzed a set of heterogeneous variables grouped into the following categories: demographic (age, gender, and address), clinical (Angle Classification, anomaly, mode of orthodontic treatment, removable appliances for Phase 1 treatment, fixed appliances for Phase 2 treatment, orthognathic surgery, extraction, mini-plate, mini-implant, and patient transfer) and time-related variables (date of first visit and orthodontic treatment time). Time series analysis was applied to each variable. Results: The sample included 14,510 patients with a median age of 19.5 years. The number of patients and their ages demonstrated a clear seasonal variation, which peaked in the summer and winter. Increasing trends were observed for the proportion of male patients, use of non-extraction treatment modality, use of ceramic brackets, patients from provinces outside the Seoul region at large, patients transferred from private practitioners, and patients who underwent orthognathic surgery performed by university surgeons. Decreasing trends included the use of metal brackets and orthodontic treatment time. Conclusions: Time series analysis revealed a seasonal variation in some characteristics, and several variables showed changing trends over the past decade.

• 한국경영과학회지
• /
• 제12권1호
• /
• pp.19-26
• /
• 1987

In analyzing time series, estimating the level or the current mean of the process plays an important role in understanding its structure and in being able to make forecasts. The studies the class of time series models where the level of the process is assumed to follow a random walk and the deviation from the level follow an ARMA process. The estimation and forecasting problem in a Bayesian framework and uses the Kalman filter to obtain forecasts based on estimates of level. In the analysis of time series, we usually make the assumption that the time series is generated by one model. However, in many situations the time series undergoes a structural change at one point in time. For example there may be a change in the distribution of random variables or in parameter values. Another example occurs when the level of the process changes abruptly at one period. In order to study such problems, the assumption that level follows a random walk process is relaxed to include a major level change at a particular point in time. The major level change is detected by examining the likelihood raio under a null hypothesis of no change and an alternative hypothesis of a major level change. The author proposes a method for estimation the size of the level change by adding one state variable to the state space model of the original Kalman filter. Detailed theoretical and numerical results are obtained for th first order autoregressive process wirth level changes.

• 한국환경과학회지
• /
• 제17권2호
• /
• pp.257-267
• /
• 2008

Groundwater recharge characteristics in a fractured granite area, Mt. Geumjeong, Korea. was interpreted using bedrock groundwater and wet-land water data. Time series analysis using autocorreclation, cross-correlation and spectral density was conducted for characterizing water level variation and recharge rate in low water and high water seasons. Autocorrelation analysis using water levels resulted in short delay time with weak linearity and memory. Cross-correlation function from cross-correlation analysis was lower in the low water season than the high water season for the bedrock groundwater. The result of water level decline analysis identified groundwater recharge rate of about 11% in the study area.