• 대한토목학회논문집
• /
• 제26권4B호
• /
• pp.355-362
• /
• 2006

본 연구에서는 수문 및 기후 시계열 자료에 존재하는 경향성을 분석하기 위하여 MK 검정, Spearman's Rho 검정, Linear Regression 검정, 비모수 Cusum 검정, Cumulative Deviation 검정, Worsley Likelihood Ratio 검정, Rank Sum 검정, Student's t 검정 등의 8가지 기법을 사용하였다. 관측된 연 강우량과 유입량 시계열 자료, 나이테 자료 그리고 SOI 자료에 적용하여 그 결과를 비교 분석 하였다. 분석 결과 시계열 자료에는 어떤 기울기를 가지거나 어느 시점을 기준으로 평균이 변화하는 두 가지의 경향성이 존재함을 확인 할 수 있었다. 경향성을 나타낸 8개의 강우자료중 4개 지점이 평균이동(shift)을 나타내었으며, 18개 지역의 나이테 지수중 8개 지역과 월별 SOI자료 중 3, 4월자료에서 경향성의 존재가 확인되었고, 소양강댐 유입량 자료에서는 경향성이 나타나지 않았다. 특히, 나이테 지수의 경우에는 평균이동으로 인한 경향성만을 가지고 있는 자료가 확인되었다. 또한 정상성 검정을 위한 ADF 검정과 비선형성 검정을 위한 BDS 통계검정 기법을 적용하였다. 본 연구를 통하여 여러 경향성 분석 기법을 비교할 수 있었으며, 실제 관측된 수문 및 기후 시계열에 존재하는 경향성을 확인 할 수 있었고, 연구 결과를 통하여 수문시계열 해석시 다양한 분석을 통한 경향성의 존재여부를 확인 하여야 한다는 것을 알 수 있었다.

• Journal of the Korean Data and Information Science Society
• /
• 제24권2호
• /
• pp.321-332
• /
• 2013

본 연구는 지속적인 저출산의 여파로 2020년에는 초등학생 수가 올해 대비 17%, 중고교생은 30%가 감소할 것이라는 예측을 가지고 초등학교 교원 수를 예측하기 위한 방법을 제시하는데 있다. 교육통계연보의 1970년부터 2010년까지의 초등교육 관련 주요 통계 자료를 이용하여 시계열 회귀모형과 시계열 그룹별 회귀모형, 지수평활법 모형을 제시하고, 제시된 모형을 이용하여 향후 10년간의 연도별 초등학교 교원 수를 예측하였다. 모형 예측 결과 시계열 그룹별 회귀 모형이 교원 수 시계열을 가장 잘 설명하는 것으로 나타났으며, 적합한 모형으로 판명되었다. 3가지 분석방법 모형에 따른 예측값에 대한 장단점과 한계를 제시한다.

• 한국지능시스템학회논문지
• /
• 제21권6호
• /
• pp.730-736
• /
• 2011

본 연구는 순차적인 시계열 자료들에서 가장 최근의 추세가 반영될 수 있는 패턴분류 모델을 설계하였다. 의사결정을 지원하는 데이터마이닝 패턴분류 모델을 설계할 때 통계 기법과 인공지능 기법을 융합한 모델들이 기존의 모델보다 우수함을 입증하였다. 특히 퍼지이론과 융합된 패턴분류 모델들의 적중률이 상대적으로 더 향상되었다. 예를 들어, 통계적 이론을 기반으로 한 SVM모델과 퍼지소속함수와의 결합, 혹은 신경망과 FCM을 결합한 모델들의 성능이 우수하였다. 실험에서 사용한 패턴분류 모델들은 BPN, PNN, FNN, FCM, SVM, FSVM, Decision Tree, Time Series Analysis, Regression Analysis 등이다. 그리고 데이터베이스는 시계열 속성을 지닌 금융시장의 경제지표 DB(한국, KOSPI200 데이터베이스)와 병원 응급실의 부정맥환자에 대한 심전도 DB(미국 MIT-BIH 데이터베이스)들을 사용하였다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume II
• /
• pp.764-767
• /
• 2006

It can be important framework data to monitor the change of land-use pattern of river boundary in design and management of river. This study analyzed the change of land-use pattern of Gab- and Yudeung River using time-series aerial images. To do this, we carried out radiation and geometric correction of image, and estimated land-use changes in inland and floodplain. As the analysis of inland, the ratio of residential, commercial, industrial, educational and public area, that is urbanized element, increases, but that of agricultural area shows a decline on the basis of 1990. Also, Minimum Distance Method, which is a kind of supervised classification method, is applied to extract water-body and sand bar layer in floodplain. As the analysis of land-use, the ratio of level-upped riverside land and water-body increases, but that of sand bar decreases. These time-series land use information can be important decision making data to evaluate the urbanization of river boundary, and especially it gives us goodness in river development project such as the composition of ecological habitat.

• 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.

• 한국해양공학회:학술대회논문집
• /
• 한국해양공학회 2000년도 추계학술대회 논문집
• /
• pp.118-122
• /
• 2000

In this study, Ringing is investigated by continuous wavelet transform. Ringing is considered to be one of the typical transient phenomena in the field of ocean engineering. The wavelet analysis is adopted to analyze ringing from the point that wavelet analysis is capable of frequency analysis as well as time domain analysis. The use mother wavelet is the Morlet wavelet. The relation between the frequency of the time series and that of wavelet can be clearly defined with Mor1et wavelet. Experimental data obtained by other researchers was used. The wave height time series and acceleration times series of the surface piercing cylinder were analyzed. The results show that the proposed scheme can detect typical frequency region by the time domain analysis which could hardly be detected if one relied on the frequency analysis.

• Smart Structures and Systems
• /
• 제22권2호
• /
• pp.175-183
• /
• 2018

Time-series data often contain one of the most valuable pieces of information in many fields including manufacturing. Because time-series data are relatively cheap to acquire, they (e.g., vibration signals) have become a crucial part of big data even in manufacturing shop floors. Recently, deep-learning models have shown state-of-art performance for analyzing big data because of their sophisticated structures and considerable computational power. Traditional models for a machinery-monitoring system have highly relied on features selected by human experts. In addition, the representational power of such models fails as the data distribution becomes complicated. On the other hand, deep-learning models automatically select highly abstracted features during the optimization process, and their representational power is better than that of traditional neural network models. However, the applicability of deep-learning models to the field of prognostics and health management (PHM) has not been well investigated yet. This study integrates the "residual fitting" mechanism inherently embedded in the wavelet transform into the convolutional neural network deep-learning structure. As a result, the architecture combines a signal smoother and classification procedures into a single model. Validation results from rotor vibration data demonstrate that our model outperforms all other off-the-shelf feature-based models.

• Communications for Statistical Applications and Methods
• /
• 제10권3호
• /
• pp.955-969
• /
• 2003

The classical Fourier analysis, which is the typical frequency domain approach, is used to detect periodic trends that are of the sinusoidal shape in time series data. In this article, using a sequence of periodic step functions, describes an adaptive Fourier series where the patterns may take general periodic shapes that include sinusoidal as a special case. The results, which extend both Fourier analysis and Walsh-Fourier analysis, are applies to investigate the shape of the periodic component. Through the real data, compare the goodness-of-fit of the model using two methods, the adaptive Fourier method which is proposed method in this paper and classical Fourier method.

• 품질경영학회지
• /
• 제31권3호
• /
• pp.160-171
• /
• 2003

Criteria for the comparison of quality of asset portfolio management are risk and return. In this paper a method to use structural time-series model to determine an optimal portfolio for the improvement of quality of asset portfolio management is suggested. In traditional mean variance analysis expected return is assumed to be time-invariant. However, it is more realistic to assume that expected return is temporally dynamic and structural time-series model can be used to reflect time-varying nature of return. A data set from an insurance company was used to show validity of suggested method.

• 웰빙융합연구
• /
• 제7권4호
• /
• pp.51-64
• /
• 2024

Purpose: This study analyzes factors influencing public interest in fermentation using Google search trends. Specifically, it examines how key elements such as oxygen, temperature, time, and pH influence fermentation-0related searches from December 2020 to September 2024. Research design, data and methodology: Data from Google Trends was collected under the Beauty & Fitness category for the terms "Fermentation," "Oxygen," "Temperature," "Time," and "pH." Time series analysis was used to track trends over four years, and a correlation analysis was conducted to assess the relationships between these terms. A linear regression model was built to determine the influence of each factor on fermentation-related searches. The dataset was split into 80% training data and 20% testing data for model validation. Results: The correlation analysis indicated moderate positive relationships between fermentation-related searches and both time and pH, while oxygen had little to no correlation. The regression model showed that time and pH were the strongest influencers of fermentation interest, explaining 25% of the variance (R-squared = 0.25). Oxygen and temperature had minimal impact in predicting fermentation-related search interest. Conclusions: Time and pH are significant factors influencing public interest in fermentation-related topics, as shown by search trends. In contrast, oxygen and temperature, while important in the fermentation process itself, did not strongly affect public search behavior. These findings provide valuable insights for businesses and researchers looking to better understand consumer interest in fermentation products.