• 정보과학회 논문지
• /
• 제41권12호
• /
• pp.1066-1074
• /
• 2014

본 논문에서는 시공간 정보를 포함하는 트윗 스트림에서 비정상적인 이벤트에 대한 상관관계를 사용자에게 시각적으로 분석하는 방법을 다양한 실험을 통하여 제안한다. 제안하는 방법으로는 트윗에서 토픽 모델링을 수행한 다음 계절요인과 추세요인을 반영한 시계열 분석 기법을 이용하여 비정상적인 이벤트 후보군을 추출한다. 추출된 토픽이 포함되어 있는 데이터를 대상으로 다시 한 번 토픽을 추출하여 시계열 분석을 수행한 다음 앞서 추출한 토픽과의 상관관계를 분석하여 비정상적인 이벤트를 탐지할 수 있도록 하였다. 비정상 이벤트를 탐지하는 모든 과정에 시각적 분석 방법을 이용하여 단순한 수치 정보가 아닌 시각적 패턴 형태로 나타냄으로써 사용자는 직관적으로 비정상 이벤트의 동향과 주기적인 패턴을 분석할 수 있도록 하였다. 실험은 2014년 1월 1일부터 2014년 6월 30일까지 국내에서 발생한 트윗을 대상으로 2개의 사건[경주 마우나 리조트 붕괴 사건(2014.02.17.), 진도 여객선 침몰 사건(2014.04.16.)]에 대해 시각적 분석 시스템을 적용하여 사용자는 쉽게 데이터를 분석하고 이해할 수 있음을 보였다.

• 응용통계연구
• /
• 제19권2호
• /
• pp.319-330
• /
• 2006

현실세계에서 관찰되는 시그널(signal)은 다양한 주파수(frequency)들의 시그널로 혼합되어 있는 경우가 많다. 예를 들어 태양 흑점 자료의 경우 약 11년 주기와 85년 주기로 변동한다는 사실은 널리 알려져 있다. 또한 경제 시계열 자료의 경우는 통상적으로 계절요인(seasonal component), 순환요인(cyclic component) 그리고 장기적인 추세요인(long-term trend)으로 분해하여 분석한다. 이러한 시계열 자료를 구성요소별로 분해하는 것은 오래된 주제중 하나이다. 전통적인 시계열자료 분석기법으로 스펙트럴 분석기법 등이 널리 사용되고 있으나 시계열 자료들이 비정상(nonstationary)일 경우에는 적용하기 어렵다. Huang et. al(1998)은 경험적 모드분해법(empirical mode decomposition)이라고 하는 자료적응적인(data-adaptive) 방법을 제안하였는데, 비정상성(nonstationarity)에 대한 강건성(robustness)으로 여러 분야에 널리 응용되고 있다. 그러나 Huang et. at(1998)은 잡음(error)에 의해 오염된 자료에 대한 구체적인 처리방법은 제시하지 못하고 있다. 본 논문을 통하여 효율적인 잡음제거 방법을 제안하고자 한다.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2001년도 추계학술대회 논문집
• /
• pp.111-116
• /
• 2001

This paper introduces how to adopt the X-12-ARIMA to decompose the railway passenger demand of the Korea National Railroad Especially, selecting on proper filters is focused. The trend filter is identical to the low pass filter in the signal Processing field, and so the seasonal filter is to band pass filter too. Some considerations, selecting a filter, are provided from the view-point of the spectrum analysis. The technique introduced in this paper will be adopted to the project that is to develope the forecasting system of Korea railway passenger demand which is a part of the high speed rail information system.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2015년도 추계 학술논문 발표대회
• /
• pp.192-193
• /
• 2015

Construction Cycle Trend Survey, which survey total value of orders and realized amounts monthly, is a valuable statistics that used to quick grasp or forecast the trend of domestic construction business. In recent periodical survey quality diagnoses, few professional users named a problem that Construction Cycle Trend Survey could not get together with the current state of the construction industry. This study examined weather Construction Cycle Trend Survey reflects the economic sentiment of construction business or not. Paired t test was performed between Construction Cycle Trend Survey and Construction Business Survey Index (CBSI), and significant differences were verified.

• 한국물환경학회지
• /
• 제25권2호
• /
• pp.295-305
• /
• 2009

The purpose of this study was to understand of water quality characteristics of lake Paldang, especially at a certain representative site, right in front of Paldang dam ($P_2$ site) and to propose the directions of water quality management of lake Paldang. Water characteristics at $P_2$ site was investigated by principle components analysis and the Pearson correlation coefficient analysis. Also, seasonality was identified by the Kruskal-Wallis test and long term trend of nutrients and chlorophyll-a was analyzed by seasonal decomposition method at lake Paldang statistically. The primary factor affecting on water quality at $P_2$ site was identified as nutrients, while physical parameters, such as rainfall and inflow rate were also important factors. At the result of linear regression analysis particulate organic phosphorus (POP) vs total phosphorus (TP) showed very high correlation of 0.78. TP loading was increased annually from 1995 to 2006. Chlorophyll-a and nutrients show seasonality at $P_2$ site. Long term trend of Chlorophyll-a was increased by increase of TP at lake Paldang.

• 대기
• /
• 제21권2호
• /
• pp.143-149
• /
• 2011

A new multi-timescale analysis method, Ensemble Empirical Mode Decomposition (EEMD), is used to diagnose the variation of the MJO activity determined by 850hPa and 200hPa zonal winds from the National Centers for Environmental Prediction/National Center for Atmospheric Research (NCEP/NCAR) Reanalysis data for the 56-yr period from 1950 to 2005. The results show that MJO activity can be decomposed into 9 quasi-periodic oscillations and a trend. With each level of contribution of the quasi-periodic oscillation discussed, the bi-seasonal oscillation, the interannual oscillation and the trend of the MJO activity are the most prominent features. The trend increases almost linearly, so that prior to around 1978 the activity of the MJO is lower than that during the latter part. This may be related to the tropical sea surface temperature(SST). It is speculated that the interdecadal change in the MJO activity appeared in around 1978 is related to the warmer SST in the equatorial warm pool, especially over the Indian Ocean.

• 대기
• /
• 제34권2호
• /
• pp.107-121
• /
• 2024

In this study, we empirically analyzed the impact of physical risks due to climate change on the soundness and operational performance of the financial industry by combining economics and climatology. Particularly, unlike previous studies, we employed the Seasonal-Trend decomposition using LOESS (STL) method to extract trends of climate-related risk variables and economic-financial variables, conducting a two-stage empirical analysis. In the first stage estimation, we found that the delinquency rate and the Bank for International Settlement (BIS) ratio of commercial banks have significant negative effects on the damage caused by natural disasters, frequency of heavy rainfall, average temperature, and number of typhoons. On the other hand, for insurance companies, the damage from natural disasters, frequency of heavy rainfall, frequency of heavy snowfall, and annual average temperature have significant negative effects on return on assets (ROA) and the risk-based capital ratio (RBC). In the second stage estimation, based on the first stage results, we predicted the soundness and operational performance indicators of commercial banks and insurance companies until 2035. According to the forecast results, the delinquency rate of commercial banks is expected to increase steadily until 2035 under assumption that recent years' trend continues until 2035. It indicates that banks' managerial risk can be seriously worsened from climate change. Also the BIS ratio is expected to decrease which also indicates weakening safety buffer against climate risks over time. Additionally, the ROA of insurance companies is expected to decrease, followed by an increase in the RBC, and then a subsequent decrease.

• International Journal of Computer Science & Network Security
• /
• 제22권1호
• /
• pp.225-233
• /
• 2022

The recent outbreak of corona virus (COVID-19) infectious disease had made its forecasting critical cornerstones in most scientific studies. This study adopts a machine learning based time series model - Auto Regressive Integrated Moving Average (ARIMA) model to forecast COVID-19 confirmed cases in Botswana over 60 days period. Findings of the study show that COVID-19 confirmed cases in Botswana are steadily rising in a steep upward trend with random fluctuations. This trend can also be described effectively using an additive model when scrutinized in Seasonal Trend Decomposition method by Loess. In selecting the best fit ARIMA model, a Grid Search Algorithm was developed with python language and was used to optimize an Akaike Information Criterion (AIC) metric. The best fit ARIMA model was determined at ARIMA (5, 1, 1), which depicted the least AIC score of 3885.091. Results of the study proved that ARIMA model can be useful in generating reliable and volatile forecasts that can used to guide on understanding of the future spread of infectious diseases or pandemics. Most significantly, findings of the study are expected to raise social awareness to disease monitoring institutions and government regulatory bodies where it can be used to support strategic health decisions and initiate policy improvement for better management of the COVID-19 pandemic.

• Fisheries and Aquatic Sciences
• /
• 제2권2호
• /
• pp.199-209
• /
• 1999

Before investigating the long-term variations in macrobenthic communities sampled in the Chokchon macrotidal flat in Inchon, Korea, from 1989 to 1996, we need to understand how environmental factors in the area vary. As potential governing agents of tidal flat communities, abiotic factors such as mean sea level, seawater, air temperature, and precipitation were considered. Data for these factors were collected at equal intervals from 1976 or 1980 to 1996, and were analyzed using a decomposition method. In this analysis, all the above variables showed strong seasonal nature, and yielded a significant trend and cyclical variation. Positive trends were seen in the seawater and air temperatures, and based upon this relationship, it was found that the biological sampling period of our program has been carried out during warmer periods in succession. This paper puts forth some hypotheses concerning the response of tidal flat macrobenthos communities to the changing environment including mild winters in succession.

• 대한토목학회논문집
• /
• 제39권1호
• /
• pp.165-174
• /
• 2019

수문관측자료에서 비정상성(nonstationarity)이 관측됨에 따라 수공구조물 설계에서 비정상성 빈도해석에 대한 연구가 활발히 진행되고 있다. 대기-해양 시스템에 내재된 기후 변동성은 비정상성 현상과 관련이 있는 것으로 알려져 있지만, 비정상성 빈도해석은 일반적으로 선형적 추세를 기반으로 이루어지고 있다. 본 연구에서는 우리나라의 기후 변동성과 극치 강우 사상의 장기 경향성을 고려하기 위하여 기상인자를 활용한 비정상성 빈도해석을 수행하였다. 먼저, 경향성이 나타나는 11개 기상관측지점의 연 최대치 강우자료에 대하여 통계적 분해 방법인 앙상블 경험적 모드분해법을 활용해 자료에 내재된 장기 경향성을 추출하였으며, 계절에 따른 다양한 기상인자와의 상관성 분석을 수행하였다. 그 결과, 연 최대 강우 발생년도를 기준으로 전년도 가을철 AMM과 전년도 가을철 AMO, 그리고 전년도 여름철 NINO4가 10개 이상의 지점에서 연 최대치 강우자료의 장기 경향성에 유의한 영향을 미치는 것으로 나타났다. 선정된 기상인자를 일반 극치(generalized extreme value, GEV) 분포모형에 적용하여 비정상성 GEV (NS-GEV) 모형을 구축하고 기존의 선형적 추세를 고려한 NS-GEV 모형과의 AIC값을 비교하여 최적모형을 선정하였다. 선정된 모형과 기존의 선형적 추세를 고려한 NS-GEV 모형에 대한 성능 평가를 통해 기상인자를 활용한 NS-GEV 모형이 극치강우사상을 반영하여 확률강우량의 과소산정 문제를 보완할 수 있음을 확인하였다.