• Title/Summary/Keyword: 시계열 분해

Search Result 237, Processing Time 0.026 seconds

The performance evaluation of dam management by using Granger causal analysis (그랜저 인과분석을 통한 댐관리 성과평가)

  • Cho, Sung-Min;Yoo, Myoung-Kwan;Lee, Deokro
    • Journal of Korea Water Resources Association
    • /
    • v.54 no.2
    • /
    • pp.135-144
    • /
    • 2021
  • This paper attempted to find implications for water resource management and water quality improvement by analyzing the causal relationship among discharge, water temperature and pollution index, which were expected to have a great effect on water quality with the rise of water temperature and precipitation change as the warming effect in recent years. For this purpose, the unit root test, cointegration test, and Granger causal test were carried out for 10 multi-purpose dams in Korean major water systems using time series data on discharge, water temperature, BOD, COD and DO. It was analyzed that the fluctuation of water temperature affected the pollution index more than the fluctuation of discharge volume. Also, Hapcheon dam and Chungju dam were the best water quality management dams based on the high causal relationship between water quality and discharge. The second rank was Daecheong dam. The third-ranking group were Yongdam and Andong dam, whose causal relationships between water quality and discharge were low. The last group were the remaining five dams.

Exploring performance improvement through split prediction in stock price prediction model (주가 예측 모델에서의 분할 예측을 통한 성능향상 탐구)

  • Yeo, Tae Geon Woo;Ryu, Dohui;Nam, Jungwon;Oh, Hayoung
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.26 no.4
    • /
    • pp.503-509
    • /
    • 2022
  • The purpose of this study is to set the rate of change between the market price of the next day and the previous day to be predicted as the predicted value, and the market price for each section is generated by dividing the stock price ranking of the next day to be predicted at regular intervals, which is different from the previous papers that predict the market price. We would like to propose a new time series data prediction method that predicts the market price change rate of the final next day through a model using the rate of change as the predicted value. The change in the performance of the model according to the degree of subdivision of the predicted value and the type of input data was analyzed.

A Study on the Variation of Daily Urban Water Demand Based on the Weather Condition (기후조건에 의한 상수도 일일 급수량의 변화에 관한 연구)

  • Lee, Gyeong-Hun;Mun, Byeong-Seok;Eom, Dong-Jo
    • Water for future
    • /
    • v.28 no.6
    • /
    • pp.147-158
    • /
    • 1995
  • The purpose of this study is to establish a method of estimating the daily urban water demand using statistical model. This method will be used for the development of the efficient management and operation of the water supply facilities. The data used were the daily urban water use, the population, the year lapse and the weather conditions such as temperature, precipitation, relative humidity, etc. Kwangju city was selected for the case study area. The raw data used in this study were rearranged either by month or by season for the purpose of analysis, and the statistical analysis was applied to the data to obtain the regression model. As a result, the multiple linear regression model was developed to estimate the daily urban water use based on the seather condition. The regression constant and the model coefficients were determined for each month of a year. The accuracy of the model was within 3% of average error and within 10% of maximum error. The developed model was found to be useful to the practical operation and management of the water supply facilities.

  • PDF

Goodwin's Growth Cycle Model and Functional Income Distribution in the Information Age of Korea: 1981~2016 (정보화 시대 한국의 기능적 소득분배와 Goodwin 성장순환모형: 1981~2016)

  • Jeong, Seungpil;Kwon, Oh-Bum
    • The Journal of Society for e-Business Studies
    • /
    • v.25 no.3
    • /
    • pp.63-76
    • /
    • 2020
  • In the 21st century, informatization is playing a huge role in people's lives. Korea is experiencing the tremendous changes in social structure and lifestyle caused by informatization. This paper focuses on economic phenomena rather than discussion on social structure due to informatization. We check whether the Goodwin model, which can comprehensively express economic growth, economic cycle, and income distribution, is suitable for the Korean economy in the information age. This model is simulated by selecting a quantitative economic methodology that estimates coefficients from time series data of the Korean economy. The simulation results confirmed that the Goodwin model is suitable for analyzing functional income distribution in Korea.

A Study on Price Discovery and Interactions Among Natural Gas Spot Markets in North America (북미 천연가스 현물시장간의 가격발견과 동태적 상호의존성에 대한 연구)

  • Park, Haesun
    • Environmental and Resource Economics Review
    • /
    • v.15 no.5
    • /
    • pp.799-826
    • /
    • 2006
  • Combining recent advances in causal flows with time series analysis, relationships among eight North American natural gas spot market prices are examined. Results indicate that price discovery tends to occur in excess demand regions and move to excess supply regions. Across North America, the U.S. Midwest region represented by Chicago spot market is the most important market for price discovery. The Ellisburg-Leidy Hub in Pennsylvania is important in price discovery, especially for markets in the eastern two-thirds of the U.S. Malin Hub in Oregon is important for the western markets including the AECO Hub in Alberta, Canada.

  • PDF

Study on the Development of Three-Dimensional Positioning System and Numerical Modeling of Fish Behavior III. Examination of the Numerical Model by the Field Experiment (3차원 어군행동 계측 시스템 개발과 어군 행동의 수치 모델링에 관한 연구 III. 현장실험에 의한 수치 모델의 검토)

  • 장호영;김동수;김영섭
    • Journal of the Korean Society of Fisheries and Ocean Technology
    • /
    • v.37 no.1
    • /
    • pp.18-23
    • /
    • 2001
  • In this paper, the several indexes represented by swimming characteristics of aquarcultured red seabream, Dchrysophrys majors in a farming water raft(10L×10W×5H) were measured by ultrasonic telemetry. The fishes tagged by pingers were tracked by the LBL method(Shin etc., 1994). The location of fishes were calculated by the hyperbolic method and the indexes were estimated by the least square method. The similarity was confirmed by the comparision between experiment and simulation on the swimming trajectory of fishes, the mean distance of individual from wall, the mean swimming speed and the mean distance between the nearest individuals. The obtained results are summerized as follows ; 1. The swimming trajectory of fishes tagged by the pingers and the swimming trajectory by the simulation for 120 minutes showed a simularity. 2. The mean swimming speed by the experiment and the simulation showed 39.2 ㎝/sec (1.4BL ㎝/sec) and 44.4 ㎝/sec (1.6BL ㎝/sec), respectively. 3. The mean swimming depth by the experiment and the simulation showed 238㎝ and 248 ㎝, respectively. 4. The mean distance of individuals from wall of the farming water raft by the experiment and the simulation showed 132 cm and 129 cm, respectively. 5. The mean distance between the nearest individuals by the experiment and the simulation showed 83 ㎝ and 61 ㎝, respectively.

  • PDF

Implementation of a Real-time Data Display System for a Catchment Scale Automated Weather Observation Network (집수역 규모 무인기상관측망을 위한 실황자료 표출시스템 구축)

  • Jung, Myung Ryong;Kim, Jin-Hee;Moon, Young Eel;Yun, Jin I.
    • Korean Journal of Agricultural and Forest Meteorology
    • /
    • v.15 no.4
    • /
    • pp.304-311
    • /
    • 2013
  • There have been increasing cases for farmers to install automated weather stations (AWS) at their farms and orchards in order to take countermeasures to more frequent weather disasters caused by climate variability and weather extremes. Although raw data are the same, the additive values as agrometeorological information may vary depending on data processing methods. User demands on appropriate information could also be different among crop species, cropping systems and even cultivars. We designed an internet based AWS data processing and display system to help diverse users (e.g., farmers), extension workers to access their weather data on specific demands. The system was implemented at a rural catchment with 52 $km^2$ land area where 14 automated weather stations are in operation. This note introduces the system and describes the major modules in detail. By linking regional AWS networks, a feasibility for this system as an early warning system is also discussed.

An Empirical Estimation on Contributions of Education Level to Economic Growth by (한국의 교육이 경제성장에 미친 영향 분석;내생성장모형과 $1975{\sim}'04$년간 자료를 이용하여)

  • Jang, Chang-Won
    • Proceedings of the Population Association of Korea Conference
    • /
    • 2006.12a
    • /
    • pp.113-128
    • /
    • 2006
  • The main theme of this paper was to investigate the role of education as a source of economic growth in Korea. In this study, first, the objective mode was built by extending neoclassical Solow growth theory. Second, the capital deepening typical of an endogenous economic per-capita growth model was developed empirically for seven East-Asian economies as for the medium term, during $1975{\sim}2004$. And then we found the meaning of coefficients of growth factors, direct relative contribution of each input to per-capita growth in seven East-Asian countries, relative indirect contribution of education to per-capita growth in Korea, accounting for difference due to accumulation in Korea. The indirect relative contributions of secondary and higher education and R&D to per-capita growth change the results somewhat. Secondary education is still the largest single contributor 83.6 percent of predicted growth is due to secondary school enrollment in Korea. Primary education comes second with 37.5 percent and followed by higher education at -52.9 percent. Physical investment gives 62.3 percent and unimproved raw labor contributes only -1.4 percent.

  • PDF

The Usefulness of a Wearable Smart Insole for Gait and Balance Analyses After Surgery for Adult Degenerative Scoliosis: Immediate and Delayed Effects (척추측만증 환자의 수술 효과 평가 수단으로서 웨어러블 스마트 깔창을 이용한 보행분석의 유용성)

  • Seo, Min Seok;Shin, Myung Jun;Kwon, Ae Ran;Park, Tae Sung;Nam, Kyoung Hyup
    • Journal of Convergence for Information Technology
    • /
    • v.10 no.2
    • /
    • pp.184-192
    • /
    • 2020
  • This study presents a gait analysis method (including time series analysis) using a smart insole as an objective and quantitative evaluating method after lumbar scoliosis surgery. The participant is a degenerative lumbar scoliosis patient. She took 3-min-gait-test four times(before and 8, 16, and 204-days after surgery) and 6-min-gait-test once(204-days after surgery) with smart-insoles in her shoes. Each insole has 8-pressure sensors, an accelerometer, and a gyroscope. The measured values were used to compare the characteristics of gait before and after surgery. The analysis showed that all of the patient's gait parameters improved after surgery. And after 6 months, the gait was more stable. However, after long walk, the swing duration of one leg was slightly shorter than that of the other again. It was a preclinical problem that could not be found in the visual examination by the practitioner. With this analysis method we could evaluate the improvement of patient quantitatively and objectively. And we could find a preclinical problem. This analysis method will lead to the studies that define and distinguish gait patterns of certain diseases, helping to determine appropriate treatments.

Development the Geostationary Ocean Color Imager (GOCI) Data Processing System (GDPS) (정지궤도 해색탑재체(GOCI) 해양자료처리시스템(GDPS)의 개발)

  • Han, Hee-Jeong;Ryu, Joo-Hyung;Ahn, Yu-Hwan
    • Korean Journal of Remote Sensing
    • /
    • v.26 no.2
    • /
    • pp.239-249
    • /
    • 2010
  • The Geostationary Ocean Color Imager (GOCI) data-processing system (GDPS), which is a software system for satellite data processing and analysis of the first geostationary ocean color observation satellite, has been developed concurrently with the development of th satellite. The GDPS has functions to generate level 2 and 3 oceanographic analytical data, from level 1B data that comprise the total radiance information, by programming a specialized atmospheric algorithm and oceanic analytical algorithms to the software module. The GDPS will be a multiversion system not only as a standard Korea Ocean Satellite Center(KOSC) operational system, but also as a basic GOCI data-processing system for researchers and other users. Additionally, the GDPS will be used to make the GOCI images available for distribution by satellite network, to calculate the lookup table for radiometric calibration coefficients, to divide/mosaic several region images, to analyze time-series satellite data. the developed GDPS system has satisfied the user requirement to complete data production within 30 minutes. This system is expected to be able to be an excellent tool for monitoring both long-term and short-term changes of ocean environmental characteristics.