• Title/Summary/Keyword: ARIMA 예측

Search Result 296, Processing Time 0.025 seconds

Prediction of water demand using deep learning and smart water meter (스마트 수도미터와 딥러닝을 활용한 수용가별 물 사용량 예측)

  • Kim, Jongsung;Song, Jaehyun
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2022.05a
    • /
    • pp.394-394
    • /
    • 2022
  • 최근 스마트 수도미터의 보급을 통해 수용가구별 물 사용 자료를 수집할 수 있다. 이런 수용가구별 물 사용 패턴은 주말, 날씨 등 다양한 요인으로 인해 비선형적 특성을 가지고 있다. 그로인해 전통적인 시계열 예측 모형인 ARIMA 모형으로 적용하기 어렵다. 따라서 본 연구에서는 딥러닝 기반의 LSTM 모형을 통해 수용가구별 물 소비량 예측 모형을 개발하였다. 이 모형은 비선형적인 물 소비 패턴을 학습하기 위해 다양한 변수를 고려하였다. 서로 다른 종류의 4개 type (A : 단독주택, B: 아파트, C: 음식점, D : 초등학교)의 수용가구에 대한 ARIMA 모형과 LSTM 모형을 개발하였고, 학습에 사용되지 않은 새로운 데이터를 적용하여 정량적으로 예측성능을 비교했다. 그 결과, 모든 수용가구에서 LSTM 모형이 ARIMA 모형보다 성능이 우수하였다 (상관계수 : 평균89% | RMSE : 평균 5.60m3). 따라서 본 연구에서 제안한 모형은 수용가구별 물 사용량을 예측하는데 높은 활용도를 보일 것으로 기대된다.

  • PDF

Time Series Analysis for Predicting Deformation of Earth Retaining Walls (시계열 분석을 이용한 흙막이 벽체 변형 예측)

  • Seo, Seunghwan;Chung, Moonkyung
    • Journal of the Korean Geotechnical Society
    • /
    • v.40 no.2
    • /
    • pp.65-79
    • /
    • 2024
  • This study employs traditional statistical auto-regressive integrated moving average (ARIMA) and deep learning-based long short-term memory (LSTM) models to predict the deformation of earth retaining walls using inclinometer data from excavation sites. It compares the predictive capabilities of both models. The ARIMA model excels in analyzing linear patterns as time progresses, while the LSTM model is adept at handling complex nonlinear patterns and long-term dependencies in the data. This research includes preprocessing of inclinometer measurement data, performance evaluation across various data lengths and input conditions, and demonstrates that the LSTM model provides statistically significant improvements in prediction accuracy over the ARIMA model. The findings suggest that LSTM models can effectively assess the stability of retaining walls at excavation sites. Additionally, this study is expected to contribute to the development of safety monitoring systems at excavation sites and the advancement of time series prediction models.

A Study on the Demand Forecasting and Efficient Operation of Jeju National Airport using seasonal ARIMA model (계절 ARIMA 모형을 이용한 제주공항 여객 수요예측 및 효율적 운영에 관한 연구)

  • Kim, Kyung-Bum;Hwang, Kyung-Soo
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.13 no.8
    • /
    • pp.3381-3388
    • /
    • 2012
  • This research is to find out the method appropriate for the forecasting of passennger demand using seasonal ARIMA model and efficient operation in Jeju National Airport. Time series monthly data for the investigation were collected ranging from January 2003 to December 2011. A total of 108 observations were used for data analysis. Research findings showed that the multiplicative seasonal ARIMA(0.1.2)(0.1.1)12 model is appropriate model. The number of passengers in Jeju National Airport will continue to rise, it was expected to surpass 20 million people.

Analysis and Prediction of Anchovy Fisheries in Korea ARIMA Model and Spectrum Analysis (한국 멸치어업의 어획량 분석과 예측 ARIMA 모델 및 스펙트럼 해석)

  • PARK Hae-Hoon;YOON Gab-Dong
    • Korean Journal of Fisheries and Aquatic Sciences
    • /
    • v.29 no.2
    • /
    • pp.143-149
    • /
    • 1996
  • Forecasts of the monthly catches of anchovy in Korea were carried out by the seasonal Autoregressive Integrated Moving Average (ARIMA) model and spectral analysis. The seasonal ARIMA model is as follows: $$(1-0.431B)(1-B^{12})Z_t=(1-0.882B^{12})e_t$$ where: $Z_t=value$ at month $t;\;B^{p}$ is a backward shift operator, that is, $B^pZ_t=Z_{t-p};$ and $e_t=error$ term at month t, which is to forecast 24 months ahead the anchovy catches in Korea. The prediction error by the Box-Cox transformation on monthly anchovy catches in Korea was less than that by the logarithmic transformation. The equation of the Box-Cox transformation was $Y'=(Y^{0.58}-1)/0.58$. Forecasts of the monthly anchovy catches for $1991\~1992$, which were compared with the actual catches, had an absolute percentage error (APE) range of $1.0\~63.2\%$. Total observed annual catches in 1991 and 1992 were 170,293 M/T and 168,234 M/T respectively, while the predicted catches were 148,201 M/T and 148,834 M/T $(API\;13.0\%\;and\;11.5\%,\;respectively)$. The spectrum analysis of the monthly catches of anchovy showed some dominant fluctuations in the periods of 2.2, 6.1, 10.2 12.0 and 14.7 months. The spectrum analysis was also useful for selecting the ARIMA model.

  • PDF

Prediction Algorithm of Threshold Violation in Line Utilization using ARIMA model (ARIMA 모델을 이용한 설로 이용률의 임계값 위반 예측 기법)

  • 조강흥;조강홍;안성진;안성진;정진욱
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.25 no.8A
    • /
    • pp.1153-1159
    • /
    • 2000
  • This paper applies a seasonal ARIMA model to the timely forecasting in a line utilization and its confidence interval on the base of the past data of the lido utilization that QoS of the network is greatly influenced by and proposes the prediction algorithm of threshold violation in line utilization using the seasonal ARIMA model. We can predict the time of threshold violation in line utilization and provide the confidence based on probability. Also, we have evaluated the validity of the proposed model and estimated the value of a proper threshold and a detection probability, it thus appears that we have maximized the performance of this algorithm.

  • PDF

Time Series Analysis and Development of Forecasting Model in Apartment House Cost Using X-12 ARIMA (X-12 ARIMA를 이용한 아파트 원가의 변동분석 및 예측모델 개발)

  • Cho, Hun-Hee
    • Korean Journal of Construction Engineering and Management
    • /
    • v.6 no.6 s.28
    • /
    • pp.98-106
    • /
    • 2005
  • The construction cost index and the forecasting model of apartment house can be efficient for evaluating the validness of the fluctuating price, and for making guidelines for construction firms when calculating their profit. In this study the previous construction cost index of apartment house was improved, and the forecasting model based on X-12 ARIMA was developed. According to the result, during the last five years the construction cost, excluding labor expense, has risen approximately to 22.7%. And during next three years, additional 16.8% rise of construction cost is expected. Those quantitative results can be utilized for evaluating the apartment house's selling price in an indirection, and be helpful to understand the variation pattern of the price.

Trend and Forecast of the Medical Care Utilization Rate, the Medical Expense per Case and the Treatment Days per Cage in Medical Insurance Program for Employees by ARIMA Model (ARIMA모델에 의한 피용자(被傭者) 의료보험(醫療保險) 수진율(受診率), 건당진료비(件當診療費) 및 건당진료일수(件當診療日數)의 추이(推移)와 예측(豫測))

  • Jang, Kyu-Pyo;Kam, Sin;Park, Jae-Yong
    • Journal of Preventive Medicine and Public Health
    • /
    • v.24 no.3 s.35
    • /
    • pp.441-458
    • /
    • 1991
  • The objective of this study was to provide basic reference data for stabilization scheme of medical insurance benefits through forecasting of the medical care utilization rate, the medical expence per case, and the treatment days per case in medical insurance program for government employees & private school teachers and for industrial workers. For the achievement of above objective, this study was carried out by Box-Jenkins time series analysis (ARIMA Model), using monthly statistical data from Jan. 1979 to Dec. 1989, of medical insurance program for government employees & private school teachers and for industrial workers. The results are as follows ; ARIMA model of the medical care utilization rate in medical insurance program for government employees & private school teachers was ARIMA (1, 1, 1) and it for outpatient in medical insurance program for industrial workers was ARIMA (1, 1, 1), while it for inpatient in medical insurance program for industrial workers was ARIMA (1, 0, 1). ARIMA model of the medical expense per case in medical insurance program for government employees & private school teachers and for outpatient in medical insurance program for industrial workers were ARIMA (1, 1, 0), while it for inpatient in medical insurance program for industrial workers was ARIMA (1, 0, 1). ARIMA model of the treatment days per case of both medical insurance program for government employees & private school teachers and industrial workers were ARIMA (1, 1, 1). Forecasting value of the medical care utilzation rate for inpatient in medical insurance program for government employees & private school teachers was 0.0061 at dec. 1989, 0.0066 at dec. 1994 and it for outpatient was 0.280 at dec. 1989, 0.294 at dec. 1994, while it for inpatient in medical insurance program for industrial workers was 0.0052 at dec. 1989, 0.0056 at dec. 1994 and it for outpatient was 0.203 at dec. 1989, 0.215 at 1994. Forecasting value of the medical expense per case for inpatient in medical insurance program for government employees & private school teachers was 332,751 at dec. 1989, 354,511 at dec. 1994 and it for outpatient was 11,925 at dec. 1989, 12,904 at dec. 1994, while it for inpatient in medical insurance program for industrial workers was 281,835 at dec. 1989, 293,973 at dec. 1994 and it for outpatient was 11,599 at dec. 1989, 11,585 at 1994. Forecasting value of the treatment days per case for inpatient in medical insurance program for government employees & private school teachers was 13.79 at dec. 1989,13.85 at an. 1994 and in for outpatient was 5.03 at dec. 1989, 5.00 at dec. 1994, while it for inpatient in medical insurance program for industrial workers was 12.23 at dec. 1989, 12.85 at dec. 1994 and it for outpatient was 4.61 at dec. 1989, 4.60 at 1994.

  • PDF

Design of ARIMA-Kalman Hybrid Model for SOH Prediction of High-Power Lithium-ion Battery (고출력 리튬이온 배터리의 SOH 예측을 위한 ARIMA-Kalman 하이브리드 모델의 설계)

  • Kim, Seungwoo;Lee, Pyeong-Yeon;Han, Dongho;Lee, Seong-Jun;Kim, Jonghoon
    • Proceedings of the KIPE Conference
    • /
    • 2019.11a
    • /
    • pp.210-211
    • /
    • 2019
  • 배터리의 안정적인 운영과 관리를 위해서 배터리의 SOH 예측은 매우 중요한 과제이다. 본 논문에서는 배터리 팩의 SOH를 예측하기 위한 ARIMA-Kalman 기반의 최적화된 하이브리드 방법을 소개한다.

  • PDF

Forecasting the Trading Volumes of Marine Transport and Ports Logistics Policy -Using Multiplicative Seasonal ARIMA Model- (해상운송의 물동량 예측과 항만물류정책 -승법 계절 ARIMA 모형을 이용하여-)

  • Kim, Chang-Beom
    • Journal of Korea Port Economic Association
    • /
    • v.23 no.1
    • /
    • pp.149-162
    • /
    • 2007
  • The purpose of this study is to forecast the marine trading volumes using multiplicative seasonal Autoregressive Integrated Moving Average(ARIMA) model. The paper proceeds by comparing the forecasting performances of the unload volumes with those of the load volumes with Box-Jenkins ARIMA model. Also, I present the predicted values based on the ARIMA model. The result shows that the trading volumes increase very slowly.

  • PDF

Application to Evaluation of Hydrologic Time Series Forecasting for Long-Term Runoff Simulation (장기유출모의를 위한 수문시계열 예측모형의 적용성 평가)

  • Yoon, Sun-Kwon;Ahn, Jae-Hyun;Kim, Jong-Suk;Moon, Young-Il
    • Journal of Korea Water Resources Association
    • /
    • v.42 no.10
    • /
    • pp.809-824
    • /
    • 2009
  • Hydrological system forecasting, which is the short term runoff historical data during the limited period in dam site, is a conditional precedent of hydrological persistence by stochastic analysis. We have forecasted the monthly hydrological system from Andong dam basin data that is the rainfall, evaporation, and runoff, using the seasonal ARIMA (autoregressive integrated moving average) model. Also we have conducted long term runoff simulations through the forecasted results of TANK model and ARIMA+TANK model. The results of analysis have been concurred to the observation data, and it has been considered for application to possibility on the stochastic model for dam inflow forecasting. Thus, the method presented in this study suggests a help to water resource mid- and long-term strategy establishment to application for runoff simulations through the forecasting variables of hydrological time series on the relatively short holding runoff data in an object basins.