• 한국수자원학회논문집
• /
• 제52권12호
• /
• pp.1075-1086
• /
• 2019

최근 기후 온난화의 발생과 이상기후의 발생빈도가 증가함에 따라 강수량, 하천유량과 같은 수문학적 요소의 예측이 복잡해지고 있으며 물부족 발생 위험도 증가하고 있다. 따라서 본 연구에서는 중단기 하천 취수량을 예측하기 위한 모델을 개발하고자 하였다. 입력인자를 선정하기 위해 취수량과 기상인자들 간의 상관성분석을 수행한 결과 온도가 가장 영향이 큰 것으로 나타났다. 또한 취수량은 시계열에 따른 증가 경향과 계절적 특성이 뚜렷하게 나타나므로 시계열분해기법을 이용하여 전처리를 수행하고 잔차에 대해 서포트 벡터 머신(SVM)을 적용하여 취수량 예측 모델을 개발하였다. 이 모델은 평균적으로 4.1%의 오차율을 나타내며, 전처리를 하지 않은 SVM 모델에 비해 높은 정확도를 나타냈다. 특히, 1~2달에 대해 중단기 예측을 수행하였을 때 더 유리한 결과를 나타냈다. 본 연구에서 개발된 취수량 예측모델은 수자원의 지속가능하고 효율적인 관리를 위해 하천수 사용허가, 수질관리, 가뭄 대책 마련에 활용이 가능할 것으로 예상된다.

• Communications for Statistical Applications and Methods
• /
• 제29권6호
• /
• pp.709-719
• /
• 2022

Recently, as the importance of environmental protection has emerged, interest in new and renewable energy is also increasing worldwide. In particular, the solar energy sector accounts for the highest production rate among new and renewable energy in Korea due to its infinite resources, easy installation and maintenance, and eco-friendly characteristics such as low noise emission levels and less pollutants during power generation. However, although climate prediction is essential since solar power is affected by weather and climate change, solar radiation, which is closely related to solar power, is not currently forecasted by the Korea Meteorological Administration. Solar radiation prediction can be the basis for establishing a reasonable new and renewable energy operation plan, and it is very important because it can be used not only in solar power but also in other fields such as power consumption prediction. Therefore, this study was conducted for the purpose of improving the accuracy of solar radiation. Solar radiation was predicted by a total of three weather variables, temperature, humidity, and cloudiness, and solar radiation outside the atmosphere, and the results were compared using various models. The CatBoost model was best obtained by fitting and comparing the Boosting series (XGB, CatBoost) and RNN series (Simple RNN, LSTM, GRU) models. In addition, the results were further improved through Time series cross-validation.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.1013-1016
• /
• 1993

This paper describes a new type of neuron model, the inputs of which are interfered with one another. It has a high mapping ability with only single unit. The learning speed is considerably improved compared with the conventional linear type neural networks. The proposed neuron model was successfully applied to the prediction problem of chaotic time series signal.

• 품질경영학회지
• /
• 제48권3호
• /
• pp.511-520
• /
• 2020

Purpose: The purpose of this study was to devise an accurate machine learning model for predicting silica concentrations following the addition of impurities, through time series analysis of mining data. Methods: The mining data were preprocessed and subjected to time series analysis using the machine learning model. Through correlation analysis, valid variables were selected and meaningless variables were excluded. To reflect changes over time, dependent variables at baseline were treated as independent variables at later time points. The relationship between independent variables and the dependent variable after n point was subjected to Pearson correlation analysis. Results: The correlation (R2) was strongest after 3 hours, which was adopted as a dependent variable. According to root mean square error (RMSE) data, the proposed method was superior to the other machine learning methods. The XGboost algorithm showed the best predictive performance. Conclusion: This study is important given the current lack of machine learning studies pertaining to the domestic mining industry. In addition, using time series analysis in mining data will show further improvement. Before establishing a predictive model for the proposed method, predictions should be made using data with time series characteristics. After doing this work, it should also improve prediction accuracy in other domains.

• 스마트미디어저널
• /
• 제13권6호
• /
• pp.24-34
• /
• 2024

시계열인 네트워크 트래픽 데이터로부터 미래를 예측할 수 있다면 효율적인 자원 배분, 악성 공격에 대한 예방, 에너지 절감 등의 효과를 거둘 수 있다. 통계 기법과 딥러닝 기법에 기반한 많은 모델이 제안되었는데, 이들 연구 대부분은 모델 구조와 학습 알고리즘을 개선하는 일에 치중하였다. 모델의 예측 성능을 높이는 또 다른 접근방법은 우수한 데이터를 확보하는 것이다. 이 논문은 우수한 데이터를 확보할 목적으로, 시계열 데이터를 증강하는 밀집 샘플링 기법을 네트워크 트래픽 예측 응용에 적용하고 성능 향상을 분석한다. 데이터셋으로는 네트워크 트래픽 분석에 널리 사용되는 UNSW-NB15를 사용한다. RMSE와 MAE, MAPE를 사용하여 성능을 분석한다. 성능 측정의 객관성을 높이기 위해 10번 실험을 수행하고 기존 희소 샘플링과 밀집 샘플링의 성능을 박스플롯으로 비교한다. 윈도우 크기와 수평선 계수를 변화시키며 성능을 비교한 결과 밀집 샘플링이 일관적으로 우수한 성능을 보였다.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2022년도 춘계학술대회
• /
• pp.391-393
• /
• 2022

최근에는 딥러닝과 빅데이터를 기반으로 한 수요예측 기술이 전자상거래, 물류, 유통 분야의 스마트화를 가속화하고 있다. 특히, 글로벌 운송 네트워크와 현대적인 지능형 물류의 중심인 항만은 4차 산업혁명으로 인한 세계 경제 및 항만 환경의 변화에 발 빠르게 대응하고 있습니다. 항만물동량 예측은 신항만 건설, 항만확장, 터미널 운영 등 다양한 분야에서 중요한 영향을 담당하고 있다. 따라서 본 연구의 목적은 항만 물동량 예측에 자주 쓰이는 시계열 분석과 타 산업에서 좋은 결과를 도출해내고 있는 딥러닝 분석을 비교하여 부산항의 미래 컨테이너 예측에 적합한 예측모델을 제시하는 것이다. 부산항 컨테이너 물동량을 이용하여 학습시키고 그 이후 물동량 예측을 진행하였다. 또한, 상관관계 분석을 통해 물동량 변화와 관련된 외부변수를 선정하여 다변량 딥러닝 예측모델에 적용하였다. 그 결과 부산항 컨테이너 물동량만 이용한 단일변수 예측모델에서 LSTM의 오차가 가장 낮았고, 외부변수를 이용한 다변수 예측모델에서도 LSTM의 성능이 가장 우수하였다.

• 산업경영시스템학회지
• /
• 제46권4호
• /
• pp.152-159
• /
• 2023

This study endeavors to enrich investment prospects in cryptocurrency by establishing a rationale for investment decisions. The primary objective involves evaluating the predictability of four prominent cryptocurrencies - Bitcoin, Ethereum, Litecoin, and EOS - and scrutinizing the efficacy of trading strategies developed based on the prediction model. To identify the most effective prediction model for each cryptocurrency annually, we employed three methodologies - AutoRegressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), and Prophet - representing traditional statistics and artificial intelligence. These methods were applied across diverse periods and time intervals. The result suggested that Prophet trained on the previous 28 days' price history at 15-minute intervals generally yielded the highest performance. The results were validated through a random selection of 100 days (20 target dates per year) spanning from January 1st, 2018, to December 31st, 2022. The trading strategies were formulated based on the optimal-performing prediction model, grounded in the simple principle of assigning greater weight to more predictable assets. When the forecasting model indicates an upward trend, it is recommended to acquire the cryptocurrency with the investment amount determined by its performance. Experimental results consistently demonstrated that the proposed trading strategy yields higher returns compared to an equal portfolio employing a buy-and-hold strategy. The cryptocurrency trading model introduced in this paper carries two significant implications. Firstly, it facilitates the evolution of cryptocurrencies from speculative assets to investment instruments. Secondly, it plays a crucial role in advancing deep learning-based investment strategies by providing sound evidence for portfolio allocation. This addresses the black box issue, a notable weakness in deep learning, offering increased transparency to the model.

• Journal of the Korean Data and Information Science Society
• /
• 제10권2호
• /
• pp.329-340
• /
• 1999

We consider a Bayesian forcasting method for the analysis of repeated surveys. It is assumed that the parameters of the superpopulation model at each time follow a stochastic model. We propose Bayesian prediction procedures for the finite population total under multiprocess dynamic generalized linear models. The multiprocess dynamic model offers a powerful framework for the modelling and analysis of time series which are subject to a abrupt changes in pattern. Some numerical studies are provided to illustrate the behavior of the proposed predictors.

• International Journal of Computer Science & Network Security
• /
• 제22권1호
• /
• pp.55-60
• /
• 2022

Churn prediction is a critical long-term problem for many business like music, games, magazines etc. The churn probability can be used to study many aspects of a business including proactive customer marketing, sales prediction, and churn-sensitive pricing models. It is quite challenging to design machine learning model to predict the customer churn accurately due to the large volume of the time-series data and the temporal issues of the data. In this paper, a parallel artificial neural network is proposed to create a highly-accurate customer churn model on a large customer dataset. The proposed model has achieved significant improvement in the accuracy of churn prediction. The scalability and effectiveness of the proposed algorithm is also studied.

• 상하수도학회지
• /
• 제11권1호
• /
• pp.109-118
• /
• 1997

In this study, we examined the structural analysis of water demand fluctuation for water distribution control of water supply network. In order to analyze for the length of stationary time series, we calculate autocorrelation coefficient of each case equally divided data size. As a result, it was found that, with the data size of around three months, any case could be used as stationary time series. we analyze cross-correlation coefficient between the daily water consumption's data and primary influence factors. As a result, we have decided to use weather conditions and maximum temperature as natural primary factors and holidays as a social factor. Applying the multiple ARIMA model, we obtains an effective model to describe the daily water demand prediction. From the forecasting result, even though we forecast water distribution quantity of the following year, estimated values well express the flctuations of measurements. Thus, the suitability of the model for practical use can be confirmed. When this model is used for practical water distribution control, water distribution quantity for the following day should be found by inputting maximum temperature and weather conditions obtained from weather forecast, and water purification plants and service reservoirs should be operated based on this information while operation of pumps and valves should be set up. Consequently, we will be able to devise a rational water management system.