• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2000년도 추계정기학술대회:지능형기술과 CRM
• /
• pp.489-497
• /
• 2000

After IMF situation, the money market environment is changing rapidly. Therefore, many companies including financial institutions and many individual investors are concerned about forecasting the money market, and they make an effort to insure the various profit and hedge methods using derivatives like option, futures and swap. In this research, we developed a prototype of forecasting system for KOSPI 200 option, especially call option, trading using artificial neural networks(ANN), To avoid the overfitting problem and the problem involved int the choice of ANN structure and parameters, we employed the ANN ensemble approach. We conducted two types of simulation. One is conducted with the hold signals taken into account, and the other is conducted without hold signals. Even though our models show low accuracy for the sample set extracted from the data collected in the early stage of IMF situation, they perform better in terms of profit and stability than the model that uses only the theoretical price.

• 한국지능시스템학회논문지
• /
• 제14권5호
• /
• pp.533-538
• /
• 2004

본 논문은 뉴로-퍼지 모델의 구조 학습을 이용하여 단기 전력 수요 예측시스템을 개발하기 위한 체계적인 방법을 제안한다. 제안된 단기 수요 예측시스템은 1시간, 24시간, 168시간의 예측 리드 타임을 갖고 예측을 수행하기 위해서 요일 유형과 시간 별로 총 96개의 초기 구조를 미리 생성하고, 이를 초기 구조 뱅크에 저장한다. 예측이 수행되는 시점에 해당하는 초기구조를 선택하여 뉴로-퍼지 모델을 초기화하고, 학습하고, 예측을 수행한다. 제안된 예측시스템은 단지 2개의 입력 변수만을 이용하기 때문에 간단한 모델 구조를 가질 뿐 아니라 학습된 퍼지 규칙을 해석하는 것이 매우 용이하다는 장점을 갖는다. 제안된 방법의 실효성을 검증하기 위해 1996년과 1997년의 한극전력의 실제 전력 수요 데이터를 이용하여 1시간, 24시간, 168시간 앞의 전력 수요를 예측하는 모의 실험을 수행한다. 실험 결과 제안된 방법은 단지 2개의 입력 변수를 사용함에도 불구하고, 기존의 예측 방법과 비교하여 예측의 정확도와 신뢰도 측면에서 우수한 성능을 얻는다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2016년도 학술발표회
• /
• pp.259-259
• /
• 2016

This study examined Artificial Neurons Networks model (ANNs) for forecast flash discharge at Southern part of Thailand by using rainfall data and discharge data. The Sungai Kolok River Basin has meant the border crossing between Thailand and Malaysia which watershed drains an area lies in Thailand 691.88 square kilometer from over all 2,175 square kilometer. The river originates in mountainous area of Waeng district then flow through Gulf of Thailand at Narathiwat Province, which the river length is approximately 103 kilometers. Almost every year, flooding seems to have increased in frequency and magnitude which is highly non-linear and complicated phenomena. The purpose of this study is to forecast runoff on Sungai Kolok at X.119A gauge station (Sungai Kolok district, Narathiwat province) for 3 days in advance by using Artificial Neural Networks model (ANNs). 3 daily rainfall stations and 2 daily runoff station have been measured by Royal Irrigation Department and Meteorological Department during flood period 2000-2014 were used as input data. In order to check an accuracy of forecasting, forecasted runoff were compared with observed data by pursuing Coefficient of determination ($R^2$). The result of the first day gets the highest accuracy and then decreased in day 2 and day 3, consequently. $R^2$values for first day, second day and third day of runoff forecasting is 0.71, 0.62 and 0.49 respectively. The results confirmed that the ANNs model can be used when the range of collected dataset is short and real-time operated. In conclusion, the ANNs model is suitable to runoff forecasting during flood incident of Sungai Kolok river because it is straightforward model and require with only a few parameters for simulation.

• 한국농공학회논문집
• /
• 제63권1호
• /
• pp.11-25
• /
• 2021

The objective of this study was to analyze the impact of activation functions on flood forecasting model based on Artificial neural networks (ANNs). The traditional activation functions, the sigmoid and tanh functions, were compared with the functions which have been recently recommended for deep neural networks; the ReLU, leaky ReLU, and ELU functions. The flood forecasting model based on ANNs was designed to predict real-time runoff for 1 to 6-h lead time using the rainfall and runoff data of the past nine hours. The statistical measures such as R2, Nash-Sutcliffe Efficiency (NSE), Root Mean Squared Error (RMSE), the error of peak time (ETp), and the error of peak discharge (EQp) were used to evaluate the model accuracy. The tanh and ELU functions were most accurate with R2=0.97 and RMSE=30.1 (㎥/s) for 1-h lead time and R2=0.56 and RMSE=124.6~124.8 (㎥/s) for 6-h lead time. We also evaluated the learning speed by using the number of epochs that minimizes errors. The sigmoid function had the slowest learning speed due to the 'vanishing gradient problem' and the limited direction of weight update. The learning speed of the ELU function was 1.2 times faster than the tanh function. As a result, the ELU function most effectively improved the accuracy and speed of the ANNs model, so it was determined to be the best activation function for ANNs-based flood forecasting.

• 한국산림과학회지
• /
• 제84권2호
• /
• pp.121-130
• /
• 1995

미국 미시간주의 여행수요(旅行需要)를 예측(豫測)하기 위하여 사용되어진 여러 모델들의 예측정확성(豫測正確性)이 검토되었다. 8가지의 연년(連年)모델들은 2년까지 예측하는데 그리고 9가지의 분기(分期)모델들은 4분기(分期)까지 예측하는데 사용되어 졌다. 연년(連年)모델의 예측정확성(豫測正確性) 평가(評價)에서, 중회귀(重回歸)모델은 1년과 2년을 예측(豫測)하는데 있어 다른 방법들 보다 더 정확(正確)했다. 분기(分期)모델에 있어서는, Winters' exponential smoothing와 Box-Jenkins 방법이 1 분기예측(分期豫測)에 있어 naive 1 s 보다 더 정확(正確)했으나 2분기(分期), 3분기(分期), 4분기(分期)를 예측(豫測)하는데 이 방법(方法)들은 naive 1 s 보다 정확(正確)하지 않았다. 정교(精巧)한 모델들은 분기별(分期別) 예측(豫測)을 하는데 있어서 단순(單純)한 모델들보다 더 정확(正確)하지 않았다. 연년(連年)모델과 분기(分期)모델을 이용한 1년간(年間) 예측비교(豫測比較)에서, 중회귀모형(重回歸模型)은 연간자료(年間資料)보다 분기자료(分期資料)에 적용(適用)할 때 더 좋은 결과(結果)를 얻었으나 그 차이(差異)가 미약(微弱)하며 다른 모델들은 일관성(一貫性)있게 좋은 결과(結果)를 갖지 않으므로 연년(連年)모델보다 分期모델을 사용하도록 강력하게 권장할 수 없다. 연년(連年)모델은 기대(期待)하였던 것처럼 예측기간(豫測期間)이 길어짐으로서 예측정확성(豫測正確性)이 감소(減少)하였으나 분기(分期)모델은 이같은 결과(結果)를 나타내지 않았다.

• International Journal of Computer Science & Network Security
• /
• 제23권8호
• /
• pp.190-198
• /
• 2023

To enhance customer satisfaction for higher profits, an e-commerce sector can establish a continuous relationship and acquire new customers. Utilize machine-learning models to analyse their customer's behavioural evidence to produce their competitive advantage to the e-commerce platform by helping to improve overall satisfaction. These models will forecast customers who will churn and churn causes. Forecasts are used to build unique business strategies and services offers. This work is intended to develop a machine-learning model that can accurately forecast retainable customers of the entire e-commerce customer data. Developing predictive models classifying different imbalanced data effectively is a major challenge in collected data and machine learning algorithms. Build a machine learning model for solving class imbalance and forecast customers. The satisfaction accuracy is used for this research as evaluation metrics. This paper aims to enable to evaluate the use of different machine learning models utilized to forecast satisfaction. For this research paper are selected three analytical methods come from various classifications of learning. Classifier Selection, the efficiency of various classifiers like Random Forest, Logistic Regression, SVM, and Gradient Boosting Algorithm. Models have been used for a dataset of 8000 records of e-commerce websites and apps. Results indicate the best accuracy in determining satisfaction class with both gradient-boosting algorithm classifications. The results showed maximum accuracy compared to other algorithms, including Gradient Boosting Algorithm, Support Vector Machine Algorithm, Random Forest Algorithm, and logistic regression Algorithm. The best model developed for this paper to forecast satisfaction customers and accuracy achieve 88 %.

• 한국수자원학회논문집
• /
• 제44권10호
• /
• pp.843-851
• /
• 2011

수문학 분야에서 중장기 유출량 예측은 입력변수의 불확실성 등으로 인하여 확률론적 방법을 사용하는 것이 바람직한 것으로 알려져 왔다. 본 연구에서는 금강유역을 대상으로 구성된 바 있는 RRFS-ESP 시스템에 PDF-ratio 방법을 기반으로한 사전처리기능을 장착하여 보다 효율적인 중장기 예측시스템으로의 확장을 시도하여 보았다. 이를 위하여 기상청에서 제공하는 확률기상정보를 이용하여 가중치를 산정하고 이를 기반으로 시나리오별 예측확률을 갱신하였다. 예측결과에 대하여 각 기법별 예측점수를 산정하여 본 결과 우선 ESP 기법에 의한 예측점수의 평균이 초보예측 점수를 상회하여 본 연구에서 구성한 RRFS-ESP 시스템의 적용성을 확인할 수 있었다. 또한 확률기상전망을 이용하여 갱신한 유입량 시나리오의 예측점수가 ESP 기법에 의한 예측점수를 상회하고 있음을 확인할 수 있어 ESP 기법에 의한 예측결과를 확률기상전망을 이용하여 갱신할 경우 예측 정확도를 보다 개선시킬 수 있음을 확인할 수 있었다.

• 한국수자원학회논문집
• /
• 제44권7호
• /
• pp.523-536
• /
• 2011

본 연구의 목적은 중소하천에서의 홍수예측을 위해 사용되는 기존의 수문학적 모형이 가지고 있는 문제점을 개선한 홍수예측 모형을 개발하는데 있다. 이를 위해 기존의 수문학적 강우-유출 모형에서 사용되는 많은 수문학적 자료 및 매개변수들의 사용 없이 오직 수위 및 강우측정 자료만을 이용하여 홍수를 예측할 수 있는 Takagi-Sugeno 퍼지 추론기법과 신경망을 연계한뉴로-퍼지홍수예측 모형을 구축하고자 하였다. 뉴로-퍼지 홍수예측 모형의 예측정확도는 입력자료로 사용되는 강우와 수위 자료의 시간적 분포 및 자료의 수에 의해 결정된다. 따라서 본 연구에서는 홍수예측 모형 구축을 위한 최적 입력 자료 조합 선정을 위해 다양한 강우와 수위의 입력자료 조합을 구성하여 적용하였고, 이를 통해 홍수 예측을 위한 뉴러-퍼지 홍수예측 모형의 최적 입력 자료 조합을 선정하였다.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 1998년도 The Korea Society for Simulation 98 춘계학술대회 논문집
• /
• pp.101-105
• /
• 1998

A large system predictor, which can perform prediction of sales trend in a huge number of distribution centers, is presented using neural predictive model. There are 20,000 number of distribution centers, and each distribution center need to forecast future demand in order to establish a reasonable inventory policy. Therefore, the number of forecasting models corresponds to the number of distribution centers, which is not possible to estimate that kind of huge number of accurate models in ERP (Enterprise Resource Planning)module. Multilayer neural net as universal approximation is employed for fitting the prediction model. In order to improve prediction accuracy, a sequential simulation procedure is performed to get appropriate network structure and also to improve forecasting accuracy. The proposed simulation procedure includes neural structure identification and virtual predictive model generation. The predictive model generation consists of generating virtual signals and estimating predictive model. The virtual predictive model plays a key role in tuning the real model by absorbing the real model errors. The complement approach, based on real and virtual model, could forecast the future demands of various distribution centers.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 추계학술대회 논문집 전력기술부문
• /
• pp.91-93
• /
• 2004

Load forecasting is essential in order to supply electrical energy stably and economically in power systems. ANNs have flexibility to predict a nonlinear feature of load profiles. In this paper, we selected just the necessary input variables used in the paper(2) which is based on the phase-space embedding of a load time-series and reviewing others. So only 5 input variables were selected to forecast for spring, fall and winter season and another input considering temperature sensitivity is added during the summer season. The training cases are also selected from all previous data composed training cases of a 7-day, 14-day and 30-day period. Finally, we selected the training case of a 7-day period because it can be used in STLF without sacrificing the accuracy of the forecast. This allows more compact ANNs, smaller training cases. Consequently, test results show that compact neural networks can be forecasted without sacrificing the accuracy.