• Communications for Statistical Applications and Methods
• /
• 제26권5호
• /
• pp.497-506
• /
• 2019

Forecasting the U.S. employment level is made using machine learning methods of the artificial neural network: deep neural network, long short term memory (LSTM), gated recurrent unit (GRU). We consider the big data of the federal reserve economic data among which 105 important macroeconomic variables chosen by McCracken and Ng (Journal of Business and Economic Statistics, 34, 574-589, 2016) are considered as predictors. We investigate the influence of the two statistical issues of the dimension reduction and time series differencing on the machine learning forecast. An out-of-sample forecast comparison shows that (LSTM, GRU) with differencing performs better than the autoregressive model and the dimension reduction improves long-term forecasts and some short-term forecasts.

• International Journal of Computer Science & Network Security
• /
• 제21권2호
• /
• pp.77-87
• /
• 2021

In this study, a novel improved second order Radial Basis Function Neural Network based method with excellent scheduling capabilities is used for the dynamic prediction of short and long-term energy required applications. The effectiveness and the reliability of the algorithm are evaluated using training operations with New England-ISO database. The dynamic prediction algorithm is implemented in Matlab and the computation of mean absolute error and mean absolute percent error, and training time for the forecasted load, are determined. The results show the impact of temperature and other input parameters on the accuracy of solar Photovoltaic load forecasting. The mean absolute percent error is found to be between 1% to 3% and the training time is evaluated from 3s to 10s. The results are also compared with the previous studies, which show that this new method predicts short and long-term load better than sigmoidal neural network and bagged regression trees. The forecasted energy is found to be the nearest to the correct values as given by England ISO database, which shows that the method can be used reliably for short and long-term load forecasting of any electrical system.

• Journal of information and communication convergence engineering
• /
• 제19권4호
• /
• pp.241-247
• /
• 2021

Particulate matter has emerged as a serious global problem, necessitating highly reliable information on the matter. Therefore, various algorithms have been used in studies to predict particulate matter. In this study, we compared the prediction performance of neural network models that have been actively studied for particulate matter prediction. Among the neural network algorithms, a deep neural network (DNN), a recurrent neural network, and long short-term memory were used to design the optimal prediction model using a hyper-parameter search. In the comparative analysis of the prediction performance of each model, the DNN model showed a lower root mean square error (RMSE) than the other algorithms in the performance comparison using the RMSE and the level of accuracy as metrics for evaluation. The stability of the recurrent neural network was slightly lower than that of the other algorithms, although the accuracy was higher.

• The Plant Pathology Journal
• /
• 제38권4호
• /
• pp.395-402
• /
• 2022

To predict rice blast, many machine learning methods have been proposed. As the quality and quantity of input data are essential for machine learning techniques, this study develops three artificial neural network (ANN)-based rice blast prediction models by combining two ANN models, the feed-forward neural network (FFNN) and long short-term memory, with diverse input datasets, and compares their performance. The Blast_Weathe long short-term memory r_FFNN model had the highest recall score (66.3%) for rice blast prediction. This model requires two types of input data: blast occurrence data for the last 3 years and weather data (daily maximum temperature, relative humidity, and precipitation) between January and July of the prediction year. This study showed that the performance of an ANN-based disease prediction model was improved by applying suitable machine learning techniques together with the optimization of hyperparameter tuning involving input data. Moreover, we highlight the importance of the systematic collection of long-term disease data.

• 전자공학회논문지C
• /
• 제34C권12호
• /
• pp.54-60
• /
• 1997

A new method to neglect the third term of the computational energy expression in the single-layer neural network with feedback is introduced. The system often converges to local minima instead of to global minima, because the computational energy is not matched exactly with the cost function being optimized. One of the factors causing these tow functions different is the third term of computational enegy expression. Regarding this third term energy very small, it is always ignored in designing the system. However, a sthe system growing, this third term energy is also growing and this grown term makes the computational energy function much different from the cost function. In results of differency between two functions, system converges to local minima more than before. In this paper, a new method to neglect te third term energy is introduced, so that the system with tis new method has been imroved.

• 물과 미래
• /
• 제29권1호
• /
• pp.163-179
• /
• 1996

본 연구에서는 일차원 St. Venat 방정식을 이용하여 한강 하류부(고안-인도교 구간)의 홍수류 특성을 분석하였다. 유한차분 모형인 NETWORK모형을 이용하여 운동량 방정식의 각항(국부가속도항, 대류가속도항, 압력항, 중력항, 마찰항)의 절대적 크기와 상대적 크기를 비교 분석하였다. 분석결과 국부가속도항과 대류가속도항이 작게 나타나고 중력항, 압력항, 마찰항 등이 대부분의 구간에서 크게 나타나서 이 세 항이 흐름을 결정하는 주요 항임을 확인할 수 있었으며 수문곡선의 상태와 하도구간에 따라서는 국부가속도항과 대류가속도항의 상대적인 비율이 무시할 수 없을 정도로 크게 나타나서 이 구간에서는 동역학적 모형이 적절한 것으로 나타났다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2002년도 학술발표회 논문집(I)
• /
• pp.51-58
• /
• 2002

In this paper, the status of forest and forestry together with the trend of forest hydrology in Japan are firstly overviewed for the mutual understanding between the Japan Society of Hydrology and Water Resources (JSHWR) and the Korean Water Resources Association (KWRA). Then, Long-Term Ecological Research recently introduced in Asia is briefly explained, and the establishment of Japan-Korea Long-Term Forest Hydrological Research Network is proposed.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 하계학술대회 논문집 C
• /
• pp.850-853
• /
• 1998

This paper proposes a new short-term load forecasting method for special day, such as Public holidays, consecutive holidays, and days before and after holidays. when the load curves are quite different from those of normal weekdays. In this paper, two Artificial Neural Network(ANN) systems are applied to short-term load forecasting for spacial days in anomalous load conditions.

• 응용통계연구
• /
• 제33권5호
• /
• pp.615-625
• /
• 2020

문서-용어 빈도행렬은 그룹정보가 존재하는 문서들의 용어를 추출한 것으로 일반적인 텍스트 마이닝에서의 자료이다. 본 연구에서는 연구 분야 성격에 따른 문서 분류를 위해 문서-용어 빈도행렬을 생성하고, 전통적인 용어 가중치 함수인 TF-IDF와 최근 잘 알려진 용어 가중치 함수인 TF-IGM을 적용하였다. 또 용어 가중치가 적용된 문서-용어 가중행렬에 문서분류 정확도 향상을 위해 핵심어를 추출하여 문서-핵심어 가중행렬을 생성하였다. 핵심어가 추출된 행렬을 바탕으로, 심층 신경망을 이용해 문서를 분류하였다. 심층 신경망에서 최적의 모델을 찾기 위해 매개변수인 은닉층과 은닉노드수를 변화해가며 문서 분류 정확도를 확인하였다. 그 결과 8개의 은닉층을 가진 심층 신경망 모델이 가장 높은 정확도를 보였으며 매개변수 변화에 따른 모든 TF-IGM 문서 분류 정확도가 TF-IDF 문서 분류 정확도보다 높은 것을 확인하였다. 또한 개별 범주에 대한 문서 분류 분석 결과를 서포트 벡터 머신과 비교했을 때 심층 신경망이 대부분의 결과에서 더 좋은 정확도를 보임을 확인하였다.

• 전기전자학회논문지
• /
• 제23권3호
• /
• pp.941-946
• /
• 2019

본 논문에서는 LTE(Long Term Evolution) SON(Self Organization Network) 환경에서 PCI(Physical Cell Identification)를 할당하는 방법에 대하여 분석하였다. PCI를 할당하는 방법에 다양한 기법들이 제시되었고 규격에서는 기본적으로 PCI를 할당하는 과정에서 다른 셀과 ID가 '충돌'(Collision) 또는 '혼란'(Confusion)을 일으킬 수 있다는 것을 제시하였다. 따라서 본 논문에서는 LTE 규격에서 제시하는 PCI '충돌', '약한충돌'(Weak Collision) 그리고 '혼란'의 시나리오가 무엇인지 내용을 살펴보았다. 또한, 각 시나리오에 대한 해결 방법으로 셀 중앙적접근과 분산적 접근 방법에 대해 살펴보았다. 논문에서는 최근 연구되고 있는 그래픽 컬러링(Graphic Coloring) 기법에 대한 접근 방법에 대해 살펴보았고 중앙접근적 방법에 대한 전략에 대해 설명하였다.