• Communications for Statistical Applications and Methods
• /
• v.26 no.5
• /
• 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
• /
• v.21 no.2
• /
• 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
• /
• v.19 no.4
• /
• 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
• /
• v.38 no.4
• /
• 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.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.12
• /
• 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.

• Water for future
• /
• v.29 no.1
• /
• pp.163-179
• /
• 1996

Flood flow characteristics of the Han River (from Goan to Indo Bridge) are analyzed using 1-dimensional St. Venant equations. NETWORK, a finite difference model, is used to calculate each term (local acceleration term, convective acceleration term, pressure force term, gravity force term, and friction force term) of the momentum equation and to analyze the flow characteristics. By the result of the study, as the general characteristics of flow in a channel that acceleration terms are very small and the other three terms are much greater is presented, three terms(pressure force term, gravity force term, friction force term) are to be main terms which decide the characteristics of flow. Specially in this region the acceleration term is noted so large that it cannot be ignored according to the shape of hydrograph and the region.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2002.05a
• /
• 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.

• Proceedings of the KIEE Conference
• /
• 1998.07c
• /
• 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.

• The Korean Journal of Applied Statistics
• /
• v.33 no.5
• /
• pp.615-625
• /
• 2020

The document-term frequency matrix is a term extracted from documents in which the group information exists in text mining. In this study, we generated the document-term frequency matrix for document classification according to research field. We applied the traditional term weighting function term frequency-inverse document frequency (TF-IDF) to the generated document-term frequency matrix. In addition, we applied term frequency-inverse gravity moment (TF-IGM). We also generated a document-keyword weighted matrix by extracting keywords to improve the document classification accuracy. Based on the keywords matrix extracted, we classify documents using a deep neural network. In order to find the optimal model in the deep neural network, the accuracy of document classification was verified by changing the number of hidden layers and hidden nodes. Consequently, the model with eight hidden layers showed the highest accuracy and all TF-IGM document classification accuracy (according to parameter changes) were higher than TF-IDF. In addition, the deep neural network was confirmed to have better accuracy than the support vector machine. Therefore, we propose a method to apply TF-IGM and a deep neural network in the document classification.

• Journal of IKEEE
• /
• v.23 no.3
• /
• pp.941-946
• /
• 2019

In this paper, the author analyzed the PCI (Physical Cell Identification) allocation methods in the LTE (Long Term Evolution) SON (Self Organization Network) environment. A variety of techniques have been proposed for how to allocate PCI, and the LTE standard fundamentally explained that collision between a cell and neighbor cells arise while a cell assign the PCI. Therefore, in this paper, the author examined the scenarios of PCI collision, weak collision, and confusion proposed by LTE specification. In addition, the cell central approach and the distributed approach were discussed as solutions for each scenario. In this paper, the author reviewed the approach of graphic coloring technique which was studied recently and explained the strategy of central approach.