• Communications for Statistical Applications and Methods
• /
• v.24 no.1
• /
• pp.67-80
• /
• 2017

Over the last few decades, ensemble forecasts based on global climate models have become an important part of climate forecast due to the ability to reduce uncertainty in prediction. Moreover in ensemble forecast, assessing the prediction uncertainty is as important as estimating the optimal weights, and this is achieved through a probabilistic forecast which is based on the predictive distribution of future climate. The Bayesian model averaging has received much attention as a tool of probabilistic forecasting due to its simplicity and superior prediction. In this paper, we propose a new Bayesian model averaging method for probabilistic ensemble forecasting. The proposed method combines a deterministic ensemble forecast based on a multivariate regression approach with Bayesian model averaging. We demonstrate that the proposed method is better in prediction than the standard Bayesian model averaging approach by analyzing monthly average precipitations and temperatures for ten cities in Korea.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.03a
• /
• pp.67-70
• /
• 1998

There were many cases to apply artificial intelligence to medicine. In this paper, we present the prediction model of the development of the NIDDM(noninsulin-dependent diabetes mellitus). It is not difficult that doctor diagnose patient as DM(diabetes mellitus). However NIDDM is usually developmented later on 40 years old and symptom appeares gradually. So screening test or prediction model is needed absolutely. Our model predicts development of NIDDM with still normal data 2 year ago. Prediction models developed are both MLP(multilayer perceptron) with backpropagation training and RBFN(radial basis function network). Performance of both models were evaluated with likelihood ratio. MLP was about two and RBFN was about three. We expect that models developed can prevent development of DM and utilize normal data.

• ETRI Journal
• /
• v.43 no.6
• /
• pp.1058-1080
• /
• 2021

Crime is not a completely random event but rather shows a pattern in space and time. Capturing the dynamic nature of crime patterns is a challenging task. Crime prediction models that rely only on neighborhood influence and demographic features might not be able to capture the dynamics of crime patterns, as demographic data collection does not occur frequently and is static. This work proposes a novel approach for crime count and hotspot prediction to capture the dynamic nature of crime patterns using taxi data along with historical crime and demographic data. The proposed approach predicts crime events in spatial units and classifies each of them into a hotspot category based on the number of crime events. Four models are proposed, which consider different covariates to select a set of independent variables. The experimental results show that the proposed combined subset model (CSM), in which static and dynamic aspects of crime are combined by employing the taxi dataset, is more accurate than the other models presented in this study.

• Journal of Information Processing Systems
• /
• v.17 no.1
• /
• pp.75-88
• /
• 2021

Automobile credit business has developed rapidly in recent years, and corresponding default phenomena occur frequently. Credit default will bring great losses to automobile financial institutions. Therefore, the successful prediction of automobile credit default is of great significance. Firstly, the missing values are deleted, then the random forest is used for feature selection, and then the sample data are randomly grouped. Finally, six prediction models of support vector machine (SVM), random forest and k-nearest neighbor (KNN), logistic, decision tree, and artificial neural network (ANN) are constructed. The results show that these six machine learning models can be used to predict the default of automobile credit. Among these six models, the accuracy of decision tree is 0.79, which is the highest, but the comprehensive performance of SVM is the best. And random grouping can improve the efficiency of model operation to a certain extent, especially SVM.

• 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 Korean Society for Atmospheric Environment
• /
• v.24 no.E2
• /
• pp.63-73
• /
• 2008

In this study, neural network models (NNMs) were examined as alternatives to dispersion models in predicting the short-term $SO_2$ concentrations in a coastal area because the performances of dispersion models in coastal areas have been found to be unsatisfactory. The NNMs were constructed for various combinations of averaging time and prediction time in advance by using the historical data of meteorological parameters and $SO_2$ concentrations in 2002 in the coastal area of Boryeung, Korea. The NNMs were able to make much more accurate predictions of 1 hr $SO_2$ concentrations at ground level in the morning in coastal area than the atmospheric dispersion models such as fumigation models, ADMS3 and ISCST3 for identical conditions of atmospheric stability, area, and weather. Even when predictions of 24-h $SO_2$ concentrations were made 24 hours in advance, the predictions and measurements were in good accordance(correlation coefficient=0.65 for n=216). This accordance level could be improved by appropriate expansion of training parameters. Thus it may be concluded that the NNMs can be successfully used to predict short-term ground level concentrations averaged over time less than 24 hours even in complex terrain. The prediction performance of ANN models tends to improve as the prediction lagging time approaches the concentration averaging time, but to become worse as the lagging time departs from the averaging time.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.3
• /
• pp.123-138
• /
• 2023

The Fourth Industrial Revolution and sensor technology have led to increased utilization of sensor data. In our modern society, data complexity is rising, and the extraction of valuable information has become crucial with the rapid changes in information technology (IT). Recurrent neural networks (RNN) and long short-term memory (LSTM) models have shown remarkable performance in natural language processing (NLP) and time series prediction. Consequently, there is a strong expectation that models excelling in NLP will also excel in time series prediction. However, current research on Transformer models for time series prediction remains limited. Traditional RNN and LSTM models have demonstrated superior performance compared to Transformers in big data analysis. Nevertheless, with continuous advancements in Transformer models, such as GPT-2 (Generative Pre-trained Transformer 2) and ProphetNet, they have gained attention in the field of time series prediction. This study aims to evaluate the classification performance and interval prediction of remaining useful life (RUL) using an advanced Transformer model. The performance of each model will be utilized to establish a health index (HI) for cutting blades, enabling real-time monitoring of machine health. The results are expected to provide valuable insights for machine monitoring, evaluation, and management, confirming the effectiveness of advanced Transformer models in time series analysis when applied in industrial settings.

• Journal of the Korean Solar Energy Society
• /
• v.37 no.1
• /
• pp.25-38
• /
• 2017

Climate change and environmental pollution are becoming serious due to the use of fossil energy. For this reason, renewable energy systems are increasing, especially photovoltaic systems being more popular. The photovoltaic system has characteristics that are affected by ambient weather conditions such as insolation, outside temperature, wind speed. Particularly, it has been confirmed that the performance of the photovoltaic system decreases as the module temperature increases. In order to grasp the influence of the module temperature in advance, several researchers have proposed the prediction models on the module temperature. In this paper, we predicted the module temperature using the aforementioned prediction model on the basis of the weather conditions in Incheon, South Korea during July and August. The influence of weather conditions (i.e. insolation, outside temperature, and wind speed) on the accuracy of the prediction models was also evaluated using the standard statistical metrics such as RMSE, MAD, and MAPE. The results show that the prediction accuracy is reduced by 3.9 times and 1.9 times as the insolation and outside temperature increased respectively. On the other hand, the accuracy increased by 6.3 times as the wind speed increased.

• ETRI Journal
• /
• v.36 no.3
• /
• pp.418-428
• /
• 2014

In social network services, such as Facebook, Google+, Twitter, and certain postings attract more people than others. In this paper, we propose a novel method for predicting the lifespan and retweet times of tweets, the latter being a proxy for measuring the popularity of a tweet. We extract information from retweet graphs, such as posting times; and social, local, and content features, so as to construct prediction knowledge bases. Tweets with a similar topic, retweet pattern, and properties are sequentially extracted from the knowledge base and then used to make a prediction. To evaluate the performance of our model, we collected tweets on Twitter from June 2012 to October 2012. We compared our model with conventional models according to the prediction goal. For the lifespan prediction of a tweet, our model can reduce the time tolerance of a tweet lifespan by about four hours, compared with conventional models. In terms of prediction of the retweet times, our model achieved a significantly outstanding precision of about 50%, which is much higher than two of the conventional models showing a precision of around 30% and 20%, respectively.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.3
• /
• pp.635-645
• /
• 2017

In this paper, we propose batting index prediction models of 2017. Due to the insufficiency of KBO pitchers data, batting index prediction models of 2016 has been developed based on elected eight batting index collecting the past three years data of MLB and KBO. It has been found that this prediction model fits well to both MLB and KBO, and the KBO model fits better than MLB in some cases. Using these prediction models, we analyzed and compared 2016's estimated values for the batting index of MLB and KBO. With the relation results between batting index prediction and batter's age for MLB and KBO, it can be determined that there is no relationship between the significant batting index and ages.