• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.2
• /
• pp.313-318
• /
• 2021

The advent of the Deep Learning has applied to many industrial and general applications having an impact on our lives these days. Certain type of machine learning model is needed to be designed for a specific problem of field. Recently, there are many instances to solve the various COVID-19 related problems using deep learning model. Therefore, in this paper, a deep learning model for predicting number of outpatients of a hospital in advance is suggested. The suggested deep learning model is designed by using the Keras in Jupyter Notebook. The prediction result is being analyzed with the real data in graph, as well as the loss rate with some validation data to verify either for the underfitting or the overfitting.

• Journal of the Korean Society for Heat Treatment
• /
• v.36 no.6
• /
• pp.374-381
• /
• 2023

This study develops and evaluates a deep learning model for predicting oxide and nitride layers based on plasma process data. We introduce a novel deep learning-based Varying Coefficient Regressor (VCR) by adapting the VCR, which previously relied on an existing unique function. This model is employed to forecast the oxide and nitride layers within the plasma. Through comparative experiments, the proposed VCR-based model exhibits superior performance compared to Long Short-Term Memory, Random Forest, and other methods, showcasing its excellence in predicting time series data. This study indicates the potential for advancing prediction models through deep learning in the domain of plasma processing and highlights its application prospects in industrial settings.

• Journal of environmental and Sanitary engineering
• /
• v.15 no.2
• /
• pp.65-74
• /
• 2000

The purpose of this study is to develop the stochastic stream water quality model for the intake station of Chung-Ju city waterworks in the Han river system. This model was based on the theory of Box-Jenkins Multiplicative ARIMA(SARIMA) and the state space model to simulate changes of water qualities. Variable of water qualities included in the model are temperature and dissolved oxygen(DO). The models development were based on the data obtained from Jan. 1990 to Dec. 1997 and followed the typical procedures of the Box-Jenkins method including identification and estimation. The seasonality of DO and temperature data to formulate for the SARIMA model are conspicuous and the period of revolution was twelve months. Both models had seasonality of twelve months and were formulates as SARIMA {TEX}$(2,1,1)(1,1,1)_{12}${/TEX} for DO and temperature. The models were validated by testing normality and independency of the residuals. The prediction ability of SARIMA model and state space model were tested using the data collected from Jan. 1998 to Oct. 1999. There were good agreements between the model predictions and the field measurements. The performance of the SARIMA model and state space model were examined through comparisons between the historical and generated monthly dissolved oxygen series. The result reveal that the state space model lead to the improved accuracy.

• Journal of the Korean Data and Information Science Society
• /
• v.13 no.2
• /
• pp.261-270
• /
• 2002

Recently, the demand of the Intelligent Transportation System(ITS) has been increased to a large extent, and a real-time traffic information service based on the internet system became very important. When ITS companies carry out real-time traffic services, they find some traffic data missing, and use the conventional method of reconstructing missing values by calculating average time trend. However, the method is found unsatisfactory, so that we develop a new method based the spatial and spatial-temporal models. A cross-validation technique shows that the spatial-temporal model outperforms the others.

• Journal of Korean Society of Forest Science
• /
• v.109 no.1
• /
• pp.99-108
• /
• 2020

Although the relationship between income and income inequality has previously been discussed, the present study applies a dynamic approach to analyze the specific relationship between forest household income and income inequality. For this analysis, a unit root test and a cointegration test were conducted to characterize the nature of income time-series data. After converting unstable time-series data into stable time-series data, a VAR model was estimated. Based on this model, an impulse-response was generated and variance-decomposition analysis was performed. These analyses showed that the effect of forest household income was relatively larger than that of the Gini coefficient, and that the impact of forest household income not only caused income to increase but also caused the Gini coefficient to decrease. In addition, the impact of the Gini coefficient had an impact on reducing forest household income and further increasing income inequality. We conclude that, with the aim of alleviating the inequality of forest household income, an income growth policy would be more effective than an income distribution policy.

• The Journal of the Korea Contents Association
• /
• v.15 no.6
• /
• pp.411-420
• /
• 2015

With the rapid increase in the price of house lease, a unique housing form in Korea, a serious social issue has been raised as to the use value of house lease and residence stability of the ordinary people. This study thus aimed to analyze the direct factors that affect lease guaranteed loan and market volatility in order to explore the right direction of financial policy to reduce housing burdens. To this end, the direct variables affecting house lease guaranteed loan, including lease price, transaction price and lending rate, were defined. Vector Error Correction Model (VECM), a time series analysis, was employed to dynamically explain the data. Based on the house lease prices and bank data on loans between January 2010 and December 2014, it was found that the increase in lease price was the direct result of the increase in lease guaranteed loan, not that of the decrease in lending rate or increase in housing transaction price.

• The Korean Journal of Applied Statistics
• /
• v.26 no.3
• /
• pp.413-420
• /
• 2013

Stochastic weather generator is a commonly used tool to simulate daily weather time series. Recently, a generalized linear model(GLM) has been proposed as a convenient approach to tting these weather generators. In the present paper, a stochastic weather generator is considered to model the time series of daily temperatures for Seoul South Korea. As a covariate, precipitation occurrence is introduced to a relate short-term predictor to short-term predictands. One of the limitations of stochastic weather generators is a marked tendency to underestimate the observed interannual variance of monthly, seasonal, or annual total precipitation. To reduce this phenomenon, we incorporate a time series of seasonal mean temperatures in the GLM weather generator as a covariate.

• KIISE Transactions on Computing Practices
• /
• v.21 no.4
• /
• pp.338-342
• /
• 2015

Recurrent Neural Network (RNN), a machine learning model which can handle time-series data, can possess more varied structures than a feed-forward neural network, since a RNN allows hidden-to-hidden connections. This research focuses on the network structure among hidden neurons, and discusses the information processing capability of RNN. Time-series learning potential and dynamics of RNNs are investigated upon several well-established network structure models. Hidden neuron network structure is found to have significant impact on the performance of a model, and the performance variations are generally correlated with the criticality of the network dynamics. Especially Preferential Attachment Network model showed an interesting behavior. These findings provide clues for performance improvement of the RNN.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.1-13
• /
• 2021

In this study, a time series analysis technique was applied to calibrate and predict traffic data for various purposes, such as planning, design, maintenance, and research. Existing algorithms have limitations in application to data such as traffic data because they show strong periodicity and seasonality or irregular data. To overcome and supplement these limitations, we applied the SARIMA model, an analytical technique that combines the autocorrelation model, the Seasonal Auto Regressive(SAR), and the seasonal Moving Average(SMA). According to the analysis, traffic volume prediction using the SARIMA(4,1,3)(4,0,3) 12 model, which is the optimal parameter combination, showed excellent performance of 85% on average. In addition to traffic data, this study is considered to be of great value in that it can contribute significantly to traffic correction and forecast improvement in the event of missing traffic data, and is also applicable to a variety of time series data recently collected.

• Journal of Aerospace System Engineering
• /
• v.18 no.4
• /
• pp.43-52
• /
• 2024

This paper presents an anomaly detection system that uses an LSTM-Autoencoder model to identify early-stage anomalies in the blade pitch system of floating wind turbines. The sensor data used in power plant monitoring systems is primarily composed of multivariate time-series data for each component. Comprising two unidirectional LSTM networks, the system skillfully uncovers long-term dependencies hidden within sequential time-series data. The autoencoder mechanism, learning solely from normal state data, effectively classifies abnormal states. Thus, by integrating these two networks, the system can proficiently detect anomalies. To confirm the effectiveness of the proposed framework, a real multivariate time-series dataset collected from a wind turbine model was employed. The LSTM-autoencoder model showed robust performance, achieving high classification accuracy.