• 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.

• Korean Journal of Computational Design and Engineering
• /
• v.17 no.4
• /
• pp.234-245
• /
• 2012

This paper proposes a multi-level product modeling framework for long-term lifecycle products. The framework can help engineers to define product models and relate them to physical instances. The framework is defined in three levels; data, design model, modeling language. The data level represents real-world products, The model level describes design models of real-world products. The modeling language level defines concepts and relationships to describe product design models. The concepts and relationships in the modeling language level enable engineers to express the semantics of product models in an engineering-friendly way. The interactions between these three levels are explained to show how the framework can manage long-term lifecycle product information. A prototype system is provided for further understanding of the framework.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.123-125
• /
• 2022

In this paper, we introduce a system applied to long short-term memory using Yolo-pose. Using Yolo-pose from image data, data divided into daily life and falls are extracted and applied to LSTM for learning. In order to prevent overfitting, training is performed 8 to 2 validation and is represented by a confusion matrix. The result of Yolo-pose recorded 100% of both sensitivity and specificity, confirming that daily life and falls were well distinguished.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.8
• /
• pp.213-224
• /
• 2020

The study assesses the impact of trade liberalization factors on changes in customs revenues in Vietnam. Research data was conducted between 2002 and 2017 on the official website of the Government's Web Portal and The World Bank. This paper uses the vector error correction model to estimate the short-term and long term relationship between data series. The results have proven that tariff reductions have a positive effect on short-term and long-term customs revenues in Vietnam. However, the implementation of other international commitments on trade liberalization has positive short-term and long-term negative impacts on customs revenues in Vietnam. The study's results also show that exchange rate has no effect on changes in customs revenues in the short term but it has a strong impact on increasing customs revenues in the long run. Based on these findings, the article also suggests a number of policies to ensure customs revenues in Vietnam in future. In order to ensure customs revenues, the government of Vietnam should: (1) having some policy to improve the efficiency of customs management in Vietnam; (2) Building appropriate VND exchange rate policy; (3) Establishing reasonable non - tariff barriers to prevent fraud and ovations cause losses in customs revenues.

• 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.

• Geotechnical Engineering
• /
• v.14 no.6
• /
• pp.127-138
• /
• 1998

In refuse landfills, a considerable amount of settlement occurs due to the decomposition of refuse over several years. In this paper, several prediction methods are applied to the measured settlement data of fresh refuse sites. The effect of biological decomposition on the settlement characteristics is investigated in predicting the long-term settlement of refuse landfill sites in view of the predicted settlement curves and the amount of long-term settlement. Irrespective of the applied models, the long term settlement may not be correctly estimated if the model parameters do not contain the decomposition effects. Among the proposed several prediction methods, Gibson & Lo model and hyperbolic model seem to represent the long-term settlement characteristics, but the power creep law seems to considerably overestimate the long-term settlement.

• The Journal of Korean Physical Therapy
• /
• v.24 no.1
• /
• pp.35-40
• /
• 2012

Purpose: This study was to analyze the factors that affect the service relationship of long term care workers for the elderly and to provide basic resource for the successful connection of long term care services. Methods: 259 subjects who were engaged in long term care units completed a self-administered questionnaire that measured the extent of service linkage among one another. The Cronbach's ${\alpha}$ score determined the internal consistency of the acquired data and the discriminated validity was estimated by Pearson's correlation coefficient. Multiple regression analysis was conducted to investigate the influence of the known factors on the service linkage. Results: Acceptance and participation negatively influenced on the service linkage. Reliance, comprehension, recognition on service, and frequent contact with others positively activated the service linkage of long term care workers. Conclusion: The establishments of systemic training courses providing education that emphasizes reliability and recognizes other services, including work environment to contact easily are needed to improve the service-linkage of long-term care workers for the elderly.

• Research in Community and Public Health Nursing
• /
• v.20 no.2
• /
• pp.243-250
• /
• 2009

Purpose: This is a qualitative study to identify dimensions of long-term care hospital care quality that provide high-level medical services for long-term care patients in Korea. Methods: Service consumers and providers were interviewed, and collected data were analyzed into thesis, type and dimension. The focus group method was applied to two provider groups and individual interview was applied to two persons who had experienced a long-term care hospital. Results: The results of analyzing the consumers and providers was integrated into 8 dimensions: physical environment, staff, clinical care and nursing, multiplicity of activity program, atmosphere, interaction with family, nutrition, and quality improvement system. Conclusion: The dimensions of long-term care hospital care quality from this study can be used as a basis of quality indicators. Quantitative studies to test these dimensions are required for establishing quality management systems.

• Health Policy and Management
• /
• v.15 no.4
• /
• pp.136-160
• /
• 2005

Before introducing the national long-term care insurance in 2008, the want for long term care service has to be estimated and analysed. This study estimates the demand and analyses what determines the want of long term care service. This study investigated data of 3f6 elderlies, that was collected by age stratified random sampling. The elderies resided in Onyang 4 - dong (urban area) and Dogo-myun (rural area) In the city of Asan. The researchers visited the elderlies and their care giver, and assessed their demand for the long term care service and examined physical, mental, socio-economic status by the assessment tools for Korean Long-Term Care System. $64\%$ of the those who are entitled to be served refuse the long term care service. $26.7\%$ of them wants for home care service and $7.9\%$ want facility care service. It is estimated that the want of home care service are three or four times as much as that of facility care service. The demand for long term care service is 5.155 times higher for those who live in rural area (p=0.000), 3.040 times higher for those who do not have spouse(p=0.057), and 3.356 times higher for the people who is in medicaid than medical insurance(p=0.029). However, income(p=0.782), means(p=0.614), living alone(p=0.223), number of family to live with (p=0.341) and age of the elderly(p=0.420) are not related with the demand of long term care service. The assessment tools for Korean Long-Term Care System for need evaluation of the long term care service can reflect the demand well.(p=0.024) If medical care will cover $80\%$ of total cost, the willingness to pay of the out of pocket money of the people with medical insurance is 67,400 Korean Won(66.77 US$) for the home care service and 182,500 Korean Won(180.78 US$) for the facility care service. There is possibility that long term care demand is still small after Introducing the long term care Insurance due to the care given by family members. When developing service delivery system of long term care insurance, rural area has to be given more consideration than urban area because of the higher demand. The people who do not have spouse or are in medicaid have to be given special consideration as well.

• Health Policy and Management
• /
• v.23 no.1
• /
• pp.90-100
• /
• 2013

Background: This study examined the relationships of dementia, stroke, and combined multimorbidity with long-term care utilizations among older people in South Korea. Methods: A nationally representative sample of 10,130 older adults who used long-term care services in 2010 were analyzed. We used the 5% sample of aged 65 years or older linked with National Health Insurance Corporation registry data of long-term care insurance system. The sample was categorized into three groups: dementia only (47.6%), stroke only (36.3%), and both dementia and stroke (16.1%). We estimated the use of institutional care, home care, and total expenditure of long-term care services, adjusting for the severity of each function (such as daily life, behavior or cognitive change, nursing care needs, and rehabilitation care needs) and sociodemographic characteristics. Results: Having dementia symptoms was positively associated with the use of institutional care services, on the other hand, having stroke symptoms was positively related with the use of home care. The total long-term care cost was higher in the group of having both dementia and stroke. Conclusion: Older persons with dementia symptoms and stroke symptoms have different patterns of long-term care utilization, and the multimorbidity increased the overall expenditure of long-term care utilization. These findings imply a need for differentiated management strategy targeting physically and cognitively impaired older persons, and special concerning for persons with multimorbidity conditions for long-term care insurance program in Korea.