Development of Organic Fertilizer Solution for Hydroponics

Lee Junghye,Hwang Kyu Hyon,Park Ju-Hyun,Ha Tai-Moon,Lee Sang-Woo,Seo Myeong-Whoon 한국원예학회 2017 한국원예학회 학술발표요지 Vol.2017 No.5

Hydroponic Nutrients Solutions for Production of Plants with Low Potassium

Junghye Lee,Ju-Hyun Park,Tae-Moon Ha,Young-seok Lee,Myeongwhoon Seo 한국원예학회 2018 한국원예학회 학술발표요지 Vol.2018 No.5

Classification of High Dimensionality Data through Feature Selection Using Markov Blanket

Junghye Lee,Chi-Hyuck Jun 대한산업공학회 2015 Industrial Engineeering & Management Systems Vol.14 No.2

A classification task requires an exponentially growing amount of computation time and number of observations as the variable dimensionality increases. Thus, reducing the dimensionality of the data is essential when the number of observations is limited. Often, dimensionality reduction or feature selection leads to better classification performance than using the whole number of features. In this paper, we study the possibility of utilizing the Markov blanket discovery algorithm as a new feature selection method. The Markov blanket of a target variable is the minimal variable set for explaining the target variable on the basis of conditional independence of all the variables to be connected in a Bayesian network. We apply several Markov blanket discovery algorithms to some high-dimensional categorical and continuous data sets, and compare their classification performance with other feature selection methods using wellknown classifiers.

Causality Analysis for Public and Private Expenditures on Health Using Panel Granger-Causality Test

Lee, Su-Dong,Lee, Junghye,Jun, Chi-Hyuck Korean Institute of Industrial Engineers 2015 Industrial Engineeering & Management Systems Vol.14 No.1

Every year governments spend their national budget on public health in order to reduce financial burden of individuals on health. Although it has been widely believed that the increase of public expenditure on health decreases private health expenditure, it has not been proved by analysis with real data. For better understanding, we conducted an empirical study on the real data of 17 OECD countries-Australia, Austria, Canada, Denmark, Finland, Germany, Iceland, Ireland, Japan, Korea, New Zealand, Norway, Portugal, Spain, Sweden, the United Kingdom, and the United States. The panel Granger-causality test is used to verify the cause-and-effect relationship between the two expenditures. As a result, public expenditure on health has a 3 to 4 year-lagged negative effect on private health expenditure in the cases of the 16 countries except for the United States.

Prediction of Hypertension Complications Risk Using Classification Techniques

Lee, Wonji,Lee, Junghye,Lee, Hyeseon,Jun, Chi-Hyuck,Park, Il-Su,Kang, Sung-Hong Korean Institute of Industrial Engineers 2014 Industrial Engineeering & Management Systems Vol.13 No.4

Chronic diseases including hypertension and its complications are major sources causing the national medical expenditures to increase. We aim to predict the risk of hypertension complications for hypertension patients, using the sample national healthcare database established by Korean National Health Insurance Corporation. We apply classification techniques, such as logistic regression, linear discriminant analysis, and classification and regression tree to predict the hypertension complication onset event for each patient. The performance of these three methods is compared in terms of accuracy, sensitivity and specificity. The result shows that these methods seem to perform similarly although the logistic regression performs marginally better than the others.

Classification of High Dimensionality Data through Feature Selection Using Markov Blanket

Lee, Junghye,Jun, Chi-Hyuck Korean Institute of Industrial Engineers 2015 Industrial Engineeering & Management Systems Vol.14 No.2

A classification task requires an exponentially growing amount of computation time and number of observations as the variable dimensionality increases. Thus, reducing the dimensionality of the data is essential when the number of observations is limited. Often, dimensionality reduction or feature selection leads to better classification performance than using the whole number of features. In this paper, we study the possibility of utilizing the Markov blanket discovery algorithm as a new feature selection method. The Markov blanket of a target variable is the minimal variable set for explaining the target variable on the basis of conditional independence of all the variables to be connected in a Bayesian network. We apply several Markov blanket discovery algorithms to some high-dimensional categorical and continuous data sets, and compare their classification performance with other feature selection methods using well-known classifiers.

Perception of and attitude toward ethical issues among Korean occupational physicians

Junghye Choi,Chunhui Suh,Jong-Tae Lee,Segyeong Lee,Chae-Kwan Lee,Gyeong-Jin Lee,Taekjoong Kim,Byung-Chul Son,Jeong-Ho Kim,Kunhyung Kim,Dae Hwan Kim,Ji Young Ryu 대한직업환경의학회 2017 대한직업환경의학회지 Vol.29 No.-

Background: Occupational physicians (OPs) have complex relationships with employees, employers, and the general public. OPs may have simultaneous obligations towards third parties, which can lead to variable conflicts of interests. Among the various studies of ethical issues related to OPs, few have focused on the Korean OPs. The aim of the present survey was to investigate the ethical contexts, the practical resolutions, and the ethical principles for the Korean OPs. Methods: An email with a self-administered questionnaire was sent to members of the Korean Society of Occupational and Environmental Medicine, comprising 150 specialists and 130 residents. The questionnaire was also distributed to 52 specialists and 46 residents who attended the annual meeting of the Korean Association of Occupational and Environmental Clinics in October 2015, and to 240 specialists by uploading the questionnaire to the online community ‘oem-doctors’ in February 2016. The responses to each question (perception of general ethical conflicts, recognition of various ethical codes for OPs, core professional values in ethics of occupational medicine, and a mock case study) were compared between specialists and residents by the chi-squared test and Fisher’s exact test. Results: Responses were received from 80 specialists and 71 residents. Most participants had experienced ethical conflicts at work and felt the need for systematic education and training. OPs suffered the most ethical conflicts in decisions regarding occupational health examination and evaluation for work relatedness. Over 60% of total participants were unaware of the ethical codes of other countries. Participants thought ‘consideration of worker’s health and safety’ (26.0%) and ‘neutrality’ (24.7%) as the prominent ethical values in professionality ofoccupational medicine. In mock cases, participants chose beneficence and justice for fitness for work and confidential information acquired while on duty, and beneficence and respect for autonomy in pre-placement examinations. Conclusions: This study evaluated the current perception of and attitude toward ethical issues among the Korean OPs. These findings will facilitate the development of a code of ethics and the ethical decision-making program forthe Korean OPs.

Samnye-eup Regeneration Plan for the Utilization of the Potentials of Local Assets

Junghye Lee,Hyunsuk Kim 전북대학교 휴양및경관계획연구소 2016 휴양및경관연구 (J East Asian Landscape Studies) Vol.10 No.1

This plan aims to seek ways of regeneration in active utilization of local assets’ potentials such as historic and cultural resources and human resources as well as natural landscape resources of Samnye-eup, which was prosperous as the largest station town during the Joseon dynasty period and as an agricultural center around Mangyeong plain during and after the Japanese colonial era. The plan consists of the theoretical investigation, analysis of current conditions, basic concept, and business plan in the order. As for the theoretical investigation, domestic researches on the use of local assets in the context of urban regeneration and existing plans for regeneration projects were examined to come up with ways of utilizing local assets for the Samnye-eup regeneration plan. In the analysis of current conditions, specific information on Samnye-eup was collected to verify the need for the general regeneration project that embodies original projects for local asset utilization in each district. As for the basic conception, this regeneration plan envisions the reutilization of three types of storage facilities, utilizing closed grain warehouses scattered about in that region. The focus of filling ‘Farming Storages’ is to strengthen the residents’ capability through creative education customized for each generation and class based on the characteristics of the education city and in association with the local university. Second, filling of ‘Sensible Storages’ has the objective of filling the largest posthouse town in Honam region, the historic place of food plundering during the Japanese colonial era, with sophisticated cultural arts. Third, filling of ‘Food Storages’ is to establish a cooperative economic community in harmony with the local food, natural landscape, and cultural environments to overcome the general agricultural decline. The business plan includes collecting opinions from and discussing with local residents and related divisions in addition to expert forums. The filling of three types of storages are classified to the physical regeneration project, social regeneration project, and economic regeneration project, each of which forms a cycle in mutual complementation. In addition, this plan seeks synergy effects by complementing existing projects conducted by the central division and Wanju-gun.

Hypertension Occurrence Analysis using a Bayesian Network

Junghye Lee(이정혜),Wonji Lee(이원지),Hyeseon Lee(이혜선),Chi-Hyuck Jun(전치혁) 한국경영과학회 2014 한국경영과학회 학술대회논문집 Vol.2014 No.5

The Bayesian network (BN) is a useful method for modeling healthcare issues since a BN can graphically represent causal relationships among variables and provide its probabilistic information,. In this study, we apply a BN method to hypertension occurrence analysis. This study used the National Health Insurance Corporation (NHIC) database from 2002 to 2010 which contains more than 100,000 cases of personal medical examinations in Korea. We investigate the causality for hypertension occurrence by a structure learning step, and then evaluate the performance to predict hypertension occurrence through parameter learning and inference steps. It is shown that the BN outperforms other prediction methods such as logistic regression, naive Bayes and support vector machine in terms of sensitivity. In addition, the BN has advantages in interpreting which variables affect the hypertension occurrence and how they are related to each other.

Hypertension Occurrence Analysis using a Bayesian Network

Junghye Lee(이정혜),Wonji Lee(이원지),Hyeseon Lee(이혜선),Chi-Hyuck Jun(전치혁) 대한산업공학회 2014 대한산업공학회 춘계학술대회논문집 Vol.2014 No.5

The Bayesian network (BN) is a useful method for modeling healthcare issues since a BN can graphically represent causal relationships among variables and provide its probabilistic information,. In this study, we apply a BN method to hypertension occurrence analysis. This study used the National Health Insurance Corporation (NHIC) database from 2002 to 2010 which contains more than 100,000 cases of personal medical examinations in Korea. We investigate the causality for hypertension occurrence by a structure learning step, and then evaluate the performance to predict hypertension occurrence through parameter learning and inference steps. It is shown that the BN outperforms other prediction methods such as logistic regression, naive Bayes and support vector machine in terms of sensitivity. In addition, the BN has advantages in interpreting which variables affect the hypertension occurrence and how they are related to each other.