• Journal of Korean Society for Quality Management
• /
• v.50 no.4
• /
• pp.701-716
• /
• 2022

Purpose: This study aims to predict the dry cargo transportation market economy. The subject of this study is the BDI (Baltic Dry Index) time-series, an index representing the dry cargo transport market. Methods: In order to increase the accuracy of the BDI time-series, we have pre-processed the original time-series via time-series decomposition and data augmentation techniques and have used them for ANN learning. The ANN algorithms used are Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) to compare and analyze the case of learning and predicting by applying time-series decomposition and data augmentation techniques. The forecast period aims to make short-term predictions at the time of t+1. The period to be studied is from '22. 01. 07 to '22. 08. 26. Results: Only for the case of the MAPE (Mean Absolute Percentage Error) indicator, all ANN models used in the research has resulted in higher accuracy (1.422% on average) in multivariate prediction. Although it is not a remarkable improvement in prediction accuracy compared to uni-variate prediction results, it can be said that the improvement in ANN prediction performance has been achieved by utilizing time-series decomposition and data augmentation techniques that were significant and targeted throughout this study. Conclusion: Nevertheless, due to the nature of ANN, additional performance improvements can be expected according to the adjustment of the hyper-parameter. Therefore, it is necessary to try various applications of multiple learning algorithms and ANN optimization techniques. Such an approach would help solve problems with a small number of available data, such as the rapidly changing business environment or the current shipping market.

• Korean Journal of Remote Sensing
• /
• v.20 no.3
• /
• pp.175-188
• /
• 2004

The objectives of this study were to estimate leaf area index (LAI) as a function of image-derived vegetation indices, and to compare measured and estimated LAI to the results of crop model simulation. Soil moisture, crop phenology, and LAI data were obtained several times during the 2001 growing season at monitoring sites established in two central Missouri experimental fields, one planted to com (Zea mays L.) and the other planted to soybean (Glycine max L.). Hyper- and multi-spectral images at varying spatial. and spectral resolutions were acquired from both airborne and satellite platforms, and data were extracted to calculate standard vegetative indices (normalized difference vegetative index, NDVI; ratio vegetative index, RVI; and soil-adjusted vegetative index, SAVI). When comparing these three indices, regressions for measured LAI were of similar quality $(r^2$ =0.59 to 0.61 for com; $r^2$ =0.66 to 0.68 for soybean) in this single-year dataset. CERES(Crop Environment Resource Synthesis)-Maize and CROPGRO-Soybean models were calibrated to measured soil moisture and yield data and used to simulate LAI over the growing season. The CERES-Maize model over-predicted LAI at all corn monitoring sites. Simulated LAI from CROPGRO-Soybean was similar to observed and image-estimated LA! for most soybean monitoring sites. These results suggest crop growth model predictions might be improved by incorporating image-estimated LAI. Greater improvements might be expected with com than with soybean.

• Journal of the Korea Convergence Society
• /
• v.10 no.2
• /
• pp.49-56
• /
• 2019

This study was to examine whether an elderly can health-related quality of life(EQ-5D) by the mediating effect of dental health determinants on the association between health practice behavior and EQ-5D. The analysis was conducted on 1,311 of above the age of 65 in elderly by using raw data from the 2015 National Health and Nutrition Survey. The data were analyzed using SPSS for windows version 24.0 and SPSS PROCESS-macro. The health practice behavior and EQ-5D by living arrangement were the highest in the one-generation family(4.62, 0.90) and the lowest the elderly living alone(4.40, 0.86). Also, analysis using the PROCESS macro indicated that the FS-T index has a mediating effect between health practice behavior and EQ-5D(${\beta}=.0011$, BCCI [.003~.0024]). These findings suggest that FS-T index is closely related to EQ-5D and this will be used as basic data for development of health promotion programs for elderly.

• Journal of Korean Academy of Nursing
• /
• v.34 no.5
• /
• pp.693-701
• /
• 2004

Purpose: The purpose of this study was to validate Quality of Life Index-Cancer (Q.L.I.-C) developed by Ferrans (1990) among Korean cancer patients. Method: This study design was exploratory factor analysis methodology. Q.L.I.-C was translated into Korean and reverse-translated into English. The subjects were 357 Korean patients with various cancers. Data were collected by questionnaires from May to August, 2000 and was analyzed by descriptive statistics, Principal Component Analysis for construct validity and Cronbach's alpha coefficient for reliability. Result: The range of factor loadings was .446～.841. The explained variance from the 5 extracted factors was 63.7% of the total variance. The first factor 'family' was 35.5%, and 'health & physical functioning', 'psychological', 'spiritual', and 'economic' factors were 11.5%, 6.9%, 5.6%, and 4.2% respectively. Because of cultural difference between Americans and Koreans, certain items such as sexuality, job status, and education were deleted from the extraction of factors in this study. The Cronbach's alpha coefficient was .9253 among the 28 items. Conclusion: Q.L.I.-C could be applied in measuring quality of life of Korean cancer patients. It also recommend to do further studiesfor validation of Q.L.I.-C American and Korean versions relating to cultural differences.

• Nutritional Sciences
• /
• v.2 no.2
• /
• pp.107-112
• /
• 1999

Diet quality index DQI) offers a new way of comparing eating habits across populations and across countries. Nutrients and food consumption data from 100 elderly Korean women aged 65 and older were collected in Seoul or Kyunggi-do, Korea by the 24 hour recall method. Diet quality index (DQI) was computed for 1049 elderly women (65 and older) from the 1994-1996 Continuing Survey of Food Intakes by Individuals (CSFII) in the US according to US dietary guidelines, and applied to the diet of elderly Korean women for purposes of comparison. A modified 16-point DQI awarded 2 points each for moderate consumption of fat ($\leq$ 30% energy), saturated fat ($\leq$ 10%), cholesterol ($\leq$ 300 mg/day), sodium ($\leq$ 2400 mg/day), and protein ($\leq$ 100% RDA), adequate intakes of carbohydrate ($\qeq$50% energy) and calcium ($\qeq$ 100% RDA), and plenty of fruits and vegetables ($\qeq$ 5 servings). Criteria were based on US dietary guidelines. Partial scores were given if subjects were close to meeting these cutoff points. Diets with $\leq$ 300 mg cholesterol/day were reported by 97% or the Korean sample and 82% of the American sample, while 90% of the Koreans and 42% of the Americans met the goal of $\leq$ 30% of energy from fat, and 98% of the Koreans and 47% of American met the recommendation of $\leq$ 10% of energy from saturated fat. In contrast, only 8% of the Korean sample met the sodium recommendation of $\leq$ 2400 mg sodium per day, whereas 54% of the American subjects met this goal. The mean DQI scores were 10.1 for the elderly American women and 11.3 for the elderly Korean women. Overall, the elderly Korean diet was more consistent with the US dietary guidelines than the elderly American diet.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.4
• /
• pp.765-773
• /
• 2011

Today, as the number of applicants for admission decreases, competition among universities is deepening in Korea. Especially, the existence of local universities has led to intense competition to increase the enrollment rate of new students and reduce dropout rate. To survive in this competition, local universities are making various efforts; however, the primary problem is improving their educational service quality. In this study, we have developed a device to measure educational service quality which can be applied to the field of higher education, and factors that determine educational service quality are dragged through this device. In addition, this research identifies which statistically significant factors play a part in overall satisfaction and word of mouth effect, and interprets 29 quality attributes using importance-satisfaction transformed index.

• Journal of Digital Convergence
• /
• v.17 no.4
• /
• pp.335-344
• /
• 2019

This study aimed to identify the effect of stress, smartphone addiction, Social support, and physiological index on quality of sleep (PSQI) and to investigate the affecting factors according to sex in highschool students. The data were collected from 210 subjects from February 6 to 16, 2018 using a structured self-report questionnaires and analyzed using descriptive statistics, t-test, ANOVA, and multiple regression with SPSS WIN Version 24.0. The quality of sleep was lower in female students than in male students. In multiple regression analysis, Awake time, School grades stress were significant predictors and explained 29.6% of quality of sleep for male students. In female students, Smart phone start age, School grades stress, Disability of daily living and Appraisal social support were significant predictors and explained 24.3% of quality of sleep. Therefore, it is expected to be used as basic data for the development of intervention programs that can solve the factors affecting the quality of sleep of adolescents, thereby helping the healthy development of youth.

• Journal of Distribution Science
• /
• v.20 no.8
• /
• pp.1-8
• /
• 2022

Purpose: Research on attracting foreign direct investment (FDI) plays an important role in helping provinces attract more FDI projects. However, with local competition, FDI enterprises also have to consider their investment. This study evaluates the provincial competitiveness to attract FDI in Thai Nguyen province, a province of Vietnam. In which provincial distribution of competitiveness is measured through nine indicators. Research design, data, and methodology: The study collects data (FDI and the provincial competitiveness index) from 2006 to 2020. The study uses Autoregressive Distributed Lag (ARDL) to text the impact of distribution of competitivenes on foreign direct investment. With time-series, the ARDL is suitable for data analysis. Results: The regression results indicate that the competition index of market entry and informal costs negatively impact attracting FDI into the province; The human resource training quality index has a positive effect on FDI. The results show that FDI enterprises pay much attention to business establishment procedures, hidden costs, and quality of human resources in the province. Conclusions: At the same time, in terms of practice, the results of this study, the authors also offer solutions to help improve the ability to attract FDI into Thai Nguyen province. The significant provincial competitiveness indicators should be taken into account for improvement first.

• Journal of the Korean Society of Food Culture
• /
• v.38 no.4
• /
• pp.270-282
• /
• 2023

We performed a study to examine the association between diet quality and nonalcoholic fatty liver disease (NAFLD). Our study included 3,586 women aged 40-64 years who participated in the sixth Korea National Health and Nutrition Examination Survey. The study subjects were classified into the NAFLD group (n=816) and the normal group (n=2,770) using the hepatic steatosis index. The anthropometric indices, blood profiles, and dietary intake data of the subjects were obtained. The waist circumference, body mass index, and the serum levels of triglycerides, fasting blood sugar, HbA1c, and systolic and diastolic blood pressures were higher in the NAFLD compared to the normal groups (p<0.001, respectively). The intakes of protein (g/kg body weight, p<0.001), potassium (p<0.001), and vitamin A (p=0.006) were significantly lower in the NAFLD group. It was observed that the higher the total Korean Healthy Eating Index score, the lower the risk of NAFLD. A reverse relationship was shown between the NAFLD risk and the intakes of total fruits, total vegetables, vegetables excluding Kimchi and pickled vegetables, meat, fish, eggs and beans. Therefore, it is recommended that middle-aged women in Korea increase their intakes of fruits, vegetables, and foods high in protein for the proper management of NAFLD.

• Journal of Korean Society for Quality Management
• /
• v.32 no.2
• /
• pp.93-108
• /
• 2004

The purpose of this research is to summarize the methodological issues in internet survey and to suggest personalized internet survey system using data mining technique for enhancing the survey quality of internet survey as well as utilizing the benefit of interactive multimedia factors of internet survey. The data mining technique used in this paper is Case Based Reasoning for adopting individual design preference affecting survey quality. For achieving the research purpose, two surveys, pre & post survey, were performed. Pre survey was done for implementing CBR database to find individual index affecting survey quality and post survey was used for measuring the peformance of personalized internet survey system. The result shows that the survey quality of personalized web survey system is better than generalized web survey system.