• Journal of Nutrition and Health
• /
• v.50 no.3
• /
• pp.284-293
• /
• 2017

Purpose: This study was conducted to examine the behavioral intentions of breastfeeding in single women using the theory of planned behavior. Methods: The questionnaires were distributed to 350 single women in her 20~30s, and 316 respondents were analyzed by descriptive statistics, Spearman's correlation, and multiple regression analysis. Results: The subjects showed strong intentions and favorable attitudes toward breastfeeding. The subjects were more favorably influenced by their mothers, siblings, friends, and coworkers who previously experienced breastfeeding than ones with no breastfeeding experiences. There were significant correlations between breastfeeding intention and attitudes (r = 0.321, p < 0.0001), subjective norms (r = 0.434, p < 0.0001), and perceived control (r = 0.307, p < 0.0001). However, regression analysis with two different age groups revealed that subjective norms (p < 0.0001) and perceived control (p < 0.001) contributed to the model of explaining breastfeeding intentions in subjects who were 25 years old or younger, whereas attitudes did not. In addition, subjects who were more than 25 years old showed that attitudes (p < 0.003) and subjective norms (p = 0.002) contributed to the model of explaining breastfeeding intentions while perceived control (p < 0.070) showed less contribution. Conclusion: These results suggest that the theory of planned behavior can be a useful tool to increase the rate of breastfeeding intentions in single women when designing educational materials, which requires consideration of age differences.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.127-142
• /
• 2016

Deep learning model is a kind of neural networks that allows multiple hidden layers. There are various deep learning architectures such as convolutional neural networks, deep belief networks and recurrent neural networks. Those have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. Among those architectures, convolutional neural networks and recurrent neural networks are classified as the supervised learning model. And in recent years, those supervised learning models have gained more popularity than unsupervised learning models such as deep belief networks, because supervised learning models have shown fashionable applications in such fields mentioned above. Deep learning models can be trained with backpropagation algorithm. Backpropagation is an abbreviation for "backward propagation of errors" and a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent. The method calculates the gradient of an error function with respect to all the weights in the network. The gradient is fed to the optimization method which in turn uses it to update the weights, in an attempt to minimize the error function. Convolutional neural networks use a special architecture which is particularly well-adapted to classify images. Using this architecture makes convolutional networks fast to train. This, in turn, helps us train deep, muti-layer networks, which are very good at classifying images. These days, deep convolutional networks are used in most neural networks for image recognition. Convolutional neural networks use three basic ideas: local receptive fields, shared weights, and pooling. By local receptive fields, we mean that each neuron in the first(or any) hidden layer will be connected to a small region of the input(or previous layer's) neurons. Shared weights mean that we're going to use the same weights and bias for each of the local receptive field. This means that all the neurons in the hidden layer detect exactly the same feature, just at different locations in the input image. In addition to the convolutional layers just described, convolutional neural networks also contain pooling layers. Pooling layers are usually used immediately after convolutional layers. What the pooling layers do is to simplify the information in the output from the convolutional layer. Recent convolutional network architectures have 10 to 20 hidden layers and billions of connections between units. Training deep learning networks has taken weeks several years ago, but thanks to progress in GPU and algorithm enhancement, training time has reduced to several hours. Neural networks with time-varying behavior are known as recurrent neural networks or RNNs. A recurrent neural network is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs. Early RNN models turned out to be very difficult to train, harder even than deep feedforward networks. The reason is the unstable gradient problem such as vanishing gradient and exploding gradient. The gradient can get smaller and smaller as it is propagated back through layers. This makes learning in early layers extremely slow. The problem actually gets worse in RNNs, since gradients aren't just propagated backward through layers, they're propagated backward through time. If the network runs for a long time, that can make the gradient extremely unstable and hard to learn from. It has been possible to incorporate an idea known as long short-term memory units (LSTMs) into RNNs. LSTMs make it much easier to get good results when training RNNs, and many recent papers make use of LSTMs or related ideas.

• Journal of Bio-Environment Control
• /
• v.30 no.4
• /
• pp.419-428
• /
• 2021

In order to develope a mobile-based greenhouse energy calculation program, firstly, the overall thermal transmittance of 10 types of major covers and 16 types of insulation materials were measured. In addition, to estimate the overall thermal transmittance when the cover and insulation materials were installed in double or triple layers, 24 combinations of double installations and 59 combinations of triple installations were measured using the hotbox. Also, the overall thermal transmittance value for a single material and the thermal resistance value were used to calculate the overall thermal transmittance value at the time of multi-layer installation of covering and insulating materials, and the linear regression equation was derived to correct the error with the measured values. As a result of developing the model for estimating thermal transmittance when installing multiple layers of coverings and insulating materials based on the value of overall thermal transmittance of a single-material, the model evaluation index was 0.90 (good when it is 0.5 or more), indicating that the estimated value was very close to the actual value. In addition, as a result of the on-site test, it was evaluated that the estimated heat saving rate was smaller than the actual value with a relative error of 2%. Based on these results, a mobile-based greenhouse energy calculation program was developed that was implemented as an HTML5 standard web-based mobile web application and was designed to work with various mobile device and PC browsers with N-Screen support. It had functions to provides the overall thermal transmittance(heating load coefficient) for each combination of greenhouse coverings and thermal insulation materials and to evaluate the energy consumption during a specific period of the target greenhouse. It was estimated that an energy-saving greenhouse design would be possible with the optimal selection of coverings and insulation materials according to the region and shape of the greenhouse.

• Journal of Korea Water Resources Association
• /
• v.51 no.12
• /
• pp.1195-1205
• /
• 2018

In the study, the water shortage of Boryeong Dam watershed ($163.6km^2$) was evaluated under future climate change scenario. The Soil and Water Assessment Tool (SWAT) was used considering future dam release derived from multiple linear regression (MLR) analysis. The SWAT was calibrated and verified by using daily observed dam inflow and storage for 12 years (2005 to 2016) with average Nash-Sutcliffe efficiency of 0.59 and 0.91 respectively. The monthly dam release by 12 years MLR showed coefficient of determination ($R^2$) of above 0.57. Among the 27 RCP 4.5 scenarios and 26 RCP 8.5 scenarios of GCM (General Circulation Model), the RCP 8.5 BCC-CSM1-1-M scenario was selected as future extreme drought scenario by analyzing SPI severity, duration, and the longest dry period. The scenario showed -23.6% change of yearly dam storage, and big changes of -34.0% and -24.1% for spring and winter dam storage during 2037~2047 period comparing with 2007~2016 period. Based on Runs theory of analyzing severity and magnitude, the future frequency of 5 to 10 years increased from 3 in 2007~2016 to 5 in 2037~2046 period. When considering the future shortened water shortage return period and the big decreases of winter and spring dam storage, a new dam operation rule from autumn is necessary for future possible water shortage condition.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.4
• /
• pp.316-328
• /
• 2021

In this study, the leaf Na content prediction model for spring potato was established using 400-1000 nm hyperspectral sensor to develop the multispectral sensor for the salinity monitoring in reclaimed land. The irrigation conditions were standard, drought, and salinity (2, 4, 8 dS/m), and the irrigation amount was calculated based on the amount of evaporation. The leaves' Na contents were measured 1st and 2nd weeks after starting irrigation in the vegetative, tuber formative, and tuber growing periods, respectively. The reflectance of the leaves was converted from 5 nm to 10 nm, 25 nm, and 50 nm of FWHM (full width at half maximum) based on the 10 nm wavelength intervals. Using the variance importance in projections of partial least square regression(PLSR-VIP), ten band ratios were selected as the variables to predict salinity damage levels with Na content of spring potato leaves. The MLR(Multiple linear regression) models were estimated by removing the band ratios one by one in the order of the lowest weight among the ten band ratios. The performance of models was compared by not only R2, MAPE but also the number of band ratios, optimal FWHM to develop the compact multispectral sensor. It was an advantage to use 25 nm of FWHM to predict the amount of Na in leaves for spring potatoes during the 1st and 2nd weeks vegetative and tuber formative periods and 2 weeks tuber growing periods. The selected bandpass filters were 15 bands and mainly in red and red-edge regions such as 430/440, 490/500, 500/510, 550/560, 570/580, 590/600, 640/650, 650/660, 670/680, 680/690, 690/700, 700/710, 710/720, 720/730, 730/740 nm.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.42 no.2
• /
• pp.127-136
• /
• 2022

This study was conducted to estimate the damage of Whole Crop Maize (WCM) according to abnormal climate using machine learning and present the damage through mapping. The collected WCM data was 3,232. The climate data was collected from the Korea Meteorological Administration's meteorological data open portal. Deep Crossing is used for the machine learning model. The damage was calculated using climate data from the Automated Synoptic Observing System (95 sites) by machine learning. The damage was calculated by difference between the Dry matter yield (DMY)_normal and DMY_abnormal. The normal climate was set as the 40-year of climate data according to the year of WCM data (1978~2017). The level of abnormal climate was set as a multiple of the standard deviation applying the World Meteorological Organization(WMO) standard. The DMY_normal was ranged from 13,845~19,347 kg/ha. The damage of WCM was differed according to region and level of abnormal climate and ranged from -305 to 310, -54 to 89, and -610 to 813 kg/ha bnormal temperature, precipitation, and wind speed, respectively. The maximum damage was 310 kg/ha when the abnormal temperature was +2 level (+1.42 ℃), 89 kg/ha when the abnormal precipitation was -2 level (-0.12 mm) and 813 kg/ha when the abnormal wind speed was -2 level (-1.60 m/s). The damage calculated through the WMO method was presented as an mapping using QGIS. When calculating the damage of WCM due to abnormal climate, there was some blank area because there was no data. In order to calculate the damage of blank area, it would be possible to use the automatic weather system (AWS), which provides data from more sites than the automated synoptic observing system (ASOS).

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.925-938
• /
• 2022

Agricultural reservoirs are an important water resource nationwide and vulnerable to abnormal climate effects such as drought caused by climate change. Therefore, it is required enhanced management for appropriate operation. Although water-level tracking is necessary through continuous monitoring, it is challenging to measure and observe on-site due to practical problems. This study presents an objective comparison between multiple AI models for water-body extraction using radar images that have the advantages of wide coverage, and frequent revisit time. The proposed methods in this study used Sentinel-1 Synthetic Aperture Radar (SAR) images, and unlike common methods of water extraction based on optical images, they are suitable for long-term monitoring because they are less affected by the weather conditions. We built four AI models such as Support Vector Machine (SVM), Random Forest (RF), Artificial Neural Network (ANN), and Automated Machine Learning (AutoML) using drone images, sentinel-1 SAR and DSM data. There are total of 22 reservoirs of less than 1 million tons for the study, including small and medium-sized reservoirs with an effective storage capacity of less than 300,000 tons. 45 images from 22 reservoirs were used for model training and verification, and the results show that the AutoML model was 0.01 to 0.03 better in the water Intersection over Union (IoU) than the other three models, with Accuracy=0.92 and mIoU=0.81 in a test. As the result, AutoML performed as well as the classical machine learning methods and it is expected that the applicability of the water-body extraction technique by AutoML to monitor reservoirs automatically.

• The Korean Journal of Coaching Psychology
• /
• v.5 no.2
• /
• pp.127-170
• /
• 2021

This study developed a measure to measure wellness-seeking behavior in important areas of life for general adults in Korea and verified its validity. For the development of the wellness scale, 31 factors derived through literature review, expert interviews, in-depth interviews, open questionnaires 1 and 2, and 182 questions were selected as the final 10 factors and 99 questions. Through exploratory factor analysis of the results of the preliminary survey of 351 adults in Korea, 58 questions of 10 factors were derived, and some of the questions reflecting important concepts in each factor were revised, and this survey was conducted with 63 questions of 10 factors. In this survey conducted on 667 people, to verify the validity of the composition concept of this test, the entire sampling was divided into two groups, one group was subjected to exploratory factor analysis, and the other group was subjected to confirmatory factor analysis. As a result of exploratory factor analysis, 63 questions of 10 factors (work, community, family, others, economic power, self-esteem, leisure, physical health, spirituality, and self-growth) were finally derived, and confirmatory factor analysis using the structural equation model verified that the model fit criteria were met. Convergence validity was verified using the K-MHC-SF and Wellness Index for Workers to verify whether the derived wellness scale and its sub-factors actually measure wellness. As a result of analyzing the relationship between the variables and factors of the Subjective Happiness Scale and Life Scale to verify the validity related to the criteria, it was found to be a significant correlation. As a result of confirming the significance of each path through multiple regression analysis, the 'self-esteem' on the wellness scale was identified as the most important factor influencing subjective happiness and life satisfaction. Finally, discussions on this research process and results, academic significance and practical significance, limitations, and future research directions were presented.

• 한국노년학
• /
• v.39 no.3
• /
• pp.467-484
• /
• 2019

The purpose of this study is to explore latent classes of longitudinal medical expenses of older people and to analyze its predictors and its effects on subjective health. Among participants of the Korean Health Panel, the sample of this study includes 1,119 people who is 65-year-old or older and reported their medical expenses for nine consecutive years. The analyses were conducted in three steps. First, Growth Mixture Model (GMM) was applied to find distinct subgroups showing similar patterns in medical expenses. The results showed four groups which were classified as high medical expenditure maintenance group, medical expenditure increase group, low medical expenditure maintenance group, and medical expenditure reduction group. Second, the multinominal logistic regression found that the presence of spouse, economic participation, the number of chronic diseases, and the type of health insurance were significant predictors of latent classes in medical expenses. In particular, the greater the number of chronic diseases, the higher the likelihood of belonging to the high medical expenditure maintenance group. In addition, medical benefit recipients are more likely to belong to the low medical cost maintenance and medical cost reduction groups. Third, multiple regression analysis revealed that the older people in the groups with low or reducing expenses reported better subjective health than people with higher expenses. This study has its meanings in exploring the heterogeneity in longitudinal medical expenses among older people and its predictors and its associations with health outcome. The results of this research provide background information in establishing public health policy for older people.

• Korean Journal of Social Welfare Studies
• /
• v.41 no.4
• /
• pp.369-393
• /
• 2010

This study examines the factors influencing Korean international adoptee's search for their birthparents. Considering that the search for birthparents is general needs for adoptees, Korean government should support their searching activities and, first of all, understand their characteristics. The research model was constructed based on the results of previous studies, and the data set of conducted by ministry of health and welfare was reanalyzed for this study. The subjects of the survey were Korean-born adoptees (who are more than 16 years old) in North America, Europe, and Australia. The research questionnaire was translated to English and French, and the survey was conducted on line. A total of 290 questionnaires were included in the analysis. Since survey was conducted on line, the missing rate of the data was relatively high. So, multiply imputed five data sets were used for analysis. Among the variables included in research model, the age group of adoptees, experience of identity crisis in their life, the first time when they became actively interested in Korean roots, the age at the time of adoption, and the attitudes of adoptive parents toward their search were significantly related to their search for birthparents. Adoptees in the age group of 30~34 had more actively participated in search compared to their reference group (which is the age group of more than 35 years old). The earlier they became actively interested in Korean roots, they tended to be more active in searching activities. Also, the experience of identity crisis in life and the age at the time of adoption were positively related to their search. Although most of adoptive parents have supported their search, the adoptees who reported that they didn't know their adoptive parents' attitude toward search, or their parents deceased had more actively participated in search for their birthparents. Some implications for adoption policy and practice were discussed based on the results of the study.