• Information Systems Review
• /
• v.25 no.1
• /
• pp.111-128
• /
• 2023

With the development of artificial intelligence technology, interest in data-based product preference estimation and personalized recommender systems is increasing. However, if the recommendation is not suitable, there is a risk that it may reduce the purchase intention of the customer and even extend to a huge financial loss due to the characteristics of the financial product. Therefore, developing a recommender system that comprehensively reflects customer characteristics and product preferences is very important for business performance creation and response to compliance issues. In the case of financial products, product preference is clearly divided according to individual investment propensity and risk aversion, so it is necessary to provide customized recommendation service by utilizing accumulated customer data. In addition to using these customer behavioral characteristics and transaction history data, we intend to solve the cold-start problem of the recommender system, including customer demographic information, asset information, and stock holding information. Therefore, this study found that the model proposed deep learning-based collaborative filtering by deriving customer latent preferences through characteristic information such as customer investment propensity, transaction history, and financial product information based on customer transaction log records was the best. Based on the customer's financial investment mechanism, this study is meaningful in developing a service that recommends a high-priority group by establishing a recommendation model that derives expected preferences for untraded financial products through financial product transaction data.

• Clinical and Experimental Pediatrics
• /
• v.51 no.11
• /
• pp.1158-1164
• /
• 2008

Purpose : To investigate the discriminative ability of pediatric index of mortality 2 (PIM2) and pediatric risk of mortality III (PRISM III) in predicting mortality in children admitted into the intensive care unit (ICU). Methods : We retrospectively analyzed variables of PIM2 and PRISM III based on medical records with children cared for in a single hospital ICU from January 2003 to December 2007. Exclusions were children who died within 2 h of admission into ICU or hopeless discharge. We used Students t test and ANOVA for general characteristics and for correlation between survivors and non-survivors for variables of PIM2 and PRISM III. In addition, we performed multiple logistic regression analysis for Hosmer-Lemeshow goodness-of-fit, receiver operating characteristic curve (ROC) for discrimination, and calculated standardized mortality ratio (SMR) for estimation of prediction. Results : We collected 193 medical records but analyzed 190 events because three children died within 2 h of ICU admission. The variables of PIM2 correlated with survival, except for the presence of post-procedure and low risk. In PRISM III, there was a significant correlation for cardiovascular/neurologic signs, arterial blood gas analysis but not for biochemical and hematologic data. Discriminatory performance by ROC showed an area under the curve 0.858 (95% confidence interval; 0.779-0.938) for PIM2, 0.798 (95% CI; 0.686-0.891) for PRISM III, respectively. Further, SMR was calculated approximately as 1 for the 2 systems, and multiple logistic regression analysis showed ${\chi}^2(13)=14.986$, P=0.308 for PIM2, ${\chi}^2(13)=12.899$, P=0.456 for PRISM III in Hosmer-Lemeshow goodness-of-fit. However, PIM2 was significant for PRISM III in the likelihood ratio test (${\chi}^2(4)=55.3$, P<0.01). Conclusion : We identified two acceptable scoring systems (PRISM III, PIM2) for the prediction of mortality in children admitted into the ICU. PIM2 was more accurate and had a better fit than PRISM III on the model tested.

• Korean Journal of Food Science and Technology
• /
• v.45 no.1
• /
• pp.59-69
• /
• 2013

This study investigated the frequency, amount and consumption patterns of 50 potentially hazardous foods (PHF) along with consumers' risk perceptions towards PHF in Korea. A quantitative survey was performed from May through August by trained interviewers, surveying 1,000 adults aged over 18 who were randomly selected from six major provinces in Korea. Consumers perceived seafood, including shellfish, mussel, sashimi and sushi, as the top foods with the highest risk, followed by raw sliced beef. The food with the highest frequency intake per month was leafy vegetables, which is used to wrap other foods, followed by blanched vegetables, fried chicken, etc. The group of middle aged individuals with economic stability had the highest frequency intake of sashimi and sushi. Respondents living in small regions consume greater PHF portions at once. Food safety education with regard to the risk of PHF is essential for consumers, with high frequent intake of PHF.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.12 no.4
• /
• pp.284-288
• /
• 2009

The International Convention for the Control and Management of Ships Ballast Water & Sediments was adopted by consensus at a diplomatic conference of IMO at 2004. To prepare the Ballast Water Management Convention, fundamental technologies such as treatment system, type approval, risk assessment and various technical informations for formulation of the regulation for national strategy shall be developed. The information item of voyage and discharge of ship's ballast water are gathered by visiting vessel and agent at port. Using the 97 results by ships type characteristic analysis on the relation between loading/unloading and discharge/uptake of ballast water, the amounts of discharge/uptake of ballast water at each port and all of country in Korea are predicted. Hence, It is apparent that the uptake of ballast water is predicted to about 70 million ton in total of Busan, Incheon, Kwangyang and Ulsan ports at 2006 which is over 3 times than discharges.

• Journal of Periodontal and Implant Science
• /
• v.43 no.5
• /
• pp.215-220
• /
• 2013

Purpose: Cigarette smoking is a major risk factor in periodontal diseases. The pathogenesis of periodontal diseases may be affected by alterations of the inflammatory response by smoke. Nitric oxide (NO) is a gaseous, colorless, highly reactive, short-lived free radical with a pivotal role in the regulation of various physiological and pathological mechanisms in the body. It is important in host defense and homeostasis, on the one hand, whereas, on the other hand, it modulates the inflammatory response in periodontitis, leading to harmful effects. The aim of this study was to assess the levels of NO in both the serum and saliva of smokers and nonsmokers having chronic periodontitis and to compare them with periodontally healthy controls. Methods: Sixty subjects participated in the study and were divided into three groups: group I, healthy nonsmoking subjects; group II, nonsmoking patients with chronic periodontitis; group III, smoking patients with chronic periodontitis. Each group consisted of twenty subjects. The biochemical estimation of NO in the collected serum and in the saliva was performed using the Griess colorimetric reaction. Results: The results showed that the mean value of the salivary and serum NO was greater in group II than in group I, and also greater in group III than in group II. Conclusions: NO appears to play an important and rather complex role in the immuno-inflammatory process and in the remodeling and maintenance of osseous structures. It is therefore logical that modulation of this mediator has potential for the treatment of a number of inflammatory conditions including periodontal disease.

• Asian-Australasian Journal of Animal Sciences
• /
• v.31 no.6
• /
• pp.798-803
• /
• 2018

Objective: The objective of this study was to estimate the genetic parameters for milk ${\beta}$-hydroxybutyrate (BHBA), acetone (Ac), fat protein ratio (FPR), and energy balance (EB) using milk test day records and investigate the effect of early lactation FPR and EB on milk ketone body concentrations. Methods: Total 262,940 test-day records collected from Korea Animal Improvement Association during the period of 2012 to 2016 were used in this study. BHBA and Ac concentrations in milk were measured by Fourier transform infrared spectroscopy (FTIR). FPR values were obtained using test day records of fat and protein percentage. EB was calculated using previously developed equation based on parity, lactation week, and milk composition data. Genetic parameters were estimated by restricted maximum likelihood procedure based on repeatability model using Wombat program. Results: Elevated milk BHBA and Ac concentrations were observed during the early lactation under the negative energy balance. Milk FPR tends to decrease with the decreasing ketone body concentrations. Heritability estimates for milk BHBA, Ac, EB, and FPR ranged from 0.09 to 0.14, 0.23 to 0.31, 0.19 to 0.52, and 0.16 to 0.42 respectively at parity 1, 2, 3, and 4. The overall heritability for BHBA, Ac, EB and FPR were 0.29, 0.32, 0.58, and 0.38 respectively. A common pattern was observed in heritability of EB and FPR along with parities. Conclusion: FPR and EB can be suggested as potential predictors for risk of hyperketonemia. The heritability estimates of milk BHBA, Ac, EB, and FPR indicate that the selective breeding may contribute to maintaining the milk ketone bodies at optimum level during early lactation.

• Journal of the Korea Society for Simulation
• /
• v.29 no.1
• /
• pp.1-9
• /
• 2020

The ballistic missile threat continues to increase with the proliferation of missile technology. In response to this threat, many kinds of interceptors have been emphasized over the years. For development of interceptor, systematic flight tests are essential. Flight tests provide valuable data that can be used to verify performance and confirm the technological progress of ballistic missile defense system including interceptor. However, during flight tests, civilians near the test region could be risk due to a lot of intercept debris. For this reason, reliable estimate of safety area for the flight tests should be preceded. In this study, prediction of safety area is performed through modeling and simulation. Firstly, behaviors of ballistic missile and interceptor are simulated for those entire phase including interception to obtain the relative intercept velocity and the relative impact angle. By using obtained data of kinetic energy, the fragment ejection velocity is calculated and fragment trajectories are simulated by considering drag, gravity and wind effects. Based on the debris field formation and hazard evaluation of debris, final safety area is calculated.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.20 no.1
• /
• pp.34-46
• /
• 2018

Climate change has become a major risk factor for the co-evolving ecological and societal systems that are interconnected through biogeochemical cycles. As the increasing emission of anthropogenic greenhouse gases (GHG) has been attributed to the principal cause of climate change, more attention has been given to the exchange between terrestrial sources/sinks of GHG and the atmosphere. In this review, we abridged a brief history of the background of GHG monitoring and the development of chamber method for the GHG measurement particularly from agriculture. Based on the reviews of prior domestic studies that analyzed the emission characteristics of GHG using chamber method, we discussed the concerns and the ways to improve chamber measurement to establish better scientific database for climate change adaptation.

• Journal of environmental and Sanitary engineering
• /
• v.16 no.4
• /
• pp.21-30
• /
• 2001

Vehicles, especially diesel-using, are a major source of airborne particulate matter(PM), nitrogen dioxide($NO_2$) and so on in metropolitan cities such as Seoul. Therefore workers, who are mainly merchants, near roadside may be highly exposed to air pollutants from exhausted emissions of vehicles. This means that occupational type and location can affect the workers＇health by exposure to outdoor pollutions of ambient as well as indoor pollutions of working condition, respectively. In this study, we simultaneously measured the PM3.5 and $NO_2$concentrations in indoor and outdoor of shoes repair shops in Seoul, which were generally located at roadside in Korea. Shoes repairmen were highly exposed to PM3.5 and $NO_2$ both indoor and outdoor of repair shops comparing with other sub-population groups. High exposure to air pollutants for shoes repairmen was considered to be outdoor source from exhausted emission of vehicles and indoor source from working condition. The $PM3.5/NO_2$ concentration ratio was $1.17{\pm}$0.59 in roadside, of which ratio was higher 7han ratios of other studies. This result suggested that major air pollutant in Seoul was fine particle. Also, this PM3.5 to $NO_2$ ratio will be used in environmental exposure and risk assessment by estimation of PM3.5 concentration as measuring the only $NO_2$ concentration with small and accurate $NO_2$ passive sampler.

• Journal of Environmental Health Sciences
• /
• v.43 no.4
• /
• pp.298-306
• /
• 2017

Objectives: Since 1998, the Korea National Health and Nutrition Examination Survey (KNHANES) has been conducted in order to investigate the health and nutritional status of Koreans. The food intake data of individuals in the KNHANES has also been utilized as source dataset for risk assessment of chemicals via food. To improve the reliability of intake estimation and prevent missing data for less-responded foods, the structure of integrated long-standing datasets is significant. However, it is difficult to merge multi-year survey datasets due to ineffective cleaning processes for handling extensive numbers of codes for each food item along with changes in dietary habits over time. Therefore, this study aims at 1) cleaning the process of abnormal data 2) generation of integrated long-standing raw data, and 3) contributing to the production of consistent dietary exposure factors. Methods: Codebooks, the guideline book, and raw intake data from KNHANES V and VI were used for analysis. The violation of the primary key constraint and the $1^{st}-3rd$ normal form in relational database theory were tested for the codebook and the structure of the raw data, respectively. Afterwards, the cleaning process was executed for the raw data by using these integrated codes. Results: Duplication of key records and abnormality in table structures were observed. However, after adjusting according to the suggested method above, the codes were corrected and integrated codes were newly created. Finally, we were able to clean the raw data provided by respondents to the KNHANES survey. Conclusion: The results of this study will contribute to the integration of the multi-year datasets and help improve the data production system by clarifying, testing, and verifying the primary key, integrity of the code, and primitive data structure according to the database normalization theory in the national health data.