• The Journal of Bigdata
• /
• v.7 no.1
• /
• pp.49-61
• /
• 2022

In sports, the proportion of data analysis in team management such as team strategy planning and marketing is increasing. In KBO(Korea Baseball Organization) league, in particular, plans such as recruiting players and fostering players are established to devise team strategies for the next year, such as FA and trade, at the end of a season. For these reasons, it is very important to predict players' performance for the next year. In this study, the target was limited to only the batter and tried to find out how to predict whether the performance of the next year will improve. As a standard record for rising and falling, OPS(On-Base Plus Slugging), which is easy to calculate and has a high relationship with team score, was used. In this study, 40 years of regular season data from 1982 to 2021 were used as data, and 11 machine learning classification models were used as experimental methods. Predicting the rise and fall of OPS, RBF SVM, Neural Net, Gaussian Process, and AdaBoost were more accurate than other classification models, and age did not significantly affect accuracy.

• Journal of the Institute of Convergence Signal Processing
• /
• v.19 no.3
• /
• pp.118-124
• /
• 2018

Obecity in pregnancy causes many problems and increases risk of pregnancy complications at the time of childbirth. But there is a lack of comprehensive analysis of factors that are negatively affected during pregnancy. Therefore, this study is intended to analyze seven factors of high-risk maternal diseases by the degree of obesity using body mass index(BMI). We conducted a cross tabulation analysis and regression analysis to analisized relationship between variables : Gestational Hypertension(GH), Gestational Diabetes Mellitus(GDM), Thyroid Stimulation Hormone(TSH), Age, Blood Urea Nitrogen Test(BUN), Total-Cholesterol(T-C), and newborn's weight. As a result, the more the obesity level of mothers increases, the more the proportion of mothers with GH, GDM, TSH increases. And there was a positive relationship between the BMI of mothers and their age, T-C, and Newborn weight, and a negative relationship to the BUN.

• Proceedings of the Korean Society of Postharvest Science and Technology of Agricultural Products Conference
• /
• 2003.10a
• /
• pp.143.1-143
• /
• 2003

본 논문은 브랜드 쌀 구매에 영향을 미치는 요인(factor)들이 소비자 특성에 따라 차이가 있는지를 분석하기 위한 목적으로 수행되었다. 분석을 위하여 서울시에 1,000명의 주부를 대상으로 설문조사를 실시하였으며, 그 주요 내용은 다음과 같다. 먼저 주부들이 쌀 구매에 영향을 미치는 11개 항목을 5점 리커르트 척도를 이용하여 분석하였다. 그 결과 소비자들이 가장 높은 점수를 부여하는 것은 쌀의 잔류 농약 정도로서 4.12점이 나왔으며, 영양가 높은 쌀(4.01점), 쌀알의 모양(3.96점) 및 쌀의 생산지(3.88점) 등의 순위가 높았다. 요인분석을 위해 고유치(eigen value) 값이 0.8 이상인 경우를 기준으로 요인 수를 분석한 결과 다섯가지의 요인이 추출되었으며, 그 특징은 유형적 차원과 무형적 차원으로 구분되었다. 전자인 유형적차원은 물리적 속성(완전미 여부, 도정일자, 잔류농약), 지역성(생산지), 외관성(크기, 모양) 및 가격성등의 가시적 차원으로 소비자가 쉽게 판단하거나 쌀간의 비교가 용이한 특성이며, 후자는 심리적 속성이나 상징성을 의미하는 것으로서 브랜드 상표와 품질 인증 마크가 가지는 신뢰성 등이 영향을 미치는 것으로 분석되었다. 무형적 차원인 식품의 안전성이 도시주부간 쌀 구매에 미치는 차별성을 알아보기 위하여 정규성 검정 결과에 따라 독립표본 T-검정을 실시하였다. 분석에서 도시주부가 특성별로 두 집단으로 구분되는 기준은 자의적 분류보다는 공통적인 기준을 이용하고자 평균값(나이, 학력, 소득, 동거가족 수)을 기준으로, 그 외의 경우는 더미변수(주부직업 유무, 주거형태 및 거주지역)를 이용하여 구분하였다. 식품의 안전성으로 추출된 요인 값의 평균에 대해 두 집단간 차이를 검정하였으며, 분석 결과 주거형태가 1％ 유의수준에서, 주부취업 여부 및 거주지역이 각각 5%유의수준에서 통계적 유의성이 있는 것으로 분석되었다. 반면 주부간 나이, 학력, 소득수준 및 동거가족 수에서는 유의미한 결과가 추정되지 못하였다. 본 연구결과를 볼 때, 식품의 안전성을 고려한 쌀의 마케팅 전략은 취업주부, 아파트 거주자 및 강남지역 주부들을 대상으로 한 판매활동 강화가 필요하다. 아울러 통계적으로 유의미한 결과를 나타내는 도시 주부의 특성 변수들을 세밀하게 구분해서 연구·분석하는 시장세분화 연구가 필요하다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.4
• /
• pp.725-732
• /
• 2020

This paper uses variables following as : to follow me well(0-9), it takes a lot of time to make a decision (0-9), lethargy(0-9) during physical activity in the exercise learning program of the children in the marginalized class. This paper classifies 'gender', 'physical education classroom', and 'upper, middle and lower' of age, and observe changes in ego-resiliency and self-control through sports rehabilitation therapy to find out changes in mental health. To achieve this, the data acquired was merged and the characteristics of large and small numbers were removed using the Label encoder and One-hot encoding. Then, to evaluate the performance by applying each algorithm of MLP, SVM, Dicesion tree, RNN, and LSTM, the train and test data were divided by 75% and 25%, and then the algorithm was learned with train data and the accuracy of the algorithm was measured with the Test data. As a result of the measurement, LSTM was the most effective in sex, MLP and LSTM in physical education classroom, and SVM was the most effective in age.

• Journal of the Society of Cosmetic Scientists of Korea
• /
• v.48 no.1
• /
• pp.25-32
• /
• 2022

In this study, basic skin characteristics data were collected by measuring skin hydration, skin melanin, skin redness, and skin torsion elasticity from Korean women in from 20's to 40's ages, and then, age and correlation analysis were conducted. This was used to create a skin index, and cluster analysis was performed to classify the groups into 4 clusters, and the skin characteristics of each cluster were confirmed. Then, two prototypes were used for two weeks to confirm the improvement effect on skin moisture, skin redness, and skin dead mass reduction, and then analyzed which product was more effective in which cluster of subjects participated in the skin characteristics test. As a result of the study, the possibility of preparing for the customized cosmetics market was confirmed by applying the skin index and cluster analysis results to product efficacy evaluation.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.131-136
• /
• 2023

Local youth outmigration is increasingly growing. Various studies are being conducted to identify the factors contributing to this problem, but there is a lack of research analyzing each region individually. Therefore, this study aims to analyze the factors influencing youth outmigration in Busan and predict the risk levels of youth population outflow using machine learning techniques. By utilizing district-level data collected from the KOSIS, we divided the population into three groups based on age (the early 20s, late 20s, and early 30s) and employed Decision Tree and Random Forest algorithms to classify and predict the risk levels of youth population outmigration. The results indicate that the predictive model for youth outmigration risk levels achieves the highest accuracies of 0.93, 0.75, and 0.63 for each age group, respectively.

• Tuberculosis and Respiratory Diseases
• /
• v.58 no.5
• /
• pp.507-514
• /
• 2005

Background : Measurement of the $FEV_1$ and PEFR in COPD patients is a significant indicator of the disease severity, the response to treatment and the acute exacerbation. However, it is not known if PEFR can be used to determine the severity of COPD because the agreement between PEFR and $FEV_1$ in COPD patients is not well known. Methods : From September, 2003 to August, 2004, 125 out patients with COPD who were treated at the pulmonary clinic in KonKuk University Hospital were enrolled in this study. The $FEV_1$ and PEFR of each patient were measured and all the data was analyzed using SPSS. Results : The average predicted $FEV_1$ % and PEFR % was $56.98{\pm}18.21%$ and $70{\pm}27.60%$, respectively. There was linear correlation between the predicted $FEV_1$ % and predicted PEFR %. There was no correlation between age of the COPD patients and the predicted PEFR %. There was correlation between dyspnea, which is a subjective symptom of the patients, and the predicted PEFR %. Conclusion : In COPD patients, the classification of the severity by PEFR tends to underestimate the state of the disease compared with the classification of the severity by the $FEV_1$. Therefore, the classification of the severity by PEFR should be interpreted carefully in patients with severe symptoms. Once the classification of the severity has made, the follow-up examination may use the PEFR instead of the $FEV_1$.

• Clinical and Experimental Pediatrics
• /
• v.49 no.7
• /
• pp.737-744
• /
• 2006

Purpose : To assess the usefulness of $^{99m}Tc-DISIDA$ scanning in the early evaluation of neonatal cholestasis and to verify the diagnostic value of this test in the differential diagnosis of biliary atresia. Methods : DISIDA scannings were performed and analyzed in 87 children(58 males and 29 females; age, 18-139 days, mean, 59.1 days) with neonatal cholestasis. Five groups according to the final diagnosis and the results of DISIDA scanning were analyzed by scatter plots using the parameters of age and the level of liver function tests(direct bilirubin, AST, ALT, ALP, GGT). The diagnostic sensitivity, specificity and accuracy of DISIDA scanning in the diagnosis of biliary atresia were compared between a higher bilirubin group and a lower bilirubin group(direct bilirubin level >5 mg/dL vs. <5 mg/dL) decided by the pattern of scatter plots. Results : DISIDA scannings in the diagnosis of biliary atresia were analyzed by high sensitivity(100 percent, 16/16) but lower specificity(70.4 percent, 50/71) and accuracy(75.9 percent, 66/87). False positivity(29.6 percent, 21/71) was higher in patients with a higher direct bilirubin level(42.5 percent for >5 mg/dL vs. 9.7 percent for <5 mg/dL, P<0.01). The age and the level of liver function tests(AST, ALT, ALP, GGT) analyzed by scatter plots revealed neither diagnostic value in predicting final diagnosis nor estimated the accuracy rate of DISIDA scanning in the evaluation of neonatal cholestasis. Conclusion : We suggest that DISIDA scannings should not be routinely used in evaluating neonatal cholestasis with elevated direct bilirubin level(>5 mg/dL), especially if it delays early diagnosis and surgical intervention.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.47 no.2
• /
• pp.109-119
• /
• 2020

This retrospective study assessed the effectiveness and side effects of conscious sedation using chloral hydrate, hydroxyzine, and N₂O/O₂ in the sedation of 149 pediatric patients over 188 sedation sessions, and to identify associated variables. The effectiveness of the sedation was evaluated using the Houpt scale, and was considered effective for scale categories of excellent or good. Effectiveness and side effects were assessed every 15 minutes. The effectiveness decreased and side effects increased over time. The effectiveness of sedation during 60 minutes was 57.4%, and one or more side effects occurred in 18.1% of sessions. Effectiveness of sedation increased with body mass index (BMI). When patients were sedated at the beginning of the procedure, the effectiveness was greater. Side effects increased with patient age. When sedation was divided into two sessions, the number of sedation did not affect the effectiveness or side effects. It can be suggested that sedation should be performed over two separate sessions, as a single prolonged session may lead to reduced effectiveness and increased side effects. To maximize effectiveness and minimize side effects, several variables such as BMI, whether to sedate at the beginning of the procedure and age should be considered thoroughly before sedation.

• Journal of the Korean Orthopaedic Association
• /
• v.55 no.4
• /
• pp.331-337
• /
• 2020

Purpose: The aim of this retrospective study was to define the prognostic factors for liposarcoma to aid in the selection of effective treatments. Materials and Methods: This study analyzed 41 cases out of 45 cases diagnosed with and treated for liposarcoma 2002 to 2015; 4 cases of well-differentiated liposarcoma were excluded. The effects of sex, age, site, stage, and histological classification on survival were analyzed retrospectively. For 28 cases diagnosed with myxoid liposarcoma, additional analysis was performed after the inclusion of round cell components. Results: The mean age at diagnosis was 52.05 years (range 25-82 years) and the average follow-up period was 63.7 months. The disease-free survival rate was 43.2%. Most factors, including sex and age, were not significantly associated with the survival rate. On the other hand, the stage (Musculoskeletal Tumor Society stage) was significantly associated with the survival rate. The survival rate of patients with myxoid liposarcoma was 69% and the local recurrence and metastasis results varied according to the presence of round cells. Conclusion: The stage of liposarcoma and the sex of the patient were found to be effective factors for prognosis. When planning the treatment for liposarcoma, the treatment outcome for liposarcoma differs according to several prognostic factors.