• 생물정신의학
• /
• 제20권2호
• /
• pp.54-60
• /
• 2013

Objectives The purpose of this study is to find the influential clinical and physical characteristics which affect apnea-hypopnea index (AHI) in suspected obstructive sleep apnea (OSA) patients. Methods We evaluated the comprehensive factors including sleep related symptoms, clinical scales, medical history, substance use, and anthropometric data of the 119 participants who complained of the symptoms of OSA. All the participants underwent attended-full night laboratory polysomnography. The correlation and multiple regression analysis were conducted to find the influential and predictive factors of AHI. Results A multiple linear regression model 1 showed that higher AHI was associated with higher body mass index (BMI)(p < 0.001) and higher frequency of observed apnea (p = 0.002). In multiple linear regression model 2, AHI was associated with higher BMI (p < 0.001) and loudness of snoring (p = 0.018). Conclusions The present preliminary results suggest that BMI and observed apnea are most influential factors that affect AHI in suspected OSA patients. In the future study we will design the prediction formula for the OSA and AHI, which is useful in the clinical medical field.

• 분석과학
• /
• 제24권6호
• /
• pp.533-543
• /
• 2011

hERG (human ether-a-go-go related gene) 이온채널은 심장 재분극의 중요 요소이며 이 채널의 저해제는 부정맥과 돌연사를 유발할 수 있다. 따라서, 신약개발과정에서 후보물질이 hERG 이온채널의 잠재적인 저해제일 경우에는 심장독성 부작용을 유발하므로, 이를 최소화하고자 많은 노력이 집중되고 있다. 본 연구는 HEK(인간 배아 신장)세포에서 얻은 202개 유기화합물의 $IC_{50}$ 데이터를 이용하여 2차원 구조-활성의 정량적 관계(2D-QSAR)방법으로 예측하는 모델을 개발하였다. hERG이온채널 저해제의 기계 학습방법으로는 다중선형회귀(Multiple Linear Regression), 서포트 벡터 머신(Support Vector Machine: SVM)방법과 인공신경망(Artificial Neural Network)방법이며, 교차검증을 적용한 모집단 기반 전진선택(forward selection)방법과 결합하여 각 학습모델에 적합한 최적의 표현자들을 결정하였다. 가장 우수한 방법은 14종의 표현자를 사용한 인공신경망방법($R^2_{CV}$=0.617, RMSECV=0.762, MAECV=0.583)이었고, 다중선형회귀방법을 통해서 hERG이온채널 저해물질의 구조적 특징과 수용체와의 상호작용을 설명할 수 있다. QSAR모델의 검증은 교차검증과 Y-scrambling test방법으로 수행하였다.

• 디지털융복합연구
• /
• 제12권7호
• /
• pp.261-266
• /
• 2014

시계열 모형에서 모수의 수가 많으면 모수추정에 따르는 오차가 커지게 되므로 예측을 하는데 많은 어려움이 있다. 만약 여러개의 시계열 자료들이 동일한 모형에서부터 얻어졌다고 하는 동질성 가설이 채택되면 모수축약을 이룰 수 있고, 더 좋은 예측값을 얻을 수 있다. 비선형 시계열 패널 자료는 각각의 시계열마다 모수들이 있기 때문에 매우 많은 모수가 존재하게되고, 모수의 수가 많으면 모수추정에 따르는 오차가 커지게 되어 예측의 정확도가 떨어지게 된다. 패널내에 존재하는 독립적인 여러 시계열들의 동질성이 만족되면 시계열을 종합하여 모수를 추정하고 검정할 수 있다. m개의 독립적인 비선형 시계열 패널 자료의 동질성 검정을 알아보기 위하여 모형을 설정하고 이 모형에 대한 정상성 조건을 구하였고, 동질성 검정통계량을 유도했으며, 구한 검정 통계량의 극한분포가 ${\chi}^2$ 분포를 따르는 것을 보였다. 실증분석에 있어서는 비선형 시계열 자료중 중선형 시계열 모형의 동질성 검정을 하고, 실제 우리나라 주식자료를 2개의 집단으로 나누어 비선형 시계열 패널 자료의 동질성 검정에 대한 분석을 하였다.

• 한국빅데이터학회지
• /
• 제4권1호
• /
• pp.63-72
• /
• 2019

전력 에너지의 경우 발전 및 송전 과정을 거쳐 사용자에게 제공된 이후에는 회수가 불가능하기 때문에 정확한 수요 예측에 기반한 최적 발전 및 송배전 계획이 필요하다. 전력 수요 예측의 실패는 2011년 9월에 발생한 대규모 정전사태와 같이 다양한 사회적·경제적 문제를 야기할 수 있다. 전력 수요 예측 관련 기존 연구에서는 ARIMA, 신경망모형 등 다양한 방법으로 개발이 되었다. 하지만 전국 단위의 평균 외기온도를 사용한다는 점과, 계절성을 구분하기 위한 획일적 기준을 적용하는 한계점으로 인해 데이터의 왜곡이나 예측모형의 성능 저하를 초래하고 있다. 이에 본 연구에서는 전력 수요 예측 모형의 성능을 향상하기 위해 전국을 5대 권역으로 구분하여 지역적 특성과 이동 기간 학습 기법을 통해 계절적 특성을 반영한 선형회귀모형과 신경망 모형의 장기적 전력 수요 예측 모형을 개발하였다. 이를 통해 중장기부터 단기에 이르기까지 다양한 범위의 수요 예측에 해당 모델을 활용할 수 있을 뿐만 아니라 특정 기간 중에 발생하는 다양한 이벤트와 예외 상황을 고려할 수 있을 것이다.

• Journal of Trauma and Injury
• /
• 제25권4호
• /
• pp.139-144
• /
• 2012

Purpose: Hypovolemic shock is the leading cause of death in multiple trauma patients with pelvic bone fracures. The purpose of this study was to develop a simple prediction method for injury severity and amount of hemorrhage via an analysis of the correlation between the site of pelvic bone fracture and the amount of transfusion and to verify the usefulness of the such a simple scoring system. Methods: We analyzed retrospectively the medical records and radiologic examination of 102 patients who had been diagnosed as having a pelvic bone fracture and who had visited the Emergency Department between January 2007 and December 2011. Fracture sites in the pelvis were confirmed and re-classified anatomically as pubis, ilium or sacrum. A multiple linear regression analysis was performed on the amount of transfusion, and a simplified scoring system was developed. The predictive value of the amount of transfusion for the scoring system as verified by using the receiver operating characteristics (ROC). The area under the curve of the ROC was compared with the injury severity score (ISS). Results: From among the 102 patients, 97 patients (M:F=68:29, mean $age=46.7{\pm}16.6years$) were enrolled for analysis. The average ISS of the patients was $16.2{\pm}7.9$, and the average amount of packed RBC transfusion for 24 hr was $3.9{\pm}4.6units$. The regression equation resulting from the multiple linear regression analysis was 'packed RBC units=1.40${\times}$(sacrum fracture)+1.72${\times}$(pubis fracture)+1.67${\times}$(ilium fracture)+0.36' and was found to be suitable (p=0.005). We simplified the regression equation to 'Pelvic Bleeding Score=sacrum+pubis+ilium.' Each fractured site was scored as 0(no fracture) point, 1(right or left) point, or 2(both) points. Sacrum had only 0 or 1 point. The score ranged from 0 to 5. The area under the curve (AUC) of the ROC was 0.718 (95% CI: 0.588-0.848, p=0.009). For an upper Pelvis Bleeding Score of 3 points, the sensitivity of the prediction for a massive transfusion was 71.4%, and the specificity was 69.9%. Conclusion: We developed a simplified scoring system for the anatomical fracture sites in the pelvis to predict the requirement for a transfusion (Pelvis Bleeding Score (PBS)). The PBS, compared with the ISS, is considered a useful predictor of the need for a transfusion during initial management.

• 보존과학회지
• /
• 제34권5호
• /
• pp.387-396
• /
• 2018

국내 목조건축문화재는 자연환경에 그대로 노출되어 있어 생물피해와 여러 환경요인에 의해 피해가 가속화되고 있다. 이에 본 연구에서는 보은 법주사와 순천 선암사에 기상인자 모니터링을 위한 자동기상측정장비를 설치하여 기상데이터를 수집하였다. 이들 데이터에 통계 모형을 적용하여 기상인자를 예측하고 기상인자별 예측성능을 비교하였다. 그 결과, 법주사와 선암사 두 곳 모두에서 대기온도와 이슬점온도의 상관계수가 0.95 이상으로 가장 높게 나타났으며 상대습도의 상관계수는 0.65로 낮게 나타났다. 결과적으로 일반선형모형은 대기온도와 이슬점온도를 예측하기에 적합하다는 것을 확인하였다. 기상인자들 사이의 상관성을 분석한 결과, 법주사와 선암사 모두 대기온도와 이슬점온도, 일사량과 증발량 사이에 강한 양의 상관성을 보였으며, 법주사에서는 대기온도와 증발량이 약한 양의 상관성을 나타내었고 선암사에서는 풍속이 대기온도와 상대습도에 대하여 약한 음의 상관성을 나타내었다. 선암사의 풍속은 겨울에 높고 여름에 평균 이하로 낮아지는 패턴을 보이는데, 이것은 대기온도와 상대습도가 높은 여름철에 수분의 증발을 막고 정체시키는 역할을 하는 것으로 판단되며, 결과적으로 이것이 선암사의 목조건축물 피해를 가속화시키는 것으로 판단된다.

• 대한임상검사과학회지
• /
• 제36권2호
• /
• pp.199-204
• /
• 2004

Height has become one of the most important factors to determine the pulmonary function test index, and there is a high correlation between them, so that they have been utilized for evaluating pulmonary function test predictive value or nomogram. Therefore, we have tried to find out that difference and if there is any correlation and linear relationship between height and forced expiratory flow curve. There were a total of 163 subjects, male 93 and female 70. This study was done at the Department of Pulmonary Function Test of Jeon-Ju Presbyterian Hospital and we measured the index at the forced expiratory flow curve of FVC, $FEV_{1.0}$, $FEV_{1.0}$/FVC, $FEF_{25-75%}$, and $FEF_{200-1200m{\ell}}$. When we subjected the group of height more than 160cm, there were gradual increments at FVC(p<0.001), $FEV_{1.0}$(p<0.001), $FEF_{25-75%}$(p<0.05) and $FEF_{200-1200m{\ell}}$(p<0.001), but no changes at $FEV_{1.0}$/FVC in terms of forced expiratory flow curve index. We have analyzed the relationship between height and forced expiratory flow curve, there was a close relationship at FVC(r=0.670, p<0.01), $FEV_{1.0}$(r=0.491, p<0.01), $FEF_{25-75%}$ (r=0.175, p<0.05) and $FEF_{200-1200m{\ell}}$(r=0.370, p<0.01) but there was reciprocal relationship at $FEV_{1.0}$/FVC(r=-0.215, p<0.01). We have tried simple regression analysis to see if height affects forced expiratory flow curve index as a sector, and the result was $FVC(\ell)=0.0642{\times}height(cm)-7.2978$(p<0.01, $R^2=0.449$), $FEV_{1.0}(\ell)=0.0407{\times}height(cm)-4.2774$ (p<0.01, $R^2=0.2411$), $FEV_{1.0}/FVC(%)=-0.2892{\times}height(cm)+121.44$(p<0.01, $R^2=0.0464$), $FEF_{25-75%}(\ell/sec)=0.0176{\times}height(cm)-0.7876$(p<0.05, $R^2=0.0237$), $FEF_{200-1200m{\ell}}(\ell/sec)=0.0967{\times}height(cm)-11.037$(p<0.01, $R^2=0.1214$) this was approved statistically. According to this study, if height is taller than average, forced expiratory flow curve index were increased, there was a close relationship between height and forced expiratory flow curve, and there was a linear relationship as sector between height and forced expiratory flow curve index. Therefore, researches that study other factors such as sex, age, weight, body surface area, and obesity indexes other than height should be done to see if there are any further relationships.

• Safety and Health at Work
• /
• 제11권1호
• /
• pp.118-124
• /
• 2020

Background: The poultry industry in Pakistan has flourished since the 1960s; however, there are scarce data regarding the impact of occupational exposure on the pulmonary health of farm workers in terms of years working in the industry. The objective of the present study was to assess the effect of poultry environment on the health of occupationally exposed poultry farmers in countries of warm climatic regions, such as Pakistan. This study will also show the effect of exposure to poultry facilities on the health of poultry farmers in the context of low-income countries with a relatively inadequate occupational exposure risk management. Materials and methods: The lung function capacity of 79 poultry workers was measured using a spirometer. Along with spirometry, a structured questionnaire was also administrated to obtain information about age, height, weight, smokers/nonsmokers, years of working experience, and pulmonary health of farm workers. The workers who were directly involved in the care and handling of birds in these intensive facilities were considered and divided into four groups based on their years of working experience: Group I (3-10 months), Group II (1-5 years), Group III (6-10 years), and Group IV (more than 11 years). The forced vital capacity (FVC), forced expiratory volume in one second (FEV1) and the FEV1/FVC ratio were considered to identify lung function abnormalities. Statistical analysis was carried out using independent sample t test, Chi-square test, Pearson's correlation, and linear regression. Results: Based on the performed spirometry, 68 (86 %) of workers were found normal and healthy, whereas 11 (14 %) had a mild obstruction. Of the 11 workers with mild obstruction, the highest number with respect to the total was in Group IV (more than 11 years of working experience) followed by Group III and Group II. Most of the workers were found healthy, which seems to be because of the healthy survivor effect. For the independent sample t test, a significant difference was noticed between healthy and nonhealthy farmers, whereas Chi-square test showed a significant association with height, drugs, and working experience. Linear regression that was stratified by respiratory symptoms showed for workers with symptoms, regression models for all spirometric parameters (FVC, FEV1, and FEV1/FVC) have better predictive power or R square value than those of workers without symptoms. Conclusion: These findings suggest that lung function capacity was directly related to years of working experience. With increasing number of working years, symptoms of various respiratory problems enhanced in the poultry workers. It should be noted that most of the poultry workers were healthy and young, the rationale being that there is a high turnover rate in this profession. The mobility in this job and our finding of 86% of the healthy workers in the present study also proposed healthy worker survivor effect.

• Tuberculosis and Respiratory Diseases
• /
• 제80권4호
• /
• pp.385-391
• /
• 2017

Background: Men with chronic obstructive pulmonary disease, have reduced endogenous testosterone levels, but the relationship between pulmonary function and endogenous testosterone levels, is inconsistent. Testicular volume is a known indicator of endogenous testosterone levels, male fertility, and male potency. In the present study, the authors investigated the relationship, between testicular volume and lung function. Methods: One hundred and eighty-one South Korean men age 40-70, hospitalized for urological surgery, were retrospectively enrolled, irrespective of the presence of respiratory disease. Study subjects underwent pulmonary function testing, prior to procedures, and testicular volumes were measured by orchidometry. Testosterone levels of patients in blood samples collected between $7{\small{AM}}$ and $11{\small{AM}}$, were measured by a direct chemiluminescent immunoassay. Results: The 181 study subjects were divided into two groups, by testicular volume (${\geq}35mL$ vs. <35 mL), the larger testes group, had better lung functions (forced vital capacity [FVC]: $3.87{\pm}0.65L$ vs. $3.66{\pm}0.65L$, p=0.037; forced expiratory volume in 1 second [$FEV_1$]: $2.92{\pm}0.57L$ vs. $2.65{\pm}0.61L$, p=0.002; FVC % predicted: $98.2{\pm}15.2%$ vs. $93.8{\pm}13.1%$, p=0.040; $FEV_1$ % predicted: $105.4{\pm}19.5%$ vs. $95.9{\pm}21.2%$, p=0.002). In addition, the proportion of patients with a $FEV_1/FVC$ of <70%, was lower in the larger testes group. Univariate analysis conducted using linear regression models, revealed that testicular volume was correlated with FVC (r=0.162, p=0.029), $FEV_1$ (r=0.218, p=0.003), $FEV_1/FVC$ (r=0.149, p=0.046), and $FEV_1$ % predicted (r=0.178, p=0.017), and multivariate analysis using linear regression models, revealed that testicular volume was a significant predictive factor for $FEV_1$ % predicted (${\beta}=0.159$, p=0.041). Conclusion: Larger testicular volume was independently associated, with favorable indices of lung function. These results suggest that androgens, may contribute to better lung function.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제12권2호
• /
• pp.59-76
• /
• 2023

코로나 시대 이후 아파트 가격 상승은 비상식적이었다. 이러한 불확실한 부동산 시장에서 가격 예측 연구는 매우 중요하다. 본 논문에서는 다양한 부동산 사이트에서 자료 수집 및 크롤링을 통해 2015년부터 2020년까지 87만개의 방대한 데이터셋을 구축하고 다양한 아파트 정보와 경제지표 등 가능한 많은 변수를 모은 뒤 미래 아파트 매매실거래가격을 예측하는 모델을 만든다. 해당 연구는 먼저 다중 공선성 문제를 변수 제거 및 결합으로 해결하였다. 이후 의미있는 독립변수들을 뽑아내는 전진선택법(Forward Selection), 후진소거법(Backward Elimination), 단계적선택법(Stepwise Selection), L1 Regularization, 주성분분석(PCA) 총 5개의 변수 선택 알고리즘을 사용했다. 또한 심층신경망(DNN), XGBoost, CatBoost, Linear Regression 총 4개의 머신러닝 및 딥러닝 알고리즘을 이용해 하이퍼파라미터 최적화 후 모델을 학습시키고 모형간 예측력을 비교하였다. 추가 실험에서는 DNN의 node와 layer 수를 바꿔가면서 실험을 진행하여 가장 적절한 node와 layer 수를 찾고자 하였다. 결론적으로 가장 성능이 우수한 모델로 2021년의 아파트 매매실거래가격을 예측한 후 실제 2021년 데이터와 비교한 결과 훌륭한 성과를 보였다. 이를 통해 머신러닝과 딥러닝은 다양한 경제 상황 속에서 투자자들이 주택을 구매할 때 올바른 판단을 할 수 있도록 도움을 줄 수 있을 것이라 확신한다.