• 대한원격탐사학회지
• /
• 제36권5_3호
• /
• pp.1053-1066
• /
• 2020

이산화황(SO₂)은 대기 중 화학 반응을 통해 2차 대기오염물질을 생성하는 전구체로, 주로 산업활동이나 주거 및 교통 활동 등을 통해 배출된다. 장기간 노출 시 호흡기 질환이나 심혈관 질환 등을 유발하여 인체 건강에 부정적인 영향을 미칠 수 있기 때문에 이에 대한 지속적인 모니터링이 필요하다. 우리나라에서는 SO₂에 대해 관측소 기반의 모니터링이 수행되고 있으나 이는 공간적으로 연속적인 정보를 제공하는 데에 한계가 있다. 따라서, 본 연구에서는 위성자료와 수치모델 자료를 융합하여 일별 13시를 타겟으로 하는 1 km의 고해상도로 공간적으로 연속적인 SO₂ 지상농도를 산출하였다. 2015년 1월부터 2019년 4월까지의 기간 동안 남한 지역에 대하여 스태킹 앙상블 기법을 이용하여 SO₂ 지상농도 추정 모델을 개발하였다. 스태킹 앙상블 기법이란 여러가지 기계학습 기법을 두 단계로 쌓는 방식으로 융합하여 단일 모델 대비 더 향상된 성능을 도출하는 방법이다. 본 연구에서는 베이스 모델로는 RF (Random Forest)와 XGB (eXtreme Gradient BOOSTing) 기법이, 메타 모델로는 MLR (Multiple Linear Regression) 기법이 사용되었다. 구축된 모델의 교차검증 결과 메타 모델은 상관계수(R) = 0.69와 root-mean-squared-error(RMSE) = 0.0032 ppm의 결과를 보였으며 이는 베이스 모델의 평균 대비 약 25% 향상된 안정성을 보였다. 또한 모델 구축에 사용되지 않은 기간에 대한 예측 검증을 수행하여 모델의 일반화 가능성을 평가하였다. 구축된 모델을 이용하여 남한 지역의 SO₂ 지상농도 공간분포를 분석한 결과 일반적인 계절성과 배출원의 변화를 잘 반영하는 패턴을 보임을 확인하였다.

• 대한원격탐사학회지
• /
• 제37권2호
• /
• pp.275-290
• /
• 2021

대기 중의 이산화황(SO2)은 주로 인위적 배출원에 의해 발생하며 화학 반응을 통해 (초)미세먼지를 형성하여 직간접적으로 주변 환경 및 인체 건강에 해로운 영향을 주는 물질이다. 특히 지상에서의 농도는 인간 활동과 밀접한 관련이 있어 모니터링의 필요성이 매우 크다. 따라서, 본 연구에서는 TROPOMI SO2 연직 컬럼 농도 산출물 및 타 위성 산물과 모델 산출물 등을 융합 활용하여 기계학습 기법에 적용하여 SO2 지상 농도 추정모델을 개발하였다. 기계학습 기법으로는 널리 활용되고 있는 RF(Random Forest)에 잔차 보정 과정을 결합한 2-step 잔차 보정 RF를 적용하였다. 개발된 모델은 무작위, 공간 및 시간별 10-fold 교차 검증을 통하여 검증하였으며, 기울기(slope) 값이 1.14-1.25, 상관계수(R) 값이 0.55-0.65, rRMSE 값이 약 58-63% 정도로 나타났다. 이는 잔차 보정이 적용되지 않은 기존의 RF 대비 slope의 경우 약 10%, R과 rRMSE의 경우 약 3% 가량 향상된 결과를 보인다. 국가별로 나누어 분석하였을 때에는 샘플 수가 적고 SO2의 전반적인 농도가 낮은 일본 지역에서의 공간별 10-fold 교차검증 성능이 소폭 감소하는 것으로 나타났다. SO2 지상농도 분포를 계절별로 표출하였을 때, 일본의 경우 다른 지역 대비 연중 저농도가 관찰되며 높은 결측 값 비율로 인하여 관측소 농도 대비 2-step 잔차 보정 RF 모델에서 과대 모의하는 경향이 관찰되었다. 대표적 고농도 발생지인 중국의 YRD(Yangtze River Delta) 와 한국의 SMA(Seoul Metropolitan Area)의 계절적 분포 변화를 추가적으로 분석하였을 때, 연료 연소로 인한 겨울철 농도 증가 패턴이 나타났다. 이는 인위적 배출원의 영향을 크게 받는 SO2의 시공간적인 분포 특성을 잘 반영하고 있는 결과이다. 따라서, 본 연구를 통하여 제안한 모델은 장기적으로 SO2 지상 농도의 시공간적 분포를 파악하는 데에 활용될 수 있을 것으로 기대된다.

• 한국환경보건학회지
• /
• 제48권2호
• /
• pp.96-105
• /
• 2022

Background: Pyrethroid insecticides account for more than 30% of the global insecticide market and are frequently used in agricultural settings and residential and public pest control among the general population. While several animal studies have suggested that exposure to pyrethroids can alter glucose homeostasis, there is only limited evidence of the association between environmental pyrethroid exposure and diabetes in humans. Objectives: This study aimed to report environmental 3-phenoxybenzoic acid (3-PBA) concentrations in urine and evaluate its association with the risk of diabetes in Korean adults. Methods: We analyzed data from the Korean National Environmental Health Survey (KoNEHS) Cycle 2 (2012~2014) and Cycle 3 (2015~2017). A total of 10,123 participants aged ≥19 years were included. Multiple logistic regressions were used to calculate the odds ratios (ORs) for diabetes according to log-transformed urinary 3-PBA levels. We also evaluated age, sex, education, monthly income, marital status, alcohol drinking, physical activity, urinary cotinine, body mass index, and sampling season as potential effect modifiers of these associations. Results: After adjusting for all the covariates, we found significant dose-response relationships between urinary 3-PBA as quartile and the prevalence of diabetes in pooled data of KoNEHS Cycles 2 and 3. In subgroup analyses, the adverse effects of pyrethroid exposure on diabetes were significantly stronger among those aged 19~39 years (p-interaction<0.001) and those who consumed high levels of cotinine (p-interaction=0.020). Conclusions: Our findings highlight the potential diabetes risk of environmental exposure to pyrethroids and should be confirmed in large prospective studies in different populations in the future.

• Journal of Gastric Cancer
• /
• 제21권2호
• /
• pp.179-190
• /
• 2021

Purpose: Reduced port laparoscopic distal gastrectomy (RPLDG) using 3 ports is less invasive than conventional laparoscopic distal gastrectomy (CLDG) using 5 ports. Although RPLDG performed by expert surgeons is safe and feasible, novice surgeons have difficulty performing this procedure. This study evaluated the surgical outcomes and feasibility of RPLDG performed by a novice surgeon. Materials and Methods: The records of 136 patients who underwent laparoscopic distal gastrectomy for gastric cancer performed by a single novice surgeon between May 2016 and December 2018 were retrospectively reviewed. Among these 136 patients, 52 underwent RPLDG and 84 underwent CLDG. The clinicopathological characteristics, operative outcomes, and short-term postoperative outcomes of the 2 groups were compared. Results: The percentage of women was significantly higher in the RPLDG group than in the CLDG group (48.1% vs. 31%; P=0.045), but other baseline characteristics did not differ significantly between the groups. Billroth II anastomosis was performed significantly more frequent (90.4% vs. 73.8%, P=0.015) and operation time was significantly shorter (207.1±43.3 min vs. 225.5±44.6 min, P=0.020) in the RPLDG group than in the CLDG group. The time to first flatus, postoperative pain score, length of postoperative hospital stay, and incidence and severity of complications did not differ significantly between the groups. Analysis of the learning curve based on the operation time showed that performing RPLDG on 20-30 patients was required to achieve technical proficiency. Conclusions: RPLDG is a safe and feasible surgical procedure for the treatment of gastric cancer, even when performed by a novice surgeon.

• Journal of Gastric Cancer
• /
• 제22권2호
• /
• pp.120-134
• /
• 2022

Purpose: This study aimed to identify prognostic factors for patients with distant lymph node-involved gastric cancer (GC) using a machine learning algorithm, a method that offers considerable advantages and new prospects for high-dimensional biomedical data exploration. Materials and Methods: This study employed 79 features of clinical pathology, laboratory tests, and therapeutic details from 289 GC patients whose distant lymphadenopathy was presented as the first episode of recurrence or metastasis. Outcomes were measured as any-cause death events and survival months after distant lymph node metastasis. A prediction model was built based on possible outcome predictors using a random survival forest algorithm and confirmed by 5×5 nested cross-validation. The effects of single variables were interpreted using partial dependence plots. A contour plot was used to visually represent survival prediction based on 2 predictive features. Results: The median survival time of patients with GC with distant nodal metastasis was 9.2 months. The optimal model incorporated the prealbumin level and the prothrombin time (PT), and yielded a prediction error of 0.353. The inclusion of other variables resulted in poorer model performance. Patients with higher serum prealbumin levels or shorter PTs had a significantly better prognosis. The predicted one-year survival rate was stratified and illustrated as a contour plot based on the combined effect the prealbumin level and the PT. Conclusions: Machine learning is useful for identifying the important determinants of cancer survival using high-dimensional datasets. The prealbumin level and the PT on distant lymph node metastasis are the 2 most crucial factors in predicting the subsequent survival time of advanced GC.

• 한국안전학회지
• /
• 제36권5호
• /
• pp.79-85
• /
• 2021

A standard engineering model that reflects the current organization system and engineering operation process of domestic nuclear power plants was developed based on the Standard Nuclear Performance Model developed by the American Nuclear Energy Association. The level 0 screen, which is the main screen of the engineering model computer system, consisted of an object tree structure, which provided information that is phased down from a higher structure level to a lower structure level (i.e., level 3). The level 1 screen provided information related to the sub-process of the engineering operation, whereas the Level 2 screen provided information related to each engineering operation activity. In addition, the Level 2 screen provided additional functions, such as linking electronic procedures/guidelines, providing electronic performance forms, and connecting legacy computer systems (such as total equipment reliability monitoring system, configuration management systems, technical information systems, risk monitoring systems, regulatory information, and electronic drawing system). This screen level increased the convenience of user's engineering tasks by implementing them. The computerization of an engineering model that connects the entire engineering tasks of an establishment enables the easy understanding of information related to the engineering process before and after the operation, and builds a foundation for the enhancement of the work efficiency and employee capacity. In addition, KHNP developed an online training module, which operates as an e-learning process, on the overview and utilization of a standard engineering model to expand the understanding of standard engineering models by plant employees and to secure competitiveness.

• Geomechanics and Engineering
• /
• 제37권3호
• /
• pp.223-241
• /
• 2024

Evaluating the performance of Tunnel Boring Machines (TBMs) stands as a pivotal juncture in the domain of hard rock mechanized tunneling, essential for achieving both a dependable construction timeline and utilization rate. In this investigation, three advanced artificial neural networks namely, gated recurrent unit (GRU), back propagation neural network (BPNN), and simple recurrent neural network (SRNN) were crafted to prognosticate TBM-rate of penetration (ROP). Drawing from a dataset comprising 1125 data points amassed during the construction of the Alborze Service Tunnel, the study commenced. Initially, five geomechanical parameters were scrutinized for their impact on TBM-ROP efficiency. Subsequent statistical analyses narrowed down the effective parameters to three, including uniaxial compressive strength (UCS), peak slope index (PSI), and Brazilian tensile strength (BTS). Among the methodologies employed, GRU emerged as the most robust model, demonstrating exceptional predictive prowess for TBM-ROP with staggering accuracy metrics on the testing subset (R² = 0.87, NRMSE = 6.76E-04, MAD = 2.85E-05). The proposed models present viable solutions for analogous ground and TBM tunneling scenarios, particularly beneficial in routes predominantly composed of volcanic and sedimentary rock formations. Leveraging forecasted parameters holds the promise of enhancing both machine efficiency and construction safety within TBM tunneling endeavors.

• Clinics in Shoulder and Elbow
• /
• 제25권2호
• /
• pp.145-153
• /
• 2022

Background: While online orthopedic resources are becoming an increasingly popular avenue for patient education, videos on YouTube are not subject to peer review. The purpose of this cross-sectional study was to evaluate the quality of YouTube videos for patient education in ulnar collateral ligament (UCL) injuries of the elbow. Methods: A search of keywords for UCL injury was conducted through the YouTube search engine. Each video was categorized by source and content. Video quality, reliability, and accuracy were assessed by two independent raters using five metrics: (1) Journal of American Medical Association (JAMA) benchmark criteria (range 0-4) for video reliability; (2) modified DISCERN score (range 1-5) for video reliability; (3) Global Quality Score (GQS; range 1-5) for video quality; (4) ulnar collateral ligament-specific score (UCL-SS; range 0-16), a novel score for comprehensiveness of health information presented; and (5) accuracy score (AS; range 1-3) for accuracy. Results: Video content was comprised predominantly of disease-specific information (52%) and surgical technique (33%). The most common video sources were physician (42%) and commercial (23%). The mean JAMA score, modified DISCERN score, GQS, UCL-SS, and AS were 1.8, 2.4, 1.9, 5.3, and 2.7 respectively. Conclusions: Overall, YouTube is not a reliable or high-quality source for patients seeking information regarding UCL injuries, especially with videos uploaded by non-physician sources. The multiplicity of low quality, low reliability, and irrelevant videos can create a cumbersome and even inaccurate learning experience for patients.

• 한국축산식품학회지
• /
• 제40권2호
• /
• pp.183-196
• /
• 2020

The protective effect of pig skin gelatin water extracts (PSW) and the low molecular weight hydrolysates of PSW generated via enzymatic hydrolysis with Flavourzyme® 1000L (LPSW) against scopolamine-induced impairment of cognitive function in mice was determined. Seventy male ICR mice weighing 20-25 g were randomly assigned to seven groups: Control (CON); scopolamine (SCO, 1 mg/kg B.W., intraperitoneally (i.p.); tetrahydroaminoacridine 10 [THA 10, tacrine; 10 mg/kg B.W. per oral (p.o.) with SCO (i.p.)]; PSW 10 (10 mg/kg B.W. (p.o.) with SCO (i.p.); PSW 40 (40 mg/kg B.W. (p.o.) with SCO (i.p.); LPSW 100 (100 mg/kg B.W. (p.o.) with SCO (i.p.); LPSW 400 (400 mg/kg B.W. (p.o.) with SCO (i.p.). All treatment groups, except CON, received scopolamine on the day of the experiment. The oxygen radical absorbance capacity of LPSW 400 at 1 mg/mL was 154.14 μM Trolox equivalent. Administration of PSW and LPSW for 15 weeks did not significantly affect on physical performance of mice. LPSW 400 significantly increased spontaneous alternation, reaching the level observed for THA and CON. The latency time of animals receiving LPSW 400 was higher than that of mice treated with SCO alone in the passive avoidance test, whereas it was shorter in the water maze test. LPSW 400 increased acetylcholine (ACh) content and decreased ACh esterase activity (p<0.05). LPSW 100 and LPSW 400 reduced monoamine oxidase-B activity. These results indicated that LPSW at 400 mg/kg B.W. is a potentially strong antioxidant and contains novel components for the functional food industry.

• 융합신호처리학회논문지
• /
• 제21권4호
• /
• pp.183-194
• /
• 2020

최근 영유아 성장기에 발생하는 고관절 이형성증(Developmental Dysplasia of Hip, DDH)의 숫자가 늘어나고 있다. DDH는 영유아 성장을 방해하고 다른 부작용도 많이 발생시키기 때문에 최대한 조기에 발견하여 치료해야 한다. 최근 들어 Convolutional Neural Networks (CNN) 및 개선된 Resnet50을 활용한 머신러닝 기법이 초음파 영상 분석에 많이 활용되고 있다. 연구 결과를 보면 컴퓨터 보조 이미지 분석이 의료현장에서 객관성과 생산성을 크게 향상시키고 있다. 본 연구의 결과는 정형외과에서의 난제인 초음파 영상을 통한 DDH 컴퓨터 보조 진단 알고리즘에도 충분히 활용될 수 있다는 것을 보여주고 있다. 본 논문에서는 CNN을 활용하여 DDH를 자동으로 측정하고 진단할 수 있는 컴퓨터 보조 진단 알고리즘을 제안하였다. DDH 측정을 위해 유아 고관절의 정상/비정상 판독을 위해 Acetabulum-Femoral head의 angle을 자동으로 계산하였으며 기존 영상을 딥 러닝하여 진단을 자동으로 하는 알고리즘을 설계하였다. 실험 결과 의사와 비교하여 진단의 속도와 정확도가 향상된다는 것을 확인하였다.