• Korean Journal of Psychosomatic Medicine
• /
• v.27 no.2
• /
• pp.101-110
• /
• 2019

Objectives : It is not clear which clinical variables are most closely associated with delirium in the Intensive Care Unit (ICU). By comparing clinical data of ICU delirium and non-delirium patients, we sought to identify variables that most effectively differentiate delirium from non-delirium. Methods : Medical records of 6,386 ICU patients were reviewed. Random Subset Feature Selection and Principal Component Analysis were utilized to select a set of clinical variables with the highest discriminatory capacity. Statistical analyses were employed to determine the separation capacity of two models-one using just the selected few clinical variables and the other using all clinical variables associated with delirium. Results : There was a significant difference between delirium and non-delirium individuals across 32 clinical variables. Richmond Agitation Sedation Scale (RASS), urinary catheterization, vascular catheterization, Hamilton Anxiety Rating Scale (HAM-A), Blood urea nitrogen, and Acute Physiology and Chronic Health Examination II most effectively differentiated delirium from non-delirium. Multivariable logistic regression analysis showed that, with the exception of vascular catheterization, these clinical variables were independent risk factors associated with delirium. Separation capacity of the logistic regression model using just 6 clinical variables was measured with Receiver Operating Characteristic curve, with Area Under the Curve (AUC) of 0.818. Same analyses were performed using all 32 clinical variables;the AUC was 0.881, denoting a very high separation capacity. Conclusions : The six aforementioned variables most effectively separate delirium from non-delirium. This highlights the importance of close monitoring of patients who received invasive medical procedures and were rated with very low RASS and HAM-A scores.

• Korean Journal of Ecology and Environment
• /
• v.52 no.4
• /
• pp.348-357
• /
• 2019

To investigate the changes of dominant species of benthic macroinvertebrates following summer precipitation variance, we surveyed twenty five sites of the main Seomjin River in May and September in 2014 and 2015. The temperature, precipitation, water quality factors and substrate composition, water depth and flow velocity, which are important factors in benthos habitat environment, were collected and measured. There is not much difference of the cumulative precipitation (CP) between 2014 (2,322.1 mm) and 2015 (2,371.0 mm) in May. However CP in september was decreased by more than half in 2015 (3,726.1 mm) than 2014 (7,678.2 mm). Due to washing effect by summer precipitation, total number of species and individuals for benthic macroinvertebrates were higher in May than in September. Chironomidae spp. and Choroterpes altioculus were dominated in May, Ecdyonurus levis, Ecdyonurus kibunensis were dominated in September. As a result of correlation analysis between community indices and environment factors, it was found that there is a significant correlation with flow velocity and substrate compositions. According to the results of cluster analysis and PCA based on environment fators and dominant species of benthic macroinvertebrates in Seomjin River, it was divided into four groups following CP and MT. Ecdyonurus levis and Ecdyonurus kibunensis reflect the effect of the decrease in summer precipitation.

• Food Science and Preservation
• /
• v.11 no.4
• /
• pp.441-447
• /
• 2004

To elucidate changes in qualifies of pork and beef during storage and identify decay point, beef (loin, tenderloin, plate) and pork (belly, loin, thigh) were stored at $4^{\circ}C$, and their pH, volatile basic nitrogen (VBN), thiobarbituric acid reacted substance (TBARS), electronic nose analysis, and sensory evaluation were performed. Belly of pork had higher values in pH, VBN and TBARS, compared to loin and thigh of pork. Electronic nose analysis clearly indicated a difference in principal component score between day 0 and day 12 of storage. Sensory evaluation showed that pork began to away at day 4 of storage and not edible after 6 days. Loin and tenderloin of beef had higher values in pH and VBN, compared to plate of beef. Regarding TBARS, all beef samples had the similar values at the beginning of storage, but loin of beef had a drastic increase after 8 days of storage, differently from tenderloin and plate of beef. Plate of beef had lower values in overall. Electronic nose analysis of beef showed the similar results with those of pork.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.834-841
• /
• 2022

Recently, applying artificial intelligence technologies in various fields of production has drawn an upsurge of research interest due to the increase for smart factory and artificial intelligence technologies. A great deal of effort is being made to introduce artificial intelligence algorithms into the defect detection task. Particularly, detection of defects on the surface of metal has a higher level of research interest compared to other materials (wood, plastics, fibers, etc.). In this paper, we compare and analyze the speed and performance of defect classification by combining machine learning techniques (Support Vector Machine, Softmax Regression, Decision Tree) with dimensionality reduction algorithms (Principal Component Analysis, AutoEncoders) and two convolutional neural networks (proposed method, ResNet). To validate and compare the performance and speed of the algorithms, we have adopted two datasets ((i) public dataset, (ii) actual dataset), and on the basis of the results, the most efficient algorithm is determined.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.26 no.2
• /
• pp.96-109
• /
• 2021

Since terrestrial input plays a major role in coastal primary production, an understanding of land-ocean coupling (LOC) is key to understand coastal ecological changes. In this study, the LOC has been classified into three stages (i.e., the baseflow, plume event and residual flow). In order to characterize its pattern in Nakdong River estuary, multi-platform data were obtained from remote sensing (geostationary ocean color image (GOCI)), in-situ measurement (marine environment information system (MEIS)), on-site measurement (discharge data and meteorological data). The MEIS data were grouped into three stages of LOC using principal component analysis (PCA), and the LOC (2013 ~ 2018) was examined at each stage using multi-platform data. In the Nakdong River estuary, the maximum value of chlorophyll-a (chl-a) was unexpectedly appeared during the plume event. It is assumed that there was no significant increase in turbidity, expected during the typical plume event, together with the weak flushing effect, caused the enhanced phytoplankton growth. Compared with other estuaries, LOC is common in estuaries affected by freshwater inflow, but LOC has different pattern depending on the size of the plume. While estuaries that form small plumes of about 10 km (low freshwater discharge and weak flushing effect) observed high chl-a in the plume event because the phytoplankton can response to the increased nutrient more rapidly. estuaries that form large plumes of more than 100 km est (high freshwater discharge and strong flushing effect) follow the typical LOC pattern conceptualized in this study (high chl-a in the residual flow).

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.116-116
• /
• 2021

자연 하천에서의 부유사 농도 계측은 주로 재래식 채집방식을 활용한 직접계측 방식에 의존하여 비용과 시간이 많이 소요되며 점 계측 방식으로 고해상도의 시공간 자료를 측정하기엔 한계가 존재한다. 이러한 한계점을 극복하기 위해 최근 위성영상과 드론을 활용하여 촬영된 다분광 혹은 초분광 영상을 통해 고해상도의 부유사 농도 시공간분포를 측정하는 기법에 대한 연구가 활발히 진행되고 있다. 하지만, 다른 하천 물리량 계측에 비해 부유사 계측 연구는 하천에 따라 부유사가 비균질적으로 분포하여 원격탐사를 통해 정확하고 전역적인 농도 분포를 재현하기는 어려운 실정이다. 이러한 부유사의 비균질성은 부유사의 입도분포, 광물특성, 침강성 등이 하천에서 다양하게 분포하기 때문이며 이로 인해 부유사는 지역별로 다양한 분광특성을 가지게 된다. 따라서, 본 연구에서는 이러한 영향을 고려한 전역적인 부유사 농도 예측 모형을 개발하기 위해 실내 실험을 통해 부유사 특성별 고유 분광 라이브러리를 구축하고 실규모 수로에서 다양한 부유사 조건에 대한 초분광 스펙트럼과 부유사 농도를 측정하는 실험을 수행하였다. 실제 부유사 농도는 광학 기반 센서인 LISST-200X와 샘플링을 통한 실험실 분석을 통해 계측되었으며, 초분광 스펙트럼 자료는 초분광 카메라를 통해 촬영한 영상에서 부유사 계측 지점에 대한 픽셀의 스펙트럼을 추출하여 구축하였다. 이렇게 생성된 자료들의 분광 다양성을 주성분 분석(Principle Component Analysis; PCA)를 통해 분석하였으며, 부유사의 입도 분포, 부유사 종류, 수온 등과의 상관관계를 통해 분광 특성과 가장 상관관계가 높은 물리적 인자를 규명하였다. 더불어 구축된 자료를 바탕으로 기계학습 기반 주요 특징 선택 알고리즘인 재귀적 특징 제거법 (Recursive Feature Elimination)과 기계학습기반 회귀 모형인 Support Vector Regression을 결합하여 초분광 영상 기반 부유사 농도 예측 모형을 개발하였으며, 이 결과를 원격탐사 계측 연구에서 일반적으로 사용되어 오던 최적 밴드비 분석 (Optimal Band Ratio Analysis; OBRA) 방법으로 도출된 회귀식과 비교하였다. 그 결과, 기존의 OBRA 기반 방법은 비선형성을 증가시켜도 좁은 영역의 파장대만을 고려하는 한계점으로 인해 부유사의 다양한 분광 특성을 반영하지 못하였으며, 본 연구에서 제시한 기계학습 기반 예측 모형은 420 nm~1000 nm에 걸쳐 폭 넓은 파장대를 고려함과 동시에 높은 정확도를 산출하였다. 최종적으로 개발된 모형을 적용해 다양한 유사 조건에 대한 부유사 시공간 분포를 매핑한 결과, 시공간적으로 고해상도의 부유사 농도 분포를 산출하는 것으로 밝혀졌다.

• Journal of Food Hygiene and Safety
• /
• v.35 no.5
• /
• pp.430-437
• /
• 2020

This is an approach study on the sensory properties (taste and odor) of 15 types of Korean conventional soups and stews using electronic nose and tongue. The relative sensor intensity for the taste components of the samples using electronic tongue was demonstrated. By SRS (sourness) sensor, sogogi-baechuguk (beef and cabbage soup) had the highest rate of 9.0. The STS (saltiness) sensor showed the highest score of 8.2 for ojingeoguk (squid soup). For the UMS (umami) sensor, which identifies savoriness, the sogogi-baechuguk was the highest at 10.1. The SWS (sweetness) sensors showed relatively little difference, with sigeumchi-doenjangguk (spinach and bean paste soup) at the highest of 7.3. According to the BRS sensor, which tests for bitterness, the siraegi-doenjangguk (dried radish green and bean paste soup) was the highest at 7.8. By principal component analysis (PCA), we observed variances of 56.21% in principal component 1 (PC1) and 25.23% in PC2. For each flavor component, we observed -0.95 and -0.20 for factor loading of PC1 and PC2 for SRS sensors, 0.96 and 0.14 for STS sensors, and -0.94 and 0.22 for PC1 and PC2 for UMS sensors, and PC1 and 0.22 for PC1 and PC2 loading for SWS sensors. The similarity between the samples identified by clustering analysis was largely identified by 4 clusters. A total of 25 kinds of volatile compounds in 15 samples were identified, and the ones showing the highest relative content in all samples were identified as ethanol and 2-methylthiophhene. The main ingredient analysis confirmed variances of 28.54% in PC1 and 20.80% in PC2 as a result of the pattern for volatile compounds in 15 samples. In the cluster analysis, it was found to be largely classified into 3 clusters. The data in this study can be used for a sensory property database of conventional Korean soups and stews using electronic sensors.

• Korean Journal of Environment and Ecology
• /
• v.22 no.4
• /
• pp.443-452
• /
• 2008

This study conducted a survey on forest and shrub vegetation in the riverside of the main stream of the Nakdong River on the southeastern part of Korea based on the method of ZM school of phytosociology. As a result, this study identified the vegetation units as ten associations and communities belonging to three classes, and four communities unclear to the upper units. The identified vegetation units were as follows: A-1 Acero-Fagetea class group, Fraxino-Ulmetaria, undecided alliance: 1) Fraxinus mandshurica community; Zelkovetalia(prov.), Zelkovion(prov.): 2) Zelkova serrata community, A-2 Salicetea sachalinensis, Salicetalia koreensis, Salicion koreensis: 3) Salicetum koreensio-chaenomeloides, 4) Salicetum koreensis, 5) Hemipteletum davidii, 6) Salicetum gracilistylae, 7) Salicetum graciliglandis, 8) Salicetum subfragilis, A-3 Rosetea multiflorae, Dioscoreo-Puerarietalia lobatae, Actinidio-Vition coignetiae: 9) Stephanandra incisa community, 10) Lycium chinense community, A-4 unclear upper units: 11) Clerodendron trichotomum community, 12) Ailanthus altissima community, 13) Robinia pseudo-acacia community. 14) Amorpha fruticosa community. The community units identified by the study corresponded with the result of cluster analysis quite nicely while the result of PCA analysis in multivariate analyses showed less correspondence with cluster analysis result, but it was interpreted as a degree of aggregation according to anthropogenic influence. The vegetation unit of forests and shrubs, unlike the herbal community in highly common with those of Japan, included five vegetation units unique to Korea at a collective level. On the basis of the above synecological study, this research discussed the relation between each community and environment, and natural environment, etc.

• Journal of Korean Society of Environmental Engineers
• /
• v.33 no.12
• /
• pp.900-906
• /
• 2011

To investigate concentration and sources of PCDD/Fs and Co-PCBs in sediments, total 52 sediment samples were measured at 17 sites in Geum River. As a result of analysis, total concentrations of PCDD/Fs and Co-PCBs were ranged from not detected (N.D.)~193.47 pg/g-d.w. (mean value: 84.52 pg/g-d.w) and 0.34~359.19 pg/g-d.w (mean value: 114.65 pg/g-d.w.) respectively. Also, toxic equivalent (TEQ) concentration of PCDD/Fs and Co-PCBs were ranged from N.D.~5.12 (mean value: 0.88) pg I-TEQ/g-d.w and N.D.~0.58 (mean value: 0.09) $WHO_{2005}$-TEQ pg/g-d.w. respectively. The upstream indicate the highest concentration and as it goes to the downstream, it has tendency to decrease. Higher chlorinated compounds were dominant in most of site which detected PCDD/Fs. Occurrence of Co-PCBs isomer patterns appear similar to each sampling site was found. The isomer patterns showed similar between sediment and PCB products. The principal component analysis also showed that the samples contained the characteristics of PCBs products.

• Korean Journal of Environmental Biology
• /
• v.27 no.2
• /
• pp.191-197
• /
• 2009

In order to characterize the ecological traits of Q. mongolica, we treated the seedlings of this species with three environmental factors, light, moisture and nutrient gradients from March to October 2007, and measured morphological and ecological 17 characters. Lastly calculated ecological niche breadth and niche overlap between Q. mongolica-Q. acutissima and Q. mongolica-Q. variabilis, and analysed them with a special reference to ecological distribution pattern and their competition relationship in Korea. The ecological niche breadth of Q. mongolica showed the lowest in nutrient treatment, but the highest in soil moisture treatment. The ecological niche value under light was intermediate. On comparison of the ecological niche breadth of three oak species, Q. mongolica showed the highest in light environment, which might be a reason for the dominant distribution in the forest plant community, Korea. The ecological niche overlap of Q. mongolica-Q. acutissima and Q. mongolica-Q. varabilis was the widest in moisture treatment, but the narrowest in nutrient treatment and the intermediate in light one. These results means that these three oak species be most competitive in moisture environment than light or nutrient one, and that there are least differentiated among oak species for soil moisture condition. Cluster and PCA ordination showed that Q. mongolica and Q. acutissima were more closely arranged than Q. mongolica and Q. variabilis. From these results, it can be explained that Q. mongolica have more similar ecological niche with Q. acutissima than with Q. variabilis, consequently competition between Q. mongolica and Q. acutissima is intensive than Q. mongolica and Q. variabilis for environment condition, especially in soil moisture.