• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.2
• /
• pp.560-569
• /
• 2016

Purpose The purpose of this study was not only to explore the factors associated with the survival of OHCA(Out-of-hospital Cardiac Arrest), but to provide ideas for improving the operation of emergency medical system in Korea. Method 90,734 OHCAs(Out-of-hospital Cardiac Arrest) with a cardiac etiology, who had been transported by 119 EMS ambulances for seven years from 2006 to 2012 in Korea, were analyzed. The data had a multilevel structure in that patient's survival in the same region is interrelated, so two-level (patient-region) logistic regression analysis was applied to adjust this correlation. Results The adjusted OR in group who were given CPR(Cardiopulmonary Resuscitation) by a bystander were 1.40 for survival to discharge. In addition, the adjusted OR in the group with an implementation of AED (automated external defibrillator) before arriving in hospital was 2.98 for survival to discharge. we categorized some continuous variables (number of emergency physician, OHCAs volume fo hospital, area deprivation level) into five quintiles. The adjusted OR in the number of emergency physician compared with Q1(lowest) was 1.29(Q2), 2.89(Q3), 3.39(Q4), 4.07(Q5), respectively. the adjusted OR in OHCAs volume of each hospital compared with Q1(lowest) was 2.06(Q2), 3.06(Q3), 3.46(Q4), 4.36(Q5), respectively. Lastly, the adjusted OR in deprivation level compared with Q1(least deprived area) was 0.72(Q4), 0.64(Q5) so that the adjusted OR of survival to discharge tended to decrease in more deprived districts. Conclusion The survival to discharge was better significantly in group given CPR by a bystander and with the implementation of AED before arriving in hospital. The survival to discharge tended to be significantly better in hospitals with a larger number of emergency physicians and higher volume of OHCAs in less deprived districts.

• Journal of the Korean Regional Science Association
• /
• v.33 no.2
• /
• pp.25-37
• /
• 2017

The paper is basically designed to investigate how regional consumption affects to regional income in Korea by introducing a model with panel cointegration, rational expectation and FM-OLS cointegration methodology. Empirical evidence reveals that the regional income could be stimulated by manipulating the regional consumption due to the fact that current regional consumption and first-lagged regional income are positively related to the level of regional income. Although there exists a possibility to increase the regional income which is associated with a spending multiplier in the group of regions with highly calculated MPC, but not in the groups of regions with middle and low calculated MPCs. To this end, it could be tentatively concluded that market-oriented system should be implemented elaborately to enable that the spending multipliers are appropriately operated in these two groups.

• Proceedings of the Korean Society of Community Living Science Conference
• /
• 2003.11a
• /
• pp.152-152
• /
• 2003

본 연구의 목적은 고추 수확과 같은 여름철 농작업 시 농민의 온열 스트레스 경감을 위한 피복 장비 개발 연구의 일환으로 두 종류의 기능성 모자를 개발하고 그 성능을 비교 검토하는 것이다. 피험자로는 건강한 남자 대학생 열 두 명이 참가하였다. 인공기후실 실험 조건은 네 가지로 모자를 쓰지 않은 경우 (Control), 챙이 넓은 시판 농작업모를 착용한 경우 (Hat A), 반사 소재의 냉각 모자를 착용한 경우 (Hat B), 반사소재이면서 통기 구조를 갖는 냉각 모자를 착용한 경우 (Hat C)이다. 인공 기후실 내 환경 조건은 기온 33$\pm$0.5$^{\circ}C$, 습도 65$\pm$5%RH, 복사 온도 39$\pm$1$^{\circ}C$로 WBGT 33$^{\circ}C$를 유지하였고, 피험자들은 120분(50분 작업, 10분 휴식, 50분 작업, 10분 휴식) 동안 모델화된 고추 수확 작업을 수행하였다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.230-230
• /
• 2023

딥러닝 알고리즘 중 과거의 정보를 저장하는 문제(장기종속성 문제)가 있는 단순 RNN(Simple Recurrent Neural Network)의 단점을 해결한 LSTM(Long short-term memory)이 등장하면서 특정한 유역의 강우-유출 모형을 구축하는 연구가 증가하고 있다. 그러나 하나의 모형으로 모든 유역에 대한 유출을 예측하는 지역화 강우-유출 모형은 서로 다른 유역의 식생, 지형 등의 차이에서 발생하는 수문학적 행동의 차이를 학습해야 하므로 모형 구축에 어려움이 있다. 따라서, 본 연구에서는 국내 12개의 유역에 대하여 LSTM 기반 분포형 지역화 강우-유출 모형을 구축한 이후 강우 이외의 보조 자료에 따른 정확도를 살펴보았다. 국내 12개 유역의 7년 (2012.01.01-2018.12.31) 동안의 49개 격자(4km²)에 대한 10분 간격 레이더 강우, MODIS 위성 이미지 영상을 활용한 식생지수 (Normalized Difference Vegetation Index), 10분 간격 기온, 유역 평균 경사, 단순 하천 경사를 입력자료로 활용하였으며 10분 간격 유량 자료를 출력 자료로 사용하여 LSTM 기반 분포형 지역화 강우-유출 모형을 구축하였다. 이후 구축된 모형의 성능을 검증하기 위해 학습에 사용되지 않은 3개의 유역에 대한 자료를 활용하여 Nash-Sutcliffe Model Efficiency Coefficient (NSE)를 확인하였다. 식생지수를 보조 자료를 활용하였을 경우 제안한 모형은 3개의 검증 유역에 대하여 하천 흐름을 높은 정확도로 예측하였으며 딥러닝 모형이 위성 자료를 통하여 식생에 의한 차단 및 토양 침투와 같은 동적 요소의 학습이 가능함을 나타낸다.

• The Journal of the Acoustical Society of Korea
• /
• v.34 no.4
• /
• pp.303-309
• /
• 2015

Speaker diarization is the task of determining the speakers for unlabeled data, and DBSCAN (Density-Based Spatial Clustering of Applications with Noise) has been widely used in the field of speaker diarization for its simplicity and computational efficiency. One challenging issue, however, is that if different clusters in non-spatial dataset are adjacent to each other, over-clustering may occur which subsequently degrades the performance of DBSCAN. In this paper, we identify the drawbacks of DBSCAN and propose a new density clustering algorithm based on local distribution property around object. Variable density criterions for local density and spreadness of object are used for effective data clustering. We compare the proposed algorithm to DBSCAN in terms of clustering accuracy. Experimental results confirm that the proposed algorithm exhibits higher accuracy than DBSCAN without over-clustering and confirm that the new approach based on local density and object spreadness is efficient.

• The KIPS Transactions:PartB
• /
• v.16B no.5
• /
• pp.377-384
• /
• 2009

A new algorithm in order to classify various contents in the image documents, such as text, figure, graph, table, etc. is proposed in this paper by classifying contents using texture-based PCA, and by segmenting document images using local entropy-based histogram. Local entropy and histogram made the binarization of image document not only robust to various transformation and noise, but also easy and less time-consuming. And texture-based PCA algorithm for each segmented region was taken notice of each content in the image documents having different texture information. Through this, it was not necessary to establish any pre-defined structural information, and advantages were found from the fact of fast and efficient classification. The result demonstrated that the proposed method had shown better performances of segmentation and classification for various images, and is also found superior to previous methods by its efficiency.

• Korean Journal of Remote Sensing
• /
• v.23 no.6
• /
• pp.521-528
• /
• 2007

The overall objective of this research was to investigate various combination of segmentation parameters and to improve classification accuracy of object-oriented classification. This research presents a method for evaluation of segmentation parameters by calculating Moran's I and Intrasegment Variance. This research used Landsat-7/ETM image of $11{\times}14$ Km developed area in Ansung, Korea. Segmented images are generated by 75 combinations of parameter. Selecting 7 combinations of high, middle and low grade expected classification accuracy was based on calculated Moran's I and Intrasegment Variance. Selected segmentation images are classified 4 classes and analyzed classification accuracy according to method of objected-oriented classification. The research result proved that classification accuracy is related to segmentation parameters. The case of high grade of expected classification accuracy showed more than 85% overall accuracy. On the other hand, low ado showed around 50% overall accuracy.

• Journal of Energy Engineering
• /
• v.8
• /
• pp.49-58
• /
• 1999

전력산업의 전통적 구조는 수직적으로 통합된 전기사업자가 지역별로 독점사업자로 활동하며 정부가 진입과 퇴출 및 가격 잭정 등에 대하여 규제하는 형태로 되어 있다. 이 형태는 1980년대 미국의 Samuel Insull 이 전력회사 사장으로서 자신의 Chicago Edison을 수직적으로 통합된 지역독점사업자로 구조를 갖춘 이래 세계 각국에서 이것을 본받음으로써 정착된 것이다. 물론 발송전부문만 수직적으로 통합되고 배전부문은 분리 분할된 경우도 있고 반대로 송배전부문은 통합되고 발전부문은 분리 분할된 경우도 있다. 또한 소규모 독립발전사업자가 지역전기사업자와 장기전력구매계약을 맺고 전력을 납품하는 경우도 있었다. (중략)

• Journal of Korean Society for Geospatial Information Science
• /
• v.20 no.4
• /
• pp.127-134
• /
• 2012

This study analyzed the present status of services by fire-suppression mobilization time of fire station where is located in Jinju city, by using network analysis of GIS targeting fire station(five 119 safety centers, one 119 division) in Jinju city area. As a result, it was indicated to be 15.9% in the ratio with less than 5 minutes of mobilization time, 34.7% in the ratio with less than 8 minutes, 94% in the ratio with less than 20 minutes out of the whole fire service area in Jinju city. Even districts with more than 20 minutes were analyzed to reach 6%. Especially, to solve vulnerability to approach the fire service in uptown districts(Jinseong, Jisu, Sabong, Ilbanseong, the whole area of Ibanseong), the 119 division is installed more to be operated. However, accessibility is still remaining in low level. Also, in case of 119 safety center of Cheonjeon, the national industrial complex and the general industrial complex are being formed on a large scale. However, analyzing the fire service level in the corresponding area, the districts with more than 8 minutes and less than 20 minutes were existing broadly. In consequence of analyzing the fire service area in Jinju city with the fire-suppression mobilization time as the above, the fire service level is failing to escape largely from the status prior to the urban-rural consolidation compared to what the jurisdictional area was largely expanded by which the administrative districts were integrated by the urban-rural consolidation in locally small-and medium-sized city. Thus, there is a need of a measure for improving this.

• Journal of Korea Multimedia Society
• /
• v.16 no.7
• /
• pp.829-840
• /
• 2013

In this paper, we propose a new lung segmentation method for chest x-ray images which can take both global and local properties into account. Firstly, the initial lung segmentation is computed by applying the active shape model (ASM) which keeps the shape of deformable model from the pre-learned model and searches the image boundaries. At the second segmentation stage, we also applied the localizing region-based active contour model (LRACM) for correcting various regional errors in the initial segmentation. Finally, to measure the similarities, we calculated the Dice coefficient of the segmented area using each semiautomatic method with the result of the manually segmented area by a radiologist. The comparison experiments were performed using 5 lung x-ray images. In our experiment, the Dice coefficient with manually segmented area was $95.33%{\pm}0.93%$ for the proposed method. Effective segmentation methods will be essential for the development of computer-aided diagnosis systems for a more accurate early diagnosis and prognosis regarding lung cancer in chest x-ray images.