• Tuberculosis and Respiratory Diseases
• /
• v.82 no.4
• /
• pp.341-347
• /
• 2019

Background: Information about the epidemiology of venous thromboembolism (VTE) recurrence in Korea is lacking. The purpose of this study was to investigate VTE cumulative recurrence rates and identify risk factors for VTE recurrence among Korean adults. Methods: A retrospective cohort study was conducted on adult patients (${\geq}18years$) admitted to a university teaching hospital for pulmonary embolism (PE) from 2005 to 2013. The main outcome of interest was a recurrence of VTE. We used Cox proportional hazard regression analyses to calculate the relative risk of VTE recurrence. Results: Five-year cumulative incidence of recurrent VTE events was 21.5% (95% confidence interval [CI], 17.7-25.4) in all cases of PE; 17% after provoked and 27% after unprovoked PE. Multivariate analysis showed that body mass index (BMI) of ${\geq}25$ (hazard ratio [HR], 2.02; 95% CI, 1.17-3.46; p=0.01) and longer anticoagulation therapy duration (HR, 0.90; 95% CI, 0.84-0.96; p<0.01) were independently associated with risk of VTE recurrence. Risk factors not found to be statistically significant at the <0.05 level included history of VTE (HR, 1.81; 95% CI, 0.84-3.88; p=0.12), unprovoked PE (HR, 1.70; 95% CI, 0.89-3.25; p=0.10), symptomatic deep vein thrombosis (HR, 1.62; 95% CI, 0.89-2.94; p=0.10), and female sex (HR, 1.42; 95% CI, 0.78-2.55; p=0.24). We found that age, history of cancer, and other co-morbidities did not significantly affect the risk of VTE recurrence. Conclusion: Recurrence of VTE after PE is high. Patients with BMI ${\geq}25$ or reduced anticoagulation therapy duration have a higher risk of recurrent VTE.

• Journal of Korean Society for Geospatial Information Science
• /
• v.15 no.4
• /
• pp.111-116
• /
• 2007

This study is aimed to analyze the accuracy of depth information of reservoir using the robot-ship equipped with GPS and echosounder. The accuracy of depth measurements by sounding data was analyzed according to change of robot-ship's speed in the water. The field experiment results showed that as robot-ship's speeds were slow, accuracy of sounding data were increased. Until Robot-ship's speed was up to 5 km/hr, the accuracy of sounding data were included reliable section of normal distribution.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.297-300
• /
• 2021

대부분의 기업에서는 우수한 인적 자원의 유출을 방지하기 위해 직원들이 이직 및 퇴사하는 이유를 연구한다. 이에 기업은 직원이 퇴사하기 전에 면담을 하거나 설문조사를 통해서 연구에 필요한 데이터를 얻는다. 하지만 설문조사에서는 직원들이 직장 생활을 하는 데에 불리할 수도 있는 의견을 드러내려고 하지 않아 정확한 결과를 얻기 힘든 것이 현실이다. 한편, 한국노동연구원에서 발표한 자료에 따르면 기업이 요구하는 최소 학력 수준과 직원의 학력 수준 간의 차이가 클수록 이직 경향이 커진다. 따라서 본 연구에서는 한국노동연구원의 자료에 착안하여, 직원이 가지고 있는 객관적 데이터인 전공, 교육수준, 재직 중인 회사 유형 등의 데이터를 기반으로 직원의 퇴사 여부를 예측하고자 한다. 퇴사 예측 모델을 생성하기 위해 Decision Tree, XGBoost, kNN, SVM을 활용하였으며 각각의 성능을 비교했다. 이 결과, 지금까지 설문조사로 진행되었던 연구에서 파악하지 못한 다양한 요인을 알아낼 수 있었다. 이를 통해 기업이 퇴사 예측 모델을 이용하여 직원이 퇴사하기 전에 미리 이를 인지하고 방지하는 데에 도움을 줄 수 있을 것으로 예상된다.

• The Magazine of the IEIE
• /
• v.43 no.2
• /
• pp.25-31
• /
• 2016

• ETRI Journal
• /
• v.43 no.5
• /
• pp.881-890
• /
• 2021

Photoplethysmography (PPG) is a noninvasive technique that can be used to conveniently measure heart rate (HR) and thus obtain relevant health-related information. However, developing an automated PPG system is difficult, because its waveforms are susceptible to motion artifacts and between-patient variation, making its interpretation difficult. We use deep neural network (DNN) filters to mimic the cognitive ability of a human expert who can distinguish the features of PPG altered by noise from various sources. Systolic (S), onset (O), and first derivative peaks (W) are recognized by three different DNN filters. In addition, the boundaries of uninformative regions caused by artifacts are identified by two different filters. The algorithm reliably derives the HR and presents recognition scores for the S, O, and W peaks and artifacts with only a 0.7-s delay. In the evaluation using data from 11 patients obtained from PhysioNet, the algorithm yields 8643 (86.12%) reliable HR measurements from a total of 10 036 heartbeats, including some with uninformative data resulting from arrhythmias and artifacts.

• Journal of Information Technology Applications and Management
• /
• v.27 no.6
• /
• pp.141-151
• /
• 2020

The job mismatch between job seekers and SMEs is becoming more and more intensifying with the serious difficulties in youth employment. In this study, a bi-directional content-based metric learning model is proposed to recommend suitable jobs for job seekers and suitable job seekers for SMEs, respectively. The proposed model not only enables bi-directional recommendation, but also enables HR matching without relearning for new job seekers and new job offers. As a result of the experiment, the proposed model showed superior performance in terms of precision, recall, and f1 than the existing collaborative filtering model named NCF+GMF. The proposed model is also confirmed that it is an evolutionary model that improves performance as training data increases.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2008.10a
• /
• pp.82-89
• /
• 2008

최근, GIS 분야에서 RFID와 GPS 센서 같은 위치 및 공간 데이타를 포함하는 다양한 GeoSensor의 활용으로 수집되는 공간 데이타가 크게 증가하면서, 대용량 공간 데이타의 빠른 처리를 위한 공간 인덱스의 중요성이 높아지고 있다. 특히, 대표적인 공간 인덱스인 R-Tree를 기반으로 검색 성능을 높이기 위한 연구가 활발히 진행되고 있다. 그러나, 기존 연구는 R-Tree에서 노드의 MBR 간의 겹침이나 트리 높이를 어느 정도 줄임으로써 다소 검색 성능을 향상시켰지만, 트리 검색에서 발생하는 불필요한 노드 접근 비용 문제를 효율적으로 해결하지 못하고 있다. 본 논문에서는 이러한 문제를 해결하고 R-Tree에서 대용량 공간 데이타의 빠른 검색을 제공하는 인덱스인 HR-Tree(Hash based R-Tree)를 제시한다. HR-Tree는 트리 검색 없이 R-Tree 리프 노드를 직접 접근할 수 있는 해시 테이블을 이용함으로써 R-Tree의 검색 성능을 높인다. 해시 테이블은 데이타 영역을 차원에 따라 반복적으로 분할한 Partition과 대응되는 R-Tree 리프 노드의 MBR과 포인터들로 구성된다. 각 Partition은 생성 과정에서 고유의 식별 코드를 갖기 때문에 Partition 코드가 주어지면 해시 테이블에서 해당 레코드를 쉽게 접근할 수 있다. 또한, HR-Tree는 R-Tree구조의 변경없이 다양한 R-Tree 변형 구조에 쉽게 적용할 수 있는 장점이 있다. 마지막으로 실험을 통하여 HR-Tree의 우수성을 입증하였다.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.8 no.4
• /
• pp.71-80
• /
• 2005

As local flash flood exceeding planned capacity occurs frequently, localized preparedness and response to flood inundation are increasingly important. Using XP-SWMM model and GIS techniques, this study analyzes inundation areas by local flash flood and develops rainfall standards for evacuation with the case of Sadang-Cheon area, a local stream and its nearby highly populated watershed in the southern part of metropolitan Seoul, Flood inundation areas overflowed from drainage systems are analyzed and mapped by amount of rainfall that is derived from reference levels of stream flow. Rainfall standards for evacuation are comprised of 'watch' (40mm/hr) in preparing for near-future inundation and 'evacuation' (65mm/hr) in responding to realized inundation. The methods suggested by this case study may be applied to other urban areas for sound flood prevention policy measures and thus risk minimization.

• Journal of the Society of Disaster Information
• /
• v.7 no.4
• /
• pp.259-265
• /
• 2011

After the commercial opening of the KTX in 2005, the high speed railroad has been rapidly emerged as the major transportation means due to its high energy efficiency. Recently, the government has announced its plan to build the future transportation system around the high speed railroad. Based on this policy, the existing lines as well as the lines under construction or design are planning to increase design speed. In this paper, the suitability of the mid-span PSC girder bridges for the high speed railroad is evaluated via dynamic analysis. IT, Precom, and WPC girder bridges are considered for the purpose of this study and, for comparison, the identical modeling method and the analysis technique are utilized. The performance indices used for dynamic performance evaluation are the natural frequency, the vertical displacement, the end axial displacement, track irregularity, etc. The KTX train is utilized as a dynamic load, and the dynamic analysis is performed up to the train speed of 420km/hr with the increment of 10km/hr.

• Spatial Information Research
• /
• v.19 no.1
• /
• pp.29-40
• /
• 2011

GOCI the world first Ocean Color Imager in Geostationary Orbit, which could obtain total 8 images of the same region a day, however, its spatial resolution(500m) is not enough to use for the accurate land application, Super Resolution(SR), reconstructing the high resolution(HR) image from multiple low resolution(LR) images introduced by computer vision field. could be applied to the time-series remotely sensed images such as GOCI data, and the higher resolution image could be reconstructed from multiple images by the SR, and also the cloud masked area of images could be recovered. As the precedent study for developing the efficient SR method for GOCI images, on this research, it reproduced the simulated data under the acquisition process of the remote sensed data, and then the simulated images arc applied to the proposed algorithm. From the proposed algorithm result of the simulated data, it turned out that low resolution(LR) images could be registered in sub-pixel accuracy, and the reconstructed HR image including RMSE, PSNR, SSIM Index value compared with original HR image were 0.5763, 52.9183 db, 0.9486, could be obtained.