• Journal of radiological science and technology
• /
• v.44 no.4
• /
• pp.359-365
• /
• 2021

A heavy particle accelerator is a device that accelerates particles using high energy and is used in various fields such as medical and industrial fields as well as research. However, secondary neutrons and particle fragments are generated by the high-energy particle beam, and among them, the neutrons do not have an electric charge and directly interact with the nucleus to cause radiation of the material. Quantitative evaluation of the radioactive material produced in this way is necessary, but there are many difficulties in actual measurement during or after operation. Therefore, this study compared and evaluated the generated radioactive material in the concrete shield for protons and carbon ions of specific energy by using the simulation code FLUKA. For the evaluation of each energy of proton beam and carbon ion, the reliability of the source term was secured within 2% of the relative error with the data of the NASA Space Radiation Laboratory(NSRL), which is an internationally standardized data. In the evaluation, carbon ions exhibited higher neutron flux than protons. Afterwards, in the evaluation of radioactive materials under actual operating conditions for disposal, a large amount of short-lived beta-decay nuclides occurred immediately after the operation was terminated, and in the case of protons with a high beam speed, more radioactive products were generated than carbon ions. At this time, radionuclides of ⁴⁴Sc, ³H and ²²Na were observed at a high rate. In addition, as the cooling time elapsed, the ratio of long-lived nuclides increased. For nonparticulate radionuclides, ³H, ²²Na, and for particulate radionuclides, ⁴⁴Ti, ⁵⁵Fe, ⁶⁰Co, ¹⁵²Eu, and ¹⁵⁴Eu nuclides showed a high ratio. In this study, it is judged that it is possible to use the particle accelerator as basic data for facility maintenance, repair and dismantling through the prediction of radioactive materials in concrete according to the cooling time after operation and termination of operation.

• Journal of Korea Water Resources Association
• /
• v.54 no.2
• /
• pp.121-133
• /
• 2021

Suspended Solids (SS) generated in rivers are mainly introduced from non-point pollutants or appear naturally in the water body, and are an important water quality factor that may cause long-term water pollution by being deposited. However, the conventional method of measuring the concentration of suspended solids is labor-intensive, and it is difficult to obtain a vast amount of data via point measurement. Therefore, in this study, a model for measuring the concentration of suspended solids based on remote sensing in the Nakdong River was developed using Sentinel-2 data that provides high-resolution multi-spectral satellite images. The proposed model considers the spectral bands and band ratios of various wavelength bands using a machine learning model, Support Vector Regression (SVR), to overcome the limitation of the existing remote sensing-based regression equations. The optimal combination of variables was derived using the Recursive Feature Elimination (RFE) and weight coefficients for each variable of SVR. The results show that the 705nm band belonging to the red-edge wavelength band was estimated as the most important spectral band, and the proposed SVR model produced the most accurate measurement compared with the previous regression equations. By using the RFE, the SVR model developed in this study reduces the variable dependence compared to the existing regression equations based on the single spectral band or band ratio and provides more accurate prediction of spatial distribution of suspended solids concentration.

• Journal of the Korean GEO-environmental Society
• /
• v.23 no.3
• /
• pp.15-22
• /
• 2022

This study aims to observe the swelling representative rocks in Korea and to suggest improvements in the use of test methods and prior analysis in relation to the weathering of rocks. The swelling test and analysis were performed on the drilling cores obtained for the ground investigation at the domestic highway construction site. For the method of determining the absorption expansion index of rocks, the method proposed in "Standard Methods for Sample Collection and Specimen Preparation" of ISRM and Korean Rock Engineers Standard Rock Test Method was used. The specimen for the measurement of the expansion displacement was cylindrical with a height of 10 cm and a diameter of 5 cm. The existing swelling analysis method evaluates the sensitivity to weathering by using the maximum expansion displacement, but since the classification by bedrock grade is unclear, it is reasonable to use the rate of change of the expansion displacement according to the immersion time. It is necessary to conduct an experiment to distinguish between weathering and fault deterioration. In addition, long-term weathering prediction technology for each cancer type is needed through the expansion displacement analysis of the chemical weathering stage.

• KNOM Review
• /
• v.23 no.2
• /
• pp.18-28
• /
• 2020

With the development of the virtual community, the benefits that IT technology provides to people in fields such as healthcare, industry, communication, and culture are increasing, and the quality of life is also improving. Accordingly, there are various malicious attacks targeting the developed network environment. Firewalls and intrusion detection systems exist to detect these attacks in advance, but there is a limit to detecting malicious attacks that are evolving day by day. In order to solve this problem, intrusion detection research using machine learning is being actively conducted, but false positives and false negatives are occurring due to imbalance of the learning dataset. In this paper, a Random Oversampling method is used to solve the unbalance problem of the UNSW-NB15 dataset used for network intrusion detection. And through experiments, we compared and analyzed the accuracy, precision, recall, F1-score, training and prediction time, and hardware resource consumption of the models. Based on this study using the Random Oversampling method, we develop a more efficient network intrusion detection model study using other methods and high-performance models that can solve the unbalanced data problem.

• International Journal of Computer Science & Network Security
• /
• v.22 no.11
• /
• pp.141-148
• /
• 2022

The development of the education system and the labor market today requires new conditions for unification and functioning, the introduction of an innovative culture in the field of Education. The construction of modern management of innovative development of a higher education institution requires consideration of the existing theoretical, methodological and practical planes on which its formation is based. The purpose of the article is to substantiate the modern paradigm of organizing the mechanism of managing the innovative development of higher education institutions. Innovation in education is represented not only by the final product of applying novelty in educational and managerial processes in order to qualitatively improve the subject and objects of management and obtain economic, social, scientific, technical, environmental and other effects, but also by the procedure for their constant updating. The classification of innovations in education is presented. Despite the positive developments in the development of Education, numerous problems remain in this area, which is discussed in the article. The concept of innovative development of higher education institutions is described, which defines the prerequisites, goals, principles, tasks and mechanisms of university development for a long-term period and should be based on the following principles: scientific, flexible, efficient and comprehensive. The role of the motivational component of the mechanism of innovative development of higher education institutions is clarified, which allows at the strategic level to create an innovative culture and motivation of innovative activity of each individual, to make a choice of rational directions for solving problems, at the tactical level - to form motives for innovative activity in the most effective directions, at the operational level - to monitor the formation of a system of motives and incentives, to adjust the directions of motivation. The necessity of the functional component of the mechanism, which consists in determining a set of steps and management decisions aimed at achieving certain goals of innovative development of higher education institutions, is proved. The monitoring component of the mechanism is aimed at developing a special system for collecting, processing, storing and distributing information about the stages of development of higher education institutions, prediction based on the objective data on the dynamics and main trends of its development, and elaboration of recommendations.

• Korean Journal of Transplantation
• /
• v.28 no.3
• /
• pp.135-143
• /
• 2014

Background: Kidney injury molecule-1 (KIM-1) is known as a good ancillary marker of acute kidney injury (AKI) and its expression has also been observed in acute rejection and chronic graft dysfunction. We tested usefulness of KIM-1 as an indicator of acute and chronic renal graft injury by correlating KIM-1 expression with renal graft function and histology. Methods: A total of 133 zero-time biopsies and 42 follow-up biopsies obtained within 1 year posttransplantation were selected. Renal tubular KIM-1 staining was graded semiquantitatively from 0 to 3 and the extent of staining was expressed as the ratio of KIM-1 positive/CD10 positive proximal tubules using Image J program. Results: KIM-1 was positive in 39.8% of zero-time biopsies. KIM-1 positive cases were predominantly male and had received grafts from donors with older age, deceased donors, and poor renal function at the time of donation, compared with KIM-1 negative cases. KIM-1 expression showed correlation with delayed graft function and acute tubular necrosis. In comparison of KIM-1 expression between stable grafts (n=23) and grafts with dysfunction (n=19) at the time of repeated biopsy, the intensity/extent of KIM-1 staining and renal histology at zero-time did not differ significantly between the two groups. Histologically, KIM-1 expression was significantly increased with both acute and chronic changes of glomeruli, tubules and interstitium, peritubular capillaritis, and arteriolar hyalinosis. Conclusions: KIM-1 can be used as an ancillary marker of AKI and a nonspecific indicator of acute inflammation and tubulointerstitial fibrosis. However, KIM-1 expression at zero-time is not suitable for prediction of long-term graft dysfunction.

• Steel and Composite Structures
• /
• v.47 no.1
• /
• pp.91-102
• /
• 2023

To study the evaluation standard and control limit of mortar filling layer void length, in this paper, the train sub-model was developed by MATLAB and the track-bridge sub-model considering the mortar filling layer void was established by ANSYS. The two sub-models were assembled into a train-track-bridge coupling dynamic model through the wheel-rail contact relationship, and the validity was corroborated by the coupling dynamic model with the literature model. Considering the randomness of fastening stiffness, mortar elastic modulus, length of mortar filling layer void, and pier settlement, the test points were designed by the Box-Behnken method based on Design-Expert software. The coupled dynamic model was calculated, and the support vector regression (SVR) nonlinear mapping model of the wheel-rail system was established. The learning, prediction, and verification were carried out. Finally, the reliable probability of the amplification coefficient distribution of the response index of the train and structure in different ranges was obtained based on the SVR nonlinear mapping model and Latin hypercube sampling method. The limit of the length of the mortar filling layer void was, thus, obtained. The results show that the SVR nonlinear mapping model developed in this paper has a high fitting accuracy of 0.993, and the computational efficiency is significantly improved by 99.86%. It can be used to calculate the dynamic response of the wheel-rail system. The length of the mortar filling layer void significantly affects the wheel-rail vertical force, wheel weight load reduction ratio, rail vertical displacement, and track plate vertical displacement. The dynamic response of the track structure has a more significant effect on the limit value of the length of the mortar filling layer void than the dynamic response of the vehicle, and the rail vertical displacement is the most obvious. At 250 km/h - 350 km/h train running speed, the limit values of grade I, II, and III of the lengths of the mortar filling layer void are 3.932 m, 4.337 m, and 4.766 m, respectively. The results can provide some reference for the long-term service performance reliability of the ballastless track-bridge system of HRS.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.291-291
• /
• 2020

제주도는 강수의 지표침투성이 좋은 화산섬의 지질특성상 지표수의 개발이용여건이 취약한 관계로 용수의 대부분을 지하수에 의존하고 있다. 따라서 제주도는 정책 및 연구적으로 오랜 기간동안 지하수의 보전관리에 많은 노력을 기울여 오고 있다. 하지만 최근 기후변화로 인한 강수의 변동성 증가로 인해 지하수위의 변동성 또한 증가할 가능성이 있으며 따라서 지하수위의 급격한 하강에 대비하여 지하수위의 예측 및 지하수 취수량 관리의 필요성이 요구되고 있다. 지하수에 절대적으로 의존하고 있는 제주도의 수자원 이용 여건을 고려할 때, 지하수의 취수량 관리를 위한 지하수위의 실시간 예측이 필요한 실정이다. 하지만 기존의 예측방법에 의한 제주도 지하수위 예측기간은 충분히 길지 않으며 예측기간이 길어지면 예측성능이 낮아지는 문제점이 있었다. 본 연구에서는 이러한 단점을 보완하기 위해 딥러닝 알고리즘인 Long Short Term Memory(LSTM)를 활용하여 제주도 남동쪽 표선유역 중산간지역의 1개 지하수위 관측정에 대해 지하수위를 예측하고 분석하였다. R 기반의 Keras 패키지에 있는 LSTM 알고리즘을 사용하였고, 입력자료는 인근의 성판악 및 교래 강우관측소의 일단위 강수량자료와 인근 취수정의 지하수 취수량자료 및 연구대상 관측정의 지하수위 자료를 사용하였으며, 사용된 자료의 기간은 2001년 2월 11일부터 2019년 10월 31일까지 이다. 2001년부터 13년의 보정 및 3년의 검증용 시계열자료를 사용하여 매개변수의 보정 및 과적합을 방지하였고, 3년의 예측용 시계열자료를 사용하여 LSTM 알고리즘의 예측성능을 평가하였다. 목표 예측일수는 1일, 10일, 20일, 30일로 설정하였으며 보정, 검증 및 예측기간에 대한 모의결과의 평가지수로는 Nash-Sutcliffe Efficiency(NSE)를 활용하였다. 모의결과, 보정, 검증 및 예측기간에 대한 1일 예측의 NSE는 각각 0.997, 0.997, 0.993 이었고, 10일 예측의 NSE는 각각 0.993, 0.912, 0.930 이었다. 20일 예측의 경우 NSE는 각각 0.809, 0.781, 0.809 이었으며 30일 예측의 경우 각각 0.677, 0.622, 0.633 이었다. 이것은 LSTM 알고리즘에 의한 10일 예측까지는 관측 지하수위 시계열자료를 매우 적절히 모의할 수 있다는 것을 의미하며, 20일 예측 또한 적절히 모의할 수 있다는 것을 의미한다. 따라서 LSTM 알고리즘을 활용하면 본 연구대상지점에 대한 2주일 또는 3주일의 안정적인 지하수위 예보가 가능하다고 판단된다. 또한 LSTM 알고리즘을 통한 실시간 지하수위 예측은 지하수 취수량 관리에 활용할 수 있을 것이다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.94-94
• /
• 2020

최근 정부의 신북방정책 추진에 따라 수자원분야에서는 동북아지역 국제 공유하천을 중심의 물 정보 및 연구협력 기회 확보와 지정학적 특성을 고려한 지역 현안해결 중심의 연구가 재조명 되고 있다. 두만강은 이러한 동북아의 중심에 위치하고 있으며, 중국, 북한, 러이사의 국경을 따라 흐르며 지역 수자원의 대부분을 공급하는 국제하천이다. 또한, 지난 2018년 5월에는 하구유역이 람사르(Ramsar) 습지로 승인됨에 따라 철새 등을 포함한 생태가치의 중요성도 크게 증가하였다. 하지만 이 지역은 유역의 지정학적 민감성과 접근이 제한된 관측 정보들로 인해 그 수자원·환경 효용성을 정확하게 파악할 수 없을 뿐만 아니라, 최근 기후변화에 따른 영향으로 홍수, 가뭄 등의 수재해와 수질오염 등의 문제가 발생하고 있어 가용한 기술기반의 직·간접적 접근을 통한 장기수문 및 환경변화 등에 대한 분석과 관리방안 수립 등의 연구가 필요하다. 본 연구에서는 이러한 미계측 두만강 유역을 대상으로 우선, 가용한 위성자료 및 광역지표모형(MERRA-2) 기반 NASA POWER(Prediction of Worldwide Energy Resource) 수문기상 자료와 SWAT(Soil and Water Assessment Tool) 모형을 활용하여 장기 수문영향을 평가하고자 한다. SWAT 모형은 전 지구적으로 활용 가능한 격자 해상도 약 30m의 위성기반 수치표고모형(DEM), 광역 토양도, 지역 토지이용도 자료를 활용하여 두만강 유역을 전체 19개 소유역 및 18개 하도, 138개 HRUs의 수문분석 단위로 구축하였으며, 모의는 미국 NOAA NCDC(National Climate Data Center) 및 중국 CMDC(China Meteorological Data Service Center)의 주요 관측지점에서 선별한 총 13개소의 위치에 대해 재분석된 기후/기상자료들(NASA POWER 강수, 기온, 풍속, 상대습도 및 일사량)을 적용, 1990년에서 2019년까지의 30개년도 연속자료를 구축활용 하였다. 한편, 모형의 검·보정은 앞서 언급한 관측 자료의 부재로 과거 문헌 등을 통해 파악할 수 있는 연 단위 수자원 총량 등을 활용해 진행코자한다. 아울러, 향후는 최근 활용 가능한 장기 위성관측 강수량을 적용, 재분석 자료 결과와의 비교를 통해 상호 분석 오류를 줄여나갈 수 있을 것으로도 판단된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.88-88
• /
• 2021

최근 수자원과 수질관리 분야에 자료기반 머신러닝 모델과 딥러닝 모델의 활용이 급증하고 있다. 그러나 딥러닝 모델은 Blackbox 모델의 특성상 고전적인 질량, 운동량, 에너지 보존법칙을 고려하지 않고, 데이터에 내재된 패턴과 관계를 해석하기 때문에 물리적 법칙을 만족하지 않는 예측결과를 가져올 수 있다. 또한, 딥러닝 모델의 예측 성능은 학습데이터의 양과 변수 선정에 크게 영향을 받는 모델이기 때문에 양질의 데이터가 제공되지 않으면 모델의 bias와 variation이 클 수 있으며 정확도 높은 예측이 어렵다. 최근 이러한 자료기반 모델링 방법의 단점을 보완하기 위해 프로세스 기반 수치모델과 딥러닝 모델을 결합하여 두 모델링 방법의 장점을 활용하는 연구가 활발히 진행되고 있다(Read et al., 2019). Process-Guided Deep Learning (PGDL) 방법은 물리적 법칙을 반영하여 딥러닝 모델을 훈련시킴으로써 순수한 딥러닝 모델의 물리적 법칙 결여성 문제를 해결할 수 있는 대안으로 활용되고 있다. PGDL 모델은 딥러닝 모델에 물리적인 법칙을 해석할 수 있는 추가변수를 도입하며, 딥러닝 모델의 매개변수 최적화 과정에서 Cost 함수에 물리적 법칙을 위반하는 경우 Penalty를 추가하는 알고리즘을 도입하여 물리적 보존법칙을 만족하도록 모델을 훈련시킨다. 본 연구의 목적은 대청호의 수심별 수온을 예측하기 위해 역학적 모델과 딥러닝 모델을 융합한 PGDL 모델을 개발하고 적용성을 평가하는데 있다. 역학적 모델은 2차원 횡방향 평균 수리·수질 모델인 CE-QUAL-W2을 사용하였으며, 대청호를 대상으로 2017년부터 2018년까지 총 2년간 수온과 에너지 수지를 모의하였다. 기상(기온, 이슬점온도, 풍향, 풍속, 운량), 수문(저수위, 유입·유출 유량), 수온자료를 수집하여 CE-QUAL-W2 모델을 구축하고 보정하였으며, 모델은 저수위 변화, 수온의 수심별 시계열 변동 특성을 적절하게 재현하였다. 또한, 동일기간 대청호 수심별 수온 예측을 위한 순환 신경망 모델인 LSTM(Long Short-Term Memory)을 개발하였으며, 종속변수는 수온계 체인을 통해 수집한 수심별 고빈도 수온 자료를 사용하고 독립 변수는 기온, 풍속, 상대습도, 강수량, 단파복사에너지, 장파복사에너지를 사용하였다. LSTM 모델의 매개변수 최적화는 지도학습을 통해 예측값과 실측값의 RMSE가 최소화 되로록 훈련하였다. PGDL 모델은 동일 기간 LSTM 모델과 동일 입력 자료를 사용하여 구축하였으며, 역학적 모델에서 얻은 에너지 수지를 만족하지 않는 경우 Cost Function에 Penalty를 추가하여 물리적 보존법칙을 만족하도록 훈련하고 수심별 수온 예측결과를 비교·분석하였다.