• 제목/요약/키워드: Prediction risk

검색결과 1,085건 처리시간 0.024초

GIS를 이용한 암반사면 파괴분석과 산사태 위험도 (Rock Slope Failure Analysis and Landslide Risk Map by Using GIS)

  • 권혜진;김교원
    • 한국지반공학회논문집
    • /
    • 제30권12호
    • /
    • pp.15-25
    • /
    • 2014
  • 본 연구에서는 지리산 북쪽의 과거 산사태 발생영역에서 조사된 절리특성과 GIS를 이용하여 추출한 지형특성을 근거하여 연구지역에서 예상되는 암반사면 파괴유형을 분석하였다. 또 해발고도, 사면방향, 사면경사, 음영도, 곡률, 하천 이격거리 등 6개의 지형특성 인자의 빈도비를 중첩하여 산사태 예측도를 작성하였으며, 산사태 예측도와 도로 및 주거지와 같은 지역의 인문적인 인자를 고려한 산사태 피해도를 조합하여 최종적으로 연구지역의 산사태 위험도를 작성하였다. 연구지역에서 발생한 산사태의 지형적 특성을 분석한 결과, 해발고도 330~710m에서 88%, 사면방향 동남-남-남서 방향($90{\sim}270^{\circ}$)에서 77.7%, 사면경사 $10{\sim}40^{\circ}$에서 93.39%, 음영도 등급3~7에서 82.78%, 곡률특성 -5~+5에서 86.28%, 하천 이격거리 400m 이내에서 82.92%가 발생하였다. 산사태가 발생한 영역의 75%는 산사태 위험도에서 위험 등급이 '높음' 이상인 지역이어서 위험 예측에 대한 신뢰성이 확인되었으며, 연구지역의 13.27%는 산사태 위험에 노출된 것으로 분석되었다.

Prediction of Prognosis in Glioblastoma Using Radiomics Features of Dynamic Contrast-Enhanced MRI

  • Elena Pak;Kyu Sung Choi;Seung Hong Choi;Chul-Kee Park;Tae Min Kim;Sung-Hye Park;Joo Ho Lee;Soon-Tae Lee;Inpyeong Hwang;Roh-Eul Yoo;Koung Mi Kang;Tae Jin Yun;Ji-Hoon Kim;Chul-Ho Sohn
    • Korean Journal of Radiology
    • /
    • 제22권9호
    • /
    • pp.1514-1524
    • /
    • 2021
  • Objective: To develop a radiomics risk score based on dynamic contrast-enhanced (DCE) MRI for prognosis prediction in patients with glioblastoma. Materials and Methods: One hundred and fifty patients (92 male [61.3%]; mean age ± standard deviation, 60.5 ± 13.5 years) with glioblastoma who underwent preoperative MRI were enrolled in the study. Six hundred and forty-two radiomic features were extracted from volume transfer constant (Ktrans), fractional volume of vascular plasma space (Vp), and fractional volume of extravascular extracellular space (Ve) maps of DCE MRI, wherein the regions of interest were based on both T1-weighted contrast-enhancing areas and non-enhancing T2 hyperintense areas. Using feature selection algorithms, salient radiomic features were selected from the 642 features. Next, a radiomics risk score was developed using a weighted combination of the selected features in the discovery set (n = 105); the risk score was validated in the validation set (n = 45) by investigating the difference in prognosis between the "radiomics risk score" groups. Finally, multivariable Cox regression analysis for progression-free survival was performed using the radiomics risk score and clinical variables as covariates. Results: 16 radiomic features obtained from non-enhancing T2 hyperintense areas were selected among the 642 features identified. The radiomics risk score was used to stratify high- and low-risk groups in both the discovery and validation sets (both p < 0.001 by the log-rank test). The radiomics risk score and presence of isocitrate dehydrogenase (IDH) mutation showed independent associations with progression-free survival in opposite directions (hazard ratio, 3.56; p = 0.004 and hazard ratio, 0.34; p = 0.022, respectively). Conclusion: We developed and validated the "radiomics risk score" from the features of DCE MRI based on non-enhancing T2 hyperintense areas for risk stratification of patients with glioblastoma. It was associated with progression-free survival independently of IDH mutation status.

Support Vector Machine을 이용한 지능형 신용평가시스템 개발 (Development of Intelligent Credit Rating System using Support Vector Machines)

  • 김경재
    • 한국정보통신학회논문지
    • /
    • 제9권7호
    • /
    • pp.1569-1574
    • /
    • 2005
  • In this paper, I propose an intelligent credit rating system using a bankruptcy prediction model based on support vector machines (SVMs). SVMs are promising methods because they use a risk function consisting of the empirical error and a regularized term which is derived from the structural risk minimization principle. This study examines the feasibility of applying SVM in Predicting corporate bankruptcies by comparing it with other data mining techniques. In addition. this study presents architecture and prototype of intelligeht credit rating systems based on SVM models.

DePreSys4의 동아시아 근미래 기후예측 성능 평가 (Assessment of Near-Term Climate Prediction of DePreSys4 in East Asia)

  • 최정;임슬희;손석우;부경온;이조한
    • 대기
    • /
    • 제33권4호
    • /
    • pp.355-365
    • /
    • 2023
  • To proactively manage climate risk, near-term climate predictions on annual to decadal time scales are of great interest to various communities. This study evaluates the near-term climate prediction skills in East Asia with DePreSys4 retrospective decadal predictions. The model is initialized every November from 1960 to 2020, consisting of 61 initializations with ten ensemble members. The prediction skill is quantitatively evaluated using the deterministic and probabilistic metrics, particularly for annual mean near-surface temperature, land precipitation, and sea level pressure. The near-term climate predictions for May~September and November~March averages over the five years are also assessed. DePreSys4 successfully predicts the annual mean and the five-year mean near-surface temperatures in East Asia, as the long-term trend sourced from external radiative forcing is well reproduced. However, land precipitation predictions are statistically significant only in very limited sporadic regions. The sea level pressure predictions also show statistically significant skills only over the ocean due to the failure of predicting a long-term trend over the land.

Quantifying Risk Factors on Cost Performance By Characterizing Capital Facility Projects

  • Jang, Myung-Hoon;Cha, Hee-Sung
    • 한국건설관리학회논문집
    • /
    • 제7권4호
    • /
    • pp.177-183
    • /
    • 2006
  • Risk-based estimation has been successfully introduced into the construction industry. By incorporating historical data associated with probability analysis, risk-based estimate is an effective decision support aid in considering whether to launch a particular project. The industry challenges, however, especially related with management issues, such as labor shortage, wage growth, and supply chain complexity, have often resulted in poor cost performance. The insufficient assessing the project characteristics (i.e., resource availability, project complexity, and project delivery method) can be the main reasons in the poor cost performance. Because the accuracy level of cost performance prediction can be enhanced by extensive evaluation of the subject project characteristics, a new approach for predicting cost performance in an earlier stage of a project can improve the Industry substantiality, in other words, value maximization. The purpose of this paper is to develop a new methodology in developing a risk-based estimate tool by incorporating extensive project characteristics. To do this, an extensive industry survey was conducted from both private and public sectors in building industry in Korea. In addition, significant project characteristics were identified in terms of cost performance indicator. Although the data collection is limited to Korean industry the suggested approach provides the industry with a straightforward methodology in risk management. As many researchers maintained that front-end planning efforts are crucial in achieving the successful outcome in building projects, the new method for risk-based estimation can Improve the cost performance as well as enhance the fulfillment in terms of business sustainability.

Psychological Risk and Protective Factors for Suicidal Ideation: A Study in an Adolescent Sample in an Insular Context

  • Ana Margarida Cunha;Claudia Carmo;Marta Bras
    • Journal of the Korean Academy of Child and Adolescent Psychiatry
    • /
    • 제34권4호
    • /
    • pp.250-257
    • /
    • 2023
  • Objectives: Adolescents are at risk of suicide. As suicide is a multifactorial process, risk and protective factors are relevant constructs for suicide prediction. This study explored the effects of risk and protective factors on suicidal ideation in adolescents on the island of São Miguel (Azores). Methods: A sample of 750 adolescents (male: n=358; 47.7%; mean age=14.67 years; standard deviation=1.85 years) from the island of São Miguel (Azores) completed several measures related to suicidal ideation and associated factors. Using a cross-sectional design, this study conducted descriptive, correlational, predictive, mediation, and moderation analyses. Results: Adolescents generally displayed high levels of risk and protective factors; an indicative proportion exhibited significant suicidal ideation with females presenting the greatest vulnerability. Furthermore, the results highlight that depression is the best predictor of suicidal ideation, however, the association between these variables is mediated. Conclusion: The data corroborate that the suicidal reality of adolescents in the Autonomous Region of the Azores is worrisome. Having substantiated the complexity of the suicidal context in young people in the present research, the need to continue studying risk/protective factors in this area is supported.

THE NUMERICAL IMPLEMENTATION OF RISK

  • Lee, Chun-Jin
    • Journal of applied mathematics & informatics
    • /
    • 제2권2호
    • /
    • pp.53-62
    • /
    • 1995
  • If one is to estimate environmemtal risk based on data or predict risk based on expert opinion the parameter environmental risk musk be defined precisely so that when data becomes available the numerical values of the estimates and/or prediction can be evaluated. Also the definitionmust be precise so that it may be successfully used in regulatory and litigation activities. The presentation is a develop-ment of a definition which lends to statistical analysis and to inference in addition lends to ease of engineering interpretation. Various impli-cations and useful extensions in measuring numerically for two or more dimensional mixed effects of several toxicants could be developed in further research.

Windborne debris and damage risk models: a review

  • Holmes, J.D.
    • Wind and Structures
    • /
    • 제13권2호
    • /
    • pp.95-108
    • /
    • 2010
  • This review paper discusses research from the last few years relating to windborne debris risk models and the essential elements of engineering damage prediction models. Generic types of windborne debris are discussed. The results of studies of debris trajectories that are relevant to damage models are described - in particular the horizontal component of debris velocity as a function of distance travelled. The merits of impact momentum versus impact kinetic energy as a relevant parameter for predicting damage are considered, and how published data from generic cannon Impact tests can be used in risk models. The quantitative variation of debris impact damage with wind speed is also discussed. Finally the main elements of previously-proposed debris damage models are described.

Quantitative Assessment of the Diagnostic Role of CDH13 Promoter Methylation in Lung Cancer

  • Zhong, Yun-Hua;Peng, Hao;Cheng, Hong-Zhong;Wang, Ping
    • Asian Pacific Journal of Cancer Prevention
    • /
    • 제16권3호
    • /
    • pp.1139-1143
    • /
    • 2015
  • In order to explore the association between cadherin 13 (CDH13) gene promoter methylation and lung carcinoma (LC) risk, we carried out a meta-analysis with searching of PubMed, Web of Science. Ultimately, 17 articles were identified and analysised by STATA 12.0 software. Overall, we found a significant relationship between CDH13 promoter methylation and LC risk (odds ratio=6.98, 95% confidence interval: 4.21-11.56, p<0.001). Subgroup analyses further revealed that LC risk was increased for individuals carrying the methylated CDH13 compared with those with unmethylated CDH13. Hence, our study identified a strong association between CDH13 gene promoter methylation and LC and highlighted a promising potential for CDH13 methylation in LC risk prediction.

Internet 기반의 터널 시공 위험도 관리 시스템 개발 (Development of An Internet-Based Tunnel Construction Risk Management System)

  • 유충식;김재훈;박영진;유정훈
    • 한국지반공학회:학술대회논문집
    • /
    • 한국지반공학회 2002년도 봄 학술발표회 논문집
    • /
    • pp.679-686
    • /
    • 2002
  • A substantial portion of the cost of a tunnelling project in urban environments is, therefore, devoted to prevent ground movement. Therefore, prediction of ground movements and assessment of risk of damage to adjacent buildings has become an essential part of the planning, design, and construction of a tunnelling project in the urban environments. An internet-based tunnelling-induced ground movements and building damage assessment system (IT-TURIMS) was developed and implemented to Daegu Metro Subway Line tunnel construction project in Korea. This paper describes the concept and implementation of IT-TURIMS. Practical significance of tunnelling risk assessment is also discussed.

  • PDF