• Investigative Magnetic Resonance Imaging
• /
• 제26권2호
• /
• pp.104-116
• /
• 2022

The purpose of this study is to systematically determine an optimal percentile cut-off in histogram analysis for calculating the mean parameters obtained from a non-Gaussian continuous-time random-walk (CTRW) diffusion model for differentiating individual glioma grades. This retrospective study included 90 patients with histopathologically proven gliomas (42 grade II, 19 grade III, and 29 grade IV). We performed diffusion-weighted imaging using 17 b-values (0-4000 s/mm²) at 3T, and analyzed the images with the CTRW model to produce an anomalous diffusion coefficient (D_m) along with temporal (𝛼) and spatial (𝛽) diffusion heterogeneity parameters. Given the tumor ROIs, we created a histogram of each parameter; computed the P-values (using a Student's t-test) for the statistical differences in the mean D_m, 𝛼, or 𝛽 for differentiating grade II vs. grade III gliomas and grade III vs. grade IV gliomas at different percentiles (1% to 100%); and selected the highest percentile with P < 0.05 as the optimal percentile. We used the mean parameter values calculated from the optimal percentile cut-offs to do a receiver operating characteristic (ROC) analysis based on individual parameters or their combinations. We compared the results with those obtained by averaging data over the entire region of interest (i.e., 100th percentile). We found the optimal percentiles for D_m, 𝛼, and 𝛽 to be 68%, 75%, and 100% for differentiating grade II vs. III and 58%, 19%, and 100% for differentiating grade III vs. IV gliomas, respectively. The optimal percentile cut-offs outperformed the entire-ROI-based analysis in sensitivity (0.761 vs. 0.690), specificity (0.578 vs. 0.526), accuracy (0.704 vs. 0.639), and AUC (0.671 vs. 0.599) for grade II vs. III differentiations and in sensitivity (0.789 vs. 0.578) and AUC (0.637 vs. 0.620) for grade III vs. IV differentiations, respectively. Percentile-based histogram analysis, coupled with the multi-parametric approach enabled by the CTRW diffusion model using high b-values, can improve glioma grading.

• 한국지반신소재학회논문집
• /
• 제23권3호
• /
• pp.15-22
• /
• 2024

연약지반을 개량하고 그 위에 구조물을 시공하는 데 있어 지반 침하량을 예측하는 것은 매우 중요한 일이다. 침하량을 예측하기 위해 과거로부터 많은 연구들이 진행되었고 많은 예측 식이 제시되었다. 침하량은 점토의 압축지수를 통해 산정할 수 있다. 본 연구에서는 부산항 신항의 함수비, 간극비, 액성한계, 소성한계, 압축지수의 데이터를 수집하여 데이터 셋을 구축하고, 구축된 데이터 셋을 통해 각 데이터 사이의 상관분석을 실시하였다. 오렌지 마이닝 프로그램을 이용하여 기계학습 알고리즘인 Random Forest, Neural Network, Linear Regression, AdaBoost, Gradient Boosting을 적용하여 압축지수 예측모델을 제시하였다. 각 모델의 결과는 오차율을 나타내는 지표 중 하나인 RMSE 값과 MAPE 값 그리고 모델의 유의미함을 나타내는 R2 값을 비교하여 평가하였다. 그 결과, 함수비가 가장 큰 상관성을 보이며, 소성한계의 경우 다른 특성들보다 다소 낮은 상관성을 나타냈다. 각 모델을 비교한 결과 AdaBoost 모델이 가장 오차율이 낮고, 결정 계수 값이 크게 도출되었다.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 2006년도 추계학술대회
• /
• pp.599-617
• /
• 2006

혼잡한 교통네트워크에서 조사된 통행량으로부터 확률적 사용자 평형을 이루는 통행분포와 통행배정을 동시에 구하기 위한 네트워크 모델과 유전알고리즘을 제안하였다. 확률적 사용자 평형을 이루는 모델은 선형제약을 가진 비선형 목적함수를 최소화하는 문제로 정식화하였다. 네트워크 모델에서는 해의 탐색공간을 줄이고 조사된 통행량을 만족시키기 위해서 흐름보존제약을 활용하였다. 목적함수는 흐름보존, 통행발생량, 통행유입량, 조사통행량 등의 제약을 만족하는 링크통행량과, 경로통행배정을 통하여 구한, 확률적 사용자 평형을 이루는 경로통행량을 만족하는 링크통행량의 차이를 최소화하는 것으로 정식화하였다. 제안된 유전알고리즘에서 유전자는 통행분포, 링크통행량, 여행비용계수 등을 나타내는 벡터로 정의하였다. 각 유전자는 목적함수의 값으로 구한 적합도에 따라 평가되며, 병행단체교차와 돌연변이에 의하여 진화한다.

• 한국구조물진단유지관리공학회 논문집
• /
• 제22권1호
• /
• pp.32-39
• /
• 2018

염해에 따라 발생하는 보수시기와 보수로 유지되는 내구수명은 보수비용 평가에 매우 중요한 요소이다. 일반적으로 사용하는 결정론적 보수비용 평가는 사용기간의 연장에 따라 계단식으로 증가하게 되며, 보수로 인해 변동되는 내구수명의 변화를 고려하지 못한다. 본 연구에서는 확률론적인 보수시기 및 비용을 평가하기 위해, 염해에 노출된 콘크리트 교각을 선정하였다. 두 가지 배합과 염화물에 노출된 외부 환경조건을 고려하여 염화물 거동을 평가하였으며, 도출된 내구수명과 수명에 대한 확률변수를 변화시키면서 보수시기 및 비용 변화를 분석하였다. 변동계수의 변화에 따른 보수회수는 큰 차이가 발생하지 않았으나, 초기의 내구수명 연장이 구조물의 보수시기 및 비용에 큰 영향을 미치고 있었다. 또한 확률론적 보수비용 산정 모델은 결정론적 모델과 다르게 연속적인 보수비용이 평가되므로 목표내구수명에 따라 보수회수를 감소시킬 수 있는 효과적인 기법임을 규명되었다.

• 대한원격탐사학회지
• /
• 제36권4호
• /
• pp.573-586
• /
• 2020

PM (particulate matter) is of interest to everyone because it can have adverse effects on human health by the infiltration from respiratory to internal organs. To date, many studies have made efforts for the prediction of PM10 and PM2.5 concentrations. Unlike previous studies, we conducted the prediction of tomorrow's PM10 concentration for the Air Korea stations using Chinese PM10 data in addition to the satellite AOD and weather variables. We constructed 230,639 matchups from the raw data over 3 million and built an RF (random forest) model from the matchups to cope with the complexity and nonlinearity. The validation statistics from the blind test showed excellent accuracy with the RMSE (root mean square error) of 9.905 ㎍/㎥ and the CC (correlation coefficient) of 0.918. Moreover, our prediction model showed a stable performance without the dependency on seasons or the degree of PM10 concentration. However, part of coastal areas had a relatively low accuracy, which implies that a dedicated model for coastal areas will be necessary. Additional input variables such as wind direction, precipitation, and air stability should also be incorporated into the prediction model as future work.

• Journal of Preventive Medicine and Public Health
• /
• 제24권2호
• /
• pp.161-170
• /
• 1991

The purpose of this study is to find the tracking of blood pressure in primary school-age children. A follow-up study was conducted from 1986 to 1990 on 330 first grade children attending primary schools in Kangwha County, Kyungki-Do. Basically we employed a linear regression model with random coefficients to figure out the relation between blood pressure changes and initial blood pressure. We obtained the following results ; 1. The mean blood pressures were increased grade went up in both sexs and were generally higher in female than male except for the systolic blood pressure at first grade. The size of difference was about 0.8 mmHg in mean systolic blood pressure and 1.5 mmHg in mean diastolic blood pressure. 2. The average annual increasing rates of systolic blood pressure were 2.5 mmHg in male and 3.1 mmHg in female respectively. For the diastolic blood pressure IV the average annual increasing rates were observed to be 3.0 mmHg in male and 2.9 mmHg in female respectively. Increasing rate of systolic blood pressure was significantly higher in female than male. 3. The adjusted regression coefficient of systolic blood pressure change on initial value was -0.11 in male and -0.13 in female and that coefficient of diastolic blood pressure change on initial value was -0.01 in male and -0.11 in female. This result shows that children with higher initial blood pressure do not pick up their blood pressure faster than others with lower initial blood pressure. There is no evidence of tracking of blood pressure in children. It is essential to find the earliest age having the tracking of blood pressure and we leave it for the further study.

• Steel and Composite Structures
• /
• 제43권5호
• /
• pp.581-601
• /
• 2022

The main objective of this research work is to investigate the free vibration behavior of annular sandwich plates resting on the Kerr foundation at thermal conditions. This sandwich configuration is composed of two FGM face sheets as coating layer and a porous GPLRC (GPL reinforced composite) core. It is supposed that the GPL nanofillers and the porosity coefficient vary continuously along the core thickness direction. To model closed-cell FG porous material reinforced with GPLs, Halpin-Tsai micromechanical modeling in conjunction with Gaussian-Random field scheme is used, while the Poisson's ratio and density are computed by the rule of mixtures. Besides, the material properties of two FGM face sheets change continuously through the thickness according to the power-law distribution. To capture fundamental frequencies of the annular sandwich plate resting on the Kerr foundation in a thermal environment, the analysis procedure is with the aid of Reddy's shear-deformation plate theory based high-order shear deformation plate theory (HSDT) to derive and solve the equations of motion and boundary conditions. The governing equations together with related boundary conditions are discretized using the generalized differential quadrature (GDQ) method in the spatial domain. Numerical results are compared with those published in the literature to examine the accuracy and validity of the present approach. A parametric solution for temperature variation across the thickness of the sandwich plate is employed taking into account the thermal conductivity, the inhomogeneity parameter, and the sandwich schemes. The numerical results indicate the influence of volume fraction index, GPLs volume fraction, porosity coefficient, three independent coefficients of Kerr elastic foundation, and temperature difference on the free vibration behavior of annular sandwich plate. This study provides essential information to engineers seeking innovative ways to promote composite structures in a practical way.

• 지질공학
• /
• 제31권3호
• /
• pp.395-432
• /
• 2021

지하수함양은 시공간적으로 다양하여 직접적으로 측정하기 어렵기 때문에 함양추정을 위해 수치모델이 널리 사용되고 있다. 이 연구에서는 지하수함양을 추정하기 위한 방법으로 기계학습법의 하나인 분류회귀트리(CART)모형을 적용하기 위해 수정된 수직식생지수(mPVI), 정규식생지수(NDVI), 정규경작지수(NDTI), 정규나지지수(NDRI) 같은 토양-식생관련 지수와 강우, 지형인자(고도, 경사, 경사방향)를 입력하고 김천지역 SWAT-MODFLOW의 함양량 결과를 추출 및 학습하여 함양량을 예측하였다. SWAT-MODFLOW의 함양량 분포에 대한 CART모형의 예측값의 전반적인 정확도는 0.5~0.7, 카파계수는 0.3~0.6으로 나타나 위성영상자료를 통해 토양-식생에 따른 함양량 변화를 합리적으로 예측할 수 있었다.

• Korean Journal of Radiology
• /
• 제25권4호
• /
• pp.363-373
• /
• 2024

Objective: To develop and evaluate a deep learning model for automated segmentation and detection of bone metastasis on spinal MRI. Materials and Methods: We included whole spine MRI scans of adult patients with bone metastasis: 662 MRI series from 302 patients (63.5 ± 11.5 years; male:female, 151:151) from three study centers obtained between January 2015 and August 2021 for training and internal testing (random split into 536 and 126 series, respectively) and 49 MRI series from 20 patients (65.9 ± 11.5 years; male:female, 11:9) from another center obtained between January 2018 and August 2020 for external testing. Three sagittal MRI sequences, including non-contrast T1-weighted image (T1), contrast-enhanced T1-weighted Dixon fat-only image (FO), and contrast-enhanced fat-suppressed T1-weighted image (CE), were used. Seven models trained using the 2D and 3D U-Nets were developed with different combinations (T1, FO, CE, T1 + FO, T1 + CE, FO + CE, and T1 + FO + CE). The segmentation performance was evaluated using Dice coefficient, pixel-wise recall, and pixel-wise precision. The detection performance was analyzed using per-lesion sensitivity and a free-response receiver operating characteristic curve. The performance of the model was compared with that of five radiologists using the external test set. Results: The 2D U-Net T1 + CE model exhibited superior segmentation performance in the external test compared to the other models, with a Dice coefficient of 0.699 and pixel-wise recall of 0.653. The T1 + CE model achieved per-lesion sensitivities of 0.828 (497/600) and 0.857 (150/175) for metastases in the internal and external tests, respectively. The radiologists demonstrated a mean per-lesion sensitivity of 0.746 and a mean per-lesion positive predictive value of 0.701 in the external test. Conclusion: The deep learning models proposed for automated segmentation and detection of bone metastases on spinal MRI demonstrated high diagnostic performance.

• KSBB Journal
• /
• 제4권2호
• /
• pp.110-117
• /
• 1989

Ca-alginate에 의하여 포괄된 고정화 Zymomonas mobilios의 담체내부에 있어서 균체자체활성을 물질이동 현상으로 규명하고자 하였다. 또한 균체활성을 장기간 유지할 수 있을때 기질의 유효확산에 다른 반응속도를 고찰하여 균일상계로의 균체량농도를 결정할 수 있는 고정화 최적화를 구하고 그 활성의 변화에 대한 경향을 비교검토하였다. 반응속도와 균체량의 관계가 이론치에 잘 일치되므로써 기질의 유효확산계수, $D_e$와 고정화균체량, $C_c$의 상관관계를 결정할 수 있었고 이로부터 고정화 균체량 250g-dry cell/ l에서 공극율 0로 될 수 있음을 알 수 있었다. 실험치의 결과는 Michaelis-Menten형반응의 0차와 1차사이를 만족하였다.