• The Journal of Engineering Geology
• /
• v.33 no.4
• /
• pp.673-687
• /
• 2023

Exploratory data analysis is the process of observing and understanding data collected from various sources to identify their distributions and correlations through their structures and characterization. This process can be used to identify correlations among conditioning factors and select the most effective factors for analysis. This can help the assessment of landslide susceptibility, because landslides are usually triggered by multiple factors, and the impacts of these factors vary by region. This study compared two stages of exploratory data analysis to examine the impact of the data exploration procedure on the landslide prediction model's performance with respect to factor selection. Deep-learning-based landslide susceptibility analysis used either a combinations of selected factors or all 23 factors. During the data exploration phase, we used a Pearson correlation coefficient heat map and a histogram of random forest feature importance. We then assessed the accuracy of our deep-learning-based analysis of landslide susceptibility using a confusion matrix. Finally, a landslide susceptibility map was generated using the landslide susceptibility index derived from the proposed analysis. The analysis revealed that using all 23 factors resulted in low accuracy (55.90%), but using the 13 factors selected in one step of exploration improved the accuracy to 81.25%. This was further improved to 92.80% using only the nine conditioning factors selected during both steps of the data exploration. Therefore, exploratory data analysis selected the conditioning factors most suitable for landslide susceptibility analysis and thereby improving the performance of the analysis.

• International Journal of Concrete Structures and Materials
• /
• v.9 no.2
• /
• pp.159-172
• /
• 2015

Estimation of the residual strength of corroded reinforced concrete beams has been studied from experimental and theoretical perspectives. The former is arduous as it involves casting beams of various sizes, which are then subjected to various degrees of corrosion damage. The latter are static; hence cannot be generalized as new coefficients need to be re-generated for new cases. This calls for dynamic models that are adaptive to new cases and offer efficient generalization capability. Computational intelligence techniques have been applied in Construction Engineering modeling problems. However, these techniques have not been adequately applied to the problem addressed in this paper. This study extends the empirical model proposed by Azad et al. (Mag Concr Res 62(6):405-414, 2010), which considered all the adverse effects of corrosion on steel. We proposed four artificial neural networks (ANN) models to predict the residual flexural strength of corroded RC beams using the same data from Azad et al. (2010). We employed two modes of prediction: through the correction factor ($C_f$) and through the residual strength ($M_{res}$). For each mode, we studied the effect of fixed and random data stratification on the performance of the models. The results of the ANN models were found to be in good agreement with experimental values. When compared with the results of Azad et al. (2010), the ANN model with randomized data stratification gave a $C_f$-based prediction with up to 49 % improvement in correlation coefficient and 92 % error reduction. This confirms the reliability of ANN over the empirical models.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.17 no.1 s.104
• /
• pp.39-44
• /
• 2006

This paper proposes a method of moments(MoM)/Monte-Carlo simulation and Physical Optics(PO) model to determine Bistatic Coherent Reflectivity of sea surfaces at various wind speeds. For the MoM simulation, a Gaussian random rough sea surface was generated based on the data of Tae-An ocean at various wind speeds and sea surface heights. The numerical results of the MoM/Monte Carlo simulations were used to verify the validity region of the PO model. It was found that the numerical result for a flat surface agrees quite well with the Fresnel reflection coefficient. The validity of the PO model on the rough sea surface is shown by using ray tracing method.

• Applied Chemistry for Engineering
• /
• v.5 no.3
• /
• pp.385-394
• /
• 1994

Numerical solutions were obtained to the model equations for various of the parameters characterizing the pore structure, effective internal diffusion, and the chemical reaction constant. The conversion was decreased with the cause of pore closure at the surface of reacting particles, reduction of porosity, surface area of reaction and effective diffusion coefficient in the solid with the progress of reaction. Total conversion was strongly dependent on the local conversion at surface. According to the decreasing of impregnated concentration of the copper oxide and the increase of the flue gases concentration, total conversion was increased. The conversion was affected by gas flow rate and pore size distribution in the reacting solid.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.2
• /
• pp.149-157
• /
• 2011

Undecided inference could be regarded as a missing data problem such as MARand MNAR. Under the assumption of MAR, undecided inference make use of logistic regression model. The probability of default for the undecided group is obtained with regression coefficient vectors for the decided group and compare with the probability of default for the decided group. And under the assumption of MNAR, undecide dinference make use of logistic regression model with additional feature random vector. Simulation results based on two kinds of real data are obtained and compared. It is found that the misclassification rates are not much different from the rate of rawdata under the assumption of MAR. However the misclassification rates under the assumption of MNAR are less than those under the assumption of MAR, and as the ratio of the undecided group is increasing, the misclassification rates is decreasing.

• Journal of Korea Planning Association
• /
• v.54 no.2
• /
• pp.54-66
• /
• 2019

This study analyzed whether a subway accessibility impact on house price is constant since its operation over time or not. The study was approached specifically to answer two research questions. One is "Are there significant temporal variations in the relationship between subway accessibility and housing price transacted after its opening?" The other one is "How the pattern of its temporal variation in housing price is formed as a function of the distance from the nearest station?" The study area is the subway station areas in the Daejeon metropolitan city, South Korea. Its first subway line has started to be opened in 2006 with 12 stations and then opened its additional 10 stations in 2007. It can be more appropriate to observe its impacts of subway accessibility on housing price because it has only one transit line with more than 10-year reaction term to its operation. The study employed alternative models to estimate yearly variation of subway accessibility on house price for the station areas with 500-meter and 1-kilometer radius respectively. While the study originally considered both a hedonic price model with interaction terms of its access distance to yearly transacted housing and a time-variant random coefficient model, the former model was finally selected because it is better fitted. Based on our analysis results, the reaction of house price to its transit line had significant temporal variation over time after opening. In addition, the pattern in its variation from our analysis results indicates that its capitalization impact on house price is over-estimated in its first several years after the opening. In addition, its positive capitalization impact is more effective in the 1000-meter station area than in the 500-meter one.

• Journal of Preventive Medicine and Public Health
• /
• v.34 no.3
• /
• pp.262-268
• /
• 2001

Objectives : To integrate the results of studies which assess an association between blood lead and blood pressure. Methods : We surveyed the existing literature using a MEDLINE search with blood lead and blood pressure as key words, including reports published from January 1980 to December 2000. The criteria for quality evaluation were as follows: 1) the study subjects must have been workers exposed to lead, and 2) both blood pressure and blood lead must have been measured and presented with sufficient details so as to estimate or calculate the size of the association as a continuous variable. Among the 129 articles retrieved, 13 studies were selected for quantitative meta-analysis. Before the integration of each regression coefficient for the association between blood pressure and blood lead, a homogeneity test was conducted. Results : As the homogeneity of studies was rejected in a fixed effect model, we used the results in a random effect model. Our quantitative meta-analysis yielded weighted regression coefficients of blood lead associated with systolic blood pressure and diastolic blood pressure results of 0.0047 (95% confidence interval [CI]: -0.0061, 0.0155) and 0.0004 (95% CI: -0.0031, 0.0039), respectively. Conclusions : The published evidence suggested that there may be a weak positive association between blood lead and blood pressure, but the association is not significant.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.8
• /
• pp.393-400
• /
• 2016

Recently, there have been various researches on efficient and automatic analysis on urban environment methods that utilize the computer vision and machine learning technology. Among many new analyses, urban safety analysis has received a major attention. In order to predict more accurately on safety score and reflect the human visual perception, it is necessary to consider the generic and local information that are most important to human perception. In this paper, we use Double-column Convolutional Neural network consisting of generic and local columns for the prediction of urban safety. The input of generic and local column used re-sized and random cropped images from original images, respectively. In addition, a new learning method is proposed to solve the problem of over-fitting in a particular column in the learning process. For the performance comparison of our Double-column Convolutional Neural Network, we compare two Support Vector Regression and three Convolutional Neural Network models using Root Mean Square Error and correlation analysis. Our experimental results demonstrate that our Double-column Convolutional Neural Network model show the best performance with Root Mean Square Error of 0.7432 and Pearson/Spearman correlation coefficient of 0.853/0.840.

• Geomechanics and Engineering
• /
• v.20 no.1
• /
• pp.19-28
• /
• 2020

The spatial variability of geotechnical properties can lead to the uncertainty of settlement for frozen soil foundation around the oil pipeline, and it can affect the stability of permafrost foundation. In this paper, the elastic modulus, cohesion, angle of internal friction and poisson ratio are taken as four independent random fields. A stochastic analysis model for the uncertain settlement characteristic of frozen soil foundation around an oil pipeline is presented. The accuracy of the stochastic analysis model is verified by measured data. Considering the different combinations for the coefficient of variation and scale of fluctuation, the influences of spatial variability of geotechnical properties on uncertain settlement are estimated. The results show that the stochastic effects between elastic modulus, cohesion, angle of internal friction and poisson ratio are obviously different. The deformation parameters have a greater influence on stochastic settlement than the strength parameters. The overall variability of settlement reduces with the increase of horizontal scale of fluctuation and vertical scale of fluctuation. These results can improve our understanding of the influences of spatial variability of geotechnical properties on uncertain settlement and provide a theoretical basis for the reliability analysis of pipeline engineering in permafrost regions.

• Journal of radiological science and technology
• /
• v.45 no.2
• /
• pp.151-158
• /
• 2022

The Cardiac Gated Blood Pool (GBP) scintigram, a nuclear medicine imaging, calculates the left ventricular Ejection Fraction (EF) by segmenting the left ventricle from the heart. However, in order to accurately segment the substructure of the heart, specialized knowledge of cardiac anatomy is required, and depending on the expert's processing, there may be a problem in which the left ventricular EF is calculated differently. In this study, using the DeepLabV3 architecture, GBP images were trained on 93 training data with a ResNet-50 backbone. Afterwards, the trained model was applied to 23 separate test sets of GBP to evaluate the reproducibility of the region of interest and left ventricular EF. Pixel accuracy, dice coefficient, and IoU for the region of interest were 99.32±0.20, 94.65±1.45, 89.89±2.62(%) at the diastolic phase, and 99.26±0.34, 90.16±4.19, and 82.33±6.69(%) at the systolic phase, respectively. Left ventricular EF was calculated to be an average of 60.37±7.32% in the ROI set by humans and 58.68±7.22% in the ROI set by the deep learning segmentation model. (p<0.05) The automated segmentation method using deep learning presented in this study similarly predicts the average human-set ROI and left ventricular EF when a random GBP image is an input. If the automatic segmentation method is developed and applied to the functional examination method that needs to set ROI in the field of cardiac scintigram in nuclear medicine in the future, it is expected to greatly contribute to improving the efficiency and accuracy of processing and analysis by nuclear medicine specialists.