• The Journal of Bigdata
• /
• v.3 no.2
• /
• pp.71-78
• /
• 2018

The study is based on machine learning techniques to increase the accuracy of the forest fire predictive model. It used 14 years of data from 2003 to 2016 in Gang-won-do where forest fire were the most frequent. To reduce weather data errors, Gang-won-do was divided into nine areas and weather data from each region was used. However, dividing the forest fire forecast model into nine zones would make a large difference between the date of occurrence and the date of not occurring. Imbalance issues can degrade model performance. To address this, several sampling methods were applied. To increase the accuracy of the model, five indices in the Canadian Frost Fire Weather Index (FWI) were used as derived variable. The modeling method used statistical methods for logistic regression and machine learning methods for random forest and xgboost. The selection criteria for each zone's final model were set in consideration of accuracy, sensitivity and specificity, and the prediction of the nine zones resulted in 80 of the 104 fires that occurred, and 7426 of the 9758 non-fires. Overall accuracy was 76.1%.

• Journal of Korean Society for Atmospheric Environment
• /
• v.33 no.1
• /
• pp.11-18
• /
• 2017

The performance of a modeling system consisting of WRF model v3.3 and CMAQ model v4.7.1 for forecasting $PM_{2.5}$ concentrations were evaluated during the period May 2012 through December 2014. Twenty-four hour averages of $PM_{2.5}$ and its major components obtained through filter sampling at the Bulgwang intensive measurement station were used for comparison. The mean predicted $PM_{2.5}$ concentration over the entire period was 68% of the mean measured value. Predicted concentrations for major components were underestimated except for $NO_3{^-}$. The model performance for $PM_{2.5}$ generally tended to degrade with increasing the concentration level. However, the mean fractional bias (MFB) for high concentration above the $80^{th}$ percentile fell within the criteria, the level of accuracy acceptable for standard model applications. Among three bias correction methods, the ratio adjustment was generally most effective in improving the performance. Albeit for limited test conditions, this analysis demonstrated that the effects of bias correction were larger when using the data with a larger bias of predicted values from measurement values.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.10 no.2 s.21
• /
• pp.35-39
• /
• 2004

Ship structures are basically an assembly of plate elements and the load-carrying capacity or the ultimate strength is one of the most important criteria for safety assessment and economic design. Also, Structural elements making up ship plated structures do not work separately, resulting in high degree of redundancy and complexity, in contrast to those of steel framed structures. To enable the behavior of such structures to be analyzed simplifications or idealizations must essentially be made considering the accuracy needed and the degree of complexity of the analysis to be used On this study, to investigate effect of modeling range, the finite element method are used and their results are compared varying the analysis ranges. The model has been selected from bottom panels of merchant ship structures. For FHA, three types of structural modeling are adopted in terms of the extent of the analysis. The purpose of the present study is to numerically calculate the characteristics of ultimate strength behavior according to the analysis ranges of stiffened panels subject to uniaxial compressive loads.

• Journal of the Korean Society of Safety
• /
• v.33 no.4
• /
• pp.84-89
• /
• 2018

The number of landslides has increased since the 2000s due to the increased frequency of heavy rainfall caused by abnormal weather. A variety of debris flow prevention facilities have been installed as a countermeasure against this problem. However, it is not easy to evaluate the efficiency of debris flow prevention structures except for the structures with constant volume such as the erosion dam, because the other structures are limited to be reproduced in simulation program for debris flow. Therefore, the methods by which the debris flow prevention structures were modeled were proposed, and the efficiency of four prevention structures installed in Baekyang Mt. in Busan was evaluated with UDS, which accuracy had been verified, using these methods. The initial amount of debris flow was determined based on landslide which occurred in 2014, and specifications of the complex retaining walls around the settlements were measured and applied modeling for terrain. The numerical results showed that the efficiency of debris flow prevention structures could be quantitatively presented. Among the debris flow prevention structures installed in Baekyang Mt., prevention structure of barrier type for debris flow was the most efficiency and debris flow prevention device was the lowest efficiency when the only depth of debris was evaluated. It seems that this study is meaningful to propose the methods which were used to model the debris flow prevention structures that could not be reproduced in most 2D debris flow numerical analysis programs. If precise verification of the presented methods is carried out, it will be possible to provide clear criteria for the efficiency evaluation method of disaster prevention structures.

• Environmental Analysis Health and Toxicology
• /
• v.27
• /
• pp.8.1-8.10
• /
• 2012

Objectives: The goal was to model and quantify the atmospheric concentrations of volatile organic compounds (VOCs) as the result of the Hebei Spirit oil spill, and to predict whether the exposure levels were abnormally high or not. Methods: We developed a model for calculating the airborne concentration of VOCs that are produced in an oil spill accident. The model was applied to a practical situation, namely the Hebei Spirit oil spill. The accuracy of the model was verified by comparing the results with previous observation data. The concentrations were compared with the currently used air quality standards. Results: Evaporation was found to be 10- to 1,000-fold higher than the emissions produced from a surrounding industrial complex. The modeled concentrations for benzene failed to meet current labor environmental standards, and the concentration of benzene, toluene, orthometa- para-xylene were higher than the values specified by air quality standards and guideline values on the ocean. The concentrations of total VOCs were much higher than indoor environmental criteria for the entire Taean area for a few days. Conclusions: The extent of airborne exposure was clearly not the same as that for normal conditions.

• Korea-Australia Rheology Journal
• /
• v.16 no.4
• /
• pp.183-191
• /
• 2004

High Deborah or Weissenberg number problems in viscoelastic flow modeling have been known formidably difficult even in the inertialess limit. There exists almost no result that shows satisfactory accuracy and proper mesh convergence at the same time. However recently, quite a breakthrough seems to have been made in this field of computational rheology. So called matrix-logarithm (here we name it tensor-logarithm) formulation of the viscoelastic constitutive equations originally written in terms of the conformation tensor has been suggested by Fattal and Kupferman (2004) and its finite element implementation has been first presented by Hulsen (2004). Both the works have reported almost unbounded convergence limit in solving two benchmark problems. This new formulation incorporates proper polynomial interpolations of the log­arithm for the variables that exhibit steep exponential dependence near stagnation points, and it also strictly preserves the positive definiteness of the conformation tensor. In this study, we present an alternative pro­cedure for deriving the tensor-logarithmic representation of the differential constitutive equations and pro­vide a numerical example with the Leonov model in 4:1 planar contraction flows. Dramatic improvement of the computational algorithm with stable convergence has been demonstrated and it seems that there exists appropriate mesh convergence even though this conclusion requires further study. It is thought that this new formalism will work only for a few differential constitutive equations proven globally stable. Thus the math­ematical stability criteria perhaps play an important role on the choice and development of the suitable con­stitutive equations. In this respect, the Leonov viscoelastic model is quite feasible and becomes more essential since it has been proven globally stable and it offers the simplest form in the tensor-logarithmic formulation.

• Computational Structural Engineering
• /
• v.10 no.4
• /
• pp.217-228
• /
• 1997

The high precision analysis by the p-version of the finite element method are fairly well established as highly efficient method for linear elastic problems, especially in the presence of stress singularity. It has been noted that the merits of the p-version are accuracy, modeling simplicity, robustness, and savings in user's and CPU time. However, little has been done to exploit their benefits in elasto-plastic analysis. In this paper, the p-version finite element model is proposed for the materially nonlinear analysis that is based on the incremental theory of plasticity using the constitutive equation for work-hardening materials, and the associated flow rule. To obtain the solution of nonlinear equation, the Newton-Raphson method and initial stiffness method, etc are used. Several numerical examples are tested with the help of the square plates with cutout, the thick-walled cylinder under internal pressure, and the circular plate with uniformly distributed load. Those results are compared with the theoretical solutions and the numerical solutions of ADINA

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.5
• /
• pp.981-989
• /
• 2010

In this study, we introduce a new architecture of fuzzy inference system. In the fuzzy inference system, we use Fuzzy C-Means clustering algorithm to form the premise part of the rules. The membership functions standing in the premise part of fuzzy rules do not assume any explicit functional forms, but for any input the resulting activation levels of such radial basis functions directly depend upon the distance between data points by means of the Fuzzy C-Means clustering. As the consequent part of fuzzy rules of the fuzzy inference system (being the local model representing input output relation in the corresponding sub-space), four types of polynomial are considered, namely constant, linear, quadratic and modified quadratic. This offers a significant level of design flexibility as each rule could come with a different type of the local model in its consequence. Either the Least Square Estimator (LSE) or the weighted Least Square Estimator (WLSE)-based learning is exploited to estimate the coefficients of the consequent polynomial of fuzzy rules. In fuzzy modeling, complexity and interpretability (or simplicity) as well as accuracy of the obtained model are essential design criteria. The performance of the fuzzy inference system is directly affected by some parameters such as e.g., the fuzzification coefficient used in the FCM, the number of rules(clusters) and the order of polynomial in the consequent part of the rules. Accordingly we can obtain preferred model structure through an adjustment of such parameters of the fuzzy inference system. Moreover the comparative experimental study between WLSE and LSE is analyzed according to the change of the number of clusters(rules) as well as polynomial type. The superiority of the proposed model is illustrated and also demonstrated with the use of Automobile Miles per Gallon(MPG), Boston housing called Machine Learning dataset, and Mackey-glass time series dataset.

• Nuclear Engineering and Technology
• /
• v.23 no.1
• /
• pp.56-65
• /
• 1991

The LOFT LOCE L2-3 was simulated using the RELAP5/MOD2 Cycle 36.04 code to assess its capability in predicting the thermal-hydraulic phenomena in LBLOCA of a PWR. The reactor vessel was simulated with two core channels and split downcomer modeling for a base case calculation using the frozen code. The result of the base calculation showed that the code predicted the hydraulic behavior, and the blowdown thermal response at high power region of the core reasonably and that the code had deficiencies in the critical How model during subcooled-two-phase transition period, in the CHF correlation at high mass flux and in the blowdown rewet criteria. An overprediction of coolant inventory due to the deficiencies yielded the poor prediction of reflood thermal response. Improvement of the code, RELAP5 / MOD2 Cycle 36.04, based on the sensitivity study increased the accuracy of the prediction of the rewet phenomena.

• Journal of the Korean Society for information Management
• /
• v.39 no.1
• /
• pp.91-117
• /
• 2022

The number of depressed patients in Korea and around the world is rapidly increasing every year. However, most of the mentally ill patients are not aware that they are suffering from the disease, so adequate treatment is not being performed. If depressive symptoms are neglected, it can lead to suicide, anxiety, and other psychological problems. Therefore, early detection and treatment of depression are very important in improving mental health. To improve this problem, this study presented a deep learning-based depression tendency model using Korean social media text. After collecting data from Naver KonwledgeiN, Naver Blog, Hidoc, and Twitter, DSM-5 major depressive disorder diagnosis criteria were used to classify and annotate classes according to the number of depressive symptoms. Afterwards, TF-IDF analysis and simultaneous word analysis were performed to examine the characteristics of each class of the corpus constructed. In addition, word embedding, dictionary-based sentiment analysis, and LDA topic modeling were performed to generate a depression tendency classification model using various text features. Through this, the embedded text, sentiment score, and topic number for each document were calculated and used as text features. As a result, it was confirmed that the highest accuracy rate of 83.28% was achieved when the depression tendency was classified based on the KorBERT algorithm by combining both the emotional score and the topic of the document with the embedded text. This study establishes a classification model for Korean depression trends with improved performance using various text features, and detects potential depressive patients early among Korean online community users, enabling rapid treatment and prevention, thereby enabling the mental health of Korean society. It is significant in that it can help in promotion.