• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.12 no.1
• /
• pp.27-38
• /
• 2000

The collapses and settlement of harbor facilities from earthquakes were known due mostly to liquefaction of reclaimed land. The most harbor quay wa1ls being designed as gravity types in Korea are known susceptible structures to liquefaction because reclaimed land was not treated resistant to earthquake. In this study, liquefaction susceptibility of reclaimed land behind a large quay walls under construction to earthquake was predicted and its stability was analyzed. In addition, liquefaction prediction methods in harbor facilities specification adopted by both Korea and Japan were compared by applying the methods to prediction of liquefaction susceptibility of reclaimed land, respectively.

• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.225-231
• /
• 2022

최근 기계번역 분야는 괄목할만한 발전을 보였으나, 번역 결과의 오류가 불완전한 의미의 왜곡으로 이어지면서 사용자로 하여금 불편한 반응을 야기하거나 사회적 파장을 초래하는 경우가 존재한다. 특히나 오역에 의해 변질된 의미로 인한 경제적 손실 및 위법 가능성, 안전에 대한 잘못된 정보 제공의 위험, 종교나 인종 또는 성차별적 발언에 의한 파장은 실생활과 문제가 직결된다. 이러한 문제를 완화하기 위해, 기계번역 품질 예측 분야에서는 치명적 오류 감지(Critical Error Detection, CED)에 대한 연구가 이루어지고 있다. 그러나 한국어에 관련해서는 연구가 존재하지 않으며, 관련 데이터셋 또한 공개된 바가 없다. AI 기술 수준이 높아지면서 다양한 사회, 윤리적 요소들을 고려하는 것은 필수이며, 한국어에서도 왜곡된 번역의 무분별한 증식을 낮출 수 있도록 CED 기술이 반드시 도입되어야 한다. 이에 본 논문에서는 영어-한국어 기계번역 분야에서의 치명적 오류를 감지하는 KoCED(English-Korean Critical Error Detection) 데이터셋을 구축 및 공개하고자 한다. 또한 구축한 KoCED 데이터셋에 대한 면밀한 통계 분석 및 다국어 언어모델을 활용한 데이터셋의 타당성 실험을 수행함으로써 제안하는 데이터셋의 효용성을 면밀하게 검증한다.

• Journal of Environmental Impact Assessment
• /
• v.26 no.4
• /
• pp.242-256
• /
• 2017

In this paper, dispersion scenarios concerning various meteorological conditions and real urban structures were made to estimate the impacts of hazardous substance leakage accidents and to reduce damages. Based on the scenario of the hazardous substance dispersion, the characteristics of the risk in the pedestrian environment were analyzed in Gangnam, Seoul. The scenarios are composed of 48 cases according to the meteorological conditions of wind direction and wind speed. In order to analyze the dispersion characteristics of the hazardous substances, simulations were conducted using a computational fluid dynamic (CFD) model with hydrogen fluoride releases. The validation for the simulated wind was conducted at a specific period, and all the calculated verification indices were within the valid range. As a result of simulated dispersion field at pedestrian level, it was found that the dispersion pattern was influenced by the flow, which was affected by the artificial obstacles. Also, in the case of the weakest wind speed of the inflow, the dispersion of the hazardous substance appeared in the direction of the windward side at the pedestrian level due to the reverse flow occurred at lower layers. Through this study, it can be seen that the artificial structures forming the city have a major impact on the flow formed in urban areas. The proposed approach can be used to simulate the dispersion of the hazardous substances and to assess the risk to pedestrians in the industrial complexes dealing with actual hazardous substances in the future.

• Journal of Korean Society of Disaster and Security
• /
• v.12 no.2
• /
• pp.65-72
• /
• 2019

More than 64% of Korea's land is occupied by mountain regions, which have terrain characteristics that make it vulnerable to mountain disasters. The trails of Taebaeksan Mountain National Park-the region considered in this study-are located in the vicinity of steep slopes, and therefore, the region is vulnerable to landslides and debris flow during heavy storms. In this study, a slope stability model, which is a deterministic analysis method, was used to examine the potential occurrence of landslides. According to the soil classification of the detailed soil map, the specific weight of soil, effective cohesion, internal friction angle of soil, effective soil depth, and ground slope were used as the parameters of the model, and slope stability was evaluated based on the DEM of a 1 m grid. The results of the slope stability analysis showed that the more hazardous the area was, the closer the ratio of groundwater/effective soil depth is to 1.0. Further, many of the private houses and commercial facilities in the lower part of the national park were shown to be exposed to danger.

• The Journal of Society for e-Business Studies
• /
• v.24 no.1
• /
• pp.91-103
• /
• 2019

An accurate prediction on near-future cash flows plays an important role for a company to attenuate the shortage risk of cash flow by preparing a plan for future investment in advance. Unfortunately, there exists a high level of uncertainty in the types of transactions that occur in the form of receivables in inter-company transactions, unlike other types of transactions, thereby making the prediction of cash flows difficult. In this study, we analyze the trend of cash flow related to account receivables that may arise between firms, by using a stochastic approach. In particular, we utilize Variable Order Markov (VOM) model to predict how future cash flows will change based on cash flow history. As a result of this study, we show that the average accuracy of the VOM model increases about 12.5% or more compared with that of other existing techniques.

• Journal of Korean Society of Forest Science
• /
• v.110 no.4
• /
• pp.610-621
• /
• 2021

The soil creep, primarily caused by earthquakes and torrential rainfall events, has widely occurred across the country. The Korea Forest Service attempted to quantify the soil creep susceptible areas using a discriminant value table to prevent or mitigate casualties and/or property damages in advance. With the advent of advanced computer technologies, machine learning-based classification models have been employed for managing mountainous disasters, such as landslides and debris flows. This study aims to quantify the soil creep susceptibility using several classifiers, namely the k-Nearest Neighbor (k-NN), Naive Bayes (NB), Random Forest (RF), and Support Vector Machine (SVM) models. To develop the classification models, we downscaled 292 data from 4,618 field survey data. About 70% of the selected data were used for training, with the remaining 30% used for model testing. The developed models have the classification accuracy of 0.727 for k-NN, 0.750 for NB, 0.807 for RF, and 0.750 for SVM against test datasets representing 30% of the total data. Furthermore, we estimated Cohen's Kappa index as 0.534, 0.580, 0.673, and 0.585, with AUC values of 0.872, 0.912, 0.943, and 0.834, respectively. The machine learning-based classifications for soil creep susceptibility were RF, NB, SVM, and k-NN in that order. Our findings indicate that the machine learning classifiers can provide valuable information in establishing and implementing natural disaster management plans in mountainous areas.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.127-137
• /
• 2019

Recidivism prediction has been a subject of constant research by experts since the early 1970s. But it has become more important as committed crimes by recidivist steadily increase. Especially, in the 1990s, after the US and Canada adopted the 'Recidivism Risk Assessment Report' as a decisive criterion during trial and parole screening, research on recidivism prediction became more active. And in the same period, empirical studies on 'Recidivism Factors' were started even at Korea. Even though most recidivism prediction studies have so far focused on factors of recidivism or the accuracy of recidivism prediction, it is important to minimize the prediction misclassification cost, because recidivism prediction has an asymmetric error cost structure. In general, the cost of misrecognizing people who do not cause recidivism to cause recidivism is lower than the cost of incorrectly classifying people who would cause recidivism. Because the former increases only the additional monitoring costs, while the latter increases the amount of social, and economic costs. Therefore, in this paper, we propose an XGBoost(eXtream Gradient Boosting; XGB) based recidivism prediction model considering asymmetric error cost. In the first step of the model, XGB, being recognized as high performance ensemble method in the field of data mining, was applied. And the results of XGB were compared with various prediction models such as LOGIT(logistic regression analysis), DT(decision trees), ANN(artificial neural networks), and SVM(support vector machines). In the next step, the threshold is optimized to minimize the total misclassification cost, which is the weighted average of FNE(False Negative Error) and FPE(False Positive Error). To verify the usefulness of the model, the model was applied to a real recidivism prediction dataset. As a result, it was confirmed that the XGB model not only showed better prediction accuracy than other prediction models but also reduced the cost of misclassification most effectively.

• Journal of Korea Multimedia Society
• /
• v.13 no.5
• /
• pp.722-729
• /
• 2010

Prediction problems are widely used in medical domains. For example, computer aided diagnosis or prognosis is a key component in a CDSS (Clinical Decision Support System). SVMs with nonlinear kernels like RBF kernels, have shown superior accuracy in prediction problems. However, they are not preferred by physicians for medical prediction problems because nonlinear SVMs are difficult to visualize, thus it is hard to provide intuitive interpretation of prediction results to physicians. Nomogram was proposed to visualize SVM classification models. However, it cannot visualize nonlinear SVM models. Localized Radial Basis Function (LRBF) was proposed which shows comparable accuracy as the RBF kernel while the LRBF kernel is easier to interpret since it can be linearly decomposed. This paper presents a new tool named VRIFA, which integrates the nomogram and LRBF kernel to provide users with an interactive visualization of nonlinear SVM models, VRIFA visualizes the internal structure of nonlinear SVM models showing the effect of each feature, the magnitude of the effect, and the change at the prediction output. VRIFA also performs nomogram-based feature selection while training a model in order to remove noise or redundant features and improve the prediction accuracy. The area under the ROC curve (AUC) can be used to evaluate the prediction result when the data set is highly imbalanced. The tool can be used by biomedical researchers for computer-aided diagnosis and risk factor analysis for diseases.

• Korean Journal of Culture and Social Issue
• /
• v.17 no.2
• /
• pp.175-197
• /
• 2011

This study aimed to expand and reconstruct the Driving Behavior Determinants' factors in order to confirm the relationship between Driving Behavior Determinants(DBD) and drivers' reckless driving behavior level. To expand the structure of DBD, drivers anger, introversion and type A characteristics were added, which were never considered as related factors in existing DBD studies before. The correlations between the new factors of DBD and reckless driving behavior(includes driver's personal records of driving experiences for the last three years) were verified. A factor analysis result showed us that new DBD questionnaire consists of five factors such as, 'Problem Evading', 'Benefits/Sensation Seeking', 'Anti-personal Anxiety', 'Anti-personal Anger', and 'Aggression'. Also, reckless driving behavior consists of 'Speeding', 'Inexperienced Coping', 'Wild Driving', 'Drunken Driving', and 'Distraction'. The result of correlation between the DBD and reckless driving behavior indicates that inappropriate level of DBD is highly correlated with dangerous driving behavior and strong possibilities of traffic accidents. Based on these results, we might be able to discriminate drivers according to DBD level and predict their reckless driving behavior through a standardization procedure. Futhermore, this will make us to provide drivers differentiated safety education service.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.12
• /
• pp.491-498
• /
• 2019

Digital twin is a technology that virtualizes physical objects of the real world on a computer. It is used by collecting sensor data through IoT, and using the collected data to connect physical objects and virtual objects in both directions. It has an advantage of minimizing risk by tuning an operation of virtual model through simulation and responding to varying environment by exploiting experiments in advance. Recently, artificial intelligence and machine learning technologies have been attracting attention, so that tendency to virtualize a behavior of physical objects, observe virtual models, and apply various scenarios is increasing. In particular, recognition of each robot's motion is needed to build digital twin for co-robot which is a heart of industry 4.0 factory automation. Compared with modeling based research for recognizing motion of co-robot, there are few attempts to predict motion based on sensor data. Therefore, in this paper, an experimental environment for collecting current and inertia data in co-robot to detect the motion of the robot is built, and a motion prediction model based on the collected sensor data is proposed. The proposed method classifies the co-robot's motion commands into 9 types based on joint position and uses current and inertial sensor values to predict them by accumulated learning. The data used for accumulating learning is the sensor values that are collected when the co-robot operates with margin in input parameters of the motion commands. Through this, the model is constructed to predict not only the nine movements along the same path but also the movements along the similar path. As a result of learning using SVM, the accuracy, precision, and recall factors of the model were evaluated as 97% on average.