• 응용통계연구
• /
• 제29권4호
• /
• pp.627-641
• /
• 2016

본 논문에서는 겉보기 무관 회귀모형을 고려하고 디리크레 프로세스 혼합모형을 오차항의 분포로 하는 비모수 베이지안 방법을 제안한다. 제안된 모형을 바탕으로 사후분포를 유도하고 디리크레 프로세스 혼합모형의 붕괴깁스표집 방법을 통해 마코프 체인 몬테 칼로 알고리듬을 구성하고 사후추론을 실시한다. 모형의 성능을 비교하기 위해 모의실험을 실시하고, 더 나아가 한국지역의 강수량 예측에 대한 실제 자료에 적용해 본다.

• 소성∙가공
• /
• 제17권6호
• /
• pp.393-400
• /
• 2008

Springback is one of the most difficult phenomena to analyze and control in sheet forming. Most of traditional springback control methods rely on experiences of skilled workers in industrial fields. This study focuses on prediction and generation of optimum reconfigurable die surfaces to control shape errors originated by springback. For this purpose, a deformation transfer function(DTF) was combined with finite element analysis of the springback in the 2D sheet forming model of elastic-perfectly plastic materials under the condition without blank holder. The results showed shape errors within 1% of the objective shape, which were comparable with analytically predicted errors. In addition to this theoretical analysis, DTF method was also applied to 2D and 3D sheet forming experiments. The experimental results showed ${\pm}0.5$ mm and ${\pm}1.0$ mm shape error distribution respectively, demonstrating that reconfigurable die surfaces were predicted well by the DTF method. Irrespective of material properties and sheet thickness, the DTF method was applicable not only to FEM simulation but also to 2D and 3D elasto-reconfigurable die forming. Consequently, this study shows that springback can be controlled effectively in the elasto-RDF system by using the DTF method.

• Geomechanics and Engineering
• /
• 제11권1호
• /
• pp.117-139
• /
• 2016

Previous studies for soil movements induced by tunneling have primarily focused on the free soil displacements. However, the stiffness of existing structures is expected to alter tunneling-induced ground movements, the sheltering influences for underground structures should be included. Furthermore, minimal attention has been given to the settings for the shield machine's operation parameters during the process of tunnels crossing above and below existing tunnels. Based on the Shanghai railway project, the soil movements induced by an earth pressure balance (EPB) shield considering the sheltering effects of existing tunnels are presented by the simplified theoretical method, the three-dimensional finite element (3D FE) simulation method, and the in-situ monitoring method. The deformation prediction of existing tunnels during complex traversing process is also presented. In addition, the deformation controlling safety measurements are carried out simultaneously to obtain the settings for the shield propulsion parameters, including earth pressure for cutting open, synchronized grouting, propulsion speed, and cutter head torque. It appears that the sheltering effects of underground structures have a great influence on ground movements caused by tunneling. The error obtained by the previous simplified methods based on the free soil displacements cannot be dismissed when encountering many existing structures.

• Structural Engineering and Mechanics
• /
• 제72권2호
• /
• pp.191-201
• /
• 2019

Finite element analysis is one of the most used tools for studying femoral neck fracture. Nerveless, consensus concerning either the choice of material characteristics, damage law and /or geometric models (linear on nonlinear) remains unreached. In this work, we propose a numerical quasi-brittle damage model to describe the behavior of the proximal femur associated with two methods to evaluate the Young modulus. Eight proximal femur finite elements models were constructed from CT scan data (4 donors: 3 women; 1 man). The numerical computations showed a good agreement between the numerical curves (load - displacement) and the experimental ones. A very encouraging result is obtained when a comparison is made between the computed fracture loads and the experimental ones ($R^2=0.825$, Relative error =6.49%). All specific numerical computation provided very fair qualitative matches with the fracture patterns for the sideway fall simulation. Finally, the comparative study based on 32 simulations adopting linear and nonlinear meshing led to the conclusion that the quantitatively results are improved when a nonlinear mesh is used.

• Journal of Information Processing Systems
• /
• 제17권3호
• /
• pp.462-472
• /
• 2021

With an increase in the scale of recommender systems, users' rating data tend to be extremely sparse. Some methods have been utilized to alleviate this problem; nevertheless, it has not been satisfactorily solved yet. Therefore, we propose an effective pre-rating method based on users' dichotomous preferences and average ratings fusion. First, based on a user-item ratings matrix, a new user-item preference matrix was constructed to analyze and model user preferences. The items were then divided into two categories based on a parameterized dynamic threshold. The missing ratings for items that the user was not interested in were directly filled with the lowest user rating; otherwise, fusion ratings were utilized to fill the missing ratings. Further, an optimized parameter λ was introduced to adjust their weights. Finally, we verified our method on a standard dataset. The experimental results show that our method can effectively reduce the prediction error and improve the recommendation quality. As for its application, our method is effective, but not complicated.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권5호
• /
• pp.1708-1727
• /
• 2021

In the advent of the twenty-first century, human beings began to closely interact with technology. Today, technology is developing, and as a result, the world wide web (www) has a very important place on the Internet and the significant task is fulfilled by Web services. A lot of Web services are available on the Internet and, therefore, it is difficult to find matching Web services among the available Web services. The recommendation systems can help in fixing this problem. In this paper, our observation was based on the recommended method such as the collaborative filtering (CF) technique which faces some failure from the data sparsity and the cold-start problems. To overcome these problems, we first applied an ontology-based clustering and then the k-nearest neighbor (KNN) algorithm for each separate cluster group that effectively increased the data density using the past user interests. Then, user ratings were predicted based on the model-based approach, such as singular value decomposition (SVD) and the predictions used for the recommendation. The evaluation results showed that our proposed approach has a less prediction error rate with high accuracy after analyzing the existing recommendation methods.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2020년도 학술발표회
• /
• pp.170-170
• /
• 2020

Due to the development of technologies, complex computation of huge data set is possible with a prevalent personal computer. Therefore, machine learning methods have been widely applied in the hydrologic field such as regression-based regional frequency analysis (RFA). The main purpose of this study is to compare two frameworks of RFA based on the artificial neural network (ANN) models: quantile regression technique (QRT-ANN) and parameter regression technique (PRT-ANN). As an output layer of the ANN model, the QRT-ANN predicts quantiles for various return periods whereas the PRT-ANN provides prediction of three parameters for the generalized extreme value distribution. Rainfall gauging sites where record length is more than 20 years were selected and their annual maximum rainfalls and various hydro-meteorological variables were used as an input layer of the ANN model. While employing the ANN model, 70% and 30% of gauging sites were used as training set and testing set, respectively. For each technique, ANN model structure such as number of hidden layers and nodes was determined by a leave-one-out validation with calculating root mean square error (RMSE). To assess the performances of two frameworks, RMSEs of quantile predicted by the QRT-ANN are compared to those of the PRT-ANN.

• 대한의용생체공학회:의공학회지
• /
• 제44권5호
• /
• pp.329-335
• /
• 2023

Perceived age is defined as age estimated based on physical appearance. Perceived age is an important indicator of the overall health status of the elderly. This is because people who appear older tend to have higher rates of morbidity and mortality than people of the same chronological age. Although perceived age is an important indicator, there is a lack of objective methods to quantify perceived age. In this paper, we construct a quantified perceived age model from face images using a convolutional neural network. The face images are enlarged to super-resolution and the skin, an important feature in perceived age, is made clear. Moreover, through Tanh-polar transformation, the central area of the face occupies a relatively larger area than the boundary area, helping the neural network better recognize facial skin features. The experimental results show mean absolute error (MAE) of 6.59, showing that the proposed model is superior to existing method.

• The Plant Pathology Journal
• /
• 제40권3호
• /
• pp.290-298
• /
• 2024

K-Maryblyt has been developed for the effective control of secondary fire blight infections on blossoms and the elimination of primary inoculum sources from cankers and newly emerged shoots early in the season for both apple and pear trees. This model facilitates the precise determination of the blossom infection timing and identification of primary inoculum sources, akin to Maryblyt, predicting flower infections and the appearance of symptoms on various plant parts, including cankers, blossoms, and shoots. Nevertheless, K-Maryblyt has undergone significant improvements: Integration of Phenology Models for both apple and pear trees, Adoption of observed or predicted hourly temperatures for Epiphytic Infection Potential (EIP) calculation, incorporation of adjusted equations resulting in reduced mean error with 10.08 degree-hours (DH) for apple and 9.28 DH for pear, introduction of a relative humidity variable for pear EIP calculation, and adaptation of modified degree-day calculation methods for expected symptoms. Since the transition to a model-based control policy in 2022, the system has disseminated 158,440 messages related to blossom control and symptom prediction to farmers and professional managers in its inaugural year. Furthermore, the system has been refined to include control messages that account for the mechanism of action of pesticides distributed to farmers in specific counties, considering flower opening conditions and weather suitability for spraying. Operating as a pivotal module within the Fire Blight Forecasting Information System (FBcastS), K-Maryblyt plays a crucial role in providing essential fire blight information to farmers, professional managers, and policymakers.

• Steel and Composite Structures
• /
• 제50권4호
• /
• pp.443-458
• /
• 2024

The construction industry, one of the biggest producers of greenhouse emissions, is under a lot of pressure as a result of growing worries about how climate change may affect local communities. Geopolymer concrete (GPC) has emerged as a feasible choice for construction materials as a result of the environmental issues connected to the manufacture of cement. The findings of this study contribute to the development of machine learning methods for estimating the properties of eco-friendly concrete, which might be used in lieu of traditional concrete to reduce CO₂ emissions in the building industry. In the present work, the compressive strength (f_c) of GPC is calculated using random forests regression (RFR) methodology where natural zeolite (NZ) and silica fume (SF) replace ground granulated blast-furnace slag (GGBFS). From the literature, a thorough set of experimental experiments on GPC samples were compiled, totaling 254 data rows. The considered RFR integrated with artificial hummingbird optimization (AHA), black widow optimization algorithm (BWOA), and chimp optimization algorithm (ChOA), abbreviated as ARFR, BRFR, and CRFR. The outcomes obtained for RFR models demonstrated satisfactory performance across all evaluation metrics in the prediction procedure. For R² metric, the CRFR model gained 0.9988 and 0.9981 in the train and test data set higher than those for BRFR (0.9982 and 0.9969), followed by ARFR (0.9971 and 0.9956). Some other error and distribution metrics depicted a roughly 50% improvement for CRFR respect to ARFR.