• Nuclear Engineering and Technology
• /
• v.50 no.5
• /
• pp.758-766
• /
• 2018

We developed numerical models to efficiently simulate the low-cycle fatigue behavior of a pipe elbow. To verify the model, in-plane cyclic bending tests of pipe elbow specimens were conducted, and a through crack occurred in the vicinity of the crown. Numerical models based on the erosion method and tie-break method are developed, and the numerical results are compared with experimental results. The calculated results of both models are in good agreement with experimental results, and the model using the tie-break method possesses two times faster calculation speed. Therefore, the numerical model based on the tie-break method would be beneficial to evaluate the strength of piping systems under seismic loadings.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.22 no.6
• /
• pp.627-636
• /
• 2002

Identification and sizing of surface breaking vertical cracks using angle beam ultrasonic testing in practical situation quite often become very difficult tasks due to the presence of non-relevant signals caused by geometric reflectors. The present work introduces effective and systematic approaches to take care of such a difficulty by use oi angle beam ultrasonic testing models that can predict the expected signals from various targets very accurately. Specifically, the model-based TIFD (Technique for Identification of Flaw signals using Deconvolution) is Proposed for the identification of the crack tip signals from the non-relevant geometric reflection signals. In addition, the model-based Size-Amplitude Curve is introduced for the reliable sizing of surface breaking vertical cracks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.8
• /
• pp.3950-3964
• /
• 2017

With the increasing popularity of 3D technology such as 3D printing, 3D modeling, etc., there is a growing need to search for similar models on the internet. Matching non-rigid shapes has become an active research field in computer graphics. In this paper, we present an efficient and effective non-rigid model retrieval method based on topological structure and local volume. The integral geodesic distances are first calculated for each vertex on a mesh to construct the topological structure. Next, each node on the topological structure is assigned a local volume that is calculated using the shape diameter function (SDF). Finally, we utilize the Hungarian algorithm to measure similarity between two non-rigid models. Experimental results on the latest benchmark (SHREC' 15 Non-rigid 3D Shape Retrieval) demonstrate that our method works well compared to the state-of-the-art.

• Journal of information and communication convergence engineering
• /
• v.19 no.4
• /
• pp.205-213
• /
• 2021

The properties of a scale-free network are little known; its node degree following a power-law distribution is among its few known properties. By selecting real-field scale-free networks from a network dataset and comparing them to other networks, such as random and non-scale-free networks, the topology characteristics of scale-free networks are identified. The assortative coefficient is identified as a key metric of a scale-free network. It is also identified that most scale-free networks have negative assortative coefficients. Traditional generation models of scale-free networks are evaluated based on the identified topology characteristics. Most representative models, such as BA and Holme&Kim, are not effective in generating real-field scale-free networks. A link-rewiring method is suggested that can control the assortative coefficient while preserving the node degree sequence. Our analysis reveals that it is possible to effectively reproduce the assortative coefficients of real-field scale-free networks through link-rewiring.

• Journal of Advanced Information Technology and Convergence
• /
• v.10 no.1
• /
• pp.45-56
• /
• 2020

Despite extensive research, performance enhancement of keyphrase (KP) extraction remains a challenging problem in modern informatics. Recently, deep learning-based supervised approaches have exhibited state-of-the-art accuracies with respect to this problem, and several of the previously proposed methods utilize Bidirectional Encoder Representations from Transformers (BERT)-based language models. However, few studies have investigated the effective application of BERT-based fine-tuning techniques to the problem of KP extraction. In this paper, we consider the aforementioned problem in the context of scientific articles by investigating the fine-tuning characteristics of two distinct BERT models - BERT (i.e., base BERT model by Google) and SciBERT (i.e., a BERT model trained on scientific text). Three different datasets (WWW, KDD, and Inspec) comprising data obtained from the computer science domain are used to compare the results obtained by fine-tuning BERT and SciBERT in terms of KP extraction.

• Earthquakes and Structures
• /
• v.24 no.5
• /
• pp.365-375
• /
• 2023

Energy dissipation systems increase the energy dissipation capacity of buildings considerably. In this study, the effect of dampers on a typical 10-storey reinforced concrete structure with a ductile moment-resisting frame was investigated. In this context, 5 different models were created according to the calculation of the slip load and the positions of the dampers in the structure. Nonlinear time-history analyzes using 11 different earthquake acceleration records were performed on the models using the ETABS program. As a result of the analyses, storey displacements, energy dissipation ratios, drift ratios, storey accelerations, storey shears, and hysteretic curves of the dampers on the first and last storey and overturning moments are presented. In the study, it was determined that friction dampers increased the energy dissipation capacities of all models. In addition, it has been determined that positioning the dampers in the outer region of the structures and taking the base shear as a basis in the slip load calculation will be more effective.

• International Journal of High-Rise Buildings
• /
• v.12 no.2
• /
• pp.153-162
• /
• 2023

Achieving sustainable spaces is one of the emerging trends of tall buildings regarding their significant impacts on the cities. Reducing energy consumption and material using is investigated as a widely used approach to achieve more efficient tall buildings. Defining more efficient geometries and form modifications have been adopted for this goal. In this paper the effect of plan shape and diagrid angle on structural efficiency of diagrid tall buildings have been studied. A parametric workbench is applied to generate and analyze models. The goal is to find effective form parameters resulting in more efficient forms. Respectively, all models were generated in Rhino/grasshopper architecturally and analyzed by a finite element plug-in structurally. Based on the results, steeper angles almost cause more displacements and needs to be more stiffened. it can be seen almost more sided models need less weight for the structures and it could lead to more efficient forms.

• Journal of Korea Artificial Intelligence Association
• /
• v.1 no.1
• /
• pp.17-21
• /
• 2023

The primary objective of this research is to utilize machine learning models to analyze factors tailored to each dataset for predicting mental health conditions. The study aims to develop appropriate models based on specific datasets, with the goal of accurately predicting mental health states through the analysis of distinct factors present in each dataset. This approach seeks to design more effective strategies for the prevention and intervention of depression, enhancing the quality of mental health services by providing personalized services tailored to individual circumstances. Overall, the research endeavors to advance the development of personalized mental health prediction models through data-driven factor analysis, contributing to the improvement of mental health services on an individualized basis.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.3
• /
• pp.346-354
• /
• 2024

Deep learning models require high computing power due to a substantial amount of computation. It is difficult to use them in devices with limited computing environments, such as coastal surveillance equipments. In this study, a lightweight model is constructed by analyzing the weight changes of the convolutional layers during the training process based on MobileNet and then pruning the layers that affects the model less. The performance comparison results show that the lightweight model maintains performance while reducing computational load, parameters, model size, and data processing speed. As a result of this study, an effective pruning method for constructing lightweight deep learning models and the possibility of using equipment resources efficiently through lightweight models in limited computing environments such as coastal surveillance equipments are presented.

• Structural Engineering and Mechanics
• /
• v.91 no.2
• /
• pp.163-175
• /
• 2024

The objective of this research is to improve public safety in civil engineering by recognizing fractures in concrete structures quickly and correctly. The study offers a new crack detection method based on advanced image processing and machine learning techniques, specifically transfer learning with convolutional neural networks (CNNs). Four pre-trained models (VGG16, AlexNet, ResNet18, and DenseNet161) were fine-tuned to detect fractures in concrete surfaces. These models constantly produced accuracy rates greater than 80%, showing their ability to automate fracture identification and potentially reduce structural failure costs. Furthermore, the study expands its scope beyond crack detection to identify concrete health, using a dataset with a wide range of surface defects and anomalies including cracks. Notably, using VGG16, which was chosen as the most effective network architecture from the first phase, the study achieves excellent accuracy in classifying concrete health, demonstrating the model's satisfactorily performance even in more complex scenarios.