• Composites Research
• /
• v.36 no.3
• /
• pp.205-210
• /
• 2023

In this study, we developed a transfer learning framework based on homogenization data for efficient prediction of the effective mechanical properties and thermal conductivity of cellular foam structures. Mean-field homogenization (MFH) based on the Eshelby's tensor allows for efficient prediction of properties in porous structures including ellipsoidal inclusions, but accurately predicting the properties of cellular foam structures is challenging. On the other hand, finite element homogenization (FEH) is more accurate but comes with relatively high computational cost. In this paper, we propose a data-driven transfer learning framework that combines the advantages of mean-field homogenization and finite element homogenization. Specifically, we generate a large amount of mean-field homogenization data to build a pre-trained model, and then fine-tune it using a relatively small amount of finite element homogenization data. Numerical examples were conducted to validate the proposed framework and verify the accuracy of the analysis. The results of this study are expected to be applicable to the analysis of materials with various foam structures.

• Journal of The Korean Association For Science Education
• /
• v.43 no.6
• /
• pp.573-582
• /
• 2023

This study aimed to explore the potential use of artificial intelligence in science education for gifted students by analyzing the structure of abstracts written by students at a gifted science academy and comparing the performance of various elements extracted using AI. The study involved an analysis of 263 graduation theses from S Science High School over five years (2017-2021), focusing on the frequency and types of background, objectives, methods, results, and discussions included in their abstracts. This was followed by an evaluation of their accuracy using AI classification methods with fine-tuning and prompts. The results revealed that the frequency of elements in the abstracts written by gifted students followed the order of objectives, methods, results, background, and discussions. However, only 57.4% of the abstracts contained all the essential elements, such as objectives, methods, and results. Among these elements, fine-tuned AI classification showed the highest accuracy, with background, objectives, and results demonstrating relatively high performance, while methods and discussions were often inaccurately classified. These findings suggest the need for a more effective use of AI, through providing a better distribution of elements or appropriate datasets for training. Educational implications of these findings were also discussed.

• Korean Journal of Radiology
• /
• v.24 no.6
• /
• pp.541-552
• /
• 2023

Objective: Detection of pneumoperitoneum using abdominal radiography, particularly in the supine position, is often challenging. This study aimed to develop and externally validate a deep learning model for the detection of pneumoperitoneum using supine and erect abdominal radiography. Materials and Methods: A model that can utilize "pneumoperitoneum" and "non-pneumoperitoneum" classes was developed through knowledge distillation. To train the proposed model with limited training data and weak labels, it was trained using a recently proposed semi-supervised learning method called distillation for self-supervised and self-train learning (DISTL), which leverages the Vision Transformer. The proposed model was first pre-trained with chest radiographs to utilize common knowledge between modalities, fine-tuned, and self-trained on labeled and unlabeled abdominal radiographs. The proposed model was trained using data from supine and erect abdominal radiographs. In total, 191212 chest radiographs (CheXpert data) were used for pre-training, and 5518 labeled and 16671 unlabeled abdominal radiographs were used for fine-tuning and self-supervised learning, respectively. The proposed model was internally validated on 389 abdominal radiographs and externally validated on 475 and 798 abdominal radiographs from the two institutions. We evaluated the performance in diagnosing pneumoperitoneum using the area under the receiver operating characteristic curve (AUC) and compared it with that of radiologists. Results: In the internal validation, the proposed model had an AUC, sensitivity, and specificity of 0.881, 85.4%, and 73.3% and 0.968, 91.1, and 95.0 for supine and erect positions, respectively. In the external validation at the two institutions, the AUCs were 0.835 and 0.852 for the supine position and 0.909 and 0.944 for the erect position. In the reader study, the readers' performances improved with the assistance of the proposed model. Conclusion: The proposed model trained with the DISTL method can accurately detect pneumoperitoneum on abdominal radiography in both the supine and erect positions.

• Journal of Power Electronics
• /
• v.17 no.2
• /
• pp.533-541
• /
• 2017

This paper presents a novel Parameter-Independent Fictive-Axis (PIFA) approach for the Voltage-Oriented Control (VOC) algorithm used in grid-tied single-phase inverters. VOC is based on the transformation of the single-phase grid current into the synchronous reference frame. As a result, an orthogonal current signal is needed. Traditionally, this signal has been obtained from fixed time delays, digital filters or a Hilbert transformation. Nevertheless, these solutions present stability and transient drawbacks. Recently, the Fictive Axis Emulation (FAE) VOC has emerged as an alternative for the generation of the quadrature current signal. FAE requires detailed information of the grid current filter along with its transfer function for signal creation. When the transfer function is not accurate, the direct and quadrature current components present steady-state oscillations as the fictive two-phase system becomes unbalanced. Moreover, the digital implementation of the transfer function imposes an additional computing burden on the VOC. The PIFA VOC presented in this paper, takes advantage of the reference current to create the required orthogonal current, which effectively eliminates the need for the filter transfer function. Moreover, the fictive signal amplitude and phase do not change with a frequency drift, which results in an increased reliability. This yields a fast, linear and stable system that can be installed without fine tuning. To demonstrate the good performance of the PIFA VOC, simulation and experimental results are presented.

• Journal of Technology Innovation
• /
• v.26 no.2
• /
• pp.69-93
• /
• 2018

As companies seek lower cost and superior quality at the same time, which depend on improvement in product architecture, they need to critically consider product architecture as part of corporate strategy. This research investigated how product architecture and organizational capability affect innovative outcomes with using architecture framework. As a result, we were able to find out Korean shipbuilding company has put much effort on integral works such as development of FGSS(Fuel gas supply system), PRS(Partial Re-liquefaction System) and weight lightening for improving fuel efficiency. And this kind of integral ability was realized by organizational capability of Korean shipbuilding company based on interactive relationship with plant workers. In contrast, Chinese shipbuilding companies focused excessively on the standard design and the convenience of research and development made by central government, overlooking the need for fine-tuning. As a result, the fuel efficiency of Chinese LNG ships turned out to be 7-10% lower than those of South Korea with using the same modules and components.

• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.953-964
• /
• 2020

Ever since media contents took over the world, the importance of typography has increased, and the influence of fonts has be n recognized. Nevertheless, the current Hangul font system is very poor and is provided passively, so it is practically impossible to understand and utilize all the shape characteristics of more than six thousand Hangul fonts. In this paper, the characteristics of Hangul font shapes were selected based on the Hangul structure of similar fonts. The stroke element detection training was performed by fine tuning Faster R-CNN Inception v2, one of the deep learning object detection models. We also propose a system that automatically extracts the stroke element characteristics from characters by introducing an automatic extraction algorithm. In comparison to the previous research which showed poor accuracy while using SVM(Support Vector Machine) and Sliding Window Algorithm, the proposed system in this paper has shown the result of 10 % accuracy to properly detect and extract stroke elements from various fonts. In conclusion, if the stroke element characteristics based on the Hangul structural information extracted through the system are used for similar classification, problems such as copyright will be solved in an era when typography's competitiveness becomes stronger, and an automated process will be provided to users for more convenience.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.2
• /
• pp.138-145
• /
• 2000

A identification algorithm that finds optimal fuzzy membership functions and rule base to fuzzy model isproposed and a fuzzy controller is designed to get more accurate position and velocity control of wheeled mobile robot. This procedure that is composed of three steps has its own unique process at each step. The elements of output term set are increased at first step and then the rule base is varied according to increase of the elements. The adjusted system is in competition with system which doesn't include any increased elements. The adjusted system will be removed if the system lost. Otherwise, the control system is replaced with the adjusted system. After finished regulation of output term set and rule base, searching for input membership functions is processed with constraints and fine tuning of output membership functions is done.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.18 no.3
• /
• pp.345-355
• /
• 2008

This paper presents a design of a tuned liquid mass damper(TLMD) for controlling bi-directional response of high-rise building structure subjected to windload. The proposed damper behaves as a tuned mass damper(TMD) of which mass is regarded as the mass of a tuned liquid column damper(TLCD) and the case wall of the TLCD itself in one direction and the TLCD in the other direction. Because the proposed device has coupled design parameter along two orthogonal directions, it is very important to select designing components by optimal fine tuning. In the designing TLMD, for easy maintenance, the rubber-bearing with small springs was applied in TMD direction. In this study, the Songdo New City Tower 1A in Korea, which has been designed and constructed two TLCDs in order to control bi-directional response, was chosen as the model building structure. The results of rotation test proved the effectiveness of bi-directional behavior of TLMD.

• KIISE Transactions on Computing Practices
• /
• v.23 no.5
• /
• pp.322-327
• /
• 2017

The classification problem in the field of Natural Language Processing has been studied for a long time. Continuing forward with our previous research, which classifies large-scale text using Convolutional Neural Networks (CNN), we implemented Recurrent Neural Networks (RNN), Long-Short Term Memory (LSTM) and Gated Recurrent Units (GRU). The experiment's result revealed that the performance of classification algorithms was Multinomial Naïve Bayesian Classifier < Support Vector Machine (SVM) < LSTM < CNN < GRU, in order. The result can be interpreted as follows: First, the result of CNN was better than LSTM. Therefore, the text classification problem might be related more to feature extraction problem than to natural language understanding problems. Second, judging from the results the GRU showed better performance in feature extraction than LSTM. Finally, the result that the GRU was better than CNN implies that text classification algorithms should consider feature extraction and sequential information. We presented the results of fine-tuning in deep neural networks to provide some intuition regard natural language processing to future researchers.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.7
• /
• pp.1541-1547
• /
• 2005

In this paper, Dualband internal antenna for GSM/DSC handset is proposed. The antenna has a size of about $38mm{\times}90mm{\times}1mm$, giving a total mobile phone PCB for support and fold type patch of about $30mm{\times}8mm{\times}3.2mm$. This antenna characteriatic facilitates the fine-tuning of the two operating frequencies of 909MHz and 1762MHz in the dualband design. The measured radiation pattern in the E-plane and H-plane for operating frequencies of 909MHz and 1762MHz is compared and analyzed. The designed and fabricated two band internal antenna for GSM/DSC handset have a gain between 0dBi and 2.0dBi at all bands. Also, the electric firld distribution and directivity on human head caused by portable phone is analyzed. An analysis model is composed of a human head model and the antenna mounted on the same ground plane as portable telephone size.