• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.124-125
• /
• 2023

Defect detection during liquid crystal display (LCD) manufacturing has always been a critical challenge. This study aims to address this issue by proposing a data augmentation method based on generative adversarial networks (GAN) to improve defect identification accuracy in LCD production. By leveraging synthetically generated image data from GAN, we effectively augment the original dataset to make it more representative and diverse. This data augmentation strategy enhances the model's generalization capability and robustness on real-world data. Compared to traditional data augmentation techniques, the synthetic data from GAN are more realistic, diverse and broadly distributed. Experimental results demonstrate that training models with GAN-generated data combined with the original dataset significantly improves the detection accuracy of critical defects in LCD manufacturing, compared to using the original dataset alone. This study provides an effective data augmentation approach for intelligent quality control in LCD production.

• Journal of The Korean Association For Science Education
• /
• v.16 no.4
• /
• pp.365-375
• /
• 1996

Improving of scientific inquiring ability is the major goal of current science curriculum, and the 6th science curriculum. But science educators consider that the existing textbooks and teaching manuals are insufficient to achieve this goal. For science teachers at teaching site to guide students efficiently in research work, development of teaching-learning programs is urgently demanded. Hypothesis Verification Learning Model(HVLM) was applied to classroom situation to improve ability of scientific inquiry in experiment teaching of middle school biology. The effects of the model were analyzed to suggest some approach method to reach the goal of science education in this study. The major results of this study are as following: 1. The students and teachers responded positively on this new learning model. an students were willing to participate in biology experiment and they said that to know what was unknown to them while exchanging ideas and opinions through the discussion, It was hard for teachers to instruct at the first time and it took much time for them to arrange materials ready, but it turned to be easier as time went on. 2. In science process skills, there was no significant difference statistically by new leaning model. Only the formulating a generalization or model showed significant difference statistically between the two groups. 3. For scientific attitude, experimental group did not show significant difference statistically between the two groups, but the experimental group showed statistically more significant positiveness in all areas afterwards than before. 4. In science achievement test, there was significantly higher than the control group. It is also analyzed that they remember the experiments in courses and results they planned and performed by themselves longer than these guided by teachers.

• Korean Journal of Construction Engineering and Management
• /
• v.21 no.4
• /
• pp.30-37
• /
• 2020

The purpose of this study is to compare and contrast the amount of overseas construction orders of South Korea and China by using various time series models that measure the overseas construction orders. Based on the analysis we propose better specification (model selection) with much more predictive power and prove the universality of the model developed by applying our findings with respect to the prediction power of overseas construction orders from other countries viewpoints (verification of generalization). The input variables include Dubai crude oil and exchange rates by country from 1981 to 2019. The VAR model is proposed based on the prediction power test, with respect to MAPE, RMSE, and MAE between the estimates and actual measurements from 2016 to 2019. We also conclude the results of the prediction of overseas construction orders time series of China are again consistent with the actual numbers. These analyses suggest the possibility of developing a comprehensive model that predict the potential construction orders of other countries.

• International Journal of Computer Science & Network Security
• /
• v.22 no.2
• /
• pp.214-222
• /
• 2022

Convolutional Neural networks (CNNs) are a category of deep learning networks that have proven very effective in computer vision tasks such as image classification. Notwithstanding, not much has been seen in its use for remote sensing image classification in developing countries. This is majorly due to the scarcity of training data. Recently, transfer learning technique has successfully been used to develop state-of-the art models for remote sensing (RS) image classification tasks using training and testing data from well-known RS data repositories. However, the ability of such model to classify RS test data from a different dataset has not been sufficiently investigated. In this paper, we propose a deep CNN model that can classify RS test data from a dataset different from the training dataset. To achieve our objective, we first, re-trained a ResNet-50 model using EuroSAT, a large-scale RS dataset to develop a base model then we integrated Augmentation and Ensemble learning to improve its generalization ability. We further experimented on the ability of this model to classify a novel dataset (Nig_Images). The final classification results shows that our model achieves a 96% and 80% accuracy on EuroSAT and Nig_Images test data respectively. Adequate knowledge and usage of this framework is expected to encourage research and the usage of deep CNNs for land cover mapping in cases of lack of training data as obtainable in developing countries.

• Wind and Structures
• /
• v.36 no.6
• /
• pp.405-421
• /
• 2023

Strong wind is the main factors of wind-damage of high-rise buildings, which often creates largely economical losses and casualties. Wind pressure plays a critical role in wind effects on buildings. To obtain the high-resolution wind pressure field, it often requires massive pressure taps. In this study, two traditional methods, including bilinear and bicubic interpolation, and two deep learning techniques including Residual Networks (ResNet) and Generative Adversarial Networks (GANs), are employed to reconstruct wind pressure filed from limited pressure taps on the surface of an ideal building from TPU database. It was found that the GANs model exhibits the best performance in reconstructing the wind pressure field. Meanwhile, it was confirmed that k-means clustering based retained pressure taps as model input can significantly improve the reconstruction ability of GANs model. Finally, the generalization ability of k-means clustering based GANs model in reconstructing wind pressure field is verified by an actual engineering structure. Importantly, the k-means clustering based GANs model can achieve satisfactory reconstruction in wind pressure field under the inputs processing by k-means clustering, even the 20% of pressure taps. Therefore, it is expected to save a huge number of pressure taps under the field reconstruction and achieve timely and accurately reconstruction of wind pressure field under k-means clustering based GANs model.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.59-64
• /
• 2024

Recently, research on the convergence of drones and artificial intelligence technologies have been conducted in various industrial fields. In this paper, we propose an illegal parking vehicle recognition model using deep learning-based object recognition and classification algorithms. The model of object recognition and classification consist of YOLOv8 and ResNet18, respectively. The proposed model was trained using image data collected in general road environment, and the trained model showed high accuracy in determining illegal parking. From simulation results, it was confirmed that the proposed model has generalization performance to identify illegal parking vehicles from various images.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 1999.10a
• /
• pp.365-373
• /
• 1999

Recently, numerous studies have demonstrated that artificial intelligence such as neural networks can be an alternative methodology for classification problems to which traditional statistical methods have long been applied. In building neural network model, the selection of independent and dependent variables should be approached with great care and should be treated as a model construction process. Irrespective of the efficiency of a learning procedure in terms of convergence, generalization and stability, the ultimate performance of the estimator will depend on the relevance of the selected input variables and the quality of the data used. Approaches developed in statistical methods such as correlation analysis and stepwise selection method are often very useful. These methods, however, may not be the optimal ones for the development of neural network models. In this paper, we propose a genetic algorithms approach to find an optimal or near optimal input variables for neural network modeling. The proposed approach is demonstrated by applications to bankruptcy prediction modeling. Our experimental results show that this approach increases overall classification accuracy rate significantly.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.17 no.9
• /
• pp.2223-2233
• /
• 1993

An engineering method is suggested to calculate the applied load versus crack extension in the elastic-plastic fracture. The condition for an increment of crack extension is set by a critical increment of crack-up opening displacement(CTOD). The ratio of the CTOD increment to the incremental crack extention is a critical crack-tip opening angle(CTOA), assumed to be constant for a material of a given thickness. The Dugdale model of crack-tip deformation in an infinite plate is applied to the method, and a complete solution for crack extension and crack instability is obtained. For finite-size specimens of arbitrary geometry in general yielding, an approximate generalization of the Dugdale model is suggested so that the approximation approaches the small-scale yielding solution in a low applied load and the finite-element solution in a large applied load. Maximum load is calculated so that an applied load attains either a limit load on an unbroken ligament or a peak load during crack extension. The proposed method was applied to three-point bend specimens of a carbon steel SM45C in various sizes. Reasonable agreements are found between calculated maximum loads and experimental failure loads. Therefore, the method can be a viable alternative to the J-R curve approach in the elastic-plastic fracture analysis.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2012.11a
• /
• pp.153-154
• /
• 2012

The accuracy of cost estimation at an early stage in school building project is one of the critical factors for successful completion. So many method and techniques have developed that can estimate construction cost using limited information available in the early stage. Among the techniques, Support Vector Machine(SVM) has received attention in various field due to its excellent capacity for self-learning and generalization performance. Therefore, the purpose of this study is to verify the applicability of cost prediction model based on SVM in school building project at the early stage. Data used in this study are 139 school building cost constructed from 2004 to 2007 in Gyeonggi-Do. And prediction error rate of 7.48% in support vector machine is obtained. So the results showed applicability of using SVM model for predicting construction cost of school building projects.

• Journal of Ocean Engineering and Technology
• /
• v.27 no.1
• /
• pp.24-30
• /
• 2013

The Korea Navy has been making constant efforts to apply M&S (modeling and simulation) to naval ship development, and the generalization of M&S for ship development is a trend. M&S for ship design is used for the V&V (verification and validation) of its design and operation, including design verification and ergonomic design that considers the crew using the Naval Ship Product Model. In addition, many parts of this M&S are repeatedly accomplished regardless of the kinds of ships. This study aims to standardize M&S, which repeatedly applies similar verifications for operation scenarios. A congestion assessment simulation for the major spaces of ships was the subject of the standardization based on the leading research results of various researchers, and a simulation automation solution was suggested. An information model using XML was proposed through the simulation automation concept, and a prototype system based on it was implemented. The usability was shown through a case study that verified the operability performance of the crew messroom.