• Smart Media Journal
• /
• v.10 no.1
• /
• pp.63-69
• /
• 2021

When a person sees a sentence and understands the sentence, the person understands the sentence by reminiscent of the main word in the sentence as an image. Text-to-image is what allows computers to do this associative process. The previous deep learning-based text-to-image model extracts text features using Convolutional Neural Network (CNN)-Long Short Term Memory (LSTM) and bi-directional LSTM, and generates an image by inputting it to the GAN. The previous text-to-image model uses basic embedding in text feature extraction, and it takes a long time to train because images are generated using several modules. Therefore, in this research, we propose a method of extracting features by using the attention mechanism, which has improved performance in the natural language processing field, for sentence embedding, and generating an image by inputting the extracted features into the GAN. As a result of the experiment, the inception score was higher than that of the model used in the previous study, and when judged with the naked eye, an image that expresses the features well in the input sentence was created. In addition, even when a long sentence is input, an image that expresses the sentence well was created.

• Journal of Korea Game Society
• /
• v.21 no.3
• /
• pp.13-24
• /
• 2021

This paper shows the face rotation applicable to game character facial illustration. Existing studies limited data to human face data, required a large amount of data, and the synthesized results were not good. In this paper, the following method was introduced to solve the existing problems of existing studies. First, a 3D model with features of the input image was rotated and then rendered as a 2D image to construct a data set. Second, by designing GAN that can learn features of various poses from the data built through the 3D model, the input image can be synthesized at a desired pose. This paper presents the results of synthesizing the game character face illustration. From the synthesized result, it can be confirmed that the proposed method works well.

• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.67-79
• /
• 2023

In the image field, data augmentation refers to increasing the amount of data through an editing method such as rotating or cropping a photo. In this study, a generative adversarial network (GAN) image was created using CycleGAN, and various colors of dogs were reflected through data augmentation. In particular, dog data from the Stanford Dogs Dataset and Oxford-IIIT Pet Dataset were used, and 10 breeds of dog, corresponding to 300 images each, were selected. Subsequently, a GAN image was generated using CycleGAN, and four learning groups were established: 2,000 original photos (group I); 2,000 original photos + 1,000 GAN images (group II); 3,000 original photos (group III); and 3,000 original photos + 1,000 GAN images (group IV). The amount of data in each learning group was augmented using existing data augmentation methods such as rotating, cropping, erasing, and distorting. The augmented photo data were used to train the MobileNet_v3_Large, ResNet-152, InceptionResNet_v2, and NASNet_Large frameworks to evaluate the classification accuracy and loss. The top-3 accuracy for each deep neural network model was as follows: MobileNet_v3_Large of 86.4% (group I), 85.4% (group II), 90.4% (group III), and 89.2% (group IV); ResNet-152 of 82.4% (group I), 83.7% (group II), 84.7% (group III), and 84.9% (group IV); InceptionResNet_v2 of 90.7% (group I), 88.4% (group II), 93.3% (group III), and 93.1% (group IV); and NASNet_Large of 85% (group I), 88.1% (group II), 91.8% (group III), and 92% (group IV). The InceptionResNet_v2 model exhibited the highest image classification accuracy, and the NASNet_Large model exhibited the highest increase in the accuracy owing to data augmentation.

• Journal of Internet Computing and Services
• /
• v.21 no.6
• /
• pp.23-31
• /
• 2020

This study was carried out to generate various images of railroad surfaces with random defects as training data to be better at the detection of defects. Defects on the surface of railroads are caused by various factors such as friction between track binding devices and adjacent tracks and can cause accidents such as broken rails, so railroad maintenance for defects is necessary. Therefore, various researches on defect detection and inspection using image processing or machine learning on railway surface images have been conducted to automate railroad inspection and to reduce railroad maintenance costs. In general, the performance of the image processing analysis method and machine learning technology is affected by the quantity and quality of data. For this reason, some researches require specific devices or vehicles to acquire images of the track surface at regular intervals to obtain a database of various railway surface images. On the contrary, in this study, in order to reduce and improve the operating cost of image acquisition, we constructed the 'Defective Railroad Surface Regeneration Model' by applying the methods presented in the related studies of the Generative Adversarial Network (GAN). Thus, we aimed to detect defects on railroad surface even without a dedicated database. This constructed model is designed to learn to generate the railroad surface combining the different railroad surface textures and the original surface, considering the ground truth of the railroad defects. The generated images of the railroad surface were used as training data in defect detection network, which is based on Fully Convolutional Network (FCN). To validate its performance, we clustered and divided the railroad data into three subsets, one subset as original railroad texture images and the remaining two subsets as another railroad surface texture images. In the first experiment, we used only original texture images for training sets in the defect detection model. And in the second experiment, we trained the generated images that were generated by combining the original images with a few railroad textures of the other images. Each defect detection model was evaluated in terms of 'intersection of union(IoU)' and F1-score measures with ground truths. As a result, the scores increased by about 10~15% when the generated images were used, compared to the case that only the original images were used. This proves that it is possible to detect defects by using the existing data and a few different texture images, even for the railroad surface images in which dedicated training database is not constructed.

• Journal of the Korean Institute of Telematics and Electronics T
• /
• v.36T no.1
• /
• pp.71-78
• /
• 1999

This paper presents a new type of energy generative ER suspension system which does not require external power sources. This is accomplished by converting vibration energy(kinetic energy) into electrical energy. In order to undertake this, an appropriate size of the ER damper is manufactured by incorporation a mechanism which changes the linear motion of the ER damper to the rotary motion. This rotary motion is amplified by gears and activates a generator to produce the electrical energy. The efficiency of energy generation is evaluated and the level of damping force with generated power is also investigated. Then, the ER suspension system is applied to the quarter car model, and its vibration isolation is experimentally evaluated with respect to the piston speed.

• Environmental Sciences Bulletin of The Korean Environmental Sciences Society
• /
• v.1 no.2
• /
• pp.119-124
• /
• 1997

Cloud streets were successfully simulated by numerical model (RAMS) including an isolated mountain near the coast, large sensible heat flux from the sea surface, uniform stratification and wind velocity with low Froude number (0.25) in the inflow boundary. The well developed cloud streets between a pair of convective rolls are simulated at a level of 1 km over the sea. The following five results were obtained: 1) For the formation of the pair of convective rolls, both strong static instability and a topographically induced mechanical disturbance are strongly required at the same time. 2) Strong sensible heat flux from the sea surface is the main energy source of the pair of convective rolls, and the buoyancy caused by condensation in the cloud is negligibly small. 3) The pair of convective rolls is a complex of two sub-rolls. One is the outer roll, which has a large radius, but weak circulation, and the other is the inner roll, which has a small radius, but strong circulation. The outer roll gathers a large amount of moisture by convergence in the lower marine boundary, and the inner roll transfers the convergent moisture to the upper boundary layer by strong upward motion between them. 4) The pair of inner rolls form the line-shaped cloud streets, and keep them narrow along the center-line of the domain. 5) Both by non-hydrostatic and by hydrostatic assumptions, cloud streets can be simulated. In our case, non-hydrostatic processes enhanced somewhat the formation of cloud streets. The horizontal size of the topography does not seem to be restricted to within the small scale where non-hydrostatic effects are important.

• Journal of Korea Game Society
• /
• v.16 no.3
• /
• pp.65-76
• /
• 2016

The paradigm of the human experience through computer as a medium is moving from cultural interface to cultural software. Mod represents this paradigm shift in digital game culture. Until now, Digital game play focused on the immersive agency in the process of achieving the goals of the game. On the other hand, In Mod, play focus on generative agency in the process of creating and solving problems in game world. Through Mod, original game perceived as transformable data and creative material. Transformation and generation of such a game content through the user's Mod presents a sustainable model of the digital game.

• Korean Institute of Interior Design Journal
• /
• v.17 no.2
• /
• pp.150-161
• /
• 2008

It requires more close cooperation process and mediator for smooth communication in this industry structure where design and engineers are separated. The database of design integrates separate system and helps connection between organizations. The application category is utilized variously from formation to operation. Architectures addressed in this content as Frank Gehry and Nox are making differentiated design on the base of 3d digital methodology and using it widely from generation to fabrication. Especially they got to be free from the generative limit as it became available to analyse, digital surface organization, and realize the complex system form. Now more integrated and delicate works got to be affordable owing to various kinds of improved CNC, RP(rapid-prototype) machines, and architecture hardwares. With a linkage of software now at their disposal, architects can create a digital model of a building and all of its design elements, and in turn use this 3d information to construct actual building components using machines driven by CNC and other advanced manufacturing techniques. Digital technologies are enabling a direct correlation between what design and construction, thus bringing to the forefront the issue of the significance of information, the production, communication, application, and control of digital information in the industrial system. The central requirement is the clear, reliable, and consistent exchange of information among all parties involved in creating a given project.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.3
• /
• pp.129-138
• /
• 2022

Collecting and labeling sufficient training data, which is essential to deep learning-based visual inspection, is difficult for manufacturers to perform because it is very expensive. This paper presents a steel plate surface defect detection system with industrial-grade detection performance by training a small amount of steel plate surface images consisting of labeled and non-labeled data. To overcome the problem of lack of training data, we propose two data augmentation techniques: program-based augmentation, which generates defect images in a geometric way, and generative model-based augmentation, which learns the distribution of labeled data. We also propose a 4-step semi-supervised learning using pseudo labels and consistency training with fixed-size augmentation in order to utilize unlabeled data for training. The proposed technique obtained about 99% defect detection performance for four defect types by using 100 real images including labeled and unlabeled data.

• Journal of Information Science Theory and Practice
• /
• v.11 no.1
• /
• pp.61-78
• /
• 2023

Ontological knowledge modelling of epic texts, though being an established research arena backed by concrete multilingual and multicultural works, still suffers from two key shortcomings. Firstly, all epic ontological models developed till date have been designed following ad-hoc methodologies, most often combining existing general purpose ontology development methodologies. Secondly, none of the ad-hoc methodologies consider the potential reuse of existing epic ontological models for enrichment, if available. This paper presents, as a unified solution to the above shortcomings, the design and development of GOMME - the first dedicated methodology for iterative ontological modelling of epics, potentially extensible to works in different research arenas of digital humanities in general. GOMME is grounded in transdisciplinary foundations of canonical norms for epics, knowledge modelling best practices, application satisfiability norms, and cognitive generative questions. It is also the first methodology (in epic modelling but also in general) to be flexible enough to integrate, in practice, the options of knowledge modelling via reuse or from scratch. The feasibility of GOMME is validated via a first brief implementation of ontological modelling of the Indian epic Mahabharata by reusing an existing ontology. The preliminary results are promising, with the GOMME-produced model being both ontologically thorough and competent performance-wise.