• Journal of Internet of Things and Convergence
• /
• v.4 no.2
• /
• pp.1-6
• /
• 2018

Techniques for generating new sample data from higher dimensional data such as images have been utilized variously for speech synthesis, image conversion and image restoration. This paper adopts Progressive Growing of Generative Adversarial Networks(PG-GANs) as an implementation model to generate high-resolution images and to enhance variation of the generated images, and applied it to fashion image data. PG-GANs allows the generator and discriminator to progressively learn at the same time, continuously adding new layers from low-resolution images to result high-resolution images. We also proposed a Mini-batch Discrimination method to increase the diversity of generated data, and proposed a Sliced Wasserstein Distance(SWD) evaluation method instead of the existing MS-SSIM to evaluate the GAN model.

• Smart Media Journal
• /
• v.10 no.2
• /
• pp.30-37
• /
• 2021

Recently, 3D contents used in various fields have been attracting people's attention due to the development of virtual reality and augmented reality technology. In order to produce 3D contents, it is necessary to model the objects as vertices. However, high-quality modeling is time-consuming and costly. In order to convert a 2D character into a 3D model, it is necessary to express it as line drawings through feature line extraction. The extraction of consistent line drawings from 2D cartoon cartoons is difficult because the styles and techniques differ depending on the designer who produces them. Therefore, it is necessary to extract the line drawings that show the geometrical characteristics well in 2D cartoon shapes of various styles. This study proposes a method of automatically extracting line drawings. The 2D Cartoon shading image and line drawings are learned by using adversarial network model, which is artificial intelligence technology and outputs 2D cartoon artwork of various styles. Experimental results show the proposed method in this research can be obtained as a result of the line drawings representing the geometric characteristics when a 2D cartoon painting as input.

• Journal of Venture Innovation
• /
• v.6 no.4
• /
• pp.153-170
• /
• 2023

Generative AI services, including ChatGPT, were becoming increasingly active. This study aimed to empirically analyze the factors that promoted and hindered the diffusion of such services from a consumer perspective. Accordingly, a research model was developed based on the Value-based Adoption Model (VAM) framework, addressing both benefit and sacrifice factors. Benefits identified included usefulness and enjoyment, while sacrifices were security and hallucination. The study analyzed how these factors affected the intention to use generative AI services. A survey was conducted among college students for empirical analysis, and 200 valid responses were analyzed. The analysis utilized structural equation modeling with AMOS 24. The empirical results showed that usefulness and enjoyment had a significant positive impact on perceived value, while security and hallucination had a significant negative impact. The order of influence on perceived value was usefulness, hallucination, security, and then enjoyment. Perceived value had a significant positive impact on usage intention. Moreover, perceived value was found to mediate the relationship between usefulness, enjoyment, security, hallucination, and the intention to use generative AI services. These findings expanded the research horizon academically by validating the effectiveness of generative AI services based on existing models and demonstrated the continued importance of usefulness in a practical context.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.129-164
• /
• 2023

In a situation where the use and introduction of Large Language Models (LLMs) is expanding due to recent developments in generative AI technology, it is difficult to find actual application cases or implementation methods for the use of internal company data in existing studies. Accordingly, this study presents a method of implementing generative AI services using the LLM application architecture using the most widely used LangChain framework. To this end, we reviewed various ways to overcome the problem of lack of information, focusing on the use of LLM, and presented specific solutions. To this end, we analyze methods of fine-tuning or direct use of document information and look in detail at the main steps of information storage and retrieval methods using the retrieval augmented generation (RAG) model to solve these problems. In particular, similar context recommendation and Question-Answering (QA) systems were utilized as a method to store and search information in a vector store using the RAG model. In addition, the specific operation method, major implementation steps and cases, including implementation source and user interface were presented to enhance understanding of generative AI technology. This has meaning and value in enabling LLM to be actively utilized in implementing services within companies.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.7
• /
• pp.2547-2567
• /
• 2021

It has been widely acknowledged that occlusion impairments adversely distress many face recognition algorithms' performance. Therefore, it is crucial to solving the problem of face image occlusion in face recognition. To solve the image occlusion problem in face recognition, this paper aims to automatically de-occlude the human face majority or discriminative regions to improve face recognition performance. To achieve this, we decompose the generative process into two key stages and employ a separate generative adversarial network (GAN)-based network in both stages. The first stage generates an initial coarse face image without an occlusion mask. The second stage refines the result from the first stage by forcing it closer to real face images or ground truth. To increase the performance and minimize the artifacts in the generated result, a new refine loss (e.g., reconstruction loss, perceptual loss, and adversarial loss) is used to determine all differences between the generated de-occluded face image and ground truth. Furthermore, we build occluded face images and corresponding occlusion-free face images dataset. We trained our model on this new dataset and later tested it on real-world face images. The experiment results (qualitative and quantitative) and the comparative study confirm the robustness and effectiveness of the proposed work in removing challenging occlusion masks with various structures, sizes, shapes, types, and positions.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.437-450
• /
• 2022

Generative adversarial networks(GANs) have demonstrated remarkable success in image synthesis. However, since GANs show instability in the training stage on large datasets, it is difficult to apply to various application fields. A single image GAN is a field that generates various images by learning the internal distribution of a single image. In this paper, we investigate five Single Image GAN: SinGAN, ConSinGAN, InGAN, DeepSIM, and One-Shot GAN. We compare the performance of each model and analyze the pros and cons of a single image GAN.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.23-30
• /
• 2022

Glaucoma is a chronic neuropathy that affects the optic nerve which can lead to blindness. The detection and prediction of glaucoma become possible using deep neural networks. However, the detection performance relies on the availability of a large number of data. Therefore, we propose different frameworks, including a hybrid of a generative adversarial network and a convolutional neural network to automate and increase the performance of glaucoma detection. The proposed frameworks are evaluated using five public glaucoma datasets. The framework which uses a Deconvolutional Generative Adversarial Network (DCGAN) and a DenseNet pre-trained model achieves 99.6%, 99.08%, 99.4%, 98.69%, and 92.95% of classification accuracy on RIMONE, Drishti-GS, ACRIMA, ORIGA-light, and HRF datasets respectively. Based on the experimental results and evaluation, the proposed framework closely competes with the state-of-the-art methods using the five public glaucoma datasets without requiring any manually preprocessing step.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.06a
• /
• pp.192-193
• /
• 2017

본 논문에서는 비디오 영상 압축 왜곡 제거를 위해 Generative Adversarial Network (GAN)을 적용한 컨벌루션 뉴럴 네트워크 (CNN) 모델을 제안한다. GAN 모델의 생성 모델 (Generator)은 노이즈가 아닌 High Efficiency Video Coding (HEVC)로 압축된 영상을 입력 받은 뒤, 압축 왜곡이 제거된 영상을 출력하며, 분류 모델 (Discriminator)은 원본 영상과 압축된 영상을 입력 받은 뒤, 원본 영상과 압축 왜곡이 포함된 압축된 영상을 분류한다. 분류 모델은 5 개 층을 쌓은 컨벌루션 뉴럴 네트워크 구조를 사용하였고, 생성 모델은 5 개 층을 쌓은 SRCNN 구조와 VDSR 구조를 기반으로 한 두 개의 모델을 이용한 실험을 통해 얻은 결과를 비교하였다. 비디오 영상 압축 왜곡 제거 실험을 위해 원본 비디오 영상을 HEVC 을 이용하여 2Mbps, 4Mbps 로 압축된 영상을 사용하였으며, 압축된 영상 대비 왜곡이 제거된 영상을 얻을 수 있었다.

• ETRI Journal
• /
• v.43 no.3
• /
• pp.511-523
• /
• 2021

The World Health Organization provides guidelines for managing the particulate matter (PM) level because a higher PM level represents a threat to human health. To manage the PM level, a procedure for measuring the PM value is first needed. We use a PM sensor that collects the PM level by laser-based light scattering (LLS) method because it is more cost effective than a beta attenuation monitor-based sensor or tapered element oscillating microbalance-based sensor. However, an LLS-based sensor has a higher probability of malfunctioning than the higher cost sensors. In this paper, we regard the overall malfunctioning, including strange value collection or missing collection data as anomalies, and we aim to detect anomalies for the maintenance of PM measuring sensors. We propose a novel architecture for solving the above aim that we call the hypothesis pruning generative adversarial network (HP-GAN). Through comparative experiments, we achieve AUROC and AUPRC values of 0.948 and 0.967, respectively, in the detection of anomalies in LLS-based PM measuring sensors. We conclude that our HP-GAN is a cutting-edge model for anomaly detection.

• Journal of information and communication convergence engineering
• /
• v.17 no.1
• /
• pp.14-20
• /
• 2019

Currently, microarray gene expression data take advantage of the sufficient classification of cancers, which addresses the problems relating to cancer causes and treatment regimens. However, the sample size of gene expression data is often restricted, because the price of microarray technology on studies in humans is high. We propose enhancing the gene expression classification of support vector machines with generative adversarial networks (GAN-SVMs). A GAN that generates new data from original training datasets was implemented. The GAN was used in conjunction with nonlinear SVMs that efficiently classify gene expression data. Numerical test results on 20 low-sample-size and very high-dimensional microarray gene expression datasets from the Kent Ridge Biomedical and Array Expression repositories indicate that the model is more accurate than state-of-the-art classifying models.