• 한국정보통신학회논문지
• /
• 제26권4호
• /
• pp.591-597
• /
• 2022

최근 데이터셋을 효율적으로 구축하는 방법으로 데이터 증강 기법과 관련하여 많은 연구가 이루어지고 있다. 이 중 대표적인 데이터 증강 기법은 생성적 적대 신경망(Generative Adversarial Network:GAN)을 활용하는 방법이며, 이는 생성자와 판별자를 서로 경쟁 학습시킴으로써 진짜 데이터와 유사한 데이터를 생성해내는 기법이다. 그러나, GAN을 학습할 때 환경 및 진행 정도에 따라 생성되는 유사 데이터 중에서 픽셀이 깨지는 파손 영상이 발생하는 경우가 있으며, 이러한 영상은 데이터셋으로 활용할 수 없고 학습 시간을 증가시키는 원인이 된다. 본 논문에서는 GAN 학습 과정에서 생성되는 영상 데이터의 히스토그램을 분석하여 이러한 파손 영상을 선별해내는 알고리즘을 개발하였으며, 기존 GAN에서 생성되는 영상과 비교해 본 결과 파손 영상의 비율을 33.3배(3,330%) 감소시켰다.

• 한국과학교육학회지
• /
• 제43권3호
• /
• pp.307-319
• /
• 2023

본 연구는 최근 주목받고 있는 텍스트 기반 생성형 인공지능에 대해 관심과 활용이 증가함에 따라 과학교육적 측면에서의 활용을 위해 생성형 인공지능의 주요 개념과 원리를 설명하고, 이를 효과적으로 활용할 수 있는 방안과 그 한계를 지적하며 이를 토대로 과학교육의 실행과 연구의 측면에서 시사점을 제공하는 것을 목적으로 한다. 최근 들어 증가하고 있는 생성형 인공지능은 대체로 인코더와 디코더로 이뤄진 트랜스포머 모델을 기반으로 하고 있으며, 인간의 피드백을 활용한 강화학습과 보상 모델에 대한 최적화, 문맥에 대한 이해 등을 통해 놀라운 발전을 이루고 있다. 특히, 다양한 사용자의 질문이나 의도를 이해하는 능력과 이를 바탕으로 한 글쓰기, 요약, 제시어 추출, 평가와 피드백 등 다양한 기능을 수행할 수 있다. 또한 교수자가 제시하는 예를 토대로 주어진 응답을 평가하거나 질문과 적절한 답변을 생성하는 등 학습자에 대한 진단과 실질적 교육내용의 구성 등 많은 유용성을 가지고 있다. 그러나 생성형 인공지능이 가지고 있는 한계로 인해 정확한 사실이나 지식에 대한 잘못된 전달, 과도한 확신으로 인한 편향, 사용자의 태도나 감정 등에 미칠 영향의 불확실성 등에 대한 문제 등에 대해 해가 없는지 검토가 필요하다. 특히, 생성형 인공지능이 제공하는 응답은 많은 사람들의 응답 데이터를 기반으로 한 확률적 접근이므로 매우 거리가 멀거나 새로운 관점을 제시하는 통찰적 사고나 혁신적 사고를 제한할 우려도 있다. 이에 따라 본 연구는 과학교수학습을 위해 인공지능의 긍정적 활용을 위한 여러 실천적 제언을 제시하였다.

• 한국멀티미디어학회논문지
• /
• 제22권12호
• /
• pp.1447-1456
• /
• 2019

As artificial intelligence technology is actively used in image processing, it is possible to generate high-quality fake images based on deep learning. Fake images generated using GAN(Generative Adversarial Network), one of unsupervised learning algorithms, have reached levels that are hard to discriminate from the naked eye. Detecting these fake images is required as they can be abused for crimes such as illegal content production, identity fraud and defamation. In this paper, we develop a deep-learning model based on CNN(Convolutional Neural Network) for the detection of StyleGAN fake images. StyleGAN is one of GAN algorithms and has an excellent performance in generating face images. We experiment with 48 number of experimental scenarios developed by combining parameters of the proposed model. We train and test each scenario with 300,000 number of real and fake face images in order to present a model parameter that improves performance in the detection of fake faces.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권10호
• /
• pp.3685-3707
• /
• 2021

In recent years, facial attribute editing has been successfully used to effectively change face images of various attributes based on generative adversarial networks and encoder-decoder models. However, existing models have a limitation in that they may change an unintended part in the process of changing an attribute or may generate an unnatural result. In this paper, we propose a model that improves the learning of the attention mask by adding a spatial attention mechanism based on the unified selective transfer network (referred to as STGAN) using semi-supervised learning. The proposed model can edit multiple attributes while preserving details independent of the attributes being edited. This study makes two main contributions to the literature. First, we propose an encoder-decoder model structure that learns and edits multiple facial attributes and suppresses distortion using an attention mask. Second, we define guide masks and propose a method and an objective function that use the guide masks for multiple facial attribute editing through semi-supervised learning. Through qualitative and quantitative evaluations of the experimental results, the proposed method was proven to yield improved results that preserve the image details by suppressing unintended changes than existing methods.

• International journal of advanced smart convergence
• /
• 제12권4호
• /
• pp.142-146
• /
• 2023

We present a method for generating 3D structures and rendering objects by combining VAE (Variational Autoencoder) and GAN (Generative Adversarial Network). This approach focuses on generating and rendering 3D models with improved quality using residual learning as the learning method for the encoder. We deep stack the encoder layers to accurately reflect the features of the image and apply residual blocks to solve the problems of deep layers to improve the encoder performance. This solves the problems of gradient vanishing and exploding, which are problems when constructing a deep neural network, and creates a 3D model of improved quality. To accurately extract image features, we construct deep layers of the encoder model and apply the residual function to learning to model with more detailed information. The generated model has more detailed voxels for more accurate representation, is rendered by adding materials and lighting, and is finally converted into a mesh model. 3D models have excellent visual quality and accuracy, making them useful in various fields such as virtual reality, game development, and metaverse.

• ETRI Journal
• /
• 제46권2호
• /
• pp.165-174
• /
• 2024

We propose a method to suppress the speckle noise and blur effects of the light field extracted from a hologram using a deep-learning technique. The light field can be extracted by bandpass filtering in the hologram's frequency domain. The extracted light field has reduced spatial resolution owing to the limited passband size of the bandpass filter and the blurring that occurs when the object is far from the hologram plane and also contains speckle noise caused by the random phase distribution of the three-dimensional object surface. These limitations degrade the reconstruction quality of the hologram resynthesized using the extracted light field. In the proposed method, a deep-learning model based on a generative adversarial network is designed to suppress speckle noise and blurring, resulting in improved quality of the light field extracted from the hologram. The model is trained using pairs of original two-dimensional images and their corresponding light-field data extracted from the complex field generated by the images. Validation of the proposed method is performed using light-field data extracted from holograms of objects with single and multiple depths and mesh-based computer-generated holograms.

• 한국과학교육학회지
• /
• 제28권8호
• /
• pp.786-795
• /
• 2008

The purpose of this research is to propose a program for teaching and learning effective problem-solving for gifted students based on abductive inference. The role of abductive inference is important for scientific discoveries and creative inferences in problem-solving processes. The characteristics of creativity and abductive inference were investigated, and the following were discussed: (a) a suggestion for a new program based on abductive inference for creative outcomes, this program largely consists of two phases: generative hypotheses and confirmative hypotheses, (b) a survey of the validity of a program. It is typical that hypotheses are confirmed in phases through experiments based on hypothetic deductive methodology. However, because generative hypotheses of this hypothetic deductive methodology are not manifest, we maintained that abductive inference strategies must be used in a Creative Teaching-learning Program for gifted science students.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2018년도 제58차 하계학술대회논문집 26권2호
• /
• pp.397-398
• /
• 2018

본 논문에서는 음악 전공자가 아니어도 원하는 악기를 선택하여 손쉽게 자신의 음악을 만들 수 있는 GAN(Generative Adversarial Network) 알고리즘 기반 음악생성 프로그램을 개발하였다. 음악분야는 진입장벽이 높아 음악 전공자가 아니면 자신만의 음악을 제작하기 힘들다. 행사나 소소한 이벤트에서도 쓸 수 있는 자신만의 음악, 방송이나 1인 미디어 등에서도 저작권 걱정 없이 쓸 수 있는 자신만의 음악을 이 GAN 알고리즘 기반 음악생성 프로그램을 이용하여 비전공자라도 손쉽게 음악을 만들 수 있다.

• 한국항공운항학회지
• /
• 제27권4호
• /
• pp.27-36
• /
• 2019

An accurate trajectory prediction is a key to the safe and efficient operations of aircraft. One way to improve trajectory prediction accuracy is to develop a model for aircraft ground speed prediction. This paper proposes a generative model for posterior aircraft ground speed prediction. The proposed method fits the Gaussian Mixture Model(GMM) to historical data of aircraft speed, and then the model is used to generates probabilistic speed profile of the aircraft. The performances of the proposed method are demonstrated with real traffic data in Incheon Flight Information Region(FIR).

• 한국정보통신학회논문지
• /
• 제25권10호
• /
• pp.1452-1455
• /
• 2021

Recently, point clouds are generated by capturing real space in 3D, and it is actively applied and serviced for performances, exhibitions, education, and training. These point cloud data require post-correction work to be used in virtual environments due to errors caused by the capture environment with sensors and cameras. In this paper, we propose an enhancement technique for 3D point cloud data by applying generative adversarial network(GAN). Thus, we performed an approach to regenerate point clouds as an input of GAN. Through our method presented in this paper, point clouds with a lot of noise is configured in the same shape as the real object and environment, enabling precise interaction with the reconstructed content.