• International Journal of Internet, Broadcasting and Communication
• /
• 제11권4호
• /
• pp.37-42
• /
• 2019

In this paper, we explore the details of three classic data augmentation methods and two generative model based oversampling methods. The three classic data augmentation methods are random sampling (RANDOM), Synthetic Minority Over-sampling Technique (SMOTE), and Adaptive Synthetic Sampling (ADASYN). The two generative model based oversampling methods are Conditional Generative Adversarial Network (CGAN) and Wasserstein Generative Adversarial Network (WGAN). In imbalanced data, the whole instances are divided into majority class and minority class, where majority class occupies most of the instances in the training set and minority class only includes a few instances. Generative models have their own advantages when they are used to generate more plausible samples referring to the distribution of the minority class. We also adopt CGAN to compare the data augmentation performance with other methods. The experimental results show that WGAN-based oversampling technique is more stable than other approaches (RANDOM, SMOTE, ADASYN and CGAN) even with the very limited training datasets. However, when the imbalanced ratio is too small, generative model based approaches cannot achieve satisfying performance than the conventional data augmentation techniques. These results suggest us one of future research directions.

• 한국IT서비스학회지
• /
• 제22권6호
• /
• pp.17-35
• /
• 2023

This study investigated how helpful the use of generative AI such as ChatGPT is in conducting engaged learning at each university. In this study, based on the experiences of users using generative AI technology, we analyzed the relationship between usability and ease in consideration of the characteristics of learners, and examined whether there is an intention to continue using generative AI technology in the future. In this study, in order to verify the factors affecting the intention to use ChatGPT technology in order to solve the problems given in the participating classes, we examined previous papers based on the Technology Acceptance Model (TAM) and the Information System Success Model (IS), extracted the factors affecting the intention of ChatGPT technology, and presented the research model and hypothesis. Empirical research on the continuous use of generative AI in participatory learning using ChatGPT was conducted to determine whether it is suitable for long-term and continuous use in the educational environment, and whether it is sustainable by examining the intention of learners to continue using it. First, user satisfaction was positively related to the intention to continue using generative AI technology. Second, if the user experience has a great influence on the intention to continue using ChatGPT technology, and users gain experiences such as usefulness, interest, and effective response in the process of using the technology, the evaluation of the technology is positively formed and the intention to continue using it is high. Third, the ease of use of the technology also showed that it was intended to be used continuously when an environment was provided in which users could easily and conveniently utilize generative AI technology.

• International Journal of Advanced Culture Technology
• /
• 제11권3호
• /
• pp.225-230
• /
• 2023

With the development of AI technology, there is a growing discussion about Text-to-Image Generative AI. We presented a Generative AI video production method and delineated a methodology for the production of personalized AI-generated videos with the objective of broadening the landscape of the video domain. And we meticulously examined the procedural steps involved in AI-driven video production and directly implemented a video creation approach utilizing the VQGAN-CLIP model. The outcomes produced by the VQGAN-CLIP model exhibited a relatively moderate resolution and frame rate, and predominantly manifested as abstract images. Such characteristics indicated potential applicability in OTT-based video content or the realm of visual arts. It is anticipated that AI-driven video production techniques will see heightened utilization in forthcoming endeavors.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 1998년도 가을 학술발표논문집 Vol.25 No.2 (2)
• /
• pp.327-329
• /
• 1998

Up-Propagation is an algorithm for inverting and learning neural network generative models. Sensory input is processed by inverting a model that generates patterns from hidden variables using top-down connections. The inversion process is iterative, utilizing a negative feedback loop that depends on an error signal propagated by bottom-up connections. The error signal is also used to learn the generative model from examples. the algorithm is benchmarked against principal component analysis in experiments on images of handwritten digits.

• 방송공학회논문지
• /
• 제23권5호
• /
• pp.614-621
• /
• 2018

본 논문에서는 generative adversarial network (GAN)을 이용한 비감독 학습을 통해 깊이 카메라로 깊이 영상을 취득할 때 발생한 손실된 부분을 복원하는 기법을 제안한다. 제안하는 기법은 3D morphable model convolutional neural network (3DMM CNN)와 large-scale CelebFaces Attribute (CelebA) 데이터 셋 그리고 FaceWarehouse 데이터 셋을 이용하여 학습용 얼굴 깊이 영상을 생성하고 deep convolutional GAN (DCGAN)의 생성자(generator)와 Wasserstein distance를 손실함수로 적용한 구별자(discriminator)를 미니맥스 게임기법을 통해 학습시킨다. 이후 학습된 생성자와 손실 부분을 복원해주기 위한 새로운 손실함수를 이용하여 또 다른 학습을 통해 최종적으로 깊이 카메라로 취득된 얼굴 깊이 영상의 손실 부분을 복원한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권12호
• /
• pp.4625-4647
• /
• 2020

The Generative Adversarial Networks, as one of the most creative deep learning models in recent years, has achieved great success in computer vision and natural language processing. It uses the game theory to generate the best sample in generator and discriminator. Recently, many deep learning models have been applied to the security field. Along with the idea of "generative" and "adversarial", researchers are trying to apply Generative Adversarial Networks to the security field. This paper presents the development of Generative Adversarial Networks. We review traditional generation models and typical Generative Adversarial Networks models, analyze the application of their models in natural language processing and computer vision. To emphasize that Generative Adversarial Networks models are feasible to be used in security, we separately review the contributions that their defenses in information security, cyber security and artificial intelligence security. Finally, drawing on the reviewed literature, we provide a broader outlook of this research direction.

• 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).

• 한국융합학회논문지
• /
• 제13권1호
• /
• pp.13-21
• /
• 2022

최근 딥러닝 기반의 자연어처리 연구는 사전 훈련된 언어 모델을 통해 대부분의 자연어처리 분야에서 우수한 성능을 보인다. 특히 오토인코더 (auto-encoder) 기반의 언어 모델은 다양한 한국어 이해 분야에서 뛰어난 성능과 쓰임을 증명하고 있다. 그러나 여전히 디코더 (decoder) 기반의 한국어 생성 모델은 간단한 문장 생성 과제에도 어려움을 겪고 있으며, 생성 모델이 가장 일반적으로 쓰이는 대화 분야에서의 세부 연구와 학습 가능한 데이터가 부족한 상황이다. 따라서 본 논문은 한국어 생성 모델을 위한 멀티턴 대화 데이터를 구축하고 전이 학습을 통해 생성 모델의 대화 능력을 개선하여 성능을 비교 분석한다. 또한, 검색 모델을 통해 외부 지식 정보에서 추천 응답 후보군을 추출하여 모델의 부족한 대화 생성 능력을 보완하는 방법을 제안한다.

• 한국정보전자통신기술학회논문지
• /
• 제16권5호
• /
• pp.279-291
• /
• 2023

최근 몇 년 동안 언어 모델 기반의 생성형 인공지능 기술은 눈에 띄게 발전하고 있다. 특히, 요약, 코드 작성과 같은 다양한 분야에서 활용 가능성이 증가하고 있어 큰 관심을 받고 있다. 이러한 관심의 반영으로, 생성형 인공지능 관련 특허 출원이 급격히 증가하는 추세를 보인다. 이러한 동향을 파악하고 이에 따른 전략을 수립하기 위해 미래 예측이 핵심적이다. 예측을 통해 해당 기술 분야의 미래 동향을 정확히 파악하여 더 효과적인 전략을 수립할 수 있다. 본 논문에서는 언어 모델 기반 생성형 인공지능 발전 방향을 확인하기 위해 현재까지 출원된 특허들을 분석하였다. 특히, 각 국가에서의 연구 및 발명 활동을 깊게 살펴보았으며, 연도별 및 세부 기술별 출원 동향을 중점적으로 분석하였다. 이러한 분석을 통해 핵심 특허들이 포함하고 있는 세부 기술을 이해하고, 향후 생성형 인공지능의 기술 개발 트렌드를 예측해 보고자 하였다.

• ETRI Journal
• /
• 제44권6호
• /
• pp.1004-1019
• /
• 2022

For autonomous driving without high-definition maps, we present a model capable of generating multiple plausible paths from egocentric images for autonomous vehicles. Our generative model comprises two neural networks: feature extraction network (FEN) and path generation network (PGN). The FEN extracts meaningful features from an egocentric image, whereas the PGN generates multiple paths from the features, given a driving intention and speed. To ensure that the paths generated are plausible and consistent with the intention, we introduce an attentive discriminator and train it with the PGN under a generative adversarial network framework. Furthermore, we devise an interaction model between the positions in the paths and the intentions hidden in the positions and design a novel PGN architecture that reflects the interaction model for improving the accuracy and diversity of the generated paths. Finally, we introduce ETRIDriving, a dataset for autonomous driving, in which the recorded sensor data are labeled with discrete high-level driving actions, and demonstrate the state-of-the-art performance of the proposed model on ETRIDriving in terms of accuracy and diversity.