• Journal of Internet Computing and Services
• /
• v.9 no.6
• /
• pp.165-177
• /
• 2008

An important issue in Multiagent reinforcement learning is how an agent should learn its optimal policy in a dynamic environment where there exist other agents able to influence its own performance. Most previous works for Multiagent reinforcement learning tend to apply single-agent reinforcement learning techniques without any extensions or require some unrealistic assumptions even though they use explicit models of other agents. In this paper, a Naive Bayesian based policy model of the opponent agent is introduced and then the Multiagent reinforcement learning method using this model is explained. Unlike previous works, the proposed Multiagent reinforcement learning method utilizes the Naive Bayesian based policy model, not the Q function model of the opponent agent. Moreover, this learning method can improve learning efficiency by using a simpler one than other richer but time-consuming policy models such as Finite State Machines(FSM) and Markov chains. In this paper, the Cat and Mouse game is introduced as an adversarial Multiagent environment. And then effectiveness of the proposed Naive Bayesian based policy model is analyzed through experiments using this game as test-bed.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.603-606
• /
• 2023

인공지능 (AI) 서비스는 현대 사회에서 중요한 역할을 맡고 있다. 그러나 이러한 서비스는 보안과 관련된 문제들을 가지고 있다. 본 논문은 AI 서비스의 보안과 관련된 문제와 해결책을 조사하고자 한다. AI 서비스의 개요와 대표적인 상용 서비스를 간략히 소개 후, AI 서비스에서 발생할 수 있는 보안상의 문제와 Chat GPT를 중심으로 한 보안 문제에 대해 다루고자 한다. 또한, 향후 AI보안 서비스 연구 분야와 적재적 기계학습 연구에 대한 전망을 살펴볼 예정이다. 이를 통해 안전하고 신뢰성 있는 AI 서비스를 제공하는데 기여하고자 한다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.2
• /
• pp.291-298
• /
• 2022

A generative adversarial network (GAN) is a network in which two internal neural networks (generative network and discriminant network) learn while competing with each other. The generator creates an image close to reality, and the delimiter is programmed to better discriminate the image of the constructor. This technology is being used in various ways to create, transform, and restore the entire image X into another image Y. This paper describes a method that can be forged into another object naturally, after extracting only a partial image from the original image. First, a new image is created through the previously trained DCGAN model, after extracting only a partial image from the original image. The original image goes through a process of naturally combining with, after re-styling it to match the texture and size of the original image using the overall style transfer technique. Through this study, the user can naturally add/transform the desired object image to a specific part of the original image, so it can be used as another field of application for creating fake images.

• Journal of Broadcast Engineering
• /
• v.25 no.1
• /
• pp.1-12
• /
• 2020

In the medical field, numerical imbalance of data due to differences in disease prevalence is a common problem. It reduces the performance of a artificial intelligence network, leading to difficulties in learning a network with good performance. Recently, generative adversarial network (GAN) technology has been introduced as a way to address this problem, and its ability has been demonstrated by successful applications in various fields. However, it is still difficult to achieve good results in solving problems with performance degraded by numerical imbalances because the image resolution of the previous studies is not yet good enough and the structure in the image is modeled locally. In this paper, we propose a multi-scale conditional generative adversarial network based on attention mechanism, which can produce high resolution images to solve the numerical imbalance problem of chest X-ray image data. The network was able to produce images for various diseases by controlling condition variables with only one network. It's efficient and effective in that the network don't need to be learned independently for all disease classes and solves the problem of long distance dependency in image generation with self-attention mechanism.

• The Journal of Korean Association of Computer Education
• /
• v.10 no.2
• /
• pp.77-87
• /
• 2007

The purpose of the study was to investigate the effects of social network centrality variables on students' performance in blended learning environment in a higher educational institution. Using data from 36-student course on Learning Theories and Their Implications on Instructional Design Practices, the researcher empirically tested how social network centrality variables - such as friendship network centrality, advice network centrality, and adversary network centrality - are correlated with academic achievement measures. Results indicate, as hypothesized, the friendship and advice centrality positively correlate with, whereas the adversary centrality being negatively correlate with application performance measures and test scores. The size and quality of posted online discussions are positively and strongly correlated with the advice network centrality.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.4
• /
• pp.194-199
• /
• 2022

Preprocessing for high-quality data is required for high accuracy and usability in various and complex image data-based industries. However, when a contaminated hostile example that combines noise with existing image or video data is introduced, which can pose a great risk to the company, it is necessary to restore the previous damage to ensure the company's reliability, security, and complete results. As a countermeasure for this, restoration was previously performed using Defense-GAN, but there were disadvantages such as long learning time and low quality of the restoration. In order to improve this, this paper proposes a method using adversarial examples created through FGSM according to image segmentation in addition to using the VQ-VAE model. First, the generated examples are classified as a general classifier. Next, the unsegmented data is put into the pre-trained VQ-VAE model, restored, and then classified with a classifier. Finally, the data divided into quadrants is put into the 4-split-VQ-VAE model, the reconstructed fragments are combined, and then put into the classifier. Finally, after comparing the restored results and accuracy, the performance is analyzed according to the order of combining the two models according to whether or not they are split.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.370-370
• /
• 2021

태풍으로 인한 피해를 줄이기 위해 경로, 강도 및 폭풍해일의 사전 예측은 매우 중요하다. 이중, 태풍의 경로와는 달리 강도 및 폭풍해일의 예측에 있어서 바람장은 수치 모델의 초기 입력값으로 요구되기 때문에 정확한 바람장 정보는 필수적이다. 대기 바람장 예측 방법은 크게 해석적 모델링, 라디오존데 측정과 위성 사진을 통한 산출로 구분할 수 있다. Holland의 해석적 모델링은 비교적 적은 입력값이 필요하지만 정확도가 낮고, 라디오존데 측정은 정확도가 높지만 점 측정에 가깝기 때문에 이차원 바람장을 산출하기에 한계가 있다. 위성 사진을 통한 바람장 산출은 위성기술의 고도화로 관측 채널 수 및 시공간 해상도가 크게 증가하고 있기 때문에 다양한 기법들이 개발되고 있다. 본 연구에서는 생성적 적대 신경망 (Generative Adversarial Network, GAN)을 통해 일련의 연속된 과거 적외 채널 위성 사진 흐름의 패턴을 학습시켜 미래 위성 사진을 예측하고, 예측된 연속적인 위성 사진들의 교차상관 (cross-correlation)을 통해 바람장을 산출하였다. GAN을 적용함에 있어 2011년부터 2019년까지 한반도 근방에 접근했던 태풍 중에 4등급 이상인 68개의 태풍의 한 시간 간격으로 촬영된 총 15,683개의 위성 사진을 학습시켜 생성된 이미지들은 실측 위성 사진들과 매우 유사한 것으로 나타났다. 또한, 생성된 이미지들의 교차상관으로 얻어진 바람장 벡터들의 풍향, 풍속, 벡터 일관성 및 수치 모델과의 비교를 통해 각각의 벡터들의 품질 계수를 구하고 정확도가 높은 벡터들만 결과에 포함하였다. 마지막으로 국내 6개의 라디오존데 관측점에서의 실측 벡터와의 비교를 통해 본 연구 결과의 실효성을 검증하였다. 본 연구에서 확장하여, 이와 같이 AI 기법과 이미지 교차상관 기법을 사용하여 얻어진 바람장으로부터 태풍 강도예측에 필요한 요소인 태풍의 눈의 위치, 최고 속도와 태풍 반경을 직접적으로 산출할 수 있고. 이러한 위성 사진을 기반으로 한 바람장은 단순화된 해석적 바람장을 대체하여 폭풍 해일 모델링의 예측 성능 개선에 기여할 것으로 보여진다.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.404-408
• /
• 2019

비지도 학습 모델인 GAN은 학습 데이터 구축이 어려운 여러 분야에 활용되고 있으며, 알려진 문제점들을 보완하기 위해 다양한 모델 결합 및 변형으로 발전하고 있다. 하지만 문장을 생성하는 GAN은 풀어야 할 문제가 많다. 그중에서도 문제가 되는 것은 완성도가 높은 문장을 생성하는데 어려움이 있다는 것이다. 본 논문에서는 단어 그래프를 구성하여 GAN의 학습에 도움을 주며 완성도가 높은 문장을 생성하는 방법을 제안한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.6
• /
• pp.700-705
• /
• 2020

Generative adversarial networks are methods of generating images by opposing two neural networks. When generating the image, randomly generated noise is rearranged to generate the image. The image generated by this method is not generated well depending on the noise, and it is difficult to generate a proper image when the number of pixels of the image is small In addition, the speed and size of data accumulation in data classification increases, and there are many difficulties in labeling them. In this paper, to solve this problem, we propose a technique to generate noise based on random noise using real data. Since the proposed system generates an image based on the existing image, it is confirmed that it is possible to generate a more natural image, and if it is used for learning, it shows a higher hit rate than the existing method using the hostile neural network respectively.

• Journal of Broadcast Engineering
• /
• v.26 no.5
• /
• pp.608-620
• /
• 2021

Recent deep learning-based face super-resolution (FSR) works showed significant performances by utilizing facial prior knowledge such as facial landmark and dictionary that reflects structural or semantic characteristics of the human face. However, most of these methods require additional processing time and memory. To solve this issue, this paper propose an efficient FSR models using knowledge distillation techniques. The intermediate features of teacher network which contains dictionary information based on major face regions are transferred to the student through adversarial multi-scale features distillation. Experimental results show that the proposed model is superior to other SR methods, and its effectiveness compare to teacher model.