• Journal of the Semiconductor & Display Technology
• /
• v.22 no.3
• /
• pp.112-118
• /
• 2023

As technology advances, the need for enhanced preparedness against cyber-attacks becomes an increasingly critical problem. Therefore, it is imperative to consider various circumstances and to prepare for cyber-attack strategic technology. This paper proposes a method to solve network security problems by applying reinforcement learning to cyber-security. In general, traditional static cyber-security methods have difficulty effectively responding to modern dynamic attack patterns. To address this, we implement cyber-attack scenarios such as 'Tiny Alpha' and 'Small Alpha' and evaluate the performance of various reinforcement learning methods using Network Attack Simulator, which is a cyber-attack simulation environment based on the gymnasium (formerly Open AI gym) interface. In addition, we experimented with different RL algorithms such as value-based methods (Q-Learning, Deep-Q-Network, and Double Deep-Q-Network) and policy-based methods (Actor-Critic). As a result, we observed that value-based methods with discrete action spaces consistently outperformed policy-based methods with continuous action spaces, demonstrating a performance difference ranging from a minimum of 20.9% to a maximum of 53.2%. This result shows that the scheme not only suggests opportunities for enhancing cybersecurity strategies, but also indicates potential applications in cyber-security education and system validation across a large number of domains such as military, government, and corporate sectors.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.5
• /
• pp.697-703
• /
• 2022

Due to the recent economic downturn caused by Covid-19 and the unstable international situation, many investors are choosing the derivatives market as a means of investment. However, the derivatives market has a greater risk than the stock market, and research on the market of market participants is insufficient. Recently, with the development of artificial intelligence, machine learning has been widely used in the derivatives market. In this paper, reinforcement learning, one of the machine learning techniques, is applied to analyze the scalping technique that trades futures in minutes. The data set consists of 21 attributes using the closing price, moving average line, and Bollinger band indicators of 1 minute and 3 minute data for 6 months by selecting 4 products among futures products traded at trading firm. In the experiment, DNN artificial neural network model and three reinforcement learning algorithms, namely, DQN (Deep Q-Network), A2C (Advantage Actor Critic), and A3C (Asynchronous A2C) were used, and they were trained and verified through learning data set and test data set. For scalping, the agent chooses one of the actions of buying and selling, and the ratio of the portfolio value according to the action result is rewarded. Experiment results show that the energy sector products such as Heating Oil and Crude Oil yield relatively high cumulative returns compared to the index sector products such as Mini Russell 2000 and Hang Seng Index.

• Journal of Preventive Medicine and Public Health
• /
• v.47 no.6
• /
• pp.298-308
• /
• 2014

Objectives: To assess the current public participation in-local health policy and its implications through the analysis of policy networks in health center programs. Methods: We examined the decision-making process in sub-health center installations and the implementation process in metabolic syndrome management program cases in two districts ('gu's) of Seoul. Participants of the policy network were selected by the snowballing method and completed self-administered questionnaires. Actors, the interactions among actors, and the characteristics of the network were analyzed by Netminer. Results: The results showed that the public is not yet actively participating in the local public health policy processes of decision-making and implementation. In the decision-making process, most of the network actors were in the public sector, while the private sector was a minor actor and participated in only a limited number of issues after the major decisions were made. In the implementation process, the program was led by the health center, while other actors participated passively. Conclusions: Public participation in Korean public health policy is not yet well activated. Preliminary discussions with various stakeholders, including civil society, are needed before making important local public health policy decisions. In addition, efforts to include local institutions and residents in the implementation process with the public officials are necessary to improve the situation.

• Journal of Science and Technology Studies
• /
• v.13 no.2
• /
• pp.137-172
• /
• 2013

Globally, awareness about obesity is increasing rapidly. In Korea, obesity is recognized as a disease and steps are being taken to treat it. From the health governance point of view, such standardized measures amplify the risk of obesity and thus play an important part in the prevention of the disease. In this context, various obesity treatments act as a medium for the problem-solving process. In recent years, obesity surgery has been viewed as a rational solution to the problem of obesity. In the context of standardization of treatment, Callon's "Process of Translation" in STS theories highlights the importance of the central actor (Obligatory Passage Point; OPP). However, in the case of obesity, it is difficult to identify a single OPP to project different perspectives of an actor's needs. "Lapband surgery" often acts as a "boundary object" in this context. This article assesses this absence of central actors in the process of problem solving through a case study of adoption of Lapband surgery in Korea. Further, we attempt to suggest an analytical framework with a boundary object and multiple translation concepts to aid solving the problem of obesity.

• International Commerce and Information Review
• /
• v.14 no.1
• /
• pp.369-390
• /
• 2012

According to diffusion of social network, social commerce based this platform have been rapidly growing with usage of multiple smart devices. In this paper, we review several definitions & classifications of social commerce, and then suggest our definition. Above all, we suggest social commerce model analysis framework in perspective of business model based on revised Timmers's definition. With this framework, we analyzes impact of social commerce on e-commerce in perspective of value, actor, and revenue models. Through this analysis, we can find social commerce impact and change existing e-commerce. Finally, we suggest implications of social commerce, future directions of social commerce, further research issues. Through this research, we expect that actors related to e-commerce have the strategic implications.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.23 no.4
• /
• pp.399-406
• /
• 2020

In this paper, we propose a time-varying proportional navigation guidance law that determines the proportional navigation gain in real-time according to the operating situation. When intercepting a target, an unidentified evasion strategy causes a loss of optimality. To compensate for this problem, proper proportional navigation gain is derived at every time step by solving an optimal control problem with the inferred evader's strategy. Recently, deep reinforcement learning algorithms are introduced to deal with complex optimal control problem efficiently. We adapt the actor-critic method to build a proportional navigation gain network and the network is trained by the Proximal Policy Optimization(PPO) algorithm to learn an evasion strategy of the target. Numerical experiments show the effectiveness and optimality of the proposed method.

• Journal of Korean Association for Spatial Structures
• /
• v.21 no.2
• /
• pp.41-48
• /
• 2021

A smart tuned mass damper (TMD) is widely studied for seismic response reduction of various structures. Control algorithm is the most important factor for control performance of a smart TMD. This study used a Deep Deterministic Policy Gradient (DDPG) among reinforcement learning techniques to develop a control algorithm for a smart TMD. A magnetorheological (MR) damper was used to make the smart TMD. A single mass model with the smart TMD was employed to make a reinforcement learning environment. Time history analysis simulations of the example structure subject to artificial seismic load were performed in the reinforcement learning process. Critic of policy network and actor of value network for DDPG agent were constructed. The action of DDPG agent was selected as the command voltage sent to the MR damper. Reward for the DDPG action was calculated by using displacement and velocity responses of the main mass. Groundhook control algorithm was used as a comparative control algorithm. After 10,000 episode training of the DDPG agent model with proper hyper-parameters, the semi-active control algorithm for control of seismic responses of the example structure with the smart TMD was developed. The simulation results presented that the developed DDPG model can provide effective control algorithms for smart TMD for reduction of seismic responses.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.15-22
• /
• 2022

The Tactile Internet technology is considered as the evolution of the internet of things. It will enable real time applications in all fields like remote surgery. It requires extra low latency which must not exceed 1ms, high availability, reliability and strong security system. Since it appearance in 2014, tremendous efforts have been made to ensure authentication between sensors, actuators and servers to secure many applications such as remote surgery. This human to machine relationship is very critical due to its dependence of the human live, the communication between the surgeon who performs the remote surgery and the robot arms, as a tactile internet actor, should be fully and end to end protected during the surgery. Thus, a secure mutual user authentication framework has to be implemented in order to ensure security without influencing latency. The existing methods of authentication require server to stock and exchange data between the tactile internet entities, which does not only make the proposed systems vulnerables to the SPOF (Single Point of Failure), but also impact negatively on the latency time. To address these issues, we propose a lightweight authentication protocol for remote surgery in a Tactile Internet environment, which is composed of a decentralized blockchain and physically unclonable functions. Finally, performances evaluation illustrate that our proposed solution ensures security, latency and reliability.

• Journal of Drive and Control
• /
• v.19 no.1
• /
• pp.51-61
• /
• 2022

This paper presents a model-free system based on a framework of a backstepping sliding mode control (BSMC) with a radial basis function neural network (RBFNN) and adaptive mechanism for electro-hydraulic systems (EHSs). First, an EHS mathematical model was dedicatedly derived to understand the system behavior. Based on the system structure, BSMC was employed to satisfy the output performance. Due to the highly nonlinear characteristics and the presence of parametric uncertainties, a model-free approximator based on an RBFNN was developed to compensate for the EHS dynamics, thus addressing the difficulty in the requirement of system information. Adaptive laws based on the actor-critic neural network (ACNN) were implemented to suppress the existing error in the approximation and satisfy system qualification. The stability of the closed-loop system was theoretically proven by the Lyapunov function. To evaluate the effectiveness of the proposed algorithm, proportional-integrated-derivative (PID) and improved PID with ACNN (ACPID), which are considered two complete model-free methods, and adaptive backstepping sliding mode control, considered an ideal model-based method with the same adaptive laws, were used as two benchmark control strategies in a comparative simulation. The simulated results validated the superiority of the proposed algorithm in achieving nearly the same performance as the ideal adaptive BSMC.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10c
• /
• pp.475-477
• /
• 2002

네트워크 상의 사이버 공격에 대한 시뮬레이터 개발을 위해서는 다양한 네트워크 구성요소의 특성을 시뮬레이션 모델에 반영할 수 있어야 하며, 다양한 사이버 공격과 이를 방어하기 위한 보안대책들의 특성을 반영할 수 있어야 한다. 본 논문에서는 네트워크 상의 사이버 공격과 방어를 시뮬레이션 하기 위하여 다양한 공격과 방어기법을 표현하기 위해 공격 및 방어 DB를 설계하고, 시뮬레이션 수행시 행동을 표현할 actor를 설계하고, 이를 이용한 공격 및 방어 시나리오 DB를 설계하고, 이들을 이용한 시나리오 생성기를 설계한다. 본 논문에서 제시한 방법을 이용하여 다양한 네트워크 구조와 보안대책을 가진 네트워크에 대한 사이버 공격 및 방어 시뮬레이션이 가능하며, 이를 통하여 네트워크에 적용된 보안대책의 적절성 파악 및 사이버 공격으로 인한 네트워크의 피해 및 피해영향 파악 등으로 확장이 가능하며, 사이버 공격에 대한 적절한 보안대책을 수립하는데 도움을 줄 수 있다.