• 사물인터넷융복합논문지
• /
• 제7권4호
• /
• pp.29-34
• /
• 2021

실 환경에서 로봇에 강화학습을 적용하기 위해서는 수많은 반복 학습이 필요하므로 가상 환경에서의 시뮬레이션을 사용할 수밖에 없다. 또한 실제 사용하는 로봇이 저사양의 하드웨어를 가지고 있는 경우 계산량이 많은 학습 알고리즘을 적용하는 것은 어려운 일이다. 본 연구에서는 저사양의 하드웨어를 가지고 있는 모바일 로봇의 장애물 충돌 회피 문제에 강화학습을 적용하기 위하여 가상의 시뮬레이션 환경으로서 Unity에서 제공하는 강화학습 프레임인 ML-Agent를 활용하였다. 강화학습 알고리즘으로서 ML-Agent에서 제공하는 DQN을 사용하였으며, 이를 활용하여 학습한 결과를 실제 로봇에 적용해 본 결과 1분간 충돌 횟수가 2회 이하로 발생하는 결과를 얻을 수 있었다.

• 정보기술과데이타베이스저널
• /
• 제6권2호
• /
• pp.1-18
• /
• 1999

The purpose of this study was to identify the effect of microcomputer networking on user perception of potential threats to security employing user attitudes as a moderating variable. A research model consisting of microcomputer networking as the independent variable, user perception of potential threats to security as the dependent variable, and user attitude toward security control as the moderating variable was developed through literature review. The results of this study provide an empirical evidence of the importance of environmental change(information systems networking) on user perception of potential threats to security. Further-more the result imply that in order to improve security performance through the reinforcement of user perception of threats to security in the organization, user attitudes should be made favorable.

• 한국항공운항학회지
• /
• 제29권4호
• /
• pp.142-152
• /
• 2021

The International Civil Aviation Organization (ICAO) and the World Customs Organization (WCO) emphasize securing supply chain security through mutual cooperation between aviation security and customs by establishing a standardized security system by regulations, procedures and practices of international air cargo. Accordingly, in accordance with the Aviation Security Act, the known consignors system aims to secure cargo security before loading air cargo into the aircraft, while the customs AEO system is a public-private cooperation program that focuses on simplification of customs clearance procedures. These systems basically have the same purpose of effectively identifying high-risk cargo through a risk-based approach in international air cargo transportation and preventing risks in advance, and the content that a common basic standard for cargo security must be established is also similar. Therefore, it is necessary to establish a cooperation system by simplifying problems such as cumbersome and redundant authentication procedures and on-site verification through coordination of security requirements for mutual recognition between the two systems. As a result, it is necessary to establish a process for coordinating security and customs' supply chain security program and maximize the effect of harmonizing supply chain security by strengthening the linkage between known consignors and AEO.

• International Journal of Computer Science & Network Security
• /
• 제24권1호
• /
• pp.226-234
• /
• 2024

The frequent handover problem and playing ping-pong effects in 5G (5th Generation) ultra-dense networking cannot be effectively resolved by the conventional handover decision methods, which rely on the handover thresholds and measurement reports. For instance, millimetre-wave LANs, broadband remote association techniques, and 5G/6G organizations are instances of group of people yet to come frameworks that request greater security, lower idleness, and dependable principles and correspondence limit. One of the critical parts of 5G and 6G innovation is believed to be successful blockage the board. With further developed help quality, it empowers administrator to run many systems administration recreations on a solitary association. To guarantee load adjusting, forestall network cut disappointment, and give substitute cuts in case of blockage or cut frustration, a modern pursuing choices framework to deal with showing up network information is require. Our goal is to balance the strain on BSs while optimizing the value of the information that is transferred from satellites to BSs. Nevertheless, due to their irregular flight characteristic, some satellites frequently cannot establish a connection with Base Stations (BSs), which further complicates the joint satellite-BS connection and channel allocation. SF redistribution techniques based on Deep Reinforcement Learning (DRL) have been devised, taking into account the randomness of the data received by the terminal. In order to predict the best capacity improvements in the wireless instruments of 5G and 6G IoT networks, a hybrid algorithm for deep learning is being used in this study. To control the level of congestion within a 5G/6G network, the suggested approach is put into effect to a training set. With 0.933 accuracy and 0.067 miss rate, the suggested method produced encouraging results.

• 정보보호학회논문지
• /
• 제33권6호
• /
• pp.1055-1065
• /
• 2023

최근 사물 인터넷을 활용한 산업 현장에서 수집되는 빅데이터를 활용해 복잡한 문제들을 해결하기 위하여 심층 강화학습 기술을 적용한 다양한 연구들이 이루어지고 있다. 심층 강화학습은 강화 학습의 시행 착오 알고리즘과 보상의 누적값을 이용해 자체 데이터를 생성하여 학습하고 신경망 구조와 파라미터 결정을 빠르게 탐색한다. 그러나 종래 방법은 학습 데이터의 크기가 커질수록 메모리 사용량과 탐색 시간이 기하급수적으로 높아지며 정확도가 떨어진다. 본 연구에서는 메타 학습을 적용한 연합학습 기반의 심층 강화학습 모델을 활용하여 55.9%만큼 보안성을 개선함으로써 프라이버시 침해 문제를 해결하고, 종래 최적화 기반 메타 학습 모델 대비 5.5% 향상된 97.8%의 분류 정확도를 달성하면서 평균 28.9%의 지연시간을 단축하였다.

• 정보보호학회논문지
• /
• 제34권5호
• /
• pp.1047-1057
• /
• 2024

최근 심층 신경망을 이용한 강화학습 모델들이 자율주행, 스마트 팩토리, 홈 네트워크 등 다양한 첨단 산업 분야에 사용되고 있으나 적대적 공격(adversarial attacks)에 취약하다는 것이 밝혀졌다. 본 논문에서는 강화학습 기반의 딥러닝 모델인 DQN과 PPO를 자율주행 가상환경 HighwayEnv에 적용하여 FGSM(Fast Gradient Sign Method), BIM(Basic Iterative Method), PGD(Projected Gradient Descent) 그리고 CW(Carlini and Wagner)을 이용하여 적대적 공격을 수행하였다. 적대적 공격에 대응하기 위해 양방향 필터(bilateral filter) 알고리즘을 사용하여 적대적 이미지의 잡음을 제거함으로써 강화학습 기반의 딥러닝 모델들이 정상적으로 작동할 수 있는 방법을 제안하였다. 그리고 HighwayEnv 환경에서 에피소드 수행 길이(episode during)의 평균과 에이전트가 획득한 보상(episode reward)의 평균을 성능평가 지표로 사용하여 공격의 성능을 평가하였다. 실험 결과 양방향 필터를 통해 적대적 이미지의 잡음을 제거한 결과, 적대적 공격이 수행되기 이전의 성능을 유지할 수 있음을 보였다.

• Earthquakes and Structures
• /
• 제11권5호
• /
• pp.823-840
• /
• 2016

The plastic hinge lengths of beams and columns are a critical demand parameter in the nonlinear analysis of structures using the finite element method. The numerical model of a plastic hinge plays an important role in evaluating the response and damage of a structure to earthquakes or other loads causing the formation of plastic hinges. Previous research demonstrates that the plastic hinge length of reinforced concrete (RC) columns is closely related to section size, reinforcement ratio, reinforcement strength, concrete strength, axial compression ratio, and so on. However, because of the limitations of testing facilities, there is a lack of experimental data on columns with large section sizes and high axial compression ratios. In this work, we conducted a series of quasi-static tests for columns with large section sizes (up to 700 mm) and high axial compression ratios (up to 0.6) to explore the propagation of plastic hinge length during the whole loading process. The experimental results show that besides these parameters mentioned in previous work, the plastic hinge of RC columns is also affected by loading amplitude and size effect. Therefore, an approach toward considering the effect of these two parameters is discussed in this work.

• International journal of advanced smart convergence
• /
• 제13권2호
• /
• pp.16-24
• /
• 2024

With an increase in the relevance of next-generation integrated networking environments, the need to effectively utilize advanced networking techniques also increases. Specifically, integrating Software-Defined Networking (SDN) with Multi-access Edge Computing (MEC) is critical for enhancing network flexibility and addressing challenges such as security vulnerabilities and complex network management. SDN enhances operational flexibility by separating the control and data planes, introducing management complexities. This paper proposes a reinforcement learning-based network path optimization strategy within SDN environments to maximize performance, minimize latency, and optimize resource usage in MEC settings. The proposed Enhanced Proximal Policy Optimization (PPO)-based scheme effectively selects optimal routing paths in dynamic conditions, reducing average delay times to about 60 ms and lowering energy consumption. As the proposed method outperforms conventional schemes, it poses significant practical applications.

• 한국정보시스템학회지:정보시스템연구
• /
• 제22권4호
• /
• pp.49-69
• /
• 2013

Recently, enterprises have reinforced security control in order to prevent infringement of personal information and abuse of customer information by insiders. However, the reinforcement of security control by enterprises makes it difficult for internal users to perform business by using a business information system. There is, therefore, a need for research on various fields, which makes it possible to establish an appropriate security control policy while minimizing an impact on business. The present research verifies and analyzes an impact on difficulty in business of internal users using customer information, which is caused by security control performed by display restriction on customer information identifiers. The present research is intended to academically develop a technique for statistically analyzing an impact degree and a causal relationship between security control and an impact on business, which is a dichotomous variable, and to practically contribute to the establishment of an efficient security policy in consideration of an impact on business when an enterprise applies security control. A research target was internal business information systems of domestic securities enterprises, data was collected by questionnaire, and verification/analysis was performed by logistic regression analysis.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2020년도 추계학술발표대회
• /
• pp.800-803
• /
• 2020

실 환경 로봇에 강화학습을 적용하기 위해서는 가상 환경 시뮬레이션이 필요하다. 그러나 가상 환경을 구축하는 플랫폼은 모두 다르고, 학습 알고리즘의 구현에 따른 성능 편차가 크다는 문제점이 있다. 또한 학습을 적용하고자 하는 대상이 실세계의 하드웨어 사양이 낮은 스마트 로봇인 경우, 계산량이 많은 학습 알고리즘을 적용하기는 쉽지 않다. 본 연구는 해당 문제를 해결하기 위해 Unity3D에서 제공하는 강화학습 프레임인 ML-Agents 모듈을 사용하여 실 환경의 저사양 스마트 로봇에 장애물을 회피하고 탐색하는 모델의 강화학습을 적용해본다. 본 연구의 유의점은 가상 환경과 실 환경의 유사함과 일정량의 노이즈 발생 처리이다. 로봇의 간단한 행동은 원만하게 학습 및 적용가능함을 확인할 수 있었다.