• Communications of the Korean Institute of Information Scientists and Engineers
• /
• v.21 no.7
• /
• pp.5-17
• /
• 2003

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.33-36
• /
• 2007

최근에 인공지능 분야에서는, 국내외적으로 강화학습(reinforcement learning)에 관한 관심이 크게 증폭되고 있다. 강화학습의 최근 경향을 살펴보면, 크게 가치함수를 직접 활용하는 방법(value function-based methods), 제어 전략에 대한 탐색을 활용하는 방법(policy search methods), 그리고 액터-크리틱 방법(actor-critic methods)의 세가지 방향으로 발전하고 있음을 알 수 있다. 본 논문에서는 이중 세 번째 부류인 액터-크리틱 방법 중 NAC(natural actor-critic) 기법의 한 종류인 RLS-NAC(recursive least-squares based natural actor-critic) 알고리즘을 다양한 트레이스 감쇠계수를 사용하여 연속제어입력(real-valued control inputs)으로 제어되는 Kimura의 기는 로봇에 대해 적용해보고, 그 성능을 기존의 SGA(stochastic gradient ascent) 알고리즘을 이용하여 학습한 경우와 비교해보도록 한다.

• The KIPS Transactions:PartD
• /
• v.9D no.4
• /
• pp.639-650
• /
• 2002

We have to carry out systematic, definite requirements analysis for the successful development of software. The UML gives the ways to grasp user or customer requirements and decide the boundary of business systems from the use case modeling. This paper presents how to extract use case diagram from the requirements specification systematically by applying the standardized rules as a part of the study for use case modeling. We modify requirements specification by applying $R_{RS}$ (Rules for Requirements Specification) and extract actor, use case, relationship by applying $R_{A}$(Rules for Actors), $R_{U}$(Rules for Use Cases) and $R_{R}$(Rules for Relationships) to the modified requirements specification separately and then become to make out use case diagram in the end. By applying the rules presented in this paper to the requirements specification for personnel management, we can reduce the existing difficulties of extracting use case diagram based on the narrative descriptions without any standardized rules.rules.

• Journal of Broadcast Engineering
• /
• v.25 no.4
• /
• pp.487-496
• /
• 2020

For the purpose of next generation technology for robot perfomances, a RAoRA (Robot Actor on Robot Arm) structure was proposed using a robot arm joined with a humanoid robot actor. Mechanical analysis, machine design and fabrication were performed for motions combined with the robot arm and the humanoid robot actor. Kinematical analysis for 3D model, spline interpolation of positions, motion control algorithm and control devices were developed for movements of the robot actor. Preliminary visualization, simulation tools and integrated operation of consoles were constructed for the non-professionals to produce intuitive and safe contents. Air walk was applied to test the developed platform. The air walk is a natural walk close to a floor or slow ascension to the air. The RAoRA also executed a performance with 5 minute-running time. Finally, the proposed platform of robot performance presented intensive and live motions which was impossible in conventional robot performances.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06a
• /
• pp.103-104
• /
• 2007

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.395-398
• /
• 2007

최근 인공지능 분야에서는 강화학습(Reinforcement Learning)에 대한 관심이 크게 증폭되고 있으며, 여러 관련 분야에 적용되고 있다. 본 논문에서는 강화학습 기법 중 액터-크리틱 계열에 속하는 RLS-NAC 알고리즘을 활용하여 Kimura의 기는 로봇의 이동을 다룰 때에 중요 파라미터의 결정을 위하여 meta-learning 기법을 활용하는 방안에 고려한다.

• The Journal of the Korea Contents Association
• /
• v.20 no.6
• /
• pp.267-278
• /
• 2020

Although the theater performance industry is a typical cultural content industry, the support at the national level has been poor and the theater workers tend to focus on individual efforts rather than active interaction with the theater environment. Therefore, there is a growing need for effective revitalization of the theater industry, which should be found in improving the quality of interaction between the theater and the theater environment. Therefore, the purpose of this study is to analyze the effects of theater actors (theaters, theater organizations) on the activation of plays by the interaction of politics, business, and technology, the main environment of the plays. For this, social network analysis was performed. As a result of the study, it was found that mediation centrality significantly influenced the visibility of theater actors. This means that the more the theater actors are at the center of information and resource flows to the elements of the theater environment, the more visibility becomes. This shows that the theater must actively acquire technology, create an avant-garde, and endeavor to expand its influence and outreach through active interaction with politics and corporations.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.6
• /
• pp.1449-1454
• /
• 2015

Virtualization lacks capabilities for enabling the application to scale efficiently because of new applications components which are raised to be configured on demand. In this paper, we propose an architecture that affords mobile app based on nomadic smartphone using not only mobile cloud computing-cloudlet architecture but also a dedicated platform that relies on using virtual private mobile networks to provide reliable connectivity through LTE(Long Term Evolution) wireless communication. The design architecture lies with how the cloudlet host discovers service and sends out the cloudlet IP and port while locating the user mobile device. We demonstrate the effectiveness of the proposed architecture by implementing an android application responsible of real time analysis by using a vehicle to applications smartphone interface approach that considers the smartphone to act as a remote users which passes driver inputs and delivers outputs from external applications.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.3
• /
• pp.607-612
• /
• 2015

As the amount of vehicle's diagnostics data increases, the actors in automotive ecosystem will encounter difficulties to perform a real time analysis in order to simulate or to design new services according to the data gathered from the connected cars. In this paper, we have conducted a study of a Big Data solution that expresses the essential deep analytics to process and analyze vast quantities of vehicles on board diagnostics data generated by cars. Hadoop and its ecosystems have been deployed to process a large data and delivered useful outcomes that may be used by actors in automotive ecosystem to deliver new services to car owners. As the Intelligent transport system is involved to guarantee safety, reduce rate of crash and injured in the accident due to speed, addressing big data solution based on vehicle diagnostics data is upcoming to monitor real time outcome from it and making collection of data from several connected cars, facilitating reliable processing and easier storage of data collected.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.4B
• /
• pp.346-353
• /
• 2011

Routing schemes that service applications with various delay times, maintaining the long network life time are required in wireless sensor & actor networks. However, it is known that network lifetime and hop count of trees used in routing methods have the tradeoff between them. In this paper, we propose a Pareto Ant Colony Optimization algorithm to find the Pareto tree set such that it optimizes these both tradeoff objectives. As it enables applications which have different delay times to select appropriate routing trees, not only satisfies the requirements of various multiple applications but also guarantees long network lifetime. We show that the Pareto tree set found by proposed algorithm consists of trees that are closer to the Pareto optimal points in terms of hop count and network lifetime than minimum spanning tree which is a representative routing tree.