• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2009년도 추계학술대회
• /
• pp.165-172
• /
• 2009

Integrated management model (SNMP/SMI) for lubiquitous egacy remote communication network or service make possible combination of various architecture. However, legacy management system cannot be applied some problems such as inefficient, complexly, implement and large network by reason of integration of voice and data, wired and wireless, and service area between service provider. For improve this, supplied JMX(Java Management eXtensions) on network management technology from SUN. JMX is integrated architecture for existing network management and monitoring. In this paper, we design and implement for integrated network management through multi-protocol agent using JMX.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제3권2호
• /
• pp.215-221
• /
• 2003

Generally, we want to be searched the newest as well as some appropriate personalized information from the internet resources. However, it is a complex and repeated procedure to search some appropriate information. Moreover, because the user's interests are changed as time goes, the real time modeling of a user's interests should be necessary. In this paper, I propose PREA system that can search and filter documents that users are interested from the World Wide Web. And then it constructs the user's interest model by a modified spreading neural network. Based on this network, PREA can easily produce some queries to search web documents, and it ranks them. The conventional spreading neural network does not have a visualization function, so that the users could not know how to be configured his or her interest model by the network. To solve this problem, PREA gives a visualization function being shown how to be made his interest user model to many users.

• 정보처리학회논문지D
• /
• 제10D권2호
• /
• pp.327-336
• /
• 2003

최근 인터넷의 급속한 성장과 초고속 통신망의 구축으로 인하여 다양한 멀티미디어 서비스들이 제공되고 있다. 그러나 현재 대부분의 멀티미디어 서비스들은 클라이언트/서버 모델을 기반으로 구축되어 있기 때문에, 중앙 서버로의 과도한 부하가 집중되어 전체적인 네트워크 속도 저하를 발생시키는 문제점을 가지고 있다. 본 논문에서는 이러한 문제점을 해결하기 위해 순수 P2P 환경으로 구축된 멀티미디어 서비스 환경에서의 자원 검색 기법을 제안한다. 제안 기법은 자율성과 이동성을 지닌 이동 에이전트를 기반으로 자원의 검색을 수행하여, 기존의 순수 P2P 환경에서의 검색 기법에서 네트워크의 불안정시 검색 결과가 유실되는 문제점을 해결한다. 제안 기법은 이동 에이전트를 사용하기 때문에 이 기종의 시스템간 서비스를 제공할 수 있는 장점을 가지고 있고, 동일 자원과 최근 요청 자원에 대한 위치 정보를 유지하므로 기존 순수 P2P 환경에서의 검색 속도보다 빠른 응답 속도를 가지는 장점을 가진다.

• 한국정보처리학회논문지
• /
• 제7권8호
• /
• pp.2505-2513
• /
• 2000

본 논문은 CORBA/SNMP 게이트웨이의 설계 및 구현에 대해 기술한다. 게이트웨이는 기존의 망관리 시스템들을 CORBA를 이용하여 통합하는데 이용된다. 본 논문의 통합 망관리 시스템은 웹과 CORBA 기술을 이용하여 구현된다. 웹은 분산 응용프로그램들에 플랫폼에 독립적이고 사용하기 쉬운 사용자 인터페이스를 제공하고, CORBA는 서로 다른 망관리 모델들을 효과적으로 통합하기 위해 사용된다. 기존의 피관리 객체들을 그대로 수용하기 위해, 제안된 통합 망관리 시스템은 서로 다른 망관리 모델 사이에 변환 게이트웨이를 사용한다. 통합 망관리 서버는 망관리 연산을 위해 기능이 확장된 웹 서버와 변환 게이트웨이들로 구성되는데, 본 논문에서는 CORBA/SNMP 게이트웨이의 설계 및 구현에 대해 기술한다. CORBA/SNMP 게이트웨이는 CORBA와 SNMP관리 모델 사이의 관리정보 및 관리연산 변환을 위한 정적, 동적 변환 기능을 수행한다. CORBA/SNMP 게이트웨이는 SNMP MIB에 대한 CORBA뷰를 제공하여, CORBA 관리자들로 하여금 SNMP에이전트들을 CORBA 연산들을 통해 접근할 수 있도록 하여준다. 또한 CORBA/SNMP게이트웨이는 SNMP 에이전트에서 발생한 통지(trap)를 받아, 그 통지를 받기를 원하는 CORBA 관리자들에 전달하는 역할을 수행한다.

• 스마트미디어저널
• /
• 제6권3호
• /
• pp.41-48
• /
• 2017

Event detection using social media has been widespread since social network services have been an active communication channel for connecting with others, diffusing news message. Especially, the real-time characteristic of social media has created the opportunity for supporting for real-time applications/systems. Social network such as Twitter is the potential data source to explore useful information by mining messages posted by the user community. This paper proposed a novel system for temporal event detection by analyzing social data. As a result, this information can be used by first responders, decision makers, or news agents to gain insight of the situation. The proposed approach takes advantages of deep learning methods that play core techniques on the main tasks including informative data identifying from a noisy environment and temporal event detection. The former is the responsibility of Convolutional Neural Network model trained from labeled Twitter data. The latter is for event detection supported by Recurrent Neural Network module. We demonstrated our approach and experimental results on the case study of earthquake situations. Our system is more adaptive than other systems used traditional methods since deep learning enables to extract the features of data without spending lots of time constructing feature by hand. This benefit makes our approach adaptive to extend to a new context of practice. Moreover, the proposed system promised to respond to acceptable delay within several minutes that will helpful mean for supporting news channel agents or belief plan in case of disaster events.

• 한국관광식음료학회지:관광식음료경영연구
• /
• 제9권
• /
• pp.163-185
• /
• 1998

It is expected that marketing environment of the hotel industry will change much this year. Hotels should make strategic marketing activities to cope with the rapid change of the environment positively. With the case study of marketing activities for American market of "L" Hotel, a deluxe hotel in Seoul, this study is to present the ways of improving marketing activities of a tourist hotel. U.S.A market has been emerging as the most important market in deluxe hotels with strong value of U.S. dollar currency. To get more Ameriean staying guests. hotels had better make effortis in American market as follow. First, hotels should select corporate market as main target market in U.S.A market. Second, hotels should make preferred corporate rate contracts with corporate travel departments of corporate accounts as their house agents Third, hotels should recognize Global Distribution System as major eservation network in U.S.A Fourth, hotels should advertise effectively in G.D.S in order that agents may reserve the hotel with its visual information. Fifth, hotels had better make the most use of three branch offices of K.N.T.O and sale offices of their affiliated reservation system to get useful information on corporates and travel agents.el agents.

• 정보보호학회논문지
• /
• 제13권4호
• /
• pp.3-11
• /
• 2003

네트워크 및 호스트의 자원을 낭비하는 DOS(Denial of Service) 및 여러 형태의 연결형/비연결형 공격은 전체 네트워크의 성능을 감소시키므로 공격 호스트를 검출하여 제거하는 일은 매우 중요한 요소이다. 공격 호스트를 검출하기 위한 효율적인 방법 중의 하나가 역추적시스템이나, 지금까지 구현된 역추적 시스템은 라우터의 동작 또는 로그 데이터 저장 및 분석에 따라 오버헤드를 야기 시키는 단점이 있다. 그러므로 본 논문에서는 라우터 및 관리자의 동작을 요구하지 않으며, 많은 양의 로그 데이터를 필요로 하지 않는 역추적 시스템을 제안하고 구현하였다. 구현된 시스템은 역추적 서버와 역추적 에이전트로 구성된다. 서버에서 스니핑과 스푸핑 기법을 이용하여 특정 패킷을 전송하면 각 네트워크에 존재하는 에이전트에서 그 패킷을 검출함으로서 근원지 호스트까지의 연결 경로 정보를 획득하여 역추적 서버로 하여금 공격 호스트를 검출할 수 있도록 한다.

• 로봇학회논문지
• /
• 제18권4호
• /
• pp.436-443
• /
• 2023

With the advancement of robot intelligence, the concept of man and unmanned teaming (MUM-T) has garnered considerable attention in military research. In this paper, we present a transformer-based architecture for predicting the health status of agents, with the help of multi-head attention mechanism to effectively capture the dynamic interaction between friendly and enemy forces. To this end, we first introduce a framework for generating a dataset of battlefield situations. These situations are simulated on a virtual simulator, allowing for a wide range of scenarios without any restrictions on the number of agents, their missions, or their actions. Then, we define the crucial elements for identifying the battlefield, with a specific emphasis on agents' status. The battlefield data is fed into the transformer architecture, with classification headers on top of the transformer encoding layers to categorize health status of agent. We conduct ablation tests to assess the significance of various factors in determining agents' health status in battlefield scenarios. We conduct 3-Fold corss validation and the experimental results demonstrate that our model achieves a prediction accuracy of over 98%. In addition, the performance of our model are compared with that of other models such as convolutional neural network (CNN) and multi layer perceptron (MLP), and the results establish the superiority of our model.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.49.2-49
• /
• 2002

This paper describes the configuration of a multi-agent system that can recognize human intentions. This system constructs ontologies of human intentions and enables knowledge acquisition and sharing between intelligent agents operating in different environments. This is achieved by using a bi-directional associative memory network. The process of intention recognition is based on fuzzy association inferences. This paper shows the process of information sharing by using ontologies. The purpose of this research is to create human-centered systems that can provide a natural interface in their interaction with people.

• 로봇학회논문지
• /
• 제14권3호
• /
• pp.157-162
• /
• 2019

The video game Tetris is one of most popular game and it is well known that its game rule can be modelled as MDP (Markov Decision Process). This paper presents a DQN (Deep Q-Network) based game agent for Tetris game. To this end, the state is defined as the captured image of the Tetris game board and the reward is designed as a function of cleared lines by the game agent. The action is defined as left, right, rotate, drop, and their finite number of combinations. In addition to this, PER (Prioritized Experience Replay) is employed in order to enhance learning performance. To train the network more than 500000 episodes are used. The game agent employs the trained network to make a decision. The performance of the developed algorithm is validated via not only simulation but also real Tetris robot agent which is made of a camera, two Arduinos, 4 servo motors, and artificial fingers by 3D printing.