• Journal of Internet Computing and Services
• /
• v.9 no.1
• /
• pp.137-143
• /
• 2008

In ubiquitous environment the multi-agent system is effective for providing intelligent services. In this paper we introduce a new scheduling service model for improving the communication performance in the multi-agent system. It is achieved by assigning a priority to the message according to the weight of formalized ACL message and the number of messages exchanged between the agents. An experiment reveals that the proposed approach allows smaller processing time per message and turnaround time than the scheduling with the existing JADE platform. Moreover, the proposed scheme allows a scalable messaging system.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.15 no.1
• /
• pp.1-11
• /
• 2015

A concept of Deep Level Situation Understanding is proposed to realize human-like natural communication (called casual communication) among multi-agent (e.g., humans and robots/machines), where the deep level situation understanding consists of surface level understanding (such as gesture/posture understanding, facial expression understanding, speech/voice understanding), emotion understanding, intention understanding, and atmosphere understanding by applying customized knowledge of each agent and by taking considerations of thoughtfulness. The proposal aims to reduce burden of humans in humans-robots interaction, so as to realize harmonious communication by excluding unnecessary troubles or misunderstandings among agents, and finally helps to create a peaceful, happy, and prosperous humans-robots society. A simulated experiment is carried out to validate the deep level situation understanding system on a scenario where meeting-room reservation is done between a human employee and a secretary-robot. The proposed deep level situation understanding system aims to be applied in service robot systems for smoothing the communication and avoiding misunderstanding among agents.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.7 no.3
• /
• pp.165-170
• /
• 2007

Recommendation systems provide users with proper services using context information being input from many sensors occasionally under ubiquitous computing environment. But in case there isn't sufficient context information for service recommendation in spite of much context information, there can be problems of resulting in inexact result. In addition, in the quantification step to use context information, there are problems of classifying context information inexactly because of using an absolute classification course. In this paper, we solved the problem of lack of necessary context information for service recommendation by using dynamic profile information. We also improved the problem of absolute classification by using a relative classification of context information in quantification step. As the result of experiments, expectation preference degree was improved by 7.5% as compared with collaborative filtering methods using an absolute quantification method where context information of P2P mobile agent is used.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.10 no.6
• /
• pp.98-107
• /
• 2011

In this paper, we propose the location determination system of an agent mobile device using the information provided by the WLAN(Wireless LAN) infrastructure. This system is configured as a typical ESS(Extended Service Set)-type WLAN structure with real-time location positioning engine and thru AP(Access Point) controller. The positioning engine collects the information of agent devices using SNMP(Small Network Management Protocol) thru AP controller and utilize those information as Cell ID. for LBS(Location Based Service). In the result of a real office environment implementation, the average success rate of inter-AP roaming is measured to 62.5% and the duration time of the device information update within the AP is average of 11 second of time, which means this system is adaptable to the location based service of above average accuracy but somewhat less urgency.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.7C
• /
• pp.696-703
• /
• 2002

In traditional approaches to IN load control, there has been a focus on the protection of individual SCPs. On the other hand, the load control of network level can be achieved by using a mobile agent technology, which is a software element responsible for moving from one system to another and performing their task. In this thesis, we propose an mobile agent mechanism and two mobile agent migration procedures and analyze the performance of the Call Gapping mechanism and the mobile agent mechanism. The mobile agent mechanism showed that the SCP load control rate and attempt the number of attempted call failure were better than those of Call Gapping mechanism. Also, the amount of SS NO.7 traffics was reduced in the case of an overload condition.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.04a
• /
• pp.374-377
• /
• 2005

유비쿼터스 컴퓨팅 환경에서는 사용자 주변의 센서로부터 각종 컨텍스트 정보를 입력받아 사용자를 식별하고 필요한 자원을 분배하는 과정이 중요하다. 하지만 사용자 식별 및 자원 분배 과정에서 특정 사용자에 의해 자원의 독점 현상이 발생되기 때문에 다른 사용자들에게 효과적으로 자원을 분배할 수 없다. 이를 위해 센서와 자원의 공유에 대한 연구가 필요하다. 본 연구에서는 휴대용 모바일 장치에서 사용자의 컨텍스트 인식과 자원의 공유를 위하여 P2P 방식을 적용한 지능형 P2P 모바일 에이전트를 제안한다. 제안하는 구조는 사용자 주변의 센서와 서비스 자원을 공유함으로써 특정 자원에 대한 독점성을 제거하고, 효과적인 사용자 컨텍스트 인식 및 서비스 지원을 목적으로 한다.

• Journal of Internet Computing and Services
• /
• v.23 no.5
• /
• pp.17-23
• /
• 2022

Network slicing is a promising paradigm and significant evolution for adjusting the heterogeneous services based on different requirements by placing dynamic virtual network functions (VNF) forwarding graph (VNFFG) and orchestrating service function chaining (SFC) based on criticalities of Quality of Service (QoS) classes. In system architecture, software-defined networks (SDN), network functions virtualization (NFV), and edge computing are used to provide resourceful data view, configurable virtual resources, and control interfaces for developing the modified deep reinforcement learning agent (MDRL-A). In this paper, task requests, tolerable delays, and required resources are differentiated for input state observations to identify the non-critical/critical classes, since each user equipment can execute different QoS application services. We design intelligent slicing for handing the cross-domain resource with MDRL-A in solving network problems and eliminating resource usage. The agent interacts with controllers and orchestrators to manage the flow rule installation and physical resource allocation in NFV infrastructure (NFVI) with the proposed formulation of completion time and criticality criteria. Simulation is conducted in SDN/NFV environment and capturing the QoS performances between conventional and MDRL-A approaches.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.5
• /
• pp.605-614
• /
• 2005

In this paper, we present the design and implementation of an agent knowledge and QoS tuning methodology to improve the flexibility of agent-based flexible video-conference system. In order to improve the flexibility during video-conferencing, we propose a new T-INTER(Tuning-INTER) architecture of knowledge part in video-conference manager (VCM) agent in which an automatic QoS parameter tuning method is imbedded. The flexible video-conference system structured based on the proposed architecture can cope with the changes in service quality required by users. The VCM agent cooperates with other agents by protocols and executes the automatic QoS parameter tuning task whenever needed. By the tuned parameters, the system is able to flexibly cope with the internal or external changes and the burden of users can be decreased. In the experimental section, it is shown that our proposed system outperforms the existing system.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.5
• /
• pp.567-572
• /
• 2005

Recently, owing to miniaturization of computer and popularization of internet, ubiquitous computing is attracting considerable attention. In ubiquitous environment, user can receive desired information service anywhere, any time. With the advent of ubiquitous age through popularization of internet, it becomes important how to provide user with ubiquitous environment, and what and how to provide to user. In this paper, method to automatically select device most suitable for user in ubiquitous environment is offered. search agents search peripherals, make a list by function, and transmit to serve. Serve learn the transmitted information through intelligent system. If user input information in the form of linguistic according to the list, serve select device suitable for work environment, and compose the system through IP address. This was realize through practical example, experimented and confirmed.

• Journal of Information Technology Services
• /
• v.10 no.1
• /
• pp.177-190
• /
• 2011

Due to the growth of economy and the advancement of IT, the life expectancy has been prolonged and the interests in health have greatly increased. Recently the request for systems that enable measuring the bio-signals of patients in the non medical organizations, such as home, and transmitting them to medical staffs at remote sites for monitoring them. In this paper, we present an agent-based u-health system for patients or suspects with heart diseases. Our system consists of portable devices for measuring bio-signals and agents that perform data collection, data storage, automatic detection of abnormal status in patients, and HL7-based data exchange in a cooperative way. The main features of the system are : the agent-based architecture facilitates the addition of new service modules as well as the modification of existing ones; an intelligent agent is provided which automatically detects situations in which the bio-signals of patients are abnormal; the medical data standard is supported so that the communication with other systems is very easy. To our survey, there have been few previous systems which support all those features in a seamless way.