• The Journal of Society for e-Business Studies
• /
• v.12 no.4
• /
• pp.99-125
• /
• 2007

Recently, as the development of Ubiquitous Smart Space (USS) such as U-City is proliferating, preparing a development methodology dedicated to USS characteristics has become one of the crucial issues to increase the productivity of the USS projects. However, since the legacy development methodologies such as traditional UML do not consider the critical components of ubiquitous computing space such as context-awareness, service oriented architecture and multi-agent communication, they are not optimized for USS analysis and design. Hence, the purpose of this paper is to propose a USS-sophisticated development methodology. To do so, a hybrid approach, BPR-USS for space reengineering and UML-USS by amending UML with corresponding toolkit based on StarUML has been implemented. To show the feasibility of the approach described in this paper, an illustrative example with an actual USS development project for a multiplex space in Seoul is shown.

• Journal of Korea Game Society
• /
• v.15 no.5
• /
• pp.89-98
• /
• 2015

The artificial intelligence (AI) of Non-Player Companions (NPC), especially opponents, is a key element to adjust the level of games in game design. Smart opponents can make games more challenging as well as allow players for diverse experiences, even in the same game environment. Since game users interact with more than one opponent in most of today's games, collaboration control of opponent characters becomes more important than ever before. In this paper, we introduce a cooperative strategy based on the A* algorithm for enemies' AI in the Pac-Man game. A survey from 17 human testers shows that the levels with our collaborative opponents are more difficult but interesting than those with either the original Pac-Man's personalities or the non-cooperative greedy opponents.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.6
• /
• pp.131-138
• /
• 2008

Mobile Ad hoc NETworks (MANETs) refer to autonomous networks in which wireless data communications are established between multiple nodes in a given coverage area without a base station or centralized administration. Because of node mobility and limited battery life, the network topology may changes frequently. Selecting the most reliable path during route discovery process is important to improve performance in ad hoc networks. In this paper, an enhanced routing protocol based on AODV(Ad hoc On-demand Distance Vector routing) by monitoring variation of receiving signal strength is proposed. New metric function that consists of node mobility and hops of path is used for routing decision. For preventing route failure by node movement during data transmission, a new route maintenance named as LRC (Local Route Change) is presented. If the node movement is detected, the routing agent switches path to its neighbor node in LRC. Simulation results show that the performance of the proposed routing scheme is superior to previous AODY protocol.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.19 no.4
• /
• pp.577-588
• /
• 2017

There are many constraints, both economically and ethically that experimenting human evacuation behavior in situations such as fire. Therefore, the evacuation behavior is simulated based on the existing studies. In recent years, the foundation has been established as computer performance advances, models closer to reality can be studied. In this study, the evacuation time in the subway platform was analyzed from modeling human behavior and smoke propagation in a fire. The evacuation efficiency was also examined by dividing the shape of the subway station platform by the stair position and comparing the evacuation times for each platform. As a result, it was found that the side platform was longer than the island platform by 36.82% more time to evacuation. The shape of the stairs is most advantageous in terms of evacuation form side type platform was 210 seconds and island type platform was 186 seconds, when a fire occurs in the center of the platform. And most favorable in location of evacuation stairs were located at 2/5 point and 4/5 from depending on the step location.

• Journal of KIISE:Information Networking
• /
• v.32 no.1
• /
• pp.100-109
• /
• 2005

A Mobile Ad-Hoc Network (MANET) supports a multi-hop wireless network without any prepared base station (BS). The MANET is capable of building a mobile network automatically without any help from DHCP servers for address allocation or routers to forward or route messages. Many routing protocols have been proposed for the MANET, but these specify the most optimized or shortest path from a source to a destination, and they assume that nodes are pre-configured before communication. To make up for this, address allocation algorithms, such as MANETConf [1] and prophet address allocation algorithm [2], have been proposed. Especially, MANETConf proposes address allocation algorithm with duplication address check. In this paper, we present a dynamic node configuration protocol based on 2-tierd hierarchical network architecture for mobile ad-hoc network, modified from [1]. Especially, it reduces the number of broadcast message exchange between nodes when a new node somes into a network, which lessens network overhead, remarkably. This protocol is based on two-tired structure, and it ensures address allocation with simple duplication address defection mechanism.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.2
• /
• pp.355-364
• /
• 2000

Application sharing for collaborative works make multiple participants to be capable of collaborative developments through sharing development tools and applications which is distributed to various system without spatial restriction. However, applying legacy application sharing to CSCW based virtual environment has a problem because it dont consider 3D space and it disturbs the harmonic interaction of participants. In this study, we designed application sharing system for collaborative works in 3D virtual environment to share application effectively on collaborative virtual environment. The designed application sharing system for collaborative works in 3D virtual environment consist of application sharing manager, group manager and communication manager. This system is able to perceive event of 3D space about application of participant on 3D virtual environment by agent which moves to participant sites and get an ordered events and conflict among participants through scheduling. Therefore, designed application sharing system for collaborative work in 3D virtual environment can support efficient collaborative works and improve reusability of legacy application through using easily legacy application in 3D virtual environment when CSCW application development for virtual environments.

• The KIPS Transactions:PartC
• /
• v.10C no.6
• /
• pp.727-738
• /
• 2003

Much research efforts are being exerted for the study of intrusion detection system(IDS). However little work has been for the communication medels and performance eveluation of the IDS. Here we present a communication framework for doing hybrid intrusion detection in which agents are used for local intrusion detections with a centralized data anaysis componenta for a global intrusion detection at multiple domains environment. We also assume the combination of host-based and network-based intrusion detection systems in the oberall framework. From the local domain, a set of information such as alert, and / or log data are reported to the upper level. At the root of the hierarchy, there is a global manager where data coalescing is performed. The global manager delivers a security policy to its lower levels as the result of aggregation and correlation of intrusion detection alerts. In this paper, we model the communication mechanisms for the hybrid IDS and develop a simular using OPNET modeller for the performance evaluation of transmission capabillities for the delivery of data and policy. We present and compare simulation results based on several scenarios focuding on communication delay.

• The KIPS Transactions:PartB
• /
• v.12B no.2 s.98
• /
• pp.191-202
• /
• 2005

The Semantic Web Services is a next-generation Web technology that supports Web services, based on the semantic Web technologies. Until now, the researches on semantic Web services may be foiled on the semantic Web document management and the inference engine to efficiently process the semantic Queries. However, in order to realize the principle semantic Web environment it is necessary to provide a semantic query interface though which users and/or agents can efficiently request semantic information. In this regard, we propose the Semantic Query Adapter(SQA) to provide a high query transparency with users, especially when querying about a complex semantic information. We first design the procedural user query interface based on a graphic view, by analyzing DAML-S Profile documents. And then, we builds a module which a user input query transforms its corresponding RDQL. We also propose the multiple semantic query generating procedure as a new method to solve the disjunctive query problem of the RDQL primitive.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.175-181
• /
• 2021

This paper analyzes the artificial intelligence-based approach for short-term energy consumption prediction. In this paper, we employ the reinforcement learning algorithms to improve the limitation of the supervised learning algorithms which usually utilize to the short-term energy consumption prediction technologies. The supervised learning algorithm-based approaches have high complexity because the approaches require contextual information as well as energy consumption data for sufficient performance. We propose a deep reinforcement learning algorithm based on multi-agent to predict energy consumption only with energy consumption data for improving the complexity of data and learning models. The proposed scheme is simulated using public energy consumption data and confirmed the performance. The proposed scheme can predict a similar value to the actual value except for the outlier data.

• Journal of Korean Association for Spatial Structures
• /
• v.23 no.2
• /
• pp.29-36
• /
• 2023

Reinforcement learning (RL) is widely applied to various engineering fields. Especially, RL has shown successful performance for control problems, such as vehicles, robotics, and active structural control system. However, little research on application of RL to optimal structural design has conducted to date. In this study, the possibility of application of RL to structural design of reinforced concrete (RC) beam was investigated. The example of RC beam structural design problem introduced in previous study was used for comparative study. Deep q-network (DQN) is a famous RL algorithm presenting good performance in the discrete action space and thus it was used in this study. The action of DQN agent is required to represent design variables of RC beam. However, the number of design variables of RC beam is too many to represent by the action of conventional DQN. To solve this problem, multi-agent DQN was used in this study. For more effective reinforcement learning process, DDQN (Double Q-Learning) that is an advanced version of a conventional DQN was employed. The multi-agent of DDQN was trained for optimal structural design of RC beam to satisfy American Concrete Institute (318) without any hand-labeled dataset. Five agents of DDQN provides actions for beam with, beam depth, main rebar size, number of main rebar, and shear stirrup size, respectively. Five agents of DDQN were trained for 10,000 episodes and the performance of the multi-agent of DDQN was evaluated with 100 test design cases. This study shows that the multi-agent DDQN algorithm can provide successfully structural design results of RC beam.