• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.1
• /
• pp.406-434
• /
• 2019

In general, an information security approach estimates the risk, where the risk is to occur due to an unusual event, and the associated consequences for cloud organization. Information Security and Risk Management (ISRA) practices vary among cloud organizations and disciplines. There are several approaches to compare existing risk management methods for cloud organizations but their scope is limited considering stereo type criteria, rather than developing an agent based task that considers all aspects of the associated risk. It is the lack of considering all existing renowned risk management frameworks, their proper comparison, and agent techniques that motivates this research. This paper proposes Agent Based Information Security Framework for Hybrid Cloud Computing as an all-inclusive method including cloud related methods to review and compare existing different renowned methods for cloud computing risk issues and by adding new tasks from surveyed methods. The concepts of software agent and intelligent agent have been introduced that fetch/collect accurate information used in framework and to develop a decision system that facilitates the organization to take decision against threat agent on the basis of information provided by the security agents. The scope of this research primarily considers risk assessment methods that focus on assets, potential threats, vulnerabilities and their associated measures to calculate consequences. After in-depth comparison of renowned ISRA methods with ABISF, we have found that ISO/IEC 27005:2011 is the most appropriate approach among existing ISRA methods. The proposed framework was implemented using fuzzy inference system based upon fuzzy set theory, and MATLAB(R) fuzzy logic rules were used to test the framework. The fuzzy results confirm that proposed framework could be used for information security in cloud computing environment.

• The Journal of Korea Robotics Society
• /
• v.12 no.3
• /
• pp.339-349
• /
• 2017

In this paper, we present a finite-time sliding mode control (FSMC) with an integral finite-time sliding surface for applying the concept of graph theory to a distributed wheeled mobile robot (WMR) system. The kinematic and dynamic property of the WMR system are considered simultaneously to design a finite-time sliding mode controller. Next, consensus and formation control laws for distributed WMR systems are derived by using the graph theory. The kinematic and dynamic controllers are applied simultaneously to compensate the dynamic effect of the WMR system. Compared to the conventional sliding mode control (SMC), fast convergence is assured and the finite-time performance index is derived using extended Lyapunov function with adaptive law to describe the uncertainty. Numerical simulation results of formation control for WMR systems shows the efficacy of the proposed controller.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.9
• /
• pp.3232-3238
• /
• 2010

As flexible manufacturing systems (FMSs) are highly automated and required flexibility to satisfy market need, dispatching rules are constrained by specific environments of manufacturing systems such as mechanical failures, absence of employees, and lack of spare parts. In this paper, an ontology-based knowledge approach is proposed to improve efficiency of system through adapting suitable dispatching rules, considering context in a FMS shop floor, which consists multiple manufacturing cells. the multi-agents monitor manufacturing system status and job so that it figures out a dispatching rule considering context. To demonstrate the proposed approach, a proof-of-concept prototype system has been implemented in the $JADE^{TM}$ platform and Protege to make OWL DL ontology.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.8
• /
• pp.758-767
• /
• 2012

In the ad-hoc wireless network environment, that the fixed sensor nodes and the sensor nodes to move are mixed, as the number of the sensor nodes with mobility are getting more, the costs to recover and maintain the whole network will increase more and more. This paper proposed the CDSR (Cost based Dynamic Source Routing) algorithm being motivated from the typical DSR algorithm, that is one of the reactive routing protocol. The cost function is defined through measuring the cost which any sensor node pays to participate in the whole network for communication. It is also showed in this paper that the proposed routing algorithm will increase the efficiency and life of whole sensor network through a series of experiments.

• Asia pacific journal of information systems
• /
• v.32 no.2
• /
• pp.226-248
• /
• 2022

The existing model for sentiment analysis of product reviews learned from past data and new data was labeled based on training. But new data was never used by the existing system for making a decision. The proposed Aspect-based multi-agent Deep Reinforcement learning Sentiment Analysis (ADRSA) model learned from its very first data without the help of any training dataset and labeled a sentence with aspect category and sentiment polarity. It keeps on learning from the new data and updates its knowledge for improving its intelligence. The decision of the proposed system changed over time based on the new data. So, the accuracy of the sentiment analysis using deep reinforcement learning was improved over supervised learning and unsupervised learning methods. Hence, the sentiments of premium customers on a particular site can be explored to other customers effectively. A dynamic environment with a strong knowledge base can help the system to remember the sentences and usage State Action Reward State Action (SARSA) algorithm with Bidirectional Encoder Representations from Transformers (BERT) model improved the performance of the proposed system in terms of accuracy when compared to the state of art methods.

• Journal of the Korea Society for Simulation
• /
• v.23 no.4
• /
• pp.75-83
• /
• 2014

Most warship combat systems inquire human operator to control several sensor and another equipments as well as decision-modeling. For this reason, many researches with multi-agent based M&S (Modeling and Simulation) have been increasingly conducted. However there cannot find any researches of M&S based analysis for anti-submarine warfare that requires a high level of mission complexity between multiple platforms. In this research, we have been developed various combat platform models such as warship, submarine and helicopter, etc. In order to apply the multi-agent-based M&S technology to the anti-submarine warfare i.e. a HVU (High Value Unit) escort mission scenario. Then we have successfully analyzed the measures of effectiveness according to the different tactics and different situations. In future, the defence engineer maybe employ our methodology and tools to analyze actual tactical problem by simply inserting actual data into our agent model.

• Journal of the Korea Society for Simulation
• /
• v.20 no.3
• /
• pp.101-109
• /
• 2011

M&S in the field of national defense is a battle system has been highly spotlighted for obtaining weapon systems, analyzing and experimentation of battle effects to reduce costs, time, and risks. It is classified as Campaign, Mission, Engagement, and Engineering levels by detail of description. In engagements, many situations on the battle field which are really unpredictable are required to be considered on the view of diverse tactics. Thus, engagement simulation is in demand to use for forecasting real-world battle situations by inserting various components which consists of real engaging situations into virtual local battle field. While developing the engagement simulation, adopting the concept of agent-based simulation gives it benefits which are improved autonomy, composability, and reusability of entities. It means reducing the time, cost and effort to develop the simulations. This paper concentrates on the framework of multi-agent based engagement simulation using Cougaar Architecture.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.4244-4274
• /
• 2021

The utilization of UAVs in various fields has led to the development of flying ad hoc network (FANET) technology. In a network environment with highly dynamic topology and frequent link changes, the traditional routing technology of FANET cannot satisfy the new communication demands. Traditional routing algorithm, based on geographic location, can "fall" into a routing hole. In view of this problem, we propose a geolocation routing protocol based on multi-agent reinforcement learning, which decreases the packet loss rate and routing cost of the routing protocol. The protocol views each node as an intelligent agent and evaluates the value of its neighbor nodes through the local information. In the value function, nodes consider information such as link quality, residual energy and queue length, which reduces the possibility of a routing hole. The protocol uses global rewards to enable individual nodes to collaborate in transmitting data. The performance of the protocol is experimentally analyzed for UAVs under extreme conditions such as topology changes and energy constraints. Simulation results show that our proposed QLGR-S protocol has advantages in performance parameters such as throughput, end-to-end delay, and energy consumption compared with the traditional GPSR protocol. QLGR-S provides more reliable connectivity for UAV networking technology, safeguards the communication requirements between UAVs, and further promotes the development of UAV technology.

• Journal of the Korea Computer Industry Society
• /
• v.2 no.3
• /
• pp.321-328
• /
• 2001

Existing internet auction systems have adopted the form which gives a win to the auction bidder who proposes the top bid price for the goods posted on the auction board. But they haven't been satisfying the automatical one-step processing for user’s convenience because they must require continuous care of user for bidding and checking as well as neglecting the convenience of user interface while participating in the electronic bidding system. The agent push mail to a auctioneer information that able to get how much profit as calculate duration time and start price with bidding history stored database. So, this thesis propose a multi-agent system in internet auction that generate the highest margin for auctioneer’s goods.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.45-55
• /
• 2022

Recently, large-scale language models (LPLM) have been shown state-of-the-art performances in various tasks of natural language processing including intent classification. However, fine-tuning LPLM requires much computational cost for training and inference which is not appropriate for dialog system. In this paper, we propose compressed intent classification model for multi-agent in low-resource like CPU. Our method consists of two stages. First, we trained sentence encoder from LPLM then compressed it through knowledge distillation. Second, we trained agent-specific adapter for intent classification. The results of three intent classification datasets show that our method achieved 98% of the accuracy of LPLM with only 21% size of it.