• Journal of KIISE:Software and Applications
• /
• v.31 no.2
• /
• pp.101-110
• /
• 2004

In dynamic systems, such as social and economic systems, complex interactions emerge among its members. In that case, their behaviors become adaptive according to Changing environment. In many cases, an individual's behaviors can be modeled by a stimulus-response system in a dynamic environment. In this paper, we use the Iterated Prisoner's Dilemma (IPD) game, which is simple yet capable of dealing with complex problems, to model the dynamic systems. We propose strategic coalition consisting of many agents and simulate their emergence in a co-evolutionary learning environment. Also we introduce the concept of confidence for agents in a coalition and show how such confidences help to improve the generalization ability of the whole coalition. Experimental results are presented to demonstrate that co-evolutionary learning with coalitions and confidence allows better performing strategies that generalize well.

• Smart Structures and Systems
• /
• v.29 no.5
• /
• pp.677-691
• /
• 2022

Water cycle algorithm (WCA) has been a very effective optimization technique for complex engineering problems. This study employs the WCA for simultaneous prediction of heating load (L_H) and cooling load (L_C) in residential buildings. This algorithm is responsible for optimally tuning a neural network (NN). Utilizing 614 records, the behavior of the L_H and L_C is explored and the captured knowledge is then used to predict for 154 unanalyzed building conditions. Since the WCA is a population-based algorithm, different numbers of the searching agents were tested to find the most optimum configuration. It was observed that the best solution is discovered by 500 agents. A comparison with five newly-developed benchmark optimizers, namely equilibrium optimizer (EO), multi-tracker optimization algorithm (MTOA), slime mould algorithm (SMA), multi-verse optimizer (MVO), and electromagnetic field optimization (EFO) revealed that the WCANN predicts the desired parameters with considerably larger accuracy. Obtained root mean square errors (1.4866, 2.1296, 2.8279, 2.5727, 2.5337, and 2.3029 for the L_H and 2.1767, 2.6459, 3.1821, 2.9732, 2.9616, and 2.6890 for the L_C) indicated that the most reliable prediction was presented by the proposed model. The EFONN, however, provided a more time-effective solution. Lastly, an explicit predictive formula was elicited from the WCANN.

• Computers and Concrete
• /
• v.34 no.1
• /
• pp.123-135
• /
• 2024

Strain-hardening cement-based composites (SHCC) under cracked condition exhibits remarkable capillary absorption due to water ingress from multiple cracks. Surface treatment using water repellent agents is an effective way for improving water resistance of SHCC, but the water resistance may remarkably decrease when cracks penetrate impregnation depth. Another way is to add water repellent agents directly into the mixture, offering SHCC integral water repellency even if cracks form later. However, although integral water repellent treatment has been proved feasible by previous studies, there is still lack of simulation work on the treated SHCC for evaluating its durability. This study presents a simulation method for capillary absorption of cracked SHCC with integral treatment based on a multi-scale approach proposed in the authors' previous work. The approach deals with water flows in bulk matrix and multiple cracks using two individual transport equations, respectively, whereas water absorbed from a crack to its adjacent matrix is treated as the mass exchange of the two equations. In this study, the approach is enhanced for the treated SHCC by integrating the influencing of water repellency into the two transport equations as well as the mass exchange term. Using the enhanced approach, capillary absorption of water repellent SHCC under cracked condition is simulated, showing much more reduced water ingress than the untreated concrete, which is consistent with total absorption data from previous tests. This approach is also capable of simulating water spatial distribution with time in treated SHCC reasonably.

• Korean Journal of Cognitive Science
• /
• v.12 no.1_2
• /
• pp.55-63
• /
• 2001

Speaking generally, agent-based technology is a kind of technology to handle the flood of information resulted from the popularization of the internet. Agent system is a multi-distributed system which consists of both homogeneous and heterogeneous agents. Generally there is a coordination agent in between which is in charge of control and m message flow among the application agents. The purpose of this thesis is to propose a coordination method among agents, some of which provide informations and some of which request them. In multi-agent system, the Information Providing Agent(IPA) registers its capabilities to Coordination Agent(CA) and the Information Requesting Agent(lRA) requests CA what it needs. To coordinate them with satisfactory results the coordination agent ought to have an ability to return a relatively proper data to the requester which is supposed to be similar even though it is not so exact as was intended. For this, this thesis proposes a scheme for an coordination agent to find an IPA which provides an information which correlates most closely with that of IRA.

• Journal of the korean academy of Pediatric Dentistry
• /
• v.32 no.4
• /
• pp.595-603
• /
• 2005

Incomplete removal of bacteria contaminated dentin or enamel associated with caries is a potential problem in restorative dentistry Secondary or residual caries, pulpal inflammation and hypersensitivity may result from bacteria left after the initial preparation, especially if an adequate seal against microleakage is not obtained. A possible solution to eliminate residual bacteria left in a cavity preparation would be to treat the cavity with cavity disinfectant wash. But a potential problem with using a cavity disinfectant with dentin bonding agents could be their interference with the ability of the resin to bond to the tooth micromechanically. The purpose of this study was to evaluate the effect of 2% chlorhexidine containing cavity disinfectant ($Consepsis^{(R)}$) on shear bond strength and microleakage of dentin bonding agents, $Adper ^{TM}$ $Scotchbond^{TM}$ Multi-Purpose, $Adper^{TM}$ Single Bond and $Adper^{TM}\;Prompt^{TM}\; L-Pop^{TM}$ Sixty and sixty sound human third molar teeth, respectively, were used for shear bond strength and microleakage test. For experimental group, cavity disinfectant was applied before dentin bonding agents, and was not applied for the control group. The result from the this study can be summarized as follows ; 1. Use of 2% chlorhexidine containing cavity disinfectant($Consepsis^{(R)}$) does not significantly affect the shear bond strength of dentin bonding agents. 2. Use of 2% chlorhexidine containing cavity disinfectant($Consepsis^{(R)}$) does not significantly affect the microleakage of dentin bonding agents.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.6 no.4
• /
• pp.82-88
• /
• 2012

The usage of recycling agent is the most effective way of enhancing the performance of recycled asphalt pavement. Generally, many countries accepted these recycling agents retarding the various types of cracks resulted in binder aging. Contrary to such general tendency, recycling agents are used as very small amount in domestic recycling plant. The main reason of this is relatively high price of recycling agent. Even though agent price is high, agent can be a effective and economical way of alternative in asphalt recycling. In this study, penetration and softning point test performed by using RTFO(Rolling Thin Film Oven) aged binder. And, PG(Performance Grade) at high temperature, fatigue and MSCR(Multi Stress Creep and Recovery) tests exercised. The oil type agent is worked well to retrieving target penetration number. In PG test, $G^*/sin{\delta}$ of agents identically showed high value and polymer type agent is good at recovery value.

• ETRI Journal
• /
• v.37 no.2
• /
• pp.369-379
• /
• 2015

Fault management of virtualized network environments using user-driven network provisioning systems (NPSs) is crucial for guaranteeing seamless virtual network services irrespective of physical infrastructure impairment. The network service interface (NSI) of the Open Grid Forum reflects the need for a common standard management API for the reservation and provisioning of user-driven virtual circuits (VCs) across global networks. NSI-based NPSs (that is, network service agents) can be used to compose user-driven VCs for mission-critical applications in a dynamic multi-domain. In this article, we first attempt to outline the design issues and challenges faced when attempting to provide mission-critical applications using dynamic VCs with a protection that is both user-driven and trustworthy in a dynamic multi-domain environment, to motivate work in this area of research. We also survey representative works that address inter-domain VC protection and qualitatively evaluate them and current NSI against the issues and challenges.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.828-831
• /
• 1997

One of the most important design factor for the image tracker is the speed of the data processing which allows real-time operation of the system and provides reasonably accurate performance at the same time. Use of powerful DSP alone does not guarantee to meet such requirement. In this paper, a simple efficient algorithm for real-time multi-target image tracking is suggested. The suggested method is based on a recursive centroiding technique and color table look-up. This method has been successfully implemented in a image processing system for Micro-Robot Soccer Tournament(MIROSOT). This tracker can track positions of a ball, 3 enemies, and 3 agents at the same time. The experimental results show that the processing time for each frame of image is less than 7ms, which is well within the 60Hz sampling interval for real-time operation.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.166-169
• /
• 2003

Reinforcement learning if a kind of machine learning. It aims to adapt an agent to a given environment with a clue to a reward and a penalty. Q-learning [8] that is a representative reinforcement learning system treats a reward and a penalty at the same time. There is a problem how to decide an appropriate reward and penalty values. We know the Penalty Avoiding Rational Policy Making algorithm (PARP) [4] and the Penalty Avoiding Profit Sharing (PAPS) [2] as reinforcement learning systems to treat a reward and a penalty independently. though PAPS is a descendant algorithm of PARP, both PARP and PAPS tend to learn a local optimal policy. To overcome it, ion this paper, we propose the Multi Best method (MB) that is PAPS with the multi-start method[5]. MB selects the best policy in several policies that are learned by PAPS agents. By applying PS, PAPS and MB to a soccer game environment based on the SoccerBots[9], we show that MB is the best solution for the soccer game environment.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.8 no.1
• /
• pp.61-67
• /
• 2008

This paper introduces the multi-vehicle routing problem(MRP) which is different from the traveling sales problem(TSP), and presents the ant system(AS) applied to the MRP. The proposed MRP is a distributive model of TSP since many vehicles are used, not just one salesman in TSP and even some constraints exist. In the AS, a set of cooperating agents called vehicles cooperate to find good solutions to the MRP. To make the proposed MRP extended more, Tokyo city model(TCM) is proposed. The goal in TCM is to find a set of routes that minimizes the total traveling time such that each vehicle can reach its destination as soon as possible. The results show that the AS can effectively find a set of routes minimizing the total traveling time even though the TCM has some constraints.