• 한국컴퓨터정보학회논문지
• /
• 제21권1호
• /
• pp.9-16
• /
• 2016

In this paper, we present a performance evaluation agent based on fuzzy cluster analysis and validity measures. The proposed agent is consists of three modules, fuzzy cluster analyzer, performance evaluation measures, and feature ranking algorithm for feature selection step in CAD system. Feature selection is an important step commonly used to create more accurate system to help human experts. Through this agent, we get the feature ranking on the dataset of mass and calcification lesions extracted from the public real world mammogram database DDSM. Also we design a CAD system incorporating the agent and apply five different feature combinations to the system. Experimental results proposed approach has higher classification accuracy and shows the feasibility as a diagnosis supporting tool.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(1)
• /
• pp.105-108
• /
• 2002

This paper analytical models of a centralized approach based on SNMP Protocol, distributed approach based on mobile agent, and mixed model which is tile existing mobile agent model in order to overcome large communication numbers of SNMP and accumulated data of mobile agent. And then, we compare and analyze these analytical models. Performance evaluation results show that performance of mobile agent and the mixed model is less sensitive to the network traffic and more profitable for complex network environment than that of SNMP.

• 한국화재소방학회논문지
• /
• 제21권4호
• /
• pp.1-11
• /
• 2007

본 연구에서는 할론 1301 및 이산화탄소를 비롯한 가스계소화설비의 성능을 시험하고 평가하기 위한 가장 중요한 핵심 요소인 배관내 약제비율, 관경비 등 소화성능에 영향을 미치는 가스계소화설비의 제한사항 및 성능확보에 필요한 요소에 대하여 연구하였다. 또한 본 연구에서는 관련 국내외 기준 분석 및 국내 가스계소화설비의 성능평가에 관한 인정기준(KFIS 002)에 따른 시스템 성능시험을 실시하고 결과를 비교 분석하였다.

• 한국화재소방학회논문지
• /
• 제28권2호
• /
• pp.14-19
• /
• 2014

현재 국내의 침윤소화약제 기술기준은 표면장력에 대한 기준만 존재하여 이를 통한 약제의 성능평가는 어려운 실정이다. 따라서 침윤소화약제의 성능평가 기법을 제시하기 위해 축소모형 실험 장치를 통한 최적화된 성능평가 방법을 제시하고자 한다. 본 연구는 해외 기준인 NFPA 18의 실험과 자체 제작된 축소모형 실험 장치를 이용한 실험의 결과 비교분석을 통해 자체 제작 축소모형 실험 장치실험 결과의 타당성을 규명하고자 한다. 목화솜을 대상으로 침투성능만을 평가하는 NFPA 18 실험과 목분을 대상으로 침투성능과 소화성능을 모두 평가하는 축소모형 실험을 비교분석한 결과 NFPA 18의 실험과 자체 제작 축소모형 실험에서 모두 소화용수의 침투성에 관한 변별력을 확인할 수 있었다. 또한 자체 제작 축소모형 실험에서는 T/C를 통한 내부온도 측정을 통해 보다 명확한 변별력을 나타냄을 확인하였다.

• ETRI Journal
• /
• 제44권2호
• /
• pp.313-326
• /
• 2022

This study presents a noble scheme for distributed and parallel simulations with optimized agent placement for simulation instances. The traditional parallel simulation has some limitations in that it does not provide sufficient performance even though using multiple resources. The main reason for this discrepancy is that supporting parallelism inevitably requires additional costs in addition to the base simulation cost. We present a comprehensive study of parallel simulation architectures, execution flows, and characteristics. Then, we identify critical challenges for optimizing large simulations for parallel instances. Based on our cost-benefit analysis, we propose a novel approach to overcome the performance constraints of agent-based parallel simulations. We also propose a solution for eliminating the synchronizing cost among local instances. Our method ensures balanced performance through optimal deployment of agents to local instances and an adaptive agent placement scheme according to the simulation load. Additionally, our empirical evaluation reveals that the proposed model achieves better performance than conventional methods under several conditions.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2022년도 가을 학술논문 발표대회
• /
• pp.89-90
• /
• 2022

Arc metal spraying is a widely used method for improving the performance of construction structures such as corrosion resistance and electromagnetic wave shielding. However, when arc metal spraying is applied to a concrete structure, adhesion performance may deteriorate. Therefore, the effect of each surface treatment method on the physical properties between the arc metal spray coating and concrete was reviewed by evaluating the deposition efficiency and adhesion performance according to the arc metal spray surface treatment method (surface reinforcing agent, roughening agent, and sealing agent). As a result, it is suggested as an optimal surface treatment condition to induce non-interface failure by using a roughening agent and to improve the properties of concrete and metal coatings by applying a surface reinforcing agent and sealing agent.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 2004년도 춘계 학술발표회 제16권1호
• /
• pp.818-821
• /
• 2004

Generally, the high performance concrete of drying cracking and autogenous shrinkage are tend to be increased. In the previous study, it was found that the using method in combination with expansive additive and shrinkage reducing agent was more effective than the separtely using method of that. This study is to investigated the durability of high performance concrete using expansive additive and shrinkage reducing agent. Test results showed that the high performance concrete using expansive additive and shrinkage reducing agent had very good not only the durability performance such as salt injury, carbonation, resistance to freezing-thawing and permeability but also the resistance to shrinkage.

• 한국화재소방학회논문지
• /
• 제28권2호
• /
• pp.20-25
• /
• 2014

본 연구는 자체제작 축소모형 실험 장치를 이용하여 목재를 대상으로 침윤소화약제의 소화성능평가를 수행하였다. 축소모형실험의 최적조건 확인을 위해 소화용수의 양과 목재의 수를 변화시켜 조건설정 실험을 진행한 결과 20 pieces의 목재를 적층한 후 물과 소화용수 100 mL를 살수한 경우에 한하여 소화성능의 변별력을 확인하였다. 따라서 해당 조건에서 현재 사용되고 있는 국내외 침윤소화약제를 대상으로 소화성능을 평가한 결과, 물의 경우에서만 재 발화가 발생하는 것을 확인하였다. 또한 살수 시간에 따른 온도분포를 통해 소화능력의 변별력을 판단할 수 있었다. 본 실험 결과를 바탕으로 추후 최적화 침윤소화약제 성능평가 방법을 제시하는데 기초자료로 활용할 수 있을 것으로 판단된다.

• Journal of Information Processing Systems
• /
• 제16권5호
• /
• pp.1074-1082
• /
• 2020

Recently, research has been actively conducted to create artificial intelligence agents that learn games through reinforcement learning. There are several factors that determine performance when the agent learns a game, but using any of the activation functions is also an important factor. This paper compares and evaluates which activation function gets the best results if the agent learns the game through reinforcement learning in the 2D racing game environment. We built the agent using a reinforcement learning algorithm and a neural network. We evaluated the activation functions in the network by switching them together. We measured the reward, the output of the advantage function, and the output of the loss function while training and testing. As a result of performance evaluation, we found out the best activation function for the agent to learn the game. The difference between the best and the worst was 35.4%.

• 한국도로학회논문집
• /
• 제16권4호
• /
• pp.45-50
• /
• 2014

PURPOSES : The objective of this study is to analyze the performance of anti-stripping agent depending on its type and content to reduce pothole, an increasing pavement distress due to abnormal climate intensity. METHODS : In the past years, U.S and many countries in Europe use hydrated lime and liquid anti-stripping agent in asphalt mixtures. Hydrated lime or liquid anti-stripping agent is substituted for filler and binder, respectively, to improve the anti-stripping property of asphalt mixtures. To investigate this, indirect tensile strength test was performed and TSR values were compared for different content of hydrated lime and types of liquid anti-stripping agent in asphalt mixture. RESULTS : Test results indicate that hydrated lime remarkably increased the asphalt mixture performance on anti-stripping denoted by the increased in TSR values from 55% to 100%. Liquid anti-stripping agent also increased the value of TSR but not significant. In addition, depending on the types of aggregate, TSR values and effect of liquid anti-stripping were different. CONCLUSIONS : Using anti-stripping agents improve the anti-stripping property of asphalt mixture especially hydrated lime; however, more experiments should be conducted to improve the reliability about the effect of liquid anti-stripping agent.