• 전자공학회논문지CI
• /
• 제41권3호
• /
• pp.55-65
• /
• 2004

신경회로망을 이용하여 주어진 문제를 해결할 때, 문제의 복잡도에 맞는 구조를 찾는 것이 중요하다. 이것은 신경회로망의 복잡도가 학습능력과 일반화 성능에 크게 영향을 주기 때문이다. 그러므로, 문제에 적합한 신경회로망의 구조를 자기 구성적으로 찾는 알고리즘이 유용하다. 본 논문에서는 시그모이드 활성함수를 가지는 전방향 다층 신경회로망에 대하여 주어진 문제에 맞는 구조를 결정하는 알고리즘을 제안한다. 개발된 알고리즘은 구조증가 알고리즘과 연결소거 알고리즘을 이용하여, 주어진 학습 데이터에 대해 가능한 한 작은 구조를 가지며 일반화 성능이 좋은 최적에 가까운 신경회로망을 찾는다. 네 가지 함수 근사화 문제에 적용하여 알고리즘의 성능을 알아본다. 실험 결과에서, 제안한 알고리즘이 기존의 알고리즘 및 고정구조를 갖는 신경회로망과 비교하였을 때 최적 구조에 가까운 신경회로망을 구성하는 것을 확인한다.

• 한국정보전자통신기술학회논문지
• /
• 제1권2호
• /
• pp.7-11
• /
• 2008

로컬 레벨의 표준화 및 시스템간의 상호운용성을 높이기 위하여 공기조화설비 제어 계통도를 지하층(8포인트)과 기준층(15포인트)으로 구분하여 설계하고 전력선통신으로 제어 네트워크를 구축하였다. 공기조화 시스템의 각 디바이스는 개방형 프로토콜인 뉴런 C로 프로그램 하였다. 연구 결과 $L_{ON}W_{ORKS}$ 프로토콜로 각 디바이스들의 자율분산제어가 가능하게 되었고 통신선의 길이와 회선수를 감소시킬 수 있었다.

• Journal of Information Science Theory and Practice
• /
• 제9권2호
• /
• pp.83-98
• /
• 2021

Research collaboration is an important strategy to improve research output, and virtual academic communities (VACs) have become an important platform to collaborate on. This paper reveals the influencing factors of researchers' collaboration intention in VACs from two attributes: individual, and inter-members. On the basis of the Social Cognitive Theory, Social Exchange Theory, social network theory, and Five-Factor Model, this paper constructed a model demonstrating the influencing factors of VACs researchers' collaboration intention. A self-administered questionnaire was employed on members of four VACs in China to collect data; subsequently, 558 usable responses were analyzed using structural equation modeling. The result showed that openness, conscientiousness, reciprocity, trust, and the social network characteristic had a significant influence on the collaboration intention of researchers in VACs, while self-efficacy, agreeableness, extroversion, neuroticism, and experience had no significant effects on the collaboration intention of researchers in VACs. This model plays a positive role in promoting the research collaboration intention of Chinese VACs researchers and in guiding the construction of VAC platforms.

• Advances in concrete construction
• /
• 제15권2호
• /
• pp.85-96
• /
• 2023

The characteristics of self-compacting concrete (SCC) made with fly ash and reinforced with polyester fibers were investigated in this research. Polyester fibers of 12 mm long and 15 micrometer diameters were utilized in M40 grade SCC mixtures at five different volume fractions 0.025%, 0.05%, 0.075%, 0.1%, 0.3% as a fiber reinforcement. To understand the influence of polyester fibers on passing ability, flowability, segregate resistance the J ring, L box, V funnel, slump flow and U box tests were performed. Polyester fibers have a direct influence, with a maximum of 0.075% polyester fibers producing excellent characteristics. ANN models were constructed using the testing data as inputs to anticipate the fresh and hardened characteristics as targeted outputs. The research revealed that R² values ranging from 0.900 to 0.997 appears to be a good correlation. The performance of ANN models and regression models for predicting the new characteristics of SCC is also evaluated.

• 한국멀티미디어학회논문지
• /
• 제14권11호
• /
• pp.1450-1457
• /
• 2011

현재, 일반적인 누수감지 모니터링 시스템은 라이선스를 지불하는 전자 지도를 이용하기에, 시스템 구축비용과 관리 주체인 지자체의 재정 지출을 높이며 유지보수, 기능 확장, 타 시스템과의 호환 등 비효율적인 문제점을 안고 있다. 이에 본 논문에서는 인터넷 범용 지도를 이용해 저비용과 고효율을 지향하는 상수도 관망 모니터링 시스템을 개발한다. 이 시스템은 호환성이 높은 무료 지도를 활용하기에 기존의 시스템보다 구축비용과 하드웨어 요구 사항은 낮아지며, 결과적으로 전체 모니터링 시스템의 성능은 향상되고, 구축 원가는 급격히 절감된다. 시공과 함께 구축할 수 있는 파이프라인 DB 구축 방식도 함께 제안하여 전반적인 시스템의 현장 적용성도 높이는 결과를 도출한다.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2010년도 춘계 학술발표회
• /
• pp.338-350
• /
• 2010

As existing materials for ground reinforcement, chemical grout material using cementitous materials and waterglass was used. But many problems in terms of ground reinforcement effects were implicated. In this study, for development and applicability verification of new materials, viscosity, fluidity, permeability, Self-Leveling, keeping of drilled hole, antiwashout underwater, resistance of water (groundwater dilution and minimize material eluting) and the early strength and long-term strength characteristics of developed materials was confirmed, and material standards, and establishing construction standards for the various model tests were conducted. As a result, high viscosity, flowability, permeability and keeping of drilled hole characteristics are excellent, in addition to the early strength properties, dilution does nat occur to groundwater, including groundwater is available for dealing with environmental issues. Application of basic and reinforcement method by Filler function in addition to structure can also or development of a new concept can be expected. In addition, middle and large-diameter drilled shaft, micropile, ground anchors, soil-nailing, steel pipes multi-grouting reinforcement for cement injection process could be used enough to even be considered.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2022년도 가을 학술논문 발표대회
• /
• pp.243-244
• /
• 2022

In this paper, experiments were conducted on signal amplification of polymer capsules for application to Ground Penetrating Radar so as to enable real-time monitoring of polymer capsules inside concrete using the Morphology Dependent Resonance phenomenon. A TEM CELL and a vector network analyzer were used to analyze the difference in resonance frequency depending on the material of the sphere and the presence or absence of fracture. In order to manufacture a capsule of a size that can be measured using millimeter waves used in GPR, we manufactured a capsule with a 3D printer and analyzed the effects of the presence or absence of coating and the size of the capsule on the resonance frequency. Resonant frequency or signal amplification is more affected by diameter than coating. The capsule showing the highest amplification is the resin-coated 50 mm diameter capsule with a 316-fold increase and the lowest capsule is the uncoated 10 mm diameter capsule with a signal amplification of 11.9 times. These results demonstrate the potential of GPR to measure the position and state of self-healing capsules, which are small-sized polymers, in real time using millimeter waves.

• Smart Structures and Systems
• /
• 제32권6호
• /
• pp.359-369
• /
• 2023

Servo-motor driven uniaxial shake tables have been widely used for education and research purposes in earthquake engineering. These shake tables are mostly displacement-controlled by a digital proportional-integral-derivative (PID) controller; however, accurate reproduction of acceleration time histories is not guaranteed. In this study, a control strategy is proposed and verified for uniaxial shake tables driven by a servo-motor. This strategy incorporates a deep-learning algorithm named Long Short-Term Memory (LSTM) network into a displacement PID feedback controller. The LSTM controller is trained by using a large number of experimental data of a self-made servo-motor driven uniaxial shake table. After the training is completed, the LSTM controller is implemented for directly generating the command voltage for the servo motor to drive the shake table. Meanwhile, a displacement PID controller is tuned and implemented close to the LSTM controller to prevent the shake table from permanent drift. The control strategy is named the LSTM-PID control scheme. Experimental results demonstrate that the proposed LSTM-PID improves the acceleration tracking performance of the uniaxial shake table for both bare condition and loaded condition with a slender specimen.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2015년도 춘계학술대회
• /
• pp.296-298
• /
• 2015

자율적인 행위자들로서 서로 영향을 끼치며 상호작용하는 선박들을 관제하는 VTSO는 불확실성으로 인한 위험을 극복하기 위해서는 적극적으로 상황을 파악하여 최선의 의사결정을 하여야 한다. VTSO는 항상 미래의 상황을 예측하면서 업무를 수행하여야 하는데 이때 VTSO에게 요구되는 것이 바로 시뮬레이션 능력이다. 시뮬레이션은 삽화기억의 구성적 성격을 활용하는 것으로서 삽화기억의 메커니즘은 미래 계획에도 그대로 활용된다. 본고에서는 반사실적 사고가 시뮬레이션에 어떻게 작동되는가를 살펴보고, VTS 상황에 이를 적용하여 보았다. 특히 반사실적 사고와 시뮬레이션을 통해서 VTSO가 업무역량을 향상시키기 위해서 어떻게 학습하여야 하는가를 고찰하였다.

• Computers and Concrete
• /
• 제24권5호
• /
• pp.399-412
• /
• 2019

In this investigation, Elman neural networks were utilized for predicting the mechanical properties of Self-Compacting Concretes (SCCs). Elman models were designed by using experimental data of many different concrete mixdesigns of various types of SCC that were collected from the literature. In order to investigate the effectiveness of the selected input variables on the network performance in predicting intended properties, utilized data in artificial neural networks were considered in two sets of 8 and 140 input variables. The obtained outcomes showed that not only can the developed Elman ANNs predict the mechanical properties of SCCs with high accuracy, but also for all of the desired outputs, networks with 140 inputs, compared to ones with 8, have a remarkable percent improvement in the obtained prediction results. The prediction accuracy can significantly be improved by using a more complete and accurate set of key factors affecting the desired outputs, as input variables, in the networks, which is leading to more similarity of the predicted results gained from networks to experimental results.