• Computers and Concrete
• /
• 제19권2호
• /
• pp.133-142
• /
• 2017

Two-stage concrete (TSC), also known as pre-placed aggregate concrete, is characterized by its unique placement technique, whereby the coarse aggregate is first placed in the formwork, then injected with a special grout. Despite its superior sustainability and technical features, TSC has remained a basic concrete technology without much use of modern chemical admixtures, new binders, fiber reinforcement or other emerging additions. In the present study, an experimental database for TSC was built. Different types of cementitious binders (single, binary, and ternary) comprising ordinary portland cement, fly ash, silica fume, and metakaolin were used to produce the various TSC mixtures. Different dosages of steel fibres having different lengths were also incorporated to enhance the mechanical properties of TSC. The database thus created was used to develop fuzzy logic models as predictive tools for the grout flowability and mechanical properties of TSC mixtures. The performance of the developed models was evaluated using statistical parameters and error analyses. The results indicate that the fuzzy logic models thus developed can be powerful tools for predicting the TSC grout flowability and mechanical properties and a useful aid for the design of TSC mixtures.

• 대한산업공학회지
• /
• 제18권1호
• /
• pp.105-120
• /
• 1992

An expert system was developed as a framework of integrating diverse and multifactored ergonomic knowledge to investigate its effectiveness in ergonomic workplace design and evolution. Although numerous computer-assisted approaches have been made to overcome the lack of integrated design principles, those models being used require very specific information of various design activities that may not be available in the design stage. On the other hand, an expert system would be an effective design aid that is capable of guiding the designer to solve a problem. However, most expert systems lack detailed evaluation capabilities due to a qualitative nature of inference mechanisms. Furthermore, those approaches were independently developed, focusing mostly on a single aspect such as biomechanics, physiology, etc. In this paper, a design framework was developed which takes advantage of expert system metholologies, a relational data base and existing ergonomic models. The pattern-directed, rule-based expert system allows the designer to gradually formulate and subsequently evaluate workplace design. A comprehensive and modularized knowledge base was built incorporating biomechanics, physiology and psychophysics, which is, in turn, capable of accessing not only qualitative knowledge but complex analytic evaluation models and massive information in the data base through an interface. A conflict resolution strategy using multiple criteria decision-making schemes was also employed to reconcile multiple design alternatives.

• 응용통계연구
• /
• 제11권2호
• /
• pp.377-387
• /
• 1998

컴퓨터의 발전에 따른 마코브체인 몬테카를로방법을 소프트웨어 신뢰확률모형에 이용하였다. 베이지안 추론에서 조건부분포를 가지고 사후분포를 결정하는데 있어서의 계산문제와 이론적인 정당성을 고려, 마코프연쇄와 메트로폴리스방법의 관계를 고찰하였으며, 특히 Mus-Okumoto와 Erlang(2)의 중첩모형에 대하여 깁스샘플링 알고리즘과 메트로폴리스 알고리즘을 활용하며 베이지안 계산과 예측 우도기준에 의 한 모형선택을 제안하고 Cox-Lewis에 의해 계시된 Thing method를 이용한 모의실험자료를 이용하여 수치적인 계산을 시행하고 그 결과가 제시되었다.

• 제어로봇시스템학회논문지
• /
• 제11권2호
• /
• pp.127-136
• /
• 2005

In this paper, a new architecture and comprehensive design methodology of genetically optimized Rule-based Fuzzy Polynomial Neural Networks(gRFPNN) are introduced and a series of numeric experiments are carried out. The architecture of the resulting gRFPNN results from asynergistic usage of the hybrid system generated by combining rule-based Fuzzy Neural Networks(FNN) with polynomial neural networks (PNN). FNN contributes to the formation of the premise part of the overall rule-based structure of the gRFPNN. The consequence part of the gRFPNN is designed using PNNs. At the premise part of the gRFPNN, FNN exploits fuzzy set based approach designed by using space partitioning in terms of individual variables and comes in two fuzzy inference forms: simplified and linear. As the consequence part of the gRFPNN, the development of the genetically optimized PNN dwells on two general optimization mechanism: the structural optimization is realized via GAs whereas in case of the parametric optimization we proceed with a standard least square method-based learning. To evaluate the performance of the gRFPNN, the models are experimented with the use of several representative numerical examples. A comparative analysis shows that the proposed gRFPNN are models with higher accuracy as well as more superb predictive capability than other intelligent models presented previously.

• 수산해양기술연구
• /
• 제55권3호
• /
• pp.206-216
• /
• 2019

This study is aimed to compare stock assessment models depending on how the models fit to observed data. Process-error model, Observation-error model, and Bayesian state-space model for the Korean Western coast fisheries were applied for comparison. Analytical results show that there is the least error between the estimated CPUE and the observed CPUE with the Bayesian state-space model; consequently, results of the Bayesian state-space model are the most reliable. According to the Bayesian State-space model, potential yield of fishery resources in the West Sea of Korea is estimated to be 231,949 tons per year. However, the results show that the fishery resources of West Sea have been decreasing since 1967. In addition, the amounts of stock in 2013 are assessed to be only 36% of the stock biomass at MSY level. Therefore, policy efforts are needed to recover the fishery resources of West Sea of Korea.

• Geomechanics and Engineering
• /
• 제27권5호
• /
• pp.511-525
• /
• 2021

In the design of underground excavation, the shear strength (SS) is a key characteristic. It describes the way the rock material resists the shear stress-induced deformations. In general, the measurement of the parameters related to rock shear strength is done through laboratory experiments, which are costly, damaging, and time-consuming. Add to this the difficulty of preparing core samples of acceptable quality, particularly in case of highly weathered and fractured rock. This study applies rock index test to the indirect measurement of the SS parameters of shale. For this aim, two efficient artificial intelligence methods, namely (1) adaptive neuro-fuzzy inference system (ANFIS) implemented by subtractive clustering method (SCM) and (2) support vector regression (SVR) optimized by Harmony Search (HS) algorithm, are proposed. Note that, it is the first work that predicts the SS parameters of shale through ANFIS-SCM and SVR-HS hybrid models. In modeling processes of ANFIS-SCM and SVR-HS, the results obtained from the rock index tests were set as inputs, while the SS parameters were set as outputs. By reviewing the obtained results, it was found that both ANFIS-SCM and SVR-HS models can provide acceptable predictions for interlocking and friction angle parameters, however, ANFIS-SCM showed a better generalization capability.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.30-33
• /
• 2023

The recent scholarly focus has been directed towards the expeditious and accurate detection of salient objects, a task that poses considerable challenges for resource-limited edge devices due to the high computational demands of existing models. To mitigate this issue, some contemporary research has favored inference speed at the expense of accuracy. In an effort to reconcile the intrinsic trade-off between accuracy and computational efficiency, we present novel model for salient object detection. Our model incorporate group-wise attentive module within the decoder of the encoder-decoder framework, with the aim of minimizing computational overhead while preserving detection accuracy. Additionally, the proposed architectural design employs attention mechanisms to generate boundary information and semantic features pertinent to the salient objects. Through various experimentation across five distinct datasets, we have empirically substantiated that our proposed models achieve performance metrics comparable to those of computationally intensive state-of-the-art models, yet with a marked reduction in computational complexity.

• Steel and Composite Structures
• /
• 제49권6호
• /
• pp.645-666
• /
• 2023

Due to the steadily declining supply of natural coarse aggregates, the concrete industry has shifted to substituting coarse aggregates generated from byproducts and industrial waste. Oil palm shell is a substantial waste product created during the production of palm oil (OPS). When considering the usage of OPSC, building engineers must consider its uniaxial compressive strength (UCS). Obtaining UCS is expensive and time-consuming, machine learning may help. This research established five innovative hybrid AI algorithms to predict UCS. Aquila optimizer (AO) is used with methods to discover optimum model parameters. Considered models are artificial neural network (AO - ANN), adaptive neuro-fuzzy inference system (AO - ANFIS), support vector regression (AO - SVR), random forest (AO - RF), and extreme gradient boosting (AO - XGB). To achieve this goal, a dataset of OPS-produced concrete specimens was compiled. The outputs depict that all five developed models have justifiable accuracy in UCS estimation process, showing the remarkable correlation between measured and estimated UCS and models' usefulness. All in all, findings depict that the proposed AO - XGB model performed more suitable than others in predicting UCS of OPSC (with R², RMSE, MAE, VAF and A_15-index at 0.9678, 1.4595, 1.1527, 97.6469, and 0.9077). The proposed model could be utilized in construction engineering to ensure enough mechanical workability of lightweight concrete and permit its safe usage for construction aims.

• 인지과학
• /
• 제17권4호
• /
• pp.303-321
• /
• 2006

본 논문은 의미 중의성 해소에 대한 화자의 직관의 계산 모형에 대한 연구로 Harris (1964)의 '분포가설'에 근거하여 핵심어와 공기하는 어휘들에 대한 분포적 정규성을 포착하는 언어 직관의 계산 모형을 제안한다. 이를 위해 분포적 정규성에 대한 화자의 처리 계산 모형을 파악하기 위하여 심리언어학적 실험을 실시하고 그 결과를 분석한다. 계산 모형으로는 논리 모형, 확률 모형, 그리고 확률 추론 모형의 세가지 모형이 설정되었다. 실험은 두 가지로 구성되었다. 첫 번째는 100만 어절 코퍼스에서 추출된 문장을 화자 직관으로 의미를 식별하는 실험이었다. 이 실험에서는 응답간 일치도가 98%로 나왔다. 두 번째 실험은, 제한된 환경에서 실험자의 반응을 관찰하기 위한 것으로, 분열문이라는 환경을 통해 핵심어와 공기어사이의 의미 관계를 살펴보았다. 또한 100만 어절 코퍼스에서 관찰된 수치와 실험에서 관찰된 관찰치사이의 상관성을 피어슨의 상관계수로 측정하였다. 그러한 측정 결과 실제 코퍼스에서 관찰되는 현상은 논리모형과 상관성이 있었고, 제한된 환경에서 실시한 결과는 확률 모형과 상관성이 있었다. 이 실험결과는 논리 모형이 우선적으로 의미 분류에 관여하나, 만약 논리 모형이 적용되지 않을 경우 확률 모형이 관여함을 보여 준다. 아울러 의미 결정 모형의 관점에서는 논리 모형이 정확하게 직관모형을 예측할 수 있었고, 확률추론 모형도 직관모형을 근사치에 가깝게 예측할 수 있었다.

• 콘크리트학회논문집
• /
• 제22권1호
• /
• pp.19-27
• /
• 2010

건축물이나 교량과 같은 RC 구조물의 경우, 다양한 유해 환경하의 재료적인 열화나 구조적 문제로 콘크리트의 노후화 및 손상이 발생하게 된다. 콘크리트의 균열이나 철근의 부식, 구조 단면의 변형 등은 구조적 안전성 저하 및 구조물 거동 특성 변화의 주요 원인이 되기도 한다. 따라서 이와 같은 콘크리트 구조물의 보수 보강을 위하여, 효과적이고 적용이 간편한 공법의 개발이 콘크리트 분야의 중요한 연구 과제 중의 하나로 인식되어 왔다. 다양한 보수 보강 기법들이 과거 수십 년 동안 개발되어 적용되고 있으며, 이중에서도 최근 FRP 복합 재료를 구조물의 외부에 접착시키는 방법을 통한 보강 방식이 많이 사용되고 있다. 이 연구는 인공 지능(AI)의 일종인 뉴로퍼지모델(ANFIS) 을 이용하여, FRP로 보강된 원주형 콘크리트 부재의 보강 효과를 분석하는데 그 목적이 있다. ANFIS 모델을 이 연구에 적용하기 위하여, 기존 연구 자료 및 실험에서 얻은 결과를 통해 학습 데이터와 시험 데이터 세트를 구축하였다. 이 연구에서 구축된 ANFIS 모델은 기존 피보강 콘크리트의 압축강도, 보강재의 두께, 보강재의 보강 겹수, 보강재의 탄성계수, 보강재의 파단강도 및 보강재와 피보강재의 체적비, 피보강재의 부재크기를 입력 자료의 파라미터로 사용하여, 압축강도, 변형률, 2차탄성계수 등을 예측하는 방식으로 활용될 수 있으며, ANFIS 모델을 통하여 예측된 결과를 기존 연구자들이 제안한 FRP 보강 콘크리트 부재의 구성 방정식과 비교할 때 더 높은 정확도로 예측이 가능함을 확인할 수 있다.