• 한국지역지리학회지
• /
• 제12권6호
• /
• pp.693-703
• /
• 2006

본 연구는 혁신유형과 네트워크 형태간의 관계를 탐색적으로 고찰하였다. 즉, 기업의 혁신유형에 따라 사회적 자본의 특성이 어떻게 다르게 나타나는지를 실증 분석하고 있다. 이 관계를 검증하기 위해 2005년 6월에서 7월 사이에 실시된 "경북 IT기업 기술혁신활동 조사"에서 나타난 168개 기업 자료를 실증적으로 분석하였다. 분석은 IT기업의 기술혁신 유형변수로 '탐색형 기업', '활용형 기업'으로 구분하였고, 사회적 자본은 네트워크의 형태를 나타내는 '구조적 변수'와 강도를 나타내는 '관계적 변수'로 구분하여 구성형태를 분석하였다. 분석 결과, 탐색형 기업에서는 네트워크의 범위가 넓고(sparse network) 약한 연계(weak tie) 관계를 가지는 반면, 활용형 기업에서는 네트워크가 범위를 좁고(dense network) 강한 연계(strong tie) 관계를 가지는 것으로 나타났다.

• Computers and Concrete
• /
• 제8권5호
• /
• pp.491-510
• /
• 2011

Before deciding if structures exposed to high temperature are to be repaired or demolished, their final state should be carefully examined. Destructive and non-destructive testing methods are generally applied for this purpose. Compressive strength and color change in mortars are observed as a result of the effects of high temperature. In this study, ordinary and pozzolan-added mortar samples were produced using different aggregates, and exposed to 100, 200, 300, 600, 900 and $1200^{\circ}C$. The samples were divided into two groups and cooled to room temperature in water and air separately. Compression tests were carried out on these samples, and the color change was evaluated by the Munsell Color System. The relationships between the change in compressive strength and color of mortars were determined by using a multi-layered feed-forward Neural Network model trained with the back-propagation algorithm. The results showed that providing accurate estimates of compressive strength by using the color components and ultrasonic pulse velocity design parameters were possible using the approach adopted in this study.

• 한국지반공학회논문집
• /
• 제19권4호
• /
• pp.287-298
• /
• 2003

본 논문에서는 피에조콘 관입시험 결과로부터 점토의 비배수전단강도를 예측하기 위한 인공신경망 이론의 적용과 최적 모델 구축에 대하여 기술하였다. 먼저 등방 및 비등방 삼축압축실험(CIUC and CAUC)으로 얻어진 비배수전단강도 결과를 바탕으로 오차역전파 알고리즘에 의하여 간단한 다층 구조를 갖는 최적 인공신경망 모델이 구성되었다. 구성된 인공신경망 모델은 모델 구축 시에 사용되지 않은 새로운 자료에 대해 비배수전단강도 예측을 수행하고 예측결과와 실내시험 결과를 비교함으로써 그 타당성이 검증되었다. 또한 기존의 이론적 방법, 경험적 방법 및 direct correlation method 등으로 예측된 비배수전단강도와 제안된 모델의 예측결과를 비교하였다. 본 논문에서 제안된 인공신경망 모델링 기법은 피에조콘 관측결과들과 비배수전단강도 간의 비선형적 상관관계를 정의하는 데에 유용하며 구성된 인공신경망 모델은 기존의 이론적 및 경험적 방법들에 비하여 예측 신뢰성이 높은 것으로 나타났다. 또한, 지금까지 주로 사용되어 온 경험적 방법들이 특정 지역에 대한 상관관계에 만족하던 것과 비교해 인공신경망 모델은 다양한 지역과 국가에서 일반적으로 적용 가능한 상관관계로서 발전될 가능성이 있음을 알 수 있었다.

• Journal of Information Processing Systems
• /
• 제13권4호
• /
• pp.987-999
• /
• 2017

Extraction of influential people from their respective domains has attained the attention of scholastic community during current epoch. This study introduces an innovative interaction strength metric for retrieval of the most influential users in the online social network. The interactive strength is measured by three factors, namely re-tweet strength, commencing intensity and mentioning density. In this article, we design a novel algorithm called IPRank that considers the communications from perspectives of followers and followees in order to mine and rank the most influential people based on proposed interaction strength metric. We conducted extensive experiments to evaluate the strength and rank of each user in the micro-blog network. The comparative analysis validates that IPRank discovered high ranked people in terms of interaction strength. While the prior algorithm placed some low influenced people at high rank. The proposed model uncovers influential people due to inclusion of a novel interaction strength metric that improves results significantly in contrast with prior algorithm.

• 한국산학기술학회논문지
• /
• 제19권12호
• /
• pp.7-13
• /
• 2018

콘크리트 강도는 시멘트, 물, 자갈, 모래 그리고 혼화재 등 내부영향요인뿐만 아니라 실제 현장에서 발생하는 현장기온과 타설지연시간 등 외부영향요인의 영향을 받게 된다. 본 연구의 목적은 콘크리트 배합설계 시 내부영향요인과 외부영향요인을 고려하여 현장 콘크리트 타설시 최적의 콘크리트 강도를 확보하는 것이다. 본 연구에서는 내부영향요인과 외부영향요인에 대한 수준을 정의하고, 모두 24개의 조합에 대한 콘크리트 강도 테스트를 한 후 콘크리트 강도예측 뉴럴 네트워크 모델을 개발했다. 본 콘크리트 강도예측 뉴럴 네트워크 모델은 현장 콘크리트 타설 시 현장기온과 타설지연시간을 고려하여 콘크리트 강도를 예측하는 기능을 제공한다. 본 콘크리트 강도예측 뉴럴 네트워크 모델은 내부영향요인과 외부영향요인을 분석하고 실제 현장에서 콘크리트를 타설할 때 양생온도와 타설지연시간을 뉴럴 네트워크 입력변수로 처리하여 콘크리트 강도를 예측하는 기능을 제공한다. 시공사는 콘크리트 강도예측 결과를 활용하여 콘크리트 배합을 조정함으로써 현장타설 콘크리트 강도를 관리할 수 있을 것이다.

• 산업경영시스템학회지
• /
• 제33권4호
• /
• pp.122-129
• /
• 2010

High-performance concrete (HPC) is a new terminology used in concrete construction industry. Several studies have shown that concrete strength development is determined not only by the water-to-cement ratio but also influenced by the content of other concrete ingredients. HPC is a highly complex material, which makes modeling its behavior a very difficult task. This paper aimed at demonstrating the possibilities of adapting artificial neural network (ANN) to predict the comprresive strength of HPC. Mahalanobis Distance (MD) outlier detection method used for the purpose increase prediction ability of ANN. The detailed procedure of calculating Mahalanobis Distance (MD) is described. The effects of outlier compared with before and after artificial neural network training. MD outlier detection method successfully removed existence of outlier and improved the neural network training and prediction performance.

• Computers and Concrete
• /
• 제21권1호
• /
• pp.47-54
• /
• 2018

Artificial neural network models can be successfully used to simulate the complex behavior of many problems in civil engineering. As compared to conventional computational methods, this popular modeling technique is powerful when the relationship between system parameters is intrinsically nonlinear, or cannot be explicitly identified, as in the case of concrete behavior. In this investigation, an artificial neural network model was developed to assess the residual compressive strength of self-compacted concrete at elevated temperatures ($20-900^{\circ}C$) and various relative humidity conditions (28-99%). A total of 332 experimental datasets, collected from available literature, were used for model calibration and verification. Data used in model development incorporated concrete ingredients, filler and fiber types, and environmental conditions. Based on the feed-forward back propagation algorithm, systematic analyses were performed to improve the accuracy of prediction and determine the most appropriate network topology. Training, testing, and validation results indicated that residual compressive strength of self-compacted concrete, exposed to high temperatures and relative humidity levels, could be estimated precisely with the suggested model. As illustrated by statistical indices, the reliability between experimental and predicted results was excellent. With new ingredients and different environmental conditions, the proposed model is an efficient approach to estimate the residual compressive strength of self-compacted concrete as a substitute for sophisticated laboratory procedures.

• Computers and Concrete
• /
• 제15권2호
• /
• pp.167-181
• /
• 2015

"Mortar or concrete pneumatically projected at high velocity onto a surface" is called Shotcrete. Models that predict shotcrete design parameters (e.g. compressive strength, slump etc) from any mixing proportions of admixtures could save considerable experimentation time consumed during trial and error based procedures. Artificial Neural Network (ANN) has been widely used for similar purposes; however, such models have been rarely applied on shotcrete design. In this study 19 samples of shotcrete test panels with varying quantities of water, steel fibers and silica fume were used to determine their slump, cost and compressive strength at different ages. A number of 3-layer Back propagation Neural Network (BPNN) models of different network architectures were used to train the network using 15 samples, while 4 samples were randomly chosen to validate the model. The predicted compressive strength from linear regression lacked accuracy with $R^2$ value of 0.36. Whereas, outputs from 3-5-3 ANN architecture gave higher correlations of $R^2$ = 0.99, 0.95 and 0.98 for compressive strength, cost and slump parameters of the training data and corresponding $R^2$ values of 0.99, 0.99 and 0.90 for the validation dataset. Sensitivity analysis of output variables using ANN can unfold the nonlinear cause and effect relationship for otherwise obscure ANN model.

• 펄프종이기술
• /
• 제33권3호
• /
• pp.1-8
• /
• 2001

Paper consists of fiber network and paper properties were highly affected by fiber characteristics. Many researchers have tried to relate fiber and paper properties. Softwood and hardwood fiber's are quite different in their properties. Generally, softwood fiber's are longer and more flexible than hardwood fibers. At present, many paper mills make mixed paper with softwood and hardwood fibers except for special grade. During fracture some fiber's are broken and others are pulled out. In this paper, the number of broken and pulled out fiber's during fracture is analyzed depending on the mixing ratio of softwood and hardwood fiber's. Fiber length, curl, kink, coarseness, WRV and formation index were measured. Double-edged strength samples were prepared to observe the number of broken and pulled out fiber's. Mixed paper strength was decreased with increasing hardwood fibers ratio. During fracture, softwood fiber's were more likely broken and hardwood fibers were more likely pulled out. The strength of paper which consists of softwood fibers was determined by fiber's broken strength and that of hardwood fibers by fiber's debonding strength. Paper strength was changed depending on the fiber's bonding capability. If the fiber is longer and more flexible, the fiber network becomes stronger and stiffer.

• Structural Engineering and Mechanics
• /
• 제61권5호
• /
• pp.605-615
• /
• 2017

Shear failure of reinforced concrete (RC) beams is a major concern for structural engineers. It has been shown through various studies that the shear strength and ductility of RC beams can be improved by adding steel fibers to the concrete. An accurate model predicting the shear strength of steel fiber reinforced concrete (SFRC) beams will help SFRC to become widely used. An artificial neural network (ANN) model consisting of an input layer, a hidden layer of six neurons and an output layer was developed to predict the shear strength of SFRC slender beams without stirrups, where the input parameters are concrete compressive strength, tensile reinforcement ratio, shear span-to-depth ratio, effective depth, volume fraction of fibers, aspect ratio of fibers and fiber bond factor, and the output is an estimate of shear strength. It is shown that the model is superior to fourteen equations proposed by various researchers in predicting the shear strength of SFRC beams considered in this study and it is verified through a parametric study that the model has a good generalization capability.