• Journal of Intelligence and Information Systems
• /
• v.21 no.4
• /
• pp.17-35
• /
• 2015

Demand forecasting is the activity of estimating the quantity of a product or service that consumers will purchase for a certain period of time. Developing precise forecasting models are considered important since corporates can make strategic decisions on new markets based on future demand estimated by the models. Many studies have developed market growth curve models, such as Bass, Logistic, Gompertz models, which estimate future demand when a market is in its early stage. Among the models, Bass model, which explains the demand from two types of adopters, innovators and imitators, has been widely used in forecasting. Such models require sufficient demand observations to ensure qualified results. In the beginning of a new market, however, observations are not sufficient for the models to precisely estimate the market's future demand. For this reason, as an alternative, demands guessed from those of most adjacent markets are often used as references in such cases. Reference markets can be those whose products are developed with the same categorical technologies. A market's demand may be expected to have the similar pattern with that of a reference market in case the adoption pattern of a product in the market is determined mainly by the technology related to the product. However, such processes may not always ensure pleasing results because the similarity between markets depends on intuition and/or experience. There are two major drawbacks that human experts cannot effectively handle in this approach. One is the abundance of candidate reference markets to consider, and the other is the difficulty in calculating the similarity between markets. First, there can be too many markets to consider in selecting reference markets. Mostly, markets in the same category in an industrial hierarchy can be reference markets because they are usually based on the similar technologies. However, markets can be classified into different categories even if they are based on the same generic technologies. Therefore, markets in other categories also need to be considered as potential candidates. Next, even domain experts cannot consistently calculate the similarity between markets with their own qualitative standards. The inconsistency implies missing adjacent reference markets, which may lead to the imprecise estimation of future demand. Even though there are no missing reference markets, the new market's parameters can be hardly estimated from the reference markets without quantitative standards. For this reason, this study proposes a case-based expert system that helps experts overcome the drawbacks in discovering referential markets. First, this study proposes the use of Euclidean distance measure to calculate the similarity between markets. Based on their similarities, markets are grouped into clusters. Then, missing markets with the characteristics of the cluster are searched for. Potential candidate reference markets are extracted and recommended to users. After the iteration of these steps, definite reference markets are determined according to the user's selection among those candidates. Then, finally, the new market's parameters are estimated from the reference markets. For this procedure, two techniques are used in the model. One is clustering data mining technique, and the other content-based filtering of recommender systems. The proposed system implemented with those techniques can determine the most adjacent markets based on whether a user accepts candidate markets. Experiments were conducted to validate the usefulness of the system with five ICT experts involved. In the experiments, the experts were given the list of 16 ICT markets whose parameters to be estimated. For each of the markets, the experts estimated its parameters of growth curve models with intuition at first, and then with the system. The comparison of the experiments results show that the estimated parameters are closer when they use the system in comparison with the results when they guessed them without the system.

• Journal of Intelligence and Information Systems
• /
• v.27 no.1
• /
• pp.23-46
• /
• 2021

Collaborative filtering, which is often used in personalization recommendations, is recognized as a very useful technique to find similar customers and recommend products to them based on their purchase history. However, the traditional collaborative filtering technique has raised the question of having difficulty calculating the similarity for new customers or products due to the method of calculating similaritiesbased on direct connections and common features among customers. For this reason, a hybrid technique was designed to use content-based filtering techniques together. On the one hand, efforts have been made to solve these problems by applying the structural characteristics of social networks. This applies a method of indirectly calculating similarities through their similar customers placed between them. This means creating a customer's network based on purchasing data and calculating the similarity between the two based on the features of the network that indirectly connects the two customers within this network. Such similarity can be used as a measure to predict whether the target customer accepts recommendations. The centrality metrics of networks can be utilized for the calculation of these similarities. Different centrality metrics have important implications in that they may have different effects on recommended performance. In this study, furthermore, the effect of these centrality metrics on the performance of recommendation may vary depending on recommender algorithms. In addition, recommendation techniques using network analysis can be expected to contribute to increasing recommendation performance even if they apply not only to new customers or products but also to entire customers or products. By considering a customer's purchase of an item as a link generated between the customer and the item on the network, the prediction of user acceptance of recommendation is solved as a prediction of whether a new link will be created between them. As the classification models fit the purpose of solving the binary problem of whether the link is engaged or not, decision tree, k-nearest neighbors (KNN), logistic regression, artificial neural network, and support vector machine (SVM) are selected in the research. The data for performance evaluation used order data collected from an online shopping mall over four years and two months. Among them, the previous three years and eight months constitute social networks composed of and the experiment was conducted by organizing the data collected into the social network. The next four months' records were used to train and evaluate recommender models. Experiments with the centrality metrics applied to each model show that the recommendation acceptance rates of the centrality metrics are different for each algorithm at a meaningful level. In this work, we analyzed only four commonly used centrality metrics: degree centrality, betweenness centrality, closeness centrality, and eigenvector centrality. Eigenvector centrality records the lowest performance in all models except support vector machines. Closeness centrality and betweenness centrality show similar performance across all models. Degree centrality ranking moderate across overall models while betweenness centrality always ranking higher than degree centrality. Finally, closeness centrality is characterized by distinct differences in performance according to the model. It ranks first in logistic regression, artificial neural network, and decision tree withnumerically high performance. However, it only records very low rankings in support vector machine and K-neighborhood with low-performance levels. As the experiment results reveal, in a classification model, network centrality metrics over a subnetwork that connects the two nodes can effectively predict the connectivity between two nodes in a social network. Furthermore, each metric has a different performance depending on the classification model type. This result implies that choosing appropriate metrics for each algorithm can lead to achieving higher recommendation performance. In general, betweenness centrality can guarantee a high level of performance in any model. It would be possible to consider the introduction of proximity centrality to obtain higher performance for certain models.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2011.05a
• /
• pp.84-84
• /
• 2011

저수지에서 수체의 거동정보는 저수지관리를 위해 매우 중요하며, 이를 수리 및 수질모형에 적용하여 다양한 예측에 활용할 수 있는 기본적인 정보이다. 그러나 저수지 수체의 흐름은 매우 느리고 조사시기에 따라 혹은 수심에 따라 영향을 받으며, 바람 등 외부요인에도 영향을 받게 됨으로 정확한 측정에 많은 어려운 문제가 있다. 따라서 보다 정확한 측정을 위해서는 최신의 기술이 적용되어야 한다. 현장조사에 적용한 저수지 수체거동조사장비(drifter)는 수체의 유동을 관측하는 장치로 GPS 및 Drogue를 장착한 장치가 저수지 수체의 흐름에 따라 이동하면서 위치정보를 무선통신으로 실시간 전송할 수 있도록 만들어진 장치이다. 수체흐름 측정장치는 크게 수체거동정보 생산부이 시스템과 수집서버 및 데이터베이스 서버로 구성되어 있다. 현장 조사시에는 부이에 장착되어 있는 GPS를 통해 현재의 위치가 매번 정해진 시간 간격마다 본체 내부의 메모리에 저장되며, 측정자가 설정한 시간간격으로 위치정보를 수신국으로 전송하도록 구성되어 있다. 수체이동부이의 데이터 수신은 CDMA를 통해 송신된 메일 데이터를 자체적으로 수집하여 데이터형태로 변환한 뒤 실시간으로 표출하고 저장되며, 최대 10개의 부이를 동시에 추적 및 모니터링할 수 있게 구성되어 있다. 본 연구는 용담댐저수지에서 평갈수기 및 풍수기로 구분하여 수체거동을 조사하였다. 평갈수기 조사는 2010년 4월부터 6월까지 총 3차례에 걸쳐 실시하였으며, 풍수기 조사는 8월에 3차례에 걸쳐 실시하였다. 수집된 자료에 의하면 평갈수기 drifter의 평균 속도는 2.25 cm/sec, 최고 속도는 3.46 cm/sec, 최저 속도는 1.15 cm/sec로 나타났으며, 풍수기 조사에서는 평균 속도 2.0 cm/sec, 최고 속도는 2.5 cm/sec, 최저 속도는 1.29 cm/sec로 조사되어 평갈수기와 풍수기간 저수지 수체의 이동속도는 유사한 것으로 평가되었다. 그러나 수기별 조사는 보다 더 많은 정보가 필요하며, 수심에 따른 차이도 있을 것으로 판단되어 좀더 다양한 조사가 수행되어야 보다 정확한 결과를 도출할수 있을 것으로 판단된다.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.11 no.2
• /
• pp.107-115
• /
• 1999

In order to develop a convenient method for the estimation of transport distance of settling stones in quiescent water or flowing water, introduced was the simple but relatively accurate equation of drag coefficient. The equation of drag coefficient introduced was confirmed to give relatively accurate evaluation for the drag force of smooth-surface sphere, and the effects of surface roughness and shape can be considered by adjusting empirical parameters. A theoretical equation has been developed for the settling velocity or settling distance of smooth-surface sphere in quiescent fluid, and the computation results have been obtained by adjusting the empirical parameter for the settling distance of stone in quiescent water. The 2nd order ordinary differential equation has been developed for the case of settling stones in flowing fluid, and a numerical model has been developed by using Runge-Kutta method for its solution. A number of cases have been tested by adjusting the empirical parameter.

• Journal of Korea Water Resources Association
• /
• v.33 no.5
• /
• pp.581-592
• /
• 2000

Turbulence structure and suspended sediment transport capacity in vegetated open-channel flows are investigated numerically in the present paper. The $\textsc{k}-\;\varepsilon$ model is employed for the turbulence closure. Mean velocity and turbulence characteristics including turbulence intensity, Reynolds stress, and production and dissipation of turbulence kinetic energy are evaluated and compared with measurement data available in the literature. The numerical results show that mean velocity is diminished due to the drag provided by vegetation, which results in the reduction of turbulence intensity and Reynolds stress. For submerged vegetation, the shear at the top of vegetation dominates turbulence production, and the turbulence production within vegetation is characterized by wakes. For emergent condition, it is observed that the turbulence generation is dominated by wakes within vegetation. In general, simulated profiles compares favorably to measured data. Computed values of eddy viscosity are used to solve the conservation equation for suspended sediment, yielding sediment concentration more uniform over the depth compared with the one in the plain channel. The simulation reveals that the suspended load decreases as the vegetation density increases and the suspended load increases as the particle diameter decreases for the same vegetation density.

• Journal of Korea Water Resources Association
• /
• v.47 no.10
• /
• pp.907-919
• /
• 2014

This study presents scour processes and its characteristics around the pile groups using the large eddy simulation (LES) coupled with sediment transport and morphodynamic models. The scour and deposition around pile groups were significantly influenced by the pile interval. In case the non-dimensional pile interval was less than 3.75, the local scours as well as the contraction scour were observed around the pile group. On the other hand, in case the non-dimensional pile interval was more than 3.75, the contraction scour disappeared and only local scours were developed at individual piles. Change in the scour depth at piles located in the upstream was similar with the case of single pile, but the scour depth around piles located in the downstream was lower and showed a significantly different tendency due to the presence of piles in the upstream. The non-dimensional maximum scour depth around the pile group decreased as the pile interval increased.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2012.05a
• /
• pp.745-749
• /
• 2012

국내 주요하천은 지속적인 산업화와 난개발로 인해 생태계파괴 및 수변생물의 서식처 환경 악화로 하천 생태계에 많은 악영향을 받고 있다. 그러나 1990년대 이후 국내에서는 하천의 기능과 생물의 다양성, 하천환경 및 생태학적인 가치와 중요성에 대한 인식이 매우 커짐에 따라 하천의 생태적 기능을 매우 중요시 하고 있으며, 하천의 난개발로 인한 피해를 복원하기 위해 활발한 연구가 진행되고 있다. 대표적인 연구로 생태계 건전화 개념을 도입하여 담수성 어류 서식처 제공 및 이동에 필요한 유량을 산정한 한국 수자원공사(1995)의 연구가 있으며, 김규호 등(1996a, 1996b)은 물고기 서식처 환경 중 특히 수심과 유속 등 수리조건을 유지하기 위한 최소유량 산정 방법을 제시하였다. 또한 노경범(2011)은 섬진강의 하천환경 회복을 위한 연구대상 구간에서의 대표어종을 선정하여 서식처 특성 파악을 위해 하천 특성을 연구하였다. 이와 같이 현재 국내에서도 하천의 기능과 생태학적 기능을 위한 노력과 연구가 진행되고 있다. 그러나 생태학적 서식처 연구에서는 아직까진 미진한 부분이 많이 있다. 그 예로 보호종이나 멸종위기어종과 같은 생물의 서식처 확보를 위한 연구가 아직까지는 많은 노력과 연구가 필요한 상태이다. 본 연구에서는 환경부에서 지정한 멸종위기 1급 어종인 퉁사리를 대상으로 서식환경 특성 연구를 진행하였으며, 퉁사리의 생태학적 서식특성과 현재 지석천 상류 유역에서 관찰되고 있는 서식구간을 중심으로 MD-SWMS (Multi-Dimensional, Surface Water Modeling System) 모형을 이용하여 수리특성 분석을 수행하였다. 이를 위해 하상재료 입도분석을 실시하였으며, 그 결과 입도가 큰 굵은모래 및 잔자갈, 굵은자갈로 구성되어 있음을 알 수 있었다. 또한, 수리학적 특성분석결과 서식구간 내에서는 비교적 빠른 유속이 나타났다. 이러한 퉁사리의 서식환경의 특성 분석으로 서식구간 내 입도가 큰 하상재료로 구성되어 있으며, 퇴적구간이 생성되지 않을 정도의 유사이송량과 유속이 필요할 것으로 분석되었다. 향후 퉁사리의 장기적인 서식환경 조성과 보존을 위해 대상구간의 유사이송의 연구와 실측 및 수변환경 모니터링을 통한 다양한 연구가 진행되어야 할 것으로 판단된다.

• Journal of Korea Game Society
• /
• v.10 no.4
• /
• pp.23-34
• /
• 2010

The current interests in e-sports is being extended to the fields of education these days. Professional game players, so called as 'Pro-Gamers', therefore, should be recognized as human resource for education, and the theoretical foundation for them needs to be established. This study examines informal learning styles, motivation, and interactions among professional game players in South Korea. The aim of this grounded theory study is to discover the trajectory of professional game players' experiences and explain what properties and interactions they are facing depending on the stage of the trajectory. This study conceptualizes educational meaning within and across the society of StarCraft Pro-Gamers, providing suggestions for the management of human resource using models constructed. Data was analyzed by interviewing 1 consultant, 2 directors and 9 Pro-Gamers. By analyzing the data, this study explored what learning strategies Pro-Gamers construct and apply in their trajectory as Pro-Gamers. It includes how they organize learning, how they formulate their motivation and goals, how they cooperate and compete, what curricula they adapt, how they become one of the ace players overcoming their slump, and how informal education works in practice in the interaction among members of a StarCraft Pro-Gamer team. Finally, in this paper the stage theory was presented. It is argued that when the stage of the players shifts (Stage Shifting). It also brings changes to proficiency properties, emotional properties, interactional properties and educational properties related to each stage. Stages are categorized by five levels: Enjoying, Struggling, Achieving, Slumping, and Recovering. Although each stage has its own properties, the stages are grouped by two main properties, one of which is a Communicative Stage and the other is a Practicing Stage.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2012.05a
• /
• pp.535-535
• /
• 2012

하천 환경의 변화는 자연적으로 일어나기도 하지만, 우리나라 경우 대부분 하천 정비, 골재 채취, 수중보와 하구둑 등 하천시설물의 건설, 그리고 댐 및 교량건설 등 인위적인 요인에 의한 변화가 지배적이다 이렇게 환경이 변화하면 하천의 평형 상태는 파괴되며 하천의 평형 상태를 복원하는 과정에서 하천의 침식 또는 퇴적이 일어나며 이러한 과정의 총체적인 결과로서 하상변동이 일어나게 된다. 하상변동은 단기적인 면에서는 하천에서의 취수, 배수, 주운동 하천관리에 직접적인 영향을 주며, 장기적인 면에서는 하천시설물의 안정, 홍수위 및 지하수위 변화, 홍수터와 같은 하천부지의 변화 등 하천 및 유역 관리에 광범위한 영향을 주고 있다 하천의 유황 및 하상재료의 인위적인 변화에 의한 장기적인 하상변동 효과를 예측하고 분석하는 것은 하천계획 및 관리 면에서 매우 중요하다. 또한 하천 정비사업 등에 의한 영향을 제대로 평가하기 위해서는 비교적 단기간의 홍수 또는 호우 사상에 대한 단기적인 하상변동 효과를 정확하게 예측하는 것은 필수적이다. 외국에서는 하상변동 예측의 필요성을 일찍이 인식하여 다수의 하상변동 예측모형이 개발되어 하천 실무에 사용되고 있으며, 국내에서도 하천 흐름의 등수 역학적 해석을 위해 여러 가지 수치 기법들에 대한 연구가 진행되고 발전되어져 왔다. 현재 국내에서는 측량 자료이용과 모형적용의 용이성을 이유로 1차원 점변 부정류 해석프로그램인 HEC-RAS 모형을 많이 사용하고 있으며 대부분의 하천 정비 기본계획 수립에 있어서도 1차원 해석 모형을 적용하고 있는 실정이다. 국내에 서 수행된 하상변동 예측에 관한 연구들은 대부분 1차원 모형이므로 하천의 사행의 진행이나 유사의 횡방향 분포 등은 고려할 수 없다. 또한 하상변동 계산 시 이동상 부분의 전체가 균일하게 상승 또는 하향하는 것으로 가정하기 때문에 흐름이 급변하는 데 적용하는 것은 적합하지 않다. 따라서 본 연구에서는 4대강살리기 사업이 진행중인 낙동강유역 구미보지점을 대상으로 2차원 흐름 및 하상변동 수치모형인 CCHE2D 모형을 적용하여 50년, 100년, 200년 빈도별로 모의를 실시, 보설치 전 후의 하상변동을 비교 분석 하였다. 모의 결과 보설치 후의 경우 보 상류단은 전반적으로 퇴적의 양상을 보였으며, 보 하류단의 만곡부의 경우 홍수량이 증가함에 따라 유속 및 소류력이 비슷한 패턴으로 증가하여 침식이 관찰되었다. 특히 보 직하류의 경우 수문을 기준으로 다량의 침식이 있음을 보였으며, 침식이 계속 진행된다면 보유실과 같은 심각한 결과를 초래할 수 있기 때문에 침식을 방지 할 수 있는 다양한 장치가 마련되어야 할 것으로 판단된다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.8
• /
• pp.579-585
• /
• 2019

Increasing the detection probability of underwater targets necessitates securing the towing stability of the active towed SONAR. In this paper, to confirm the effects of tail wing fin on towing attitude and towing stability, two scale model experiments and one sea trials were conducted and the results were analyzed. The scale model tests measured the towing behavior of each of the tail fin shapes according to towing speed in a towing tank. The shape of the tail fin used in the scale model test was tested with an I-type tail fine and four Y-type tail fins, totaling five tail fins of the two kinds. The first scale model test confirmed that the Y-type tail fin was superior to the I-type tail fin in towing attitude and towing stability. The second scale model test confirmed the characteristics of the vertical tail fin height increase and the lower horizontal tail fin inclination angle application shape based on the Y-type tail fin. The shape of the application of the lower horizontal tail fin inclination angle showed the best performance. In order to verify the results of the scale model test, a full size model was constructed, sea trials were performed, and the towing attitude was measured. The results were similar to those of the scale model test.