• Journal of the Society of Disaster Information
• /
• v.9 no.1
• /
• pp.11-21
• /
• 2013

This study proposed cost prediction equation model by considering duration, construction, size, actual cost with the subway construction started by the actual cost system which was introduced since 2004. Costs - scale exponent n(confidence range: 0.5 to 0.7) for cost prediction of subway construction was drawn total cost(0.713), net cost(0.77) in point of the 11 subway construction data. The cost prediction equation model of the subway construction which was presented in this study is able to effectively apply to business planning, preliminary investigation, feasibility study, basic design stage to estimate the approximate cost in the future.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.11
• /
• pp.529-536
• /
• 2015

When rendering both three-dimensional objects and photo images together, the non-photorealistic rendering results are in visual discord since the two contents have their own independent color distributions. This paper proposes a non-photorealistic rendering technique which renders both three-dimensional objects and photo images such as cartoons and sketches. The proposed technique computes the color distribution property of the photo images and reduces the number of colors of both photo images and 3D objects. NPR is performed based on the reduced colormaps and edge features. To enhance the natural scene presentation, the image region segmentation process is preferred when extracting and applying colormaps. However, the image segmentation technique needs a lot of computational operations. It takes a long time for non-photorealistic rendering for large size frames. To speed up the time-consuming segmentation procedure, we use GPGPU for the parallel computing using the GPU. As a result, we significantly improve the execution speed of the algorithm.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.1_2
• /
• pp.128-136
• /
• 2006

The stippling techniques, which represent objects with numerous points using pen and ink. The previous stippling techniques for Non-Photorsealistc Rendering(NPR) use single-colored points to represent the tone of gray image ur the material of surface. This paper presents a new stippling technique with various colored points based on the analysis of color information. By using the color information of the input image on HSV model, we define the color weight function that allows to determine automatically the number and size of points. The color jittering based on Munsell's color model can generate stippling drawings using various colored points to represent the image. Our color stippling method is expected to be used in many areas such as animation, digital art, video processing and CG tool.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.307-332
• /
• 2022

One of the most intensively conducted research areas in business application study is a bankruptcy prediction model, a representative classification problem related to loan lending, investment decision making, and profitability to financial institutions. Many research demonstrated outstanding performance for bankruptcy prediction models using artificial intelligence techniques. However, since most machine learning algorithms are "black-box," AI has been identified as a prominent research topic for providing users with an explanation. Although there are many different approaches for explanations, this study focuses on explaining a bankruptcy prediction model using a counterfactual example. Users can obtain desired output from the model by using a counterfactual-based explanation, which provides an alternative case. This study introduces a counterfactual generation technique based on a genetic algorithm (GA) that leverages both domain knowledge (i.e., causal feasibility) and feature importance from a black-box model along with other critical counterfactual variables, including proximity, distribution, and sparsity. The proposed method was evaluated quantitatively and qualitatively to measure the quality and the validity.

• Journal of the Society of Naval Architects of Korea
• /
• v.29 no.4
• /
• pp.18-26
• /
• 1992

This paper describes a design model for conceptual design of ship. Existing design models have some problems. For example, operating environment of batch versions can not reflect design procedure of real world truely and reliability of results are not high because means of performance estimation are based only on empirical formula. To improve these problems of existing design models, a new design model has been developed. The new model consists of interactive environment with databases of main engine and existing ship data. To develop user-oriented system, graphic user interface(GUI) is adapted.

• 한국게임학회지
• /
• v.6 no.1
• /
• pp.66-69
• /
• 2009

지속적인 성장을 거듭하고 있는 온라인 게임은 사회적 상호작용과 집단 경쟁 등 스탠드 얼론(stand alone) 게임에서는 느낄 수 없는 새로운 재미를 제공하고 있다. 그럼에도 불구하고 온라인 게임 플레이의 경험 중가장 핵심적인 주제인 재미에 대한 연구는 휴리스틱한(heuristic) 연구에 머물고 있다. 본 연구는 기존 연구의 한계를 극복하고, 게임플레이의 재미에 대한 과학적인 평가를 위해 MMORPG의 재미 평가 모델을 제시하고, 그 유용성을 검증하는 데 목적이 있다. 본 연구는 동기이론, 몰입(Flow) 이론, 기존의 문헌연구와 설문조사를 통하여 온라인 게임의 핵심적인 재미 요소를 도출하였다. 도출된 20여개 의 요인들을 매트릭스 분석을 통해 범주화하고, Ermi & Mayra(2005)의 게임플레이 경험 모델에 통합하였다. 다양하고 정성적인 평가기준을 체계화하기 위해 AHP(Analytical Hierarchy Process) 이론에 입각하여 감각적 재미, 도전적 재미, 상상적 재미, 사회적 상호작용의 재미의 4개 측면을 포함하는 계층분석도를 구성하였고, 게임업계 전문가들의 검토와 중요도 평가를 통해 MMORPG의 재미 평가 모델을 제안하였다. 제안된 모델에 의해 구성된 설문문항을 3개 MMORPG를 즐기고 있는 이용자 87명을 대상으로 평가한 결과, WOW, Aion, Lineage2순으로 각각 75.247점, 68.649점, 62.205점을 얻어냈다. 이러한 평가 결과는 현재 MMORPG 중에서 가장 높은 시장점유율과 매출 실적이 좋은 WOW를 가장 재미있는 게임으로 선정하였고, Aion과 Lineage2도 현재의 시장 점유율과 매출 실적과도 정확하게 일치하고 있다. 이러한 결과로 본 연구에서 제안된 MMORPG의 재미 평가 모델의 유효성이 검증되었다. 본 연구의 결과는 가장 재미있는 게임의 선정뿐만 아니라 각 게임의 재미 요소별 강약점을 분석하여, 왜 어떤 게임은 성공적이며, 다른 게임들은 그렇지 않은가에 대한 이해를 제공할 수 있다. 결론적으로 본 연구에서 제안된 MMORPG의 재미 평가 모델은 어떤 게임이 가장 재미있는 게임인지를 선정하는데 활용될 수 있으며, 궁극적으로는 보다 구체적인 재미 요소별 분석을 가능하게 하여 보다 재미있는 온라인 게임을 개발하는데 기여할 것이다. 그러나 다른 장르까지 확장하여 활용하기 위해서는 후속 연구가 뒷받침되어야 한다.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.55-71
• /
• 2013

The prediction model is the main factor affecting the performance of a knowledge-based system for bankruptcy prediction. Earlier studies on prediction modeling have focused on the building of a single best model using statistical and artificial intelligence techniques. However, since the mid-1980s, integration of multiple techniques (hybrid techniques) and, by extension, combinations of the outputs of several models (ensemble techniques) have, according to the experimental results, generally outperformed individual models. An ensemble is a technique that constructs a set of multiple models, combines their outputs, and produces one final prediction. The way in which the outputs of ensemble members are combined is one of the important issues affecting prediction accuracy. A variety of combination schemes have been proposed in order to improve prediction performance in ensembles. Each combination scheme has advantages and limitations, and can be influenced by domain and circumstance. Accordingly, decisions on the most appropriate combination scheme in a given domain and contingency are very difficult. This paper proposes a confidence-based selection approach as part of an ensemble bankruptcy-prediction scheme that can measure unified confidence, even if ensemble members produce different types of continuous-valued outputs. The present experimental results show that when varying the number of models to combine, according to the creation type of ensemble members, the proposed combination method offers the best performance in the ensemble having the largest number of models, even when compared with the methods most often employed in bankruptcy prediction.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.6D
• /
• pp.829-837
• /
• 2011

Construction cost estimation in planning phase which calculates the cost for performing construction tasks is used for various ways. Meanwhile, in the case of road construction, the existing cost estimating method in early phase based on numerical mean value of the past is not accurate to be used. This paper propose neural network model for estimating road construction cost in planning phase to solve the limit of current cost estimating method. The model was designed using past road construction bidding records, and variables of model were optimized through trial and error. The estimation result of the model was compared with regression analysis and government's standard and it was verified that the model is better in accuracy. It is expected that the proposed model will be used for road cost estimation in planning phase.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.163-166
• /
• 2000

본 논문은 CD-ROM Title 컨텐츠의 검색과 제어를 위한 음성인식 시스템 개발을 목적으로 한다. 인식명령어는 학교 졸업앨범 또는 회사홍보용 CD-ROM Title컨텐츠의 타이틀(상품안내, 회사소개, 업무실적 등)로 구성된다. 모델은 지속시간을 고려한 DMS 모델, 인식은 OSDP를 사용하였다.

• Computational Structural Engineering
• /
• v.5 no.4
• /
• pp.29-40
• /
• 1992

본 기사는 진동방지 및 제어기술의 중요성을 인식하고 이에 수반되는 동역학적 이론 및 기술에 대한 최근 연구 실적과 동향, 그리고 특히 건물에 적용예가 많은 일본의 진동방지 및 제어 장치들을 중심으로 실제 상업제품으로 완성된 것들의 특성을 조사하며, 또한 이의 구조해석을 위해 각종 형태별 진동방지 장치의 해석모델 및 경험론적으로 제시하고 있는 설계지침에 대하여 알아보고자 한다.