• Journal of KIISE:Software and Applications
• /
• v.27 no.9
• /
• pp.942-951
• /
• 2000

일반적으로 컴퓨터를 이용한 디자인 지원 시스템은 다지이너의 행동과 같은 데이터를 통계적으로 분석하여 일련의 디자인 행위를 추출해 내는 인공지능의 접근 방식을 사용하여 왔다. 그러나 이는 많은 양의 수집된 데이터를 기반한 방법이기 때문에 계속해서 변화하는 유행에 대처할 수 없을 뿐만 아니라 개인의 취향을 반영하기도 어렵다. 이같은 문제점을 해결하기 위해 이 논문에서는 대화형 유전자 알고리즘(Interactive Genetic Algorithm : IGA)을 이용하여 명시적으로 표현하기 어려운 취향을 적절히 반영하는 디자인 지원 시스템을 제안한다. IGA는 상호작용에서 얻어지는 사용자의 평가를 적합도 함수로 사용하는 유전자 알고리즘의 하나로, 일반적인 적합도 함수를 결정하기 어려운 디자인이나 예술 등의 문제 해결에 사용될 수 있다. 한편, 몇 개의 부분적인 곡선으로 의상의 디자인을 표현하였던 기존의 방법들과는 달리 전체 디자인을 목과 몸통, 팔과 소매, 치마와 허리선의 세 가지 부분 디자인으로 나누어 표현함으로써 좀더 현실적인 여성복을 디자인할 수 있었다. 시스템의 인터페이스를 보완하기 위해 OpenGL을 이용한 3차원 모델이 사용되었으며, 사용자들을 대상으로 한 실험 결과 제안한 의상 디자인 지원 시스템이 효과적임을 알 수 있었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.280-283
• /
• 2011

인터넷 환경에서 무차별적으로 유통되는 스팸 문서로 인한 사회적 문제가 커져 가고 있는 가운데 스팸문서를 차단하기 위한 활발한 연구들이 이루어지고 있다. 이 가운데 대표적인 연구는 자질어를 이용한 기계학습 기반의 스팸 차단 기술이다. 그러나 이 방법은 미리 선택된 자질어로만 구성된 분류 모델을 사용하기 때문에 Term Spamming(단어 조작에 의한 스팸 차단 행위)에 취약하며, 스팸 차단의 성능과 학습 소요 시간이 선택된 자질어의 품질과 수에 민감하게 영향을 받는다는 문제점이 있다. 본 논문에서는 이러한 문제를 해결하기 위해 스팸 문서에서 등장하는 특수 문자의 빈도와 반복되는 단어의 특징을 이용한 스팸 탐지 방법을 제안한다. 제안 방법은 각 문서에서 등장하는 특수 문자의 비율과 최다 출현 단어의 반복 패턴을 정의하고 기계학습 알고리즘을 적용하여 스팸 분류 모델을 생성한다. 제안 방법의 성능 평가를 위해 E-mail 데이터와 블로그의 Post 데이터를 사용하여 자질어 기반의 스팸 차단 방법과 비교 실험을 진행하였다. 실험 결과 본 논문에서 제안하는 방법이 분류 정확도와 학습 소요 시간에 있어 우수한 성능을 보이는 것을 확인하였다.

• The KIPS Transactions:PartC
• /
• v.9C no.6
• /
• pp.841-846
• /
• 2002

We applies a seasonal ARIMA model to the timely forecasting in a line utilization and its confidence interval on the base of the past data of the line utilization that QoS of the network is greatly influenced by. And this paper proposes the learning algorithm of dynamic threshold in line utilization using the SARIMA model. We can find the proper dynamic threshold in timely line utilization on the various network environments and provide the confidence based on probability. Also, we have evaluated the validity of the proposed model and estimated the value of a proper threshold on real network. Network manager can overcome a shortcoming of original threshold method and maximize the performance of this algorithm.

• Journal of Korea Multimedia Society
• /
• v.7 no.3
• /
• pp.388-398
• /
• 2004

This paper focuses on the reduction method of message traffic occurred when multiple participants collaborate in the distributed virtual environment. It is referred to as filtering method of update message to minimize data traffic exchanged in the virtual environment, and it is the essential process to improve the scalability of the virtual environment. Spatial partitioning method, a popular filtering technique, divides the whole environment into smaller sub-parts in order to make it small the regions to be maintained consistently. However, it is less flexible and adaptable because the information of area of interest must be configured before simulation. In this paper, the concept of dynamic area of interest is proposed, which is highly adaptable by applying dynamic environmental elements to AOI management. It uses multiple layering and multiple consistency algorithms for dynamic management, and makes it possible to consume system resource efficiently. For performance evaluation, experiments are performed with virtual avatars, measuring message traffic. Finally, the proposed model could be applied to the AOI management systems which accommodate massive users like MMORPG, or virtual communities.

• The KIPS Transactions:PartD
• /
• v.11D no.6
• /
• pp.1295-1300
• /
• 2004

Although model checking has gained its popularity as one of the most effective approaches to the formal verification, it has to deal with the state explosion problem to be widely used in industry. In order to mitigate the problem, this paper proposes an ion technique to obtain a reduced model M' from a given original model M. Our technique Identifies the set of necessary variables for model checking and projects the state space onto them. The model M' is smaller in both size and behavior than the original model M, written M'$\leq$M. Since the result of reachability analysis with M' is preserved in M, we can do reachability analysis with model checking using M' instead of M. The abstraction technique is applied to Push Push games, and two model checkers - Cadence SMV and NuSMV - are used to solve the games. As a result, most of unsolved games with the usual model checking are solved with the ion technique. In addition, ion shows that there is much of time and space improvement. With Cadence SMV, there is 87% time improvement and 79% space one. And there is 83% time improvement and 56% space one with NuSMV.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.6
• /
• pp.179-186
• /
• 2008

In this paper we analyse the effects of Bayesian algorithm in teaming class imbalance problems and compare the performance evaluation methods. The teaming performance of the Bayesian algorithm is evaluated over the class imbalance problems generated by priori data distribution, imbalance data rate and discrimination complexity. The experimental results are calculated by the AUC(Area Under the Curve) values of both ROC(Receiver Operator Characteristic) and PR(Precision-Recall) evaluation measures and compared according to imbalance data rate and discrimination complexity. In comparison and analysis, the Bayesian algorithm suffers from the imbalance rate, as the same result in the reported researches, and the data overlapping caused by discrimination complexity is the another factor that hampers the learning performance. As the discrimination complexity and class imbalance rate of the problems increase, the learning performance of the AUC of a PR measure is much more variant than that of the AUC of a ROC measure. But the performances of both measures are similar with the low discrimination complexity and class imbalance rate of the problems. The experimental results show 4hat the AUC of a PR measure is more proper in evaluating the learning of class imbalance problem and furthermore gets the benefit in designing the optimal learning model considering a misclassification cost.

• Korean Journal of Construction Engineering and Management
• /
• v.21 no.6
• /
• pp.56-65
• /
• 2020

Urban renovation projects (reconstruction and redevelopment) have a longer licensing period than general housing projects, and many consultations with the licensing authorities require expertise. Most of the members of the union do not have basic knowledge of the maintenance business, so they have a lot of authority to promote smooth business Is entrusted to the union leader. However, contrary to the original purpose entrusted by the members, it is easy to find a case where the business is suspended because the union leader is exposed to corruption for the private interests of the union, and the members' disputes could not be resolved. In order to overcome this risk, the problem of the maintenance project was found through a questionnaire survey composed of practical experts, and a solution was presented through the KCSI evaluation model. This study mentioned the necessity of a responsible CM that can make independent business decisions without interference from the union, rather than a management-type CM limited to the cooperative's work assistance. In order to promote the construction industry's national role, it was necessary to revitalize responsible CM, so six practical alternatives were proposed.

• Convergence Security Journal
• /
• v.17 no.4
• /
• pp.11-16
• /
• 2017

MANET composed of only mobile node is applied to various environments because of its advantage which can construct network quickly in emergency situation. However, many routing vulnerabilities are exposed due to the dynamic topology and link failures by the movement of nodes. It can significantly degrade network performance. In this paper, we propose a secure routing protocol based on trust model. The domain-based network structure is used for efficient trust evaluation and management of nodes in the proposed technique. The reliability evaluation of nodes was performed by the discard ratio of control packet and data packet of the nodes. The abnormal nodes are detected by performing traffic check and inspecting of nodes on a path that generates excessive traffic in order to increase the efficiency of routing. It is confirmed through experiments of the proposed technique that data transmission is performed securely even if an attack exists on the path.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.11C
• /
• pp.10-23
• /
• 2001

It is difficult to satisfy the QoS(Quality of Service) guarantee which is required by real-time application services only with the Best-Effort(BE) service adopted in the current Internet. Therefore, worldwide research is being made on the method of QoS provisioning. Among them, the QoS guarantee mechanism using the Diffserv(Differentiated Service) was discussed in this paper. First we analyzed how the DiffServ performance was affected by traffic models. For this, we performed the research for the random, bursts, and self-similar traffic modeling method. We then designed and implemented an OPNET simulator, and performed the simulation 7d performance evaluation for diverse input parameters. Based on the results of performance evaluation, it was confirmed that QoS guarantee is possible for the EF(Expedited Forwarding) class with the DiffServ function under every environments considered and the service separation between EF and BE(Best Effort) classes is also possible. We also analyzed the performance variation and dynamic behavior of DiffServ mechanism based on the resource allocation between E? and BE classes in WFQ(Weighted Fair Queueing).

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.7 no.1
• /
• pp.39-47
• /
• 2009

The METRO-K is a model for a radiological dose assessment due to a radioactive contamination in the Korean urban environment. The model has been taken part in the Urban Remediation Working Group within the IAEA's (International Atomic Energy Agency) EMRAS (${\mathbf{\underline{E}}}nvironmental$ ${\mathbf{\underline{M}}}odeling$ for ${\mathbf{\underline{RA}}}diation$ ${\mathbf{\underline{S}}}afety$) program. The Working Croup designed for the intercomparison of radioactive contamination to be resulted from the explosion of a radiological dispersal device in a hypothetical city. This paper dealt intensively with a part among a lot of predictive results which had been performed in the EMRAS program. The predictive results of three different models (METRO-K, RESRAD-RDD, CPHR) were submitted to the Working Group. The gap of predictive results was due to the difference of mathemathical modeling approaches, parameter values, understanding of assessors. Even if final results (for example, dose rates from contamintaed surfaces which might affect to a receptor) are similar, the understanding on the contribution of contaminated surfaces showed a great difference. Judging from the authors, it is due to the lack of understanding and information on radioactive terrors as well as the social and cultural gaps which assessors have been experienced. Therefore, it can be known that the experience of assessors and their subjective judgements might be important factors to get reliable results. If the acquisition of a little additional information is possible, it was identified that the METRO-K might be a useful tool for decision support against contamination resulting from radioactive terrors by improving the existing model.