• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권10호
• /
• pp.5132-5148
• /
• 2017

Cyber attacks are evolving commensurate with recent developments in information security technology. Intrusion detection systems collect various types of data from computers and networks to detect security threats and analyze the attack information. The large amount of data examined make the large number of computations and low detection rates problematic. Feature selection is expected to improve the classification performance and provide faster and more cost-effective results. Despite the various feature selection studies conducted for intrusion detection systems, it is difficult to automate feature selection because it is based on the knowledge of security experts. This paper proposes a feature selection technique to overcome the performance problems of intrusion detection systems. Focusing on feature selection, the first phase of the proposed system aims at constructing a feature subset using a sequential forward floating search (SFFS) to downsize the dimension of the variables. The second phase constructs a classification model with the selected feature subset using a random forest classifier (RFC) and evaluates the classification accuracy. Experiments were conducted with the NSL-KDD dataset using SFFS-RF, and the results indicated that feature selection techniques are a necessary preprocessing step to improve the overall system performance in systems that handle large datasets. They also verified that SFFS-RF could be used for data classification. In conclusion, SFFS-RF could be the key to improving the classification model performance in machine learning.

• Journal of information and communication convergence engineering
• /
• 제13권2호
• /
• pp.97-104
• /
• 2015

In this paper, we propose a data envelopment analysis (DEA) and analytic hierarchy process (AHP) integrated model to improve the selection process in the acquisition of a weapon system which is the key component to the success of the project. In particular, we applied DEA in the first stage to choose a frontier group among the candidates in the selection process of the next-generation fighter system (the 3rd FX) in Korea. Then, by using the Delphi technique, we surveyed military experts and applied AHP to determine the best choice among the candidates. The results of the study match the actual decision made by the Korean government in the weapon system acquisition. The results of the proposed DEA-AHP integrated method in the selection of the next-generation fighter systems in Korea demonstrate the usefulness of the method. In this paper, we also discuss the future implications of the proposed model.

• 한국IT서비스학회지
• /
• 제5권3호
• /
• pp.187-201
• /
• 2006

Nowadays, many organizations more increasingly show their interests in developing informations systems through not only in-house development but outsourcing. Selecting a proper information system developer, however, is not easy task partly due to the absence of evaluation criteria pertinent to explain the pros and cons of information system developers considered. Further, much care should be taken of choosing an appropriate decision method applicable to semi-structured or strategical decision making problems such as selection of information system developer even though evaluation criteria are well provided. The purpose of this paper is to provide for the selection process, ranging from identification of problem structure to solution method, of information system developer with the use of Analytic Hierarchy Process(AHP).

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2001년도 추계학술대회 논문집 전력기술부문
• /
• pp.157-160
• /
• 2001

The selection of voltage is one of the most significant factors in the design of power system for industrial plant. It is a major factor in determining over-all system cost, flexibility, and ease of future expansion. This paper presents the study results on the selection of economic voltage for low voltage power distribution system.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2007년도 한국지능정보시스템학회
• /
• pp.351-356
• /
• 2007

Factory location selection is very important to the success of operation of the whole supply chain, but few effective solutions exist to deliver a good result, motivated by this, this paper tries to introduce a new factory location selection methodology by employing the artificial neural networks technology. First, we reviewed previous research related to factory location selection problems, and then developed a (neural network-based factory selection model) NNFSM which adopted back-propagation neural network theory, next, we developed computer program using C++ to demonstrate our proposed model. then we did case study by choosing a Korean steelmaking company P to show how our proposed model works,. Finnaly, we concluded by highlighting the key contributions of this paper and pointing out the limitations and future research directions of this paper. Compared to other traditional factory location selection methods, our proposed model is time-saving; more efficient.and can produce a much better result.

• 한국육종학회지
• /
• 제40권1호
• /
• pp.48-53
• /
• 2008

본 연구에서는 벼멸구 저항성 개통 육성과정 중에 수행한 PS와 MAS system간의 선발 효율을 정확성, 소요시간, 소요비용 등의 요인으로 비교 분석함으로써 MAS system의 선발 효율을 제시하고, 이를 이용하여 효과적인 MAS system을 구축하고 실용화하기 위한 방안을 제시하였다. DNA marker를 이용하여 벼멸구 저항성 개체를 선발하고 MAS 체제를 확립하기 위하여 '삼강/낙동' 조합의 $F_2$집단, RIL($F_6$), DH집단, 여교잡집단($BC_6F_5$)을 대상으로 PS와 marker 검정을 병행하여 두 검정 방법 간에 각 잡종집단 및 세대별 저항성과 감수성 계통(개체)의 비율을 비교한 바 95%이상 일치하였다. MAS 체제와 PS간의 선발효율을 비교한 바 MAS는 PS에 비해 약 32%의 비용이 절감되었고, 검정에 소요되는 기간도 기존의 PS에서는 30일인데 비해 MAS에서는 7일로 크게 단축되었다. 이 결과를 바탕으로 MAS에 의한 벼멸구 저항성 계통 선발 체계를 확립 할 수 있었다.

• 대한전자공학회논문지TC
• /
• 제47권3호
• /
• pp.22-30
• /
• 2010

본 논문은 AMC(Adaptive Modulation and Coding)와 MIMO(Multiple Input Multiple Output)를 결합하여 전송률 및 전송 신뢰도 향상을 가져오는 통신 시스템을 구현한다. 또한 Precoding과 Antenna Subset Selection을 효율적으로 적용하고 MIMO 선택 기법을 결합하여, 최종적으로 AMC와 MIMO 선택 기법이 결합된 통신 시스템을 설계하고 성능을 분석한다. 모의 실험 환경은 안테나 간 상관성이 존재하지 않는 주파수비 선택적 레일리 페이딩 채널을 고려하였으며, 확산인자는 16을 적용하였다. 그 외의 여러 모의 실험 환경은 HSDPA(High Speed Downlink Packet Access) 표준에 근거하여 구성하도록 노력하였다. 본 논문에서 제안한 "AMC와 MIMO 선택 기볍이 결합된 시스템"은 기존의 "AMC와 각 MIMO의 결합 시스템들" 보다 높은 보여주었으며, 열악한 채널 환경에서도 안정적인 전송률을 확보해 주었다. 제안된 시스템은 약 8dB에서 최대 전송률을 나타내었으며, 제안된 시스템과 동일한 최대 전송률올 갖눈 기종의 "AMC와 D-STTD $4{\times}2$ 결합 시스템"과 비교하였을 때 약 6dB 정도 먼저 최대 전송률을 나타냈다. 또한 최대 전송률에 이르기 전까지 거의 모든 SNR(Signal to Noise Ratio)서 기존의 시스템보다 약 2배 정도 높은 전송률을 보였다. 구체적으로 SNR이 2dB인 지점에서 기존의 시스템은 약 2.5Mbps의 전송률을 나타냈으며, 제안된 시스템은 그 2배가 넘는 약 6.4MBps의 전송률을 나타냈다. 또한 SNR이 2dB인 지점에서는 각각 약 7.5Mbps와 15.3Mbps의 전송률을 나타내어 역시 2배에 가까운 차이가 나는 것을 확인할 수 있었다. 제안된 시스템은 AMC 기법을 사용하는 주 목적인 전송률의 향상에 크게 기여하였으며, 특히 평균 전송률의 향상에 효과적임을 확인하였다.

• 동의생리병리학회지
• /
• 제28권4호
• /
• pp.440-445
• /
• 2014

Korean medical system is unique system that has two medical system, Western medical institution and Korean medical institution. In this environment, patients who use each medical institution have different selection factors. The study explores the selection factors' difference of korean/western medical institutions. The empirical analysis of the surveyed data produced the following outcomes. The result of factor analysis, four factors were extracted. That was Human services, Costs and Physical Environment, Prestige and reputation, Public relations and reliability. Overall, the four selection factor importance scores of Korean medical institution were higher than western medical institution's. These findings show that there is a difference between korean and western medical institutions in terms of selection factors. After this study, More study about medical management and healthcare policy including korean medical characteristics is needed.

• 국제학술발표논문집
• /
• The 2th International Conference on Construction Engineering and Project Management
• /
• pp.662-671
• /
• 2007

Since variety of construction projects with their individual specifications could be handled through different procurement systems, selection of the most appropriate project delivery system is a vital step towards more efficient project execution. The appropriate selection of project delivery system may also ensure more competent management of the project. Its impacts are not only limited to the first stages of the project, as it could also influence pre-construction, construction and operational phases of the project. Among different approaches exerted for this purpose, none has taken uncertainty into account, despite the fact that during first stages of the project most of the selection factors are still uncertain and not clearly defined. This paper, hence, aims to provide a fuzzy insight into the project delivery system selection. Through this approach more tangible model of the evaluation process may be presented. Proposed fuzzy method is indeed a multi criteria decision making model, based on the group of criteria, assigned for the evaluation procedure. A case study is also conducted, based on the opinion of an invented group of the experts.

• 한국산업정보학회논문지
• /
• 제9권3호
• /
• pp.11-18
• /
• 2004

웹 기반 학습 시스템에서 평가를 위한 문제출제 방식에 대해 많은 연구가 이루어지고 있다. 이러한 원격 교육에서 출제되는 문제들은 고정 출제나 무작위 출제 방식 또는 난이도에 따른 자동 출제 방식을 사용하고 있다. 본 논문에서는 산업 기사 시험을 대비하는 학생들을 위한 웹 기반 학습 시스템을 설계함에 있어 기사 시험에 맞는 새로운 문제 출제 알고리즘을 제시한다. 일반적으로 기사 시험은 평균 점수에 맞는 난이도별 문제 출제와 함께 전체 학습 범위에서 골고루 시험 문제가 출제되어야 하는 특징이 있다. 따라서 제시된 알고리즘에서는 자동 문제 출제를 함에 있어 난이도뿐만이 아니라 전체 학습 범위에 대한 분포도 고려하여 문제를 골고루 출제한다. 이는 난이도에 의한 자동 출제 방식에 비해 기사 시험을 준비하는 학습자에게 보다 효과적인 학습 진단 방법을 제공할 수 있다.