• 한국멀티미디어학회논문지
• /
• 제21권5호
• /
• pp.617-625
• /
• 2018

Phishing website has become a crucial concern in cyber security applications. It is performed by fraudulently deceiving users with the aim of obtaining their sensitive information such as bank account information, credit card, username, and password. The threat has led to huge losses to online retailers, e-business platform, financial institutions, and to name but a few. One way to build anti-phishing detection mechanism is to construct classification algorithm based on machine learning techniques. The objective of this paper is to compare different classifier ensemble approaches, i.e. random forest, rotation forest, gradient boosted machine, and extreme gradient boosting against single classifiers, i.e. decision tree, classification and regression tree, and credal decision tree in the case of website phishing. Area under ROC curve (AUC) is employed as a performance metric, whilst statistical tests are used as baseline indicator of significance evaluation among classifiers. The paper contributes the existing literature on making a benchmark of classifier ensembles for web phishing detection.

• Industrial Engineering and Management Systems
• /
• 제6권1호
• /
• pp.83-93
• /
• 2007

This paper gives an attempt to build a decision support tool linked with a simulation software called ARENA for evaluating and comparing the performance of the push and pull material driven strategies operating in the flow shop environment with a bottleneck resource as the shop's constraint. To be fair for such evaluation, the comparison must be made fairly under the optimal setting of both systems' operating parameters. In this study, an optimal-seeking heuristic algorithm, Genetic Algorithm (GA), is employed to suggest a systems' best design based on the economic consideration, which is the profit generated from the system. Results from the study have revealed interesting outcomes, letting us know the strength and weakness of the push and pull mechanisms as well as the effect of each operating parameter to the overall system's financial performance.

• Journal of Multimedia Information System
• /
• 제5권2호
• /
• pp.99-104
• /
• 2018

Phishing website has become a crucial concern in cyber security applications. It is performed by fraudulently deceiving users with the aim of obtaining their sensitive information such as bank account information, credit card, username, and password. The threat has led to huge losses to online retailers, e-business platform, financial institutions, and to name but a few. One way to build anti-phishing detection mechanism is to construct classification algorithm based on machine learning techniques. The objective of this paper is to compare different classifier ensemble approaches, i.e. random forest, rotation forest, gradient boosted machine, and extreme gradient boosting against single classifiers, i.e. decision tree, classification and regression tree, and credal decision tree in the case of website phishing. Area under ROC curve (AUC) is employed as a performance metric, whilst statistical tests are used as baseline indicator of significance evaluation among classifiers. The paper contributes the existing literature on making a benchmark of classifier ensembles for web phishing detection.

• 한국비블리아학회지
• /
• 제4권1호
• /
• pp.49-83
• /
• 1980

Rapid expansion has taken place in development of cooperative arrangements among libraries, in computerization, mechanization, and centralization of library services; in sizes of collections; and in the variety of services offered by libraries. These increasing complexities of library organizational arrangements and expansions in activities and services make it all the more important for libraries to define their objectives clearly and to have methods for measuring the level of attainment of these objectives. Libraries, as all other institutions and organizations, are faced with the economic problem of allocating their limited resources in such a manner as to generate maximum benefits and calculating the costs of a library. Furthermore, they should be able to measure their performance or degree of achievement of objectives. In order to it, it is essential to set a standard and review the time and motion study. This study is an attempt to build a general standard applicable to Korean university libraries to provide a persuasive basis to university library administrators in their work management: The usefulness of this study are given below. (1) It helps to balance available resources with estimated workload. (2) It helps in managing a library more efficiency and more economically (3) It helps in objective evaluation of individual employee performance and in evaluation of the organization as a whole. (4) It helps the librarian plan for financial and personnel needs on the basis of sound production figures.

• 경영정보학연구
• /
• 제21권2호
• /
• pp.139-155
• /
• 2019

최근 국내 전자상거래시장은 산업전반에 전자상거래의 확산을 통해 괄목할 만한 성장을 이루고 있다. 그럼에도 우리 중소기업의 전자상거래 활용 비율은 매우 저조한 것으로 나타나고 있다. 이렇게 중소기업의 B2B 전자상거래시장 참여율이 저조한 이유는 다양한 원인이 있을 수 있으나, 중소기업이 참여하는 B2B 전자상거래시장의 특성을 고려한 실증적 성과 측정 및 평가의 부재도 주요한 원인으로 사료된다. 따라서 본 연구는 B2B 전자상거래 참여기업이라면 대부분 활용경험이 있는 공적신용보증기관이 e-Marketplace와 연계하여 제공하고 있는 전자상거래 보증 이용기업을 대상으로 B2B 전자상거래 활용효과를 분석하고자 하였다. 이를 위해 선행 연구를 통하여 도출한 14개 재무관련 항목을 이용하여 재무적 관점에서 경영성과 분석 및 가설검증을 진행하였다. 본 연구결과를 통한 시사점은 B2B 전자상거래 보증 이용기업의 재무적 관점의 실증적 성과분석이 향후 B2B 전자상거래 보증의 활성화를 위한 정책수립의 기초자료로 활용되어 중소기업의 전자상거래 확대 지원을 통해 안정적인 비즈니스 환경을 구축하는데 기여할 수 있을 것으로 기대된다.

• 지식경영연구
• /
• 제22권2호
• /
• pp.247-268
• /
• 2021

투자자들은 기업가치를 평가하기 위하여 재무비율을 활용하는데 특히 PER과 PBR은 적정 기업가치를 판단하는데 중요한 역할을 하는 대표적인 수치로 알려져 있다. 금융자료는 꼬리가 매우 두터운 형태의 분포를 따르는 경우가 많은데, PER과 PBR은 첨도가 매우 높으며 해당 재무비율의 극단치들은 기업의 다양한 이해관계자들의 의사결정 시 중요한 역할을 한다. 본 논문에서는 통계학의 극단치이론에서 주로 활용되는 GPD와 최근 새롭게 제안된 분포인 exGPD를 도입하고, 두 분포 간의 성능을 비교하기 위해 시뮬레이션을 수행하여 적합도를 살펴본 후 우측 꼬리에 속하는 90, 95, 99% 퍼센타일 값을 추정하여 실제 값과 비교한다. 다음으로 국내 증권시장에 상장된 정보기술군(IT) 기업들의 PER, PBR 자료에 근거하여 실증분석을 수행한다. 분석 결과 특히 PBR에서 exGPD가 GPD에 비해 자료의 우측 꼬리 영역을 보다 효과적으로 설명함을 확인하였다. 따라서, 재무비율에 기반한 기업가치평가 또는 위험관리 시 극단치의 특성을 효과적으로 반영할 수 있는 exGPD와 같은 분포를 활용한다면 꼬리 영역에 담긴 정보를 보다 정확하게 파악할 수 있다. 이는 기업 내부 위험관리자의 효과적인 지식경영을 돕고, 투자자를 비롯하여 다양한 외부 이해관계자들에게 유용한 지식을 제공할 수 있다.

• 한국경영과학회지
• /
• 제40권2호
• /
• pp.1-17
• /
• 2015

In this paper, we propose a portfolio selection model utilizing a Markov chain for investing in the foreign exchange market based on market forecasts and exchange rate movement predictions. The proposed model is utilized to compute optimum investment portfolio weights for investing in margin-based markets such as the FX margin market. We further present an objective investment algorithm for applying the proposed model in real-life investments. Empirical performance of the proposed model and investment algorithm is evaluated by conducting an experiment in the FX market consisting of the 7 most traded currency pairs, for a period of 9 years, from the beginning of 2005 to the end of 2013. We compare performance with 1) the Dollar Index, 2) a 1/N Portfolio that invests the equal amount in the N target assets, and 3) the Barclay BTOP FX Index. Performance is compared in terms of cumulated returns and Sharpe ratios. The results suggest that the proposed model outperforms all benchmarks during the period of our experiment, for both performance measures. Even when compared in terms of pre- and post-financial crisis, the proposed model outperformed all other benchmarks, showing that the model based on objective data and mathematical optimization achieves superior performance empirically.

• 융합정보논문지
• /
• 제8권2호
• /
• pp.209-218
• /
• 2018

본 연구는 수도권의 중소 벤처기업에 근무하고 있는 관리자를 대상으로 하여 정보시스템 특성과 조직특성이 과정적 경영성과에 미치는 영향을 분석하였다. ICT 도입과 기업성과에 대한 선행연구에서는 대기업과 일반 중소기업을 대상으로 한 연구가 주류를 이루고 있는데, 본 연구에서는 중소벤처기업의 특성을 고려하여 연구를 수행하였다. 연구결과 시스템 특성의 시스템 적합성, 시스템 품질, IT 자산은 과정적 경영성과에 긍정적인 영향을 미치는 것으로 분석되었고, 조직특성의 관리자 인지, 인적자원의 역량은 과정적 경영성과에 긍정적인 영향을 미치는 것으로 분석되었으나 평가와 보상은 경영성과에 긍정적인 영향을 미치지 않는 것으로 분석되었다. 이러한 연구결과는 선행연구에서 제시하고 있는 연구결과와 대부분 동일한 분석결과를 보이고 있었다. 벤처기업은 자금력이나 기술, 조직관리 능력이 일반 중소기업 보다 대부분 열악하다. 그러나 새로운 정보시스템의 도입과 확산 요인은 일반 중소기업과 큰 차이가 없음을 알 수 있었다.

• 융합경영연구
• /
• 제6권4호
• /
• pp.51-64
• /
• 2018

Purpose - This study is intended to look into the influences of restaurant consumers' e-WOM information communication on product perception risk, benefit and WOM effect. Research design, data, and Methodology - To achieve this, a survey was empirically carried out to 426 restaurant consumers. Results - The findings are as follows. First, the influence of e-WOM on product perception risk showed that WOM information sender characteristics, WOM information recipient characteristics and online community had a statistically significant positive influence on product perception risk. Second, the influence of e-WOM on product risk benefit showed that WOM information sender characteristics, WOM information recipient characteristics and online communication had a statistically significant positive influence on product risk benefit. Third, WOM risk perception had a statistically significant positive influence on WOM acceptance. Fourth, WOM risk benefit had a statistically significant positive influence on WOM effect. Conclusions - As for the above-mentioned findings, the communication between e-WOM sender and recipient had a positive influence on the product evaluation and attitude change in the restaurant industry, and the WOM effect had an influence on the financial performance and non-financial performance. The communication attaches importance to a direct using and tasting experience due to the nature of restaurant industry when it is simultaneously performed as a positive mechanism between sender and recipient through each channel of these factors. But the e-WOM culture can lead to the WOM effect when both sender and recipient share the persuasive communicability in reality that diversifies communication methods, having a positive influence on the management performance.

• 한국공간구조학회논문집
• /
• 제20권4호
• /
• pp.131-139
• /
• 2020

In this paper, the hybrid prefabricated retrofit method is suggested and examined. Six specimens were manufactured in order to evaluate their flexural performance of RC beams. Test parameters include the added beam depth, the thickness of bottom plate, the number of the steel plate with openings. The effects of these parameters on the flexural performance of reinforced concrete beams were examined. The load-deflection behavior and modes of cracks are presented from the test results. At the test result, the flexural capacity and the ductility of the hybrid prefabricated retrofit method was increased satbly. Also, comparing the flexural performance of RC beam and retrofitted RC beams, it was increased that the flexural strength is about 3.3 times, the ductility is about 2.55 times, and energy dissipation capacity is about 7.34 times.