• Journal of Digital Convergence
• /
• v.18 no.12
• /
• pp.525-531
• /
• 2020

In today's IT environment where various pieces of information are distributed in large volumes, recommendation systems are in the spotlight capable of figuring out users' needs fast and helping them with their decisions. The current recommendation systems, however, have a couple of problems including that user preference may not be reflected on the systems right away according to their changing tastes or interests and that items with no relations to users' preference may be recommended, being induced by advertising. In an effort to solve these problems, this study set out to propose a Fuzzy-AHP-based movie recommendation system by applying the BRNN(Bidirectional Recurrent Neural Network) language model. Applied to this system was Fuzzy-AHP to reflect users' tastes or interests in clear and objective ways. In addition, the BRNN language model was adopted to analyze movie-related data collected in real time and predict movies preferred by users. The system was assessed for its performance with grid searches to examine the fitness of the learning model for the entire size of word sets. The results show that the learning model of the system recorded a mean cross-validation index of 97.9% according to the entire size of word sets, thus proving its fitness. The model recorded a RMSE of 0.66 and 0.805 against the movie ratings on Naver and LSTM model language model, respectively, demonstrating the system's superior performance in predicting movie ratings.

• Journal of Digital Convergence
• /
• v.19 no.8
• /
• pp.319-325
• /
• 2021

With the advancement of wireless technology and the rapid growth of the infrastructure of mobile communication technology, systems applying AI-based platforms are drawing attention from users. In particular, the system that understands users' tastes and interests and recommends preferred items is applied to advanced e-commerce customized services and smart homes. However, there is a problem that these recommendation systems are difficult to reflect in real time the preferences of various users for tastes and interests. In this research, we propose a Fuzzy-AHP-based movies recommendation system using the Gated Recurrent Unit (GRU) language model to address a problem. In this system, we apply Fuzzy-AHP to reflect users' tastes or interests in real time. We also apply GRU language model-based models to analyze the public interest and the content of the film to recommend movies similar to the user's preferred factors. To validate the performance of this recommendation system, we measured the suitability of the learning model using scraping data used in the learning module, and measured the rate of learning performance by comparing the Long Short-Term Memory (LSTM) language model with the learning time per epoch. The results show that the average cross-validation index of the learning model in this work is suitable at 94.8% and that the learning performance rate outperforms the LSTM language model.

• Journal of the military operations research society of Korea
• /
• v.35 no.1
• /
• pp.33-49
• /
• 2009

At the long period of time, Many powerful countries are going to prepare on building Future Combat System(FCS). R.O.K. Army also have to prepare for Future Combat on the line of Military Transformation. First, This paper presents the reason for building R.O.K. Army FCS. Second, R.O.K. Army could get good use of Master Plan frame for FCS enterprise as apply to this paper that FCS consist on an individual combat system for the priority of determination by Analytic Hierarchy Process(AHP)

• Proceedings of the Korean Society for Quality Management Conference
• /
• 2009.10a
• /
• pp.182-185
• /
• 2009

특정분야의 기술에 대한 중요도를 평가할 경우 일반적으로 해당 분야 기술의 전문가들의 의견을 델파이 방법을 이용하여 수렴하고 AHP 분석을 통해 기술의 우선순위를 결정하곤 한다. 그러나 전문가들의 직관적 판단에 의존하는 델파이 기법과 AHP 분석은 전문가 집단을 어떻게 선정하느냐에 따라 다른 결과를 초래하거나 항상 최적의 대안을 제시한다는 보장을 하지 못하므로 이에 대한 보완이 필요하다. 본 연구는 해당 기술 분야의 객관적인 자료인 특허 문서를 분석하여 델파이를 통해 도출된 전문가들의 기술 평가 결과의 타당성을 확인하도록 특허맵 분석을 활용할 것과 많은 대상 기술과 다양한 기술 평가 기준을 한꺼번에 고려하여 기술간 우선순위, 기술간 유사성, 기술군간 관련성을 쉽게 확인할 수 있는 SOM 신경망 분석을 활용할 것을 제안한다.

• 한국IT서비스학회:학술대회논문집
• /
• 2006.11a
• /
• pp.299-307
• /
• 2006

글로벌 비즈니스 환경에 있어서 경쟁력을 유지 혹은 강화시키기 위한 방법으로 많은 기업들이 경영혁신 활동에 주력하고 있다. 식스 시그마는 이러한 활동을 가능케 하는 핵심적인 방법론이자 도구로써 주목 받고 있다. 따라서 본 연구에서는 식스 시그마의 도입에 따른 성과요인을 분석하여 보다 체계적인 프레임워크를 제시함으로써 그 성공 가능성을 관리할 수 있도록 하는 것이 주요한 목적이라 하겠다. 이를 위해 전문가 집단을 대상으로 한 델파이 조사방법과 이를 분석하기 위한 도구로써 계층적 분석기법(AHP)을 적용하였다. 분석결과, 총 12개의 요인들이 도출되었으며 중요도에 따라 가중치를 계산하여 이를 실제 식스 시그마 프로젝트에 적용하여 연구에 제시된 프레임워크를 검증토록 하였다. 본 연구는 다양한 산업 및 기업에서 식스 시그마 방법론의 적용이 급속히 확대되어 가는 추세에서 프로젝트의 성패를 가늠짓게 하는 중요 요인들을 보다 객관적인 프레임워크로 제시되었다는 점에서 그 의의가 있을 것이다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.333-334
• /
• 2021

코로나 19로 인해 인류의 생존을 위협받고 주변의 많은 환경이 변화되고 있다. 사람과 사람이 만나는 당연한 일상이 이제는 위협으로 다가오고 있다. 비대면 생활이 일상화되어가고 있는 현재. 온라인 및 모바일을 통한 소통은 이미 우리의 삶 속에 자리 잡고 있다. 우리나라의 인터넷 환경은 매우 잘 발달되어 있어 우리의 생활 곳곳에서 활용할 수 있다. 이러한 인터넷 발달은 사람의 삶의 질을 높여주는 요소들에 도움을 주는데 그것이 바로 비대면 쇼핑이다. 비대면 쇼핑은 상품을 직접 보지 않고 온라인, 모바일, TV 등의 매개체를 통해 구매하는 형식이라 할 수 있다. 최근 코로나 19의 확산으로 인해 이러한 비대면 쇼핑을 통한 구매 활동은 점점 늘어났다. 비대면 쇼핑이 주된 쇼핑형태로 자리잡고 있는 현재. 비대면 쇼핑의 구매 결정에 대한 요인 분석은 소비자 측면에서 의미있는 분석이 될 것이다. AHP 분석기법을 이용하여 소비자 입장에서 비대면 쇼핑의 구매 결정요인으로 작용 하는 항목들에 대한 중요도를 분석하고자 한다.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.19 no.1
• /
• pp.1-6
• /
• 2016

Ballast water in ship operation is essential for a safe voyage. However ballast water can contain unwanted organisms that are the cause of disturbing the ecosystem by the transfer of potential invasive species. To prevent the destruction of the environment, the International Convention for the Control and Management of Ship's Ballast Water and Sediments(BWM Convention) was adopted in 2004. BWMS (Ballast Water Management System) has been developed to prevent the transportation of organisms to another region in order to fulfill the requirements IMO (International Maritime Organization) regulations. Nowadays there are about 50 approved Ballast Water Management Systems of various types globally. The most common BWMS types are UV (Ultra Violet), Electrolysis and Ozone. Among these types there are many difficulties in determining the optimum type of BWMS which can be suitable for the user and designer's requirements. The main objective of this research is to select the best BWMS type by using AHP. To apply AHP, the most important criteria for the BWMS development are derived by users and designers. From our results, we can give a guide BWMS type to the developers of BWMS.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.2
• /
• pp.595-601
• /
• 2018

The era of autonomous vehicles, which drive themselves and in whose operation the driver does not intervene, is fast approaching. The safety of autonomous vehicles can be guaranteed only if they recognize the road infrastructure. However, the road infrastructure consists of road safety facilities, traffic operation systems, and cross-sectional concerns, which include a variety of components, such as types, shapes, and sizes. Therefore, it is necessary to prioritize the road information. This study was conducted to select the priority with which the road infrastructure attributes should be acquired using the AHP (Analytical Hierarchy Process) method. The road infrastructure attributes were categorized into 2 levels, levels 1 and 2, which consisted of 3 and 26 types of attributes, respectively. As a result of the AHP analysis, it was found that the highest priorities of the road infrastructure are the road safety facilities, traffic operation systems and cross sectional concerns. Also, in level-2, the priorities of the safety barriers (road safety facilities), traffic signals (traffic operation systems), and the median (cross sectional) are the highest. Also, this study provides application examples of road infrastructure extraction with the Point Cloud. The results are expected to support the recognition of technology for autonomous vehicles.

• The Journal of Society for e-Business Studies
• /
• v.22 no.1
• /
• pp.107-122
• /
• 2017

Nowadays, digital forensic experts are not only computer experts who restore and find deleted files, but also general experts who posses various capabilities including knowledge about processes/laws, communication skills, and ethics. However, there have been few studies about qualifications or competencies required for digital forensic experts comparing with their importance. Therefore, in this study, AHP questionnaires were distributed to digital forensic experts and analyzed to derive priorities of competencies; the first-tier questions which consisted of knowledge, technology, and attitude, and the second-tier ones which have 20 items. Research findings showed that the most important competency was knowledge, followed by technology and attitude but no significant difference was found. Among 20 items of the second-tier competencies, the most important competency was "digital forensics equipment/tool program utilization skill" and it was followed by "data extraction and imaging skill from storage devices." Attitude such as "judgment," "morality," "communication skill," "concentration" were subsequently followed. The least critical one was "substantial law related to actual cases." Previous studies on training/education for digital forensics experts focused on law, IT knowledge, and usage of analytic tools while attitude-related competencies have not given proper attention. We hope this study can provide helpful implications to design curriculum and qualifying exam to foster digital forensic experts.

• Journal of Korean Society of Forest Science
• /
• v.99 no.1
• /
• pp.111-124
• /
• 2010

This study has intended to develop an evaluation model to select suitable locations of recreation forests in accordance with their types, and to apply the models to the feasibility study of selecting suitable recreation forest locations of candidate sites. To reach this goal, this study employed a Delphi expert survey method and Analytic Hierarchy Process (AHP) for the whole process of model building. And the followings are what this study has found during model building and application process. First, the assessment criteria for classifying recreation forests and selecting suitable locations were initially identified through justification process with two rounds of expert review, after broken down into 2 categories, and then further divided into 6 items and 12 indicators accompanying with hierarchical structure. Second, in the third phase of Delphi expert survey, the relative weights of the assessment criteria were derived by employing AHP. Through overlaying two evaluation categories including resource and usability, 4 types of recreation forest were presented. In the forth phase of the Delphi survey, this study has developed an evaluation model to select suitable locations of recreation forests in accordance with their types using relative weights of the selected indicators through. This study has applied the models to the feasibility study of selecting suitable recreation forest locations of candidate sites, and found that the usability of recreation forest was severely affected by the distance from the capital region, that the closer the locations of natural recreation forests from the capital region, the more advantageous. The developed model can be used to designate recreation forests in accordance with their types.