• 시스템엔지니어링학술지
• /
• 제11권2호
• /
• pp.61-73
• /
• 2015

The early-phase naval ship design demands requirements synthesis rather than design synthesis, which conducts engineering design for several domains on a detailed level. Requirements synthesis focuses on creating a balanced set of required operational capabilities satisfying user's needs and concept of operations. Requirements are evolved from capability based languages to function based language by statistical exploration and engineering design which are derived in the following order: concept alternative, concept baseline, initial baseline and functional baseline. The early-phase naval ship design process can be divided into three passes: concept definition, concept exploration and concept development. Main activities and outcomes in each pass are shortly presented. Concept definition is the first important step that produces a concept baseline through extensive design space exploration promptly. Design space exploration applies a statistical approach to explore design trends of existing ships and produce feasible design range corresponding to concept alternative. It further helps naval systems engineers and operational researchers by inducing useful responses to user and stakeholders' questions at a sufficient degree of confidence and success in the very early ship design. The focus of this paper is on the flow of design space exploration, and its application to a high-speed patrol craft. The views expressed in this paper are those of the authors, and do not reflect the official policy or rule of the Navy.

• 한국정보시스템학회지:정보시스템연구
• /
• 제26권2호
• /
• pp.1-23
• /
• 2017

Purpose Facebook is a social network service that has the highest number of Monthly Active Users around the world. Hence, marketers have selected Facebook as the most important platform to get customer engagement. With respect to the customer engagement enhancement, the most popular and engaging post type in the Facebook brand fan pages related to what was usually classified as 'sweepstakes'. Sweepstakes refer to a form of gambling where the entire prize may be awarded to the winner. Which makes customers more engaged with the brand. This study aims to explore sweepstakes-oriented social media marketing approaches based on the application of big data analytics. Design/methodology/approach we collect sweepstakes data from each company based on the data crawling from the Facebook brand fan pages. The output of this study explains how companies in each category of FCB grid can design and apply sweepstakes for their social media marketing. Findings The results show that they have one thing in common across the four quadrants of FCB grid. Regardless of the quadrants, most frequently observed type is 'Simple/Quiz or Comments/Quatrains [event type of sweepstakes] + Gifticon [type of reward prize] + Image [type of message display] + No URL [Link toother website] +Single-Gift-Offer [type of reward prize payment]'. So, if the position of the brand is hard to be defined by the FCB grid model, then this general rule can be applied to all types of brands. Also some differences between the quadrants of the FCB grid were observed. This study offers several research implications by analyzing Sweepstakes-oriented social media marketing approaches in Facebook brand fan pages. By using the FCB grid model, this study provides guidance on how companies can design their sweepstakes-oriented social media marketing approaches in the context of Facebook brand fan pages by considering their context.

• 한국콘텐츠학회논문지
• /
• 제11권10호
• /
• pp.59-68
• /
• 2011

축구 경기를 분석하고 이를 팀 전략 수립에 활용하는 축구 분석관의 역할이 강조됨에 따라, 방송용 축구 경기에서 주요 이벤트의 탐지와 같은 절차적 기능 이상의 고수준의 해석 방법들이 요구되고 있다. 본 논문에서는 인터넷 기반의 텍스트 방송인 축구 웹 캐스트에서 실시간으로 제공하는 텍스트 정보를 기반으로 텍스트 마이닝을 이용한 축구 경기의 전략 수립이 가능한 고수준의 해석 기법을 제안한다. 제안하는 해석기법은 축구 웹 캐스트의 텍스트 정보와 도메인 지식을 기반으로 축구 경기의 다양한 속성, 동작 그리고 이벤트 등 메타데이터를 추출하고, 인덱싱하고, 텍스트 마이닝의 다양한 해석 기법인 연관 규칙 마이닝, 성장도 분석, 그리고 패스파인더 네트워크 분석 기법 등을 사용함으로써 유용한 지식을 추출한다. 실제 2010년 월드컵의 스페인 팀 경기들을 중계한 웹 캐스트의 텍스트 정보를 대상으로 제안된 기법의 타당성을 실험적으로 검증한다.

• 한국운동역학회지
• /
• 제17권1호
• /
• pp.81-90
• /
• 2007

The effort identifying positioning information of the moving object in real time has been a issue not only in sport biomechanics but also other academic areas. In order to solve this issue, this study tried to track the movement of a pitched ball that might provide an easier prediction because of a clear focus and simple movement of the object. Machine learning has been leading the research of extracting information from continuous images such as object tracking. Though the rule-based methods in artificial intelligence prevailed for decades, it has evolved into the methods of statistical approach that finds the maximum a posterior location in the image. The development of machine learning, accompanied by the development of recording technology and computational power of computer, made it possible to extract the trajectory of pitched baseball from recorded images. We present a method of baseball tracking, based on object tracking methods in machine learning. We introduce three state-of-the-art researches regarding the object tracking and show how we can combine these researches to yield a novel engine that finds trajectory from continuous pitching images. The first research is about mean shift method which finds the mode of a supposed continuous distribution from a set of data. The second research is about the research that explains how we can find the mode and object region effectively when we are given the previous image's location of object and the region. The third is about the research of representing data into features that we can deal with. From those features, we can establish a distribution to generate a set of data for mean shift. In this paper, we combine three works to track baseball's location in the continuous image frames. From the information of locations from two sets of images, we can reconstruct the real 3-D trajectory of pitched ball. We show how this works in real pitching images.

• 제어로봇시스템학회논문지
• /
• 제8권2호
• /
• pp.126-135
• /
• 2002

The study is concerned with an approach to the design of new architectures of fuzzy neural networks and the discussion of comprehensive design methodology supporting their development. We propose an Adaptive Fuzzy Polynomial Neural Networks(APFNN) based on Fuzzy Neural Networks(FNN) and Self-organizing Networks(SON) for model identification of complex and nonlinear systems. The proposed AFPNN is generated from the mutually combined structure of both FNN and SON. The one and the other are considered as the premise and the consequence part of AFPNN, respectively. As the premise structure of AFPNN, FNN uses both the simplified fuzzy inference and error back-propagation teaming rule. The parameters of FNN are refined(optimized) using genetic algorithms(GAs). As the consequence structure of AFPNN, SON is realized by a polynomial type of mapping(linear, quadratic and modified quadratic) between input and output variables. In this study, we introduce two kinds of AFPNN architectures, namely the basic and the modified one. The basic and the modified architectures depend on the number of input variables and the order of polynomial in each layer of consequence structure. Owing to the specific features of two combined architectures, it is possible to consider the nonlinear characteristics of process system and to obtain the better output performance with superb predictive ability. The availability and feasibility of the AFPNN are discussed and illustrated with the aid of two representative numerical examples. The results show that the proposed AFPNN can produce the model with higher accuracy and predictive ability than any other method presented previously.

• 한국인터넷방송통신학회논문지
• /
• 제11권4호
• /
• pp.91-97
• /
• 2011

본 논문에서는 Mackey-Glass시계열의 예측에서 유전자알고리즘을 이용하는 구조적인 동정과 뉴로퍼지에 의한 파라미터 동정의 학습방법과 하이브리드 시스템을 제안하였다. 본 방법은 두 가지로 구성되었다. 하나는 입력공간에 대한 분할을 통하여 유전 알고리즘을 이용하여 퍼지 규칙베이스를 구축하고 다른 하나는 이 규칙베이스를 토대로 기울기 최하강법을 이용하여 제어규칙의 변수에 대한 파라미터 동정이다. 제안된 방법을 성능을 검증하기 위하여 입력의 패턴을 시간간격에 따라서 x(t-3), x(t-6)과 x(t-9)의 세 가지로 구성하였다. 많은 시뮬레이션을 통하여 유전알고리즘에 의한 구조적인 동정으로 인하여 학습초기에 오차가 작은 것을 알 수 있었다. 표2에서와 같이 성능을 확인 할 수 있었다.

• 한국정보통신학회논문지
• /
• 제21권2호
• /
• pp.450-460
• /
• 2017

T파는 심장의 심실의 재분극을 나타내는 파라미터로써 부정맥 진단에 있어 매우 중요하다. T 파를 검출하기 위한 기존 연구방법으로는 주파수 분석과 비선형 접근방법 등이 제안되어 왔지만 검출 정확도가 낮다는 문제점이 있다. 이는 T파의 경우 P파와 중복되는 경우가 발생하기 때문이다. 본 연구에서는 QRS 구간을 제거한 후, 이동평균을 통한 P파와 T파의 대상 영역을 추출하여 정확히 T파를 검출하는 알고리즘을 제안한다. 이를 위해 전처리를 통해 잡음이 제거된 심전도 신호에서 Q, R, S를 검출한다. 이후 검출된 QRS 구간을 제거, 이동평균을 통해 4개의 PAC 패턴과 기타부정맥에 대한 판단규칙을 적용하여 P, T파의 대상 영역을 추출하고, 이를 대상으로 RR 간격과 RT 간격의 문턱치를 적용하여 T파를 검출하였다. 제안한 방법의 우수성을 입증하기 위해 MIT-BIH 부정맥 데이터베이스 48개의 레코드를 대상으로 한 T파의 평균 검출율은 95.32%의 성능을 나타내었다.

• Industrial Engineering and Management Systems
• /
• 제4권1호
• /
• pp.1-22
• /
• 2005

This paper presents new scheduling heuristics, namely Mean Progressive Weighted Tardiness Estimator (MPWT) Heuristic Method and modified priority rules with sequence-dependent setup times consideration. These are designed to solve job shop scheduling problems with new performance measures - progressive weighted tardiness penalties. More realistic constraints, which are inter-machine overlapping sequence-dependent setup times, are considered. In real production environments, inter-machine overlapping sequence-dependent setups are significant. Therefore, modified scheduling generation algorithms of active and nondelay schedules for job shop problems with inter-machine overlapping sequence-dependent setup times are proposed in this paper. In addition, new customer-based measures of performance, which are total earliness and progressive weighted tardiness, and total progressive weighted tardiness, are proposed. The objective of the first experiment is to compare the proposed priority rules with the consideration of sequence-dependent setup times and the standard priority rules without setup times consideration. The results indicate that the proposed priority rules with setup times consideration are superior to the standard priority rules without the consideration of setup times. From the second experiment and the third experiment to compare the proposed MPWT heuristic approach with the efficient priority rules with setup times consideration, the MPWT heuristic method is significantly superior to the Batched Apparent Tardiness Cost with Sequence-dependent Setups (BATCS) rule, and other priority rules based on total earliness and progressive weighted tardiness, and total earliness and tardiness.

• Advances in nano research
• /
• 제7권6호
• /
• pp.405-417
• /
• 2019

This research is devoted to study post-buckling analysis of functionally graded carbon nanotubes reinforced composite (FG-CNTRC) micro plate with cut out subjected to magnetic field and resting on elastic medium. The basic formulation of plate is based on first order shear deformation theory (FSDT) and the material properties of FG-CNTRCs are presumed to be changed through the thickness direction, and are assumed based on rule of mixture; moreover, nonlocal Eringen's theory is applied to consider the size-dependent effect. It is considered that the system is embedded in elastic medium and subjected to longitudinal magnetic field. Energy approach, domain decomposition and Rayleigh-Ritz methods in conjunction with Newton-Raphson iterative technique are employed to trace the post-buckling paths of FG-CNTRC micro cut out plate. The influence of some important parameters such as small scale effect, cut out dimension, different types of FG distributions of CNTs, volume fraction of CNTs, aspect ratio of plate, magnitude of magnetic field, elastic medium and biaxial load on the post-buckling behavior of system are calculated. With respect to results, it is concluded that the aspect ratio and length of square cut out have negative effect on post-buckling response of micro composite plate. Furthermore, existence of CNTs in system causes improvement in the post-buckling behavior of plate and different distributions of CNTs in plate have diverse response. Meanwhile, nonlocal parameter and biaxial compression load on the plate has negative effect on post-buckling response. In addition, imposing magnetic field increases the post-buckling load of the microstructure.

• 한국정보통신학회논문지
• /
• 제25권6호
• /
• pp.785-791
• /
• 2021

본 연구는 서비스 로봇이 물건배달 서비스를 수행하기 위해 인식된 물체의 위치기반 정보로부터 최적의 작업 목적지를 추정하기 위한 방법론을 제안한다. 위치 추정 프로세스는 격자지도에 일반화된 보로노이 그래프를 적용하여 노드와 링크로 구성되는 초기 위상학 지도 작성, RGB-D센서를 이용하여 물체의 인식과 위치정보 추출, 장애물의 형상 및 거리정보를 수집한 후 ,무게중심법과 세선화를 병행하는 하이브리드 기법을 적용하여 서비스 로봇이 물건잡기 작업을 수행할 수 있는 최적의 이동위치를 추정하게 된다. 그런 다음, 노드 위치선정 규칙에 따라 추정된 위치와 기존 노드의 기하학적 거리비교를 통해 로봇의 작업 목적지에 대한 최적의 노드정보를 갱신하게 된다.