Big Data Analysis using Experimental Optimization, Data Mining, and Decision Making Methodology : 실험적 최적화와 데이터마이닝, 의사결정론을 활용한 빅데이터 분석
저자
발행사항
전주 : 전북대학교 일반대학원, 2015
학위논문사항
Thesis(doctoral)-- 전북대학교 일반대학원 : 산업시스템공학과 2015. 2
발행연도
2015
작성언어
영어
주제어
발행국(도시)
대한민국
형태사항
xiv, 155 p. ; 26 cm
일반주기명
지도교수: 배준수
소장기관
Nowadays, complex industrial problems require multidisciplinary approaches to expedite the technological development and problem solving advancement. In this context, the thesis presents implementation of Big Data Analysis, multicriteria decision support system, data mining as well as Design of Experiment methodology with the aim to introduce, demonstrate and develop a framework for improvement and optimization that serves two main objective: the first involves the fundamental aspect of the research methodology (big data analysis, multicriteria decision support system, data mining as well as Design of Experiment) to be implemented in various engineering problems and to ensure the accuracy and validity of the implemented approach by means of verification and validation. The second objective concerns on the development and integration of applied research to provide problem solving, improvement and optimization of a specific engineering case.
For instance, five different case studies which represent multidisciplinary engineering problems were carried out. Firstly, the robust and popular Design of Experiment Taguchi method was implemented to optimize six important operating parameters in fuel cells stack. The analysis of variance (ANOVA) was carried out to evaluate the importance of parameters and their interaction with regard to the optimization of three objective functions, i.e. fuel cell performance, fuel cell efficiency and possibility to further improve efficiency by utilizing the waste heat from fuel cell for industrial heating. It was found that the best combination of operating parameters of fuel cells stack can be optimized using Taguchi method with confidence level of ~ 95% and the total efficiency can be improved up to 85% by utilizing waste heat for industrial heating.
The second industrial problem deals with the requirement for improved mixing in microreactor technology without adding complexity in the mass manufacturing of the micromixer. Here, a novel wavy channel micromixer was introduced for the first time to improve the mixing performance while keeping simple manufacturing process by means of stamping method. Furthermore, the design parameters were optimized by using Design of Experiment Taguchi method. For high quality product where the mixing quality is of paramount important, e.g. pharmaceutical product, it is advised to optimized the objective function of the design by larger the better in term of mixing performance. On the other hand, for cheap and mass production products, it is suggested to optimized the design with respect to the figure of merit, defined as mixing quality per unit pumping power.
The third industrial problem incorporates optimization of industrial manufacturing of plastic injection molding (PIM). The data mining technique was used for the first time to optimize the PIM process. The optimization results based on data mining technique were compared against conventional method. It was found that the data mining method yields good optimization outcome comparable to the conventional counterpart. The main advantage of the proposed method was that it does not disturb the PIM process while performing optimization, while the conventional method does disturb the PIM process.
The fourth study demonstrates the capability of data mining technique together with multicriteria decision support system PROMETHEE method to be used to analyzed large data of liver patients. The classification algorithm based on available UCI repository utilizing WEKA, the data comprises 345 patients of BUPA liver disorder were developed as a framework classification tool in data mining. Furthermore, the PROMETHEE method was implemented to analyze and help doctor to diagnose patient disorder for the first time. It was found that combining data mining and PROMETHEE method can accurately predict patient disorder and help doctor to decide necessary treatment to cure patient.
The last case study presents application of multicriteria decision support system to be used to predict and improve search engine, i.e. Google search ranking. The PROMETHEE method was introduced for the first time to predict Google search ranking. 30 keywords and 120 websites were analyzed for search ranking prediction utilizing manual PROMETHEE method as well as visual PROMETHEE software. The results from visual PROMETHEE were verified against analytical solution from manual method as well as were validated against ranking results from Google data. Good agreement between prediction and experimental data were obtained. To improve the PROMETHEE prediction, the weight value of PROMETHEE method was optimized using Taguchi method. The novel feedback-loop concept was introduced to improve the Google search ranking.
Finally, this thesis provide insight of multidisciplinary approaches from industrial and information engineering perspective in combination with several other engineering discipline to expedite technological developments in various area. This also provides basic guideline for engineers and practitioners to implement Big Data Analysis, multicriteria decision support system, data mining and Design of Experiment for improvement and optimization in engineering problems.
분석정보
서지정보 내보내기(Export)
닫기소장기관 정보
닫기권호소장정보
닫기오류접수
닫기오류 접수 확인
닫기음성서비스 신청
닫기음성서비스 신청 확인
닫기이용약관
닫기학술연구정보서비스 이용약관 (2017년 1월 1일 ~ 현재 적용)
학술연구정보서비스(이하 RISS)는 정보주체의 자유와 권리 보호를 위해 「개인정보 보호법」 및 관계 법령이 정한 바를 준수하여, 적법하게 개인정보를 처리하고 안전하게 관리하고 있습니다. 이에 「개인정보 보호법」 제30조에 따라 정보주체에게 개인정보 처리에 관한 절차 및 기준을 안내하고, 이와 관련한 고충을 신속하고 원활하게 처리할 수 있도록 하기 위하여 다음과 같이 개인정보 처리방침을 수립·공개합니다.
주요 개인정보 처리 표시(라벨링)
목 차
3년
또는 회원탈퇴시까지5년
(「전자상거래 등에서의 소비자보호에 관한3년
(「전자상거래 등에서의 소비자보호에 관한2년
이상(개인정보보호위원회 : 개인정보의 안전성 확보조치 기준)개인정보파일의 명칭 | 운영근거 / 처리목적 | 개인정보파일에 기록되는 개인정보의 항목 | 보유기간 | |
---|---|---|---|---|
학술연구정보서비스 이용자 가입정보 파일 | 한국교육학술정보원법 | 필수 | ID, 비밀번호, 성명, 생년월일, 신분(직업구분), 이메일, 소속분야, 웹진메일 수신동의 여부 | 3년 또는 탈퇴시 |
선택 | 소속기관명, 소속도서관명, 학과/부서명, 학번/직원번호, 휴대전화, 주소 |
구분 | 담당자 | 연락처 |
---|---|---|
KERIS 개인정보 보호책임자 | 정보보호본부 김태우 | - 이메일 : lsy@keris.or.kr - 전화번호 : 053-714-0439 - 팩스번호 : 053-714-0195 |
KERIS 개인정보 보호담당자 | 개인정보보호부 이상엽 | |
RISS 개인정보 보호책임자 | 대학학술본부 장금연 | - 이메일 : giltizen@keris.or.kr - 전화번호 : 053-714-0149 - 팩스번호 : 053-714-0194 |
RISS 개인정보 보호담당자 | 학술진흥부 길원진 |
자동로그아웃 안내
닫기인증오류 안내
닫기귀하께서는 휴면계정 전환 후 1년동안 회원정보 수집 및 이용에 대한
재동의를 하지 않으신 관계로 개인정보가 삭제되었습니다.
(참조 : RISS 이용약관 및 개인정보처리방침)
신규회원으로 가입하여 이용 부탁 드리며, 추가 문의는 고객센터로 연락 바랍니다.
- 기존 아이디 재사용 불가
휴면계정 안내
RISS는 [표준개인정보 보호지침]에 따라 2년을 주기로 개인정보 수집·이용에 관하여 (재)동의를 받고 있으며, (재)동의를 하지 않을 경우, 휴면계정으로 전환됩니다.
(※ 휴면계정은 원문이용 및 복사/대출 서비스를 이용할 수 없습니다.)
휴면계정으로 전환된 후 1년간 회원정보 수집·이용에 대한 재동의를 하지 않을 경우, RISS에서 자동탈퇴 및 개인정보가 삭제처리 됩니다.
고객센터 1599-3122
ARS번호+1번(회원가입 및 정보수정)