빅데이터를 활용한 부산항 환적화물 물동량 이상치 탐지 분석
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 신재영 | - |
dc.contributor.author | 박미혜 | - |
dc.date.accessioned | 2019-12-16T02:54:18Z | - |
dc.date.available | 2019-12-16T02:54:18Z | - |
dc.date.issued | 2018 | - |
dc.identifier.uri | http://repository.kmou.ac.kr/handle/2014.oak/11681 | - |
dc.identifier.uri | http://kmou.dcollection.net/common/orgView/200000016037 | - |
dc.description.abstract | 부산항의 환적화물은 최근 5년 동안 연평균 8.27%의 증가율을 나타내고 있 다. 이는 국내 환적화물 물동량의95%를 차지하나, 2016년 9월 한진해운사태를 비롯해 미국 대통령 트럼프의 보호무역주의, 중국 환율 조작국 지정 등의 경제 기조와 세계 교역량의 감소와 선대의 축소 등으로 인한 물량 감소는 부산항에 좋지 않은 영향을 주고 있다. 그러나 현재 선사에서 마케팅을 위해 활용하고 있 는 자료로는 부산항에 신고된 수출입 환적 화물의 물량 통계뿐이다. 물론 원시 데이터는 있지만 공개되지 않고 있고, 월별 년별 집계된 데이터가 대부분이다. 그래서 부산항 전체 뿐만 아니라 다른 국가, 항만, 각 선사별로 부산항으로 환적 되는 물량의 변화가 어떤지, 특별히 나타나는 이상치는 없는지 분석하는 자료가 필요하다. 본 논문은 변화되고 있는 환적화물의 흐름을 빅데이터 기반으로 분석하고, 이를 통해 부산항이 데이터 기반 마케팅 관점에서 환적 화물의 부산항 글로벌 경쟁력 강화 전략을 수립하는데 도움을 주는 것을 목표로 한다. 분석을 위한 자 료는 부산항만공사의 Port-MIS 자료 중 부산항을 경유하는 환적화물 자료 및 를 활용한다. 또한 터미널에서 관리하고 있는 COARRI, CODECO 자료도 포함 했다. 부산항 전체는 시계열분석 방법의 하나인 ARIMA 분석 방법을 사용하였 고, 국가별, 포트별 선사별 분석에서는 이동평균법(MA)방법을 사용하여 신뢰수 준 95%하에서 벗어나는 것을 이상치로 간주하였다. 또한 해당 이상치를 감지한 국가 및 항만에 대해서 상세하게 분석하여 어떤 국가에서 어떤 항만, 어떤 선사 의 환적화물 물량이 이상이 있는지 그 원인은 무엇이며, 다른 경쟁 항만은 어떤 일이 있어나고 있는지 환적화물 물동량 패턴을 분석하여 항만공사, 항만청, 선 사, 터미널 운영사 등 부산항을 이용하는 항만 주체들의 의사 결정에 도움을 주 고자 한다. | - |
dc.description.tableofcontents | Abstract ······································································································1 제1장 서 론 ································································································8 1.1 연구의 배경과 필요성 ···············································································9 1.2 연구의 방법 ·······························································································9 제2장 이론적 고찰 ··················································································11 2.1. 빅데이터의 개념과 특징 ········································································11 2.1.1. 빅데이터의 정의 ···························································································11 2.1.2. 빅데이터 출현배경 ·······················································································12 2.1.3. 빅데이터 특징 ·······························································································15 2.2. 빅데이터 예측 분석 기법 ······································································18 2.2.1. 빅데이터 분석 기법 ·····················································································18 2.2.2. 시계열모형 ···································································································20 2.3. 해운 항만 물류 빅데이터 연구 사례 ··················································24 2.3.1. 해운 항만 물류 빅데이터 연구 사례 ·····················································26 2.3.2 물동량 변화, 예측 연구 사례 ·····································································29 제3장 부산항 환적화물 물동량 현황 및 흐름 패턴 분석 ··············35 3.1. 부산항 환적화물 물동량 현황 ······························································35 3.2. 부산항 환적화물 물동량 흐름 패턴 분석 ··········································36 - 4 - 제4장 부산항 환적화물 물동량 이상 감지 ········································42 4.1. 현행 부산항 환적화물 물동량 이상 감지 방법 ······························ 42 4.1.1. 현행 환적 화물 물동량 이상 변화 감지 방법 ·······································42 4.1.2. 시계열 모형을 이용한 환적화물 물동량 이상 감지 방법 ··················· 43 4.2. 부산항 환적화물 물동량 이상 감지 분석 ········································44 4.2.1. 이동평균법(MA)을 활용한 국가, 항만, 선사별 물동량 이상 감지 ··· 44 4.2.1.1 국가별 물동량 이상 감지 사례 ·······························································46 4.2.1.2 항만별 물동량 이상 감지 사례 ·······························································49 4.2.1.3 선사별 물동량 이상 감지 사례 ·······························································54 4.2.2. ARIMA 분석 방법을 활용한 부산항 전체 물동량 이상 감지 ··········· 57 4.2.3. 부산항 전체 물동량 이상 감지 ·······························································60 제5장 결 론 ····························································································61 5.1. 연구결과의 요약 및 시사점 ··································································61 5.2. 연구의 한계점과 과제 ············································································63 참고 문헌 ··································································································65 <국내 문헌> ····································································································65 <외국 문헌> ····································································································67 <관련 사이트> ································································································6 | - |
dc.format.extent | 67 | - |
dc.language | kor | - |
dc.publisher | 한국해양대학교 | - |
dc.rights | 한국해양대학교 논문은 저작권에 의해 보호받습니다. | - |
dc.title | 빅데이터를 활용한 부산항 환적화물 물동량 이상치 탐지 분석 | - |
dc.type | Dissertation | - |
dc.date.awarded | 2018-02 | - |
dc.contributor.alternativeName | Park Mihye | - |
dc.contributor.department | 해양금융·물류대학원 항만물류학과 | - |
dc.contributor.affiliation | 한국해양대학교 | - |
dc.description.degree | Master | - |
dc.subject.keyword | 환적화물,빅데이터,부산항,물동량,이상치 | - |
dc.title.translated | Detecting abnormal changes in transshipment cargo throughput in Busan Port using big-data | - |
dc.identifier.holdings | 000000001979▲200000000139▲200000016037▲ | - |
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.