악성 심실 부정맥(MVA)의 자발적 예측은 구조 작업의 지연을 방지하는 데 유용하다. 최근 연구자들은 심전도(ECG)에서 파생된 다양한 기능을 사용하여 MVA를 예측하는 몇 가지 알고리듬을 개발했다. 그러나 여전히 불분명한 예측에 대한 ECG 기능 수의 영향, 발생 MVA에 대한 경고가 매우 늦게 도착할 가능성, 설정 몇 분 전에 MVA를 예측하는 알고리듬의 성능 불확실성 등 MVA 예측과 관련하여 해결되지 않은 몇 가지 문제가 있다. 앞서 언급한 문제를 극복하기 위해 본 연구는 의사결정 트리 분류기에 구현된 ECG 기능의 수와 유형에 대한 심층 연구를 수행한다. 또한 본 연구는 MVA에 대한 경고 지연을 최소화하기 위해 MVA 발생 전 알고리듬의 실행 시간을 조사한다. 마지막으로, 본 연구는 MVA 예측 알고리듬의 성능을 때때로 드러내기 위해 알고리듬의 민감성과 특수성을 모두 연구하는 것을 목표로 한다. 분석 결과를 강화하기 위해 서포트 벡터 머신과 순진한 베이즈 같은 여러 분류기도 비교 연구를 위해 검사된다. 목표를 달성하기 위해 필요한 단계는 세 가지입니다. 첫 번째 단계는 기존의 관련 연구에 대한 문헌 검토이다. 2단계에서는 MVA를 예측하기 위한 4개 모듈의 설계와 개발을 다룬다. 엄격한 실험은 기능 선택 및 분류 모듈에서 수행된다. 결과는 의사결정 트리 분류기가 있는 8개의 심전도 기능이 실행 시간 및 민감도 측면에서 우수한 예측 성능을 달성했음을 보여준다. 또한 결과는 부정맥 사건이 시작되기 전 4차 5분 간격(15.1분~20분)에서 민감도와 특이도에 대한 가장 높은 비율이 각각 95%와 90%임을 보여준다. 이러한 결과는 네 번째 5분 간격이 예측을 수행하기에 가장 좋은 시간이 될 것임을 암시한다.
제 1편 : MATLAB 기본편
1. MATLAB 기본사용편 ···················· 003
1.1 MATLAB 시작하기 ·························· 003
명령창(command Window)에서의 입력 005
도움말(Help)의 이용 ······························· 007
1.2 입력 오류의 수정 ····························· 008
계산의 중지 ·············································· 009
MATLAB 종료하기 ································· 009
1.3 연산과 변수의 할당 ·························· 009
연산자 우선순위 ······································· 011
내장함수 ···················································· 012
1.4 데이터의 표현 ··································· 013
1.5 변수의 처리 ······································· 015
변수 이름 ·················································· 015
clear 명령어 ············································· 016
특수변수와 정수 ······································· 017
whos 명령어 ············································ 017
1.6 벡터와 행렬 ······································· 018
벡터 ··························································· 018
행렬 ·························································· 023
스크린 출력과 억제 ································· 024
1.7 랜덤(Random)수와 복소수 ·············· 025
랜덤 수 ····················································· 025
복소수 ······················································· 027
1.8 기호를 이용한 연산 ·························· 028
기호식에서의 치환 ··································· 029
1.9 코드 파일 ·········································· 030
스크립트 코드 파일 ································· 030
코멘트의 추가 ·········································· 032
함수 코드 파일 ···································· 033
사용자 정의함수 ······································ 036
1.10 간단한 그래프의 생성 ····················· 037
ezplot을 이용한 그래프 ·························· 037
plot을 이용한 그래프 ·························· 039
3차원 그래프 ··········································· 042
1.11 MATLAB과 엑셀(Excel)의 접속 043
엑셀 데이터 불러오기 ····························· 043
데이터 가져오기 옵션 ························· 046
스크립트 생성 옵션 ································· 049
함수 생성 옵션 ········································ 049
생성된 데이터를 엑셀파일로 저장하기 ·· 050
제 2편 : 연구논문
ECG-based prediction algorithm for imminent malignant ventricular
arrhythmias using decision tree
1. Introduction 52
2. Databases 54
3. Methods 55
4. Discussion 64
5. Conclusion 67
6. References 68
