메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색

논문 기본 정보

자료유형
학위논문
저자정보

맹환 (원광대학교, 원광대학교 일반대학원)

지도교수
최동운
발행연도
2022
저작권
원광대학교 논문은 저작권에 의해 보호받습니다.

이용수57

표지
AI에게 요청하기
추천
검색

이 논문의 연구 히스토리 (2)

초록· 키워드

오류제보하기
사물 인터넷과 웨어러블 기기 등의 스마트 디바이스의 등장 및 빠른 대중화와 함께 의료 정보 기술의 급속한 발전으로 사람들은 개인의 신체와 건강 관리에 보다 높은 수준의 관심을 보이고 있다. 이미 심부전, 졸도, 전도 등 다양한 질환들에 대한 예측모델이 완성되었지만, 공황장애는 관련 데이터가 매우 복잡하여 정량적으로 평가하고 측정하기 어렵기 때문에 전통적인 수학적, 통계학적 방법으로는 정확한 공황장애 예측 모형을 수립하기 어렵다. 따라서 컨텍스트 기술의 도움으로 공황장애를 조기에 진단하고 예방하는 것이 필요한다.
본 논문은 의료 및 건강 검진 기록을 바탕으로 공황장애 추론 모델을 구축하기 위한 온톨로지를 제안하고, 환자의 진단 피드백을 통합하여 KNN 및 SVM 학습 알고리즘을 기반으로 질병 위험 예측 시스템을 설계 및 완성하며, 알고리즘의 성능. 먼저 KNN과 SVM 알고리즘을 이용하여 상태 체크 데이터에 대한 전처리 및 특징 선택 기술을 제안한다. 그 후, 공황장애 증상을 예측하기 위한 모델을 설계하고, 적절한 평가 지표를 선택하기 위해 알고리즘을 비교하여 학습 알고리즘의 장점을 검증한다. 마지막으로 학습 알고리즘을 핵심으로 모델 효과 피드백 알고리즘 성능에 따라 공황장애 예측 시스템을 설계한다. 본 논문에서는 KNN 및 SVM 학습 알고리즘을 기반으로 질병 위험 예측 시스템을 설계 및 완성하고 알고리즘 성능의 장점을 검증하였다. KNN과 SVM 알고리즘을 비교하여 SVM이 공황 장애에 더 나은 진단 효과가 있다고 판단되어 공황 장애 진단 및 식별의 목적을 달성한다.

목차

CHAPTER 1. INTRODUCTION ········································································ 1
1.1 Background ·········································································································· 1
1.2 Current status of domestic and international research ··································· 5
1.3 Research Purpose and Dissertation Structure ·················································· 8
CHAPTER 2. Related works ············································································· 10
2.1 Context-aware ···································································································· 10
2.1.1 Definition of Context-aware ·································································· 10
2.1.2 Context-aware technology ······································································ 13
2.1.3 Architecture of context-aware computing ············································ 17
2.2 Ontology ············································································································ 26
2.2.1 Definition of Ontology ·········································································· 26
2.2.2 Ontology modeling meta-language ······················································· 28
2.2.3 Ontology Description Language ···························································· 30
2.2.4 Guidelines for ontology construction ··················································· 31
2.3 IOT ····················································································································· 33
2.3.1 Definition of IOT ··················································································· 33
2.3.2 IOT Technology ····················································································· 34
2.4 Panic disorder care system ·············································································· 39
2.4.1 Overview of panic disorder ·································································· 39
2.4.2 Factors influencing the onset of panic disorder ································· 40
2.4.3 Diagnostic criteria for panic disorder ·················································· 41
- ii -
CHAPTER 3. The design of panic disorder care system based on context
awareness ····················································································· 43
3.1 Panic disorder prediction system based on context awareness ··················· 43
3.1.1 Context information ontology modeling ·············································· 46
3.1.2 Context information based on Panic Disorder ···································· 54
3.1.3 Based on smart devices IoT and Context ·········································· 59
3.2 Hardware configuration ···················································································· 60
3.3 Software application technology ····································································· 62
3.3.1 Composition of Ontology ······································································ 62
3.4 Prediction of panic disorder by machine learning KNN and SVM algorithm
··························································································································· 68
3.4.1 Technical Implementation of Algorithmic Systems ···························· 68
3.4.2 Performance evaluation criteria of the model ····································· 76
CHAPTER 4. The Design of App Screen and validation of panic disorder care
system ·························································································· 83
4.1 Panic attack data analysis ················································································ 83
4.1.1 Model building and effect comparison ················································ 84
4.1.2 The flow of the improved algorithm is described in detail ············· 86
4.1.3 Comparison and analysis of the data with SVM and KNN algorithms
················································································································· 88
4.2 System Design ·································································································· 91
4.2.1 Functional design ···················································································· 91
4.2.2 System Implementation ·········································································· 93
4.2.3 Screen design of panic disorder case system ····································· 97
CHAPTER 5. CONCLUSION ··········································································· 99

최근 본 자료

전체보기

댓글(0)

0