지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술대회자료
- 저자정보
- 발행연도
- 2018.6
- 수록면
- 1,663 - 1,666 (4page)
이용수
초록· 키워드
오류제보하기
Health care systems or Hospital Information systems have accumulated a lot of amount of medical data. The naive feature set might have noisy or redundant features. The performance of complex model for the initial data can deteriorate, since the naive data set might have noisy or redundant features and they require a lot of resources and time for computation.
To Challenge this problem, We applied a series of feature selection(FS) techniques to the prediction of the modified Rankin Scale (mRS), which is a measure of the daily activity disorder of people suffering from stroke, using the 8 famous FS.
The experiment compared the performance of classifications with FS algorithms using stroke data set that is supposed of 81 representation features for stroke. Experimental results show that, Random Foest(RF) classification with a filter based for FS using of f-score and t-score performed best in accuracy. It was also demonstrated that Genetic algorithm(GA) with RF produced the most effective set in the 3 wrapper methods.
GA with RF produced the most effective feature set for mRS prediction, This can have almost the same accuracy with 69.6% less model learning time than all features.
To Challenge this problem, We applied a series of feature selection(FS) techniques to the prediction of the modified Rankin Scale (mRS), which is a measure of the daily activity disorder of people suffering from stroke, using the 8 famous FS.
The experiment compared the performance of classifications with FS algorithms using stroke data set that is supposed of 81 representation features for stroke. Experimental results show that, Random Foest(RF) classification with a filter based for FS using of f-score and t-score performed best in accuracy. It was also demonstrated that Genetic algorithm(GA) with RF produced the most effective set in the 3 wrapper methods.
GA with RF produced the most effective feature set for mRS prediction, This can have almost the same accuracy with 69.6% less model learning time than all features.
목차
Abstract
I. 서론
II. 관련 작업
III. 본론
IV. 구현
V. 결론 및 향후 연구 방향
참고문헌
참고문헌 (0)
참고문헌 신청함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
New Feature Selection Method for Text Categorization
Journal of information and communication convergence engineering
2017 .03
-
Feature Selection Based on Bi-objective Differential Evolution
Journal of Computing Science and Engineering
2017 .12
-
Feature selection based on rough set theory using feature space decomposition for mixed-type data
대한산업공학회 춘계공동학술대회 논문집
2016 .04
-
A Feature Selection Method for Classifying Highly Similar Text Documents
Industrial Engineering & Management Systems
2021 .06
-
Performance Evaluation of a Feature-Importance-based Feature Selection Method for Time Series Prediction
Journal of information and communication convergence engineering
2023 .03
-
다변량 시계열 데이터 분류를 위한 특징 선택 방법
대한산업공학회지
2017 .12
-
An improved feature selection based on the effective range minimizing redundancy among features for multi-class data
대한산업공학회 춘계공동학술대회 논문집
2015 .04
-
다양한 지역특징들의 결합 특징을 이용한 기체 분류 방법
한국컴퓨터정보학회논문지
2016 .09
-
A Novel Enhanced Random Forest for Medical Data Classification using Correlation Pearson and Best Number of Trees
Journal of Computing Science and Engineering
2024 .03
-
ModifiedFAST: A New Optimal Feature Subset Selection Algorithm
Journal of information and communication convergence engineering
2015 .06
-
Diagnosis of Alzheimer’s Disease using Wrapper Feature Selection Method
스마트미디어저널
2023 .04
-
A comparative study of filter methods based on information entropy
Journal of Advanced Marine Engineering and Technology (JAMET)
2016 .06
-
이종 특징 결합을 이용한 하이브리드 패턴 인식 방법
한국컴퓨터정보학회논문지
2015 .11
-
결정트리 기반의 비정상계약 분류모델을 위한 변수 선택 기법 연구
Proceedings of KIIT Conference
2023 .11
-
Dynamic Mutual Information Based Feature Selection for Multi-label Learning
대한산업공학회 추계학술대회 논문집
2018 .11
-
Extraction of Critical Low-Level Image Features for Effective Emotion Analysis
제어로봇시스템학회 논문지
2019 .04
-
설비진단을 위한 초음파 신호의 특징분석 적용
한국소음진동공학회논문집
2017 .10
-
유전 알고리즘 기반 특징 분석 기법을 이용한 고 신뢰성 유도 전동기 결함 분류
한국소음진동공학회 학술대회논문집
2015 .04
-
데이터의 중요 특성 선택과 전처리에 기반한 분류체계의 적용
한국산학기술학회 논문지
2021 .08
-
Biological Feature Selection and Disease Gene Identification using New Stepwise Random Forests
Industrial Engineering & Management Systems
2017 .03
이 논문의 저자 정보
이 논문과 함께 이용한 논문
뇌졸중 환자의 감각 이상 간호알고리즘 개발 및 적용
이윤정
,
이지아
성인간호학회지
2018
.06
급성기 뇌졸중 입원환자 가족 간호제공자의 부담감 영향요인
임정순
,
정복례
한국간호교육학회지
2018
.05
뇌졸중 환자의 연하장애와 음성과의 상관관계 연구
유영진
,
유태영
한국언어치료학회 학술발표대회 논문집
2020
.11
노인코호트 DB를 이용한 딥러닝 기반의 뇌졸중 질환 예측 모델
유재학
,
권순현
,
호치멍 벤자민
외 4명
디지털콘텐츠학회논문지
2020
.06
수면장애 환자와 일반인의 음성 차이점 분석
이강진
,
이상붕
,
최영성
외 5명
한국통신학회 학술대회논문집
2019
.01
최근 본 자료
댓글(0)
0