Cited time in webofscience Cited time in scopus

Neighborhood 러프집합 모델을 활용한 유방종양의 진단적 특징 선택

Title
Neighborhood 러프집합 모델을 활용한 유방종양의 진단적 특징 선택
Alternative Title
A Diagnostic Feature Subset Selection of Breast Tumor Based on Neighborhood Rough Set Model
Author(s)
손창식최락현강원석이종하
DGIST Authors
손창식최락현강원석이종하
Issued Date
2016-12
Type
Article
ISSN
1229-3741
Abstract
특징선택은 데이터 마이닝, 기계학습 분야에서 가장 중요한 이슈 중 하나로, 원본 데이터에서가장 좋은 분류 성능을 보여줄 수 있는 특징들을 찾아내는 방법이다. 본 논문에서는 정보 입자성을 기반으로한 neighborhood 러프집합 모델을 이용한 특징선택 방법을 제안한다. 제안된 방법의 효과성은 5,252명의유방 초음파 영상으로부터 추출된 298가지의 특징들 중에서 유방 종양의 진단과 관련된 유용한 특징들을선택하는 문제에 적용되었다. 실험결과 19가지의 진단적 특징을 찾을 수 있었고, 이때에 평균 분류 정확성은97.6%를 보였다.


Feature selection is the one of important issue in the field of data mining and machinelearning. It is the technique to find a subset of features which provides the best classificationperformance, from the source data. We propose a feature subset selection method using the neighborhoodrough set model based on information granularity. To demonstrate the effectiveness of proposed method,it was applied to select the useful features associated with breast tumor diagnosis of 298 shape featuresextracted from 5,252 breast ultrasound images, which include 2,745 benign and 2,507 malignant cases.
Experimental results showed that 19 diagnostic features were strong predictors of breast cancerdiagnosis and then average classification accuracy was 97.6%.
URI
http://hdl.handle.net/20.500.11750/4883
DOI
10.9723/jksiis.2016.21.6.013
Publisher
한국산업정보학회
Related Researcher
  • 강원석 Kang, Won-Seok
  • Research Interests Digital Phenotyping; Data Mining & Machine Learning for Text & Multimedia; Brain-Sense-ICTConvergence Computing; Computational Olfaction Measurement; Simulation&Modeling
Files in This Item:

There are no files associated with this item.

Appears in Collections:
Division of Intelligent Robotics 1. Journal Articles

qrcode

  • twitter
  • facebook
  • mendeley

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE