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
학술저널
저자정보
Romany F. Mansour (New Valley - Assiut University)
저널정보
대한의용생체공학회 Biomedical Engineering Letters (BMEL) Biomedical Engineering Letters (BMEL) Vol.8 No.1
발행연도
2018.1
수록면
41 - 57 (17page)

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색

초록· 키워드

오류제보하기
The high-pace rise in advanced computing andimaging systems has given rise to a new research dimensioncalled computer-aided diagnosis (CAD) system forvarious biomedical purposes. CAD-based diabeticretinopathy (DR) can be of paramount significance toenable early disease detection and diagnosis decision. Considering the robustness of deep neural networks(DNNs) to solve highly intricate classification problems, inthis paper, AlexNet DNN, which functions on the basis ofconvolutional neural network (CNN), has been applied toenable an optimal DR CAD solution. The DR modelapplies a multilevel optimization measure that incorporatespre-processing, adaptive-learning-based Gaussian mixturemodel (GMM)-based concept region segmentation, connectedcomponent-analysis-based region of interest (ROI)localization, AlexNet DNN-based highly dimensional featureextraction, principle component analysis (PCA)- andlinear discriminant analysis (LDA)-based feature selection,and support-vector-machine-based classification to ensureoptimal five-class DR classification. The simulation resultswith standard KAGGLE fundus datasets reveal that theproposed AlexNet DNN-based DR exhibits a better performancewith LDA feature selection, where it exhibits aDR classification accuracy of 97.93% with FC7 features,whereas with PCA, it shows 95.26% accuracy. Comparativeanalysis with spatial invariant feature transform (SIFT)technique (accuracy—94.40%) based DR feature extractionalso confirms that AlexNet DNN-based DR outperformsSIFT-based DR.

목차

등록된 정보가 없습니다.

참고문헌 (51)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

이 논문의 저자 정보

최근 본 자료

전체보기

댓글(0)

0