RFE and Chi-Square Based Feature Selection Approach for Detection of Diabetic Retinopathy

DOI

10.2991/aer.k.201124.069How to use a DOI?

Keywords

programming assessment tool, programming, clustering, K-Means

Abstract

Diabetic retinopathy, which is one of the complications in diabetes, is an eye disease that can lead to blindness. The damage happens in retina as result of a long period of diabetic mellitus. People usually do research using image data in diabetic patients. This paper presents the idea of using feature selection in diabetic retinopathy. In this study, we use the data of diabetic patients that will be extracted with feature selection method. The feature selection used in this study is Recursive Feature Elimination (RFE) and Chi-Square. Then, the classification of diabetic retinopathy is done by using Support Vector Machine (SVM). Based on the experiment’s result with various hyperparameters tunning, the classification model obtains the accuracy of 97%-100% for both methods.

Copyright

© 2020, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Alifah
AU  - Titin Siswantining
AU  - Devvi Sarwinda
AU  - Alhadi Bustamam
PY  - 2020
DA  - 2020/11/24
TI  - RFE and Chi-Square Based Feature Selection Approach for Detection of Diabetic Retinopathy
BT  - Proceedings of the International Joint Conference on Science and Engineering (IJCSE 2020)
PB  - Atlantis Press
SP  - 380
EP  - 386
SN  - 2352-5401
UR  - https://doi.org/10.2991/aer.k.201124.069
DO  - 10.2991/aer.k.201124.069
ID  - 2020
ER  -