RFE and Chi-Square Based Feature Selection Approach for Detection of Diabetic Retinopathy
Alifah, Titin Siswantining, Devvi Sarwinda, Alhadi Bustamam
Available Online 24 November 2020.
- https://doi.org/10.2991/aer.k.201124.069How to use a DOI?
- programming assessment tool, programming, clustering, K-Means
- 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.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
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 - https://doi.org/10.2991/aer.k.201124.069 ID - Alifah2020 ER -