상세정보
학술대회
Reduction of Overfitting in Diabetes Prediction Using Deep Learning Neural Network
- 발행일
- 201709
- 출처
- International Conference on IT Convergence and Security (ICITCS) 2017 (LNEE 449), v.449, pp.35-43
- 협약과제
- 17ZS1700, 조선해양 및 육상플랜트의 스마트 HSE 시스템 개발, 장병태
- 초록
- Accurate prediction of diabetes is an important issue in health prognostics. However, data overfitting degrades the prediction accuracy in diabetes prognosis. In this paper, a reliable prediction system for the disease of diabetes is presented using a dropout method to address the overfitting issue. In the proposed method, deep learning neural network is employed where fully connected layers are followed by dropout layers. The proposed neural network outperforms other state-of-art methods in better prediction scores for the Pima Indians Diabetes Data Set.
- KSP 제안 키워드
- Accurate prediction, Data sets, Learning neural network, Prediction System, Prediction accuracy, State-of-art, deep learning(DL), diabetes prediction