RDDL: A systematic ensemble pipeline tool that streamlines balancing training schemes to reduce the effects of data imbalance in rare-disease-related deep-learning applications
- 22 July 2023
- journal article
- research article
- Published by Elsevier in Computational Biology and Chemistry
- Vol. 106, 107929
Abstract
No abstract availableKeywords
Funding Information
- National Science and Technology Council
- Ministry of Science and Technology, Taiwan (110-2222-E-006-017, 111-2221-E-006-231)
- National Cheng Kung University
This publication has 26 references indexed in Scilit:
- A systematic study of the class imbalance problem in convolutional neural networksNeural Networks, 2018
- Imbalanced Deep Learning by Minority Class Incremental RectificationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2018
- Challenges in Research and Health Technology Assessment of Rare Disease Technologies: Report of the ISPOR Rare Disease Special Interest GroupValue in Health, 2018
- The Cancer Genome Atlas: Creating Lasting Value beyond Its DataCell, 2018
- Focal Loss for Dense Object Detection2017
- Efficient mini-batch training for stochastic optimization2014
- Measurement of mRNA abundance using RNA-seq data: RPKM measure is inconsistent among samplesTheory in Biosciences, 2012
- Evaluating the effect of unbalanced data in biomedical document classificationJournal of Integrative Bioinformatics, 2011
- Experimental perspectives on learning from imbalanced data2007
- SMOTE: Synthetic Minority Over-sampling TechniqueJournal of Artificial Intelligence Research, 2002