Parallel versus cascaded logistic regression trained single-hidden feedforward neural network for medical data
作者：
Highlights：
• Two efficient extensions of the LogSLFN for multiple decision classes are proposed.
• Experimental results on 2 datasets to compare the proposed models are presented.
• A statistical comparison between the parallel and cascaded extensions is done.
• The classification accuracy for the parallel extension of the LogSLFN is consistent and high.
• A statistical analysis of the proposed models versus state-of-the-art ones is performed.
摘要
•Two efficient extensions of the LogSLFN for multiple decision classes are proposed.•Experimental results on 2 datasets to compare the proposed models are presented.•A statistical comparison between the parallel and cascaded extensions is done.•The classification accuracy for the parallel extension of the LogSLFN is consistent and high.•A statistical analysis of the proposed models versus state-of-the-art ones is performed.
论文关键词：Logistic regression,Single hidden feedforward neural networks,Multiple-decision classes,Statistical assessment,Gene expression,Liver fibrosis stadialization
论文评审过程：Received 2 April 2020, Revised 20 December 2020, Accepted 24 December 2020, Available online 30 December 2020, Version of Record 9 January 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2020.114538
