A league-winner algorithm for defect classification in an industrial web inspection system
作者：
Highlights：
• Classifier performance drastically increases by including pairwise comparisons.
• Zero-impurity Decision-Tree classifier based on number of positives is designed.
• Paper shows a formal and understandable formulation of neural network algorithms.
• Decision tree and multilayer neural networks can give rise to similar results.
• Issues appearing during the real inspection system implementation are described.
摘要
•Classifier performance drastically increases by including pairwise comparisons.•Zero-impurity Decision-Tree classifier based on number of positives is designed.•Paper shows a formal and understandable formulation of neural network algorithms.•Decision tree and multilayer neural networks can give rise to similar results.•Issues appearing during the real inspection system implementation are described.
论文关键词：Pattern recognition,pairwise comparison,artificial neural networks,decision tree,supervised training,gradient descent
论文评审过程：Received 4 September 2019, Revised 17 January 2021, Accepted 16 February 2021, Available online 26 February 2021, Version of Record 18 March 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.114753
