Linear dimensionality reduction for classification via a sequential Bayes error minimisation with an application to flow meter diagnostics
作者：
Highlights：
• We propose a supervised linear dimensionality reduction algorithm.
• The algorithm reduces the dimensionality of data to K−1 for the K-class problem.
• The linearly reduced data is well-suited for Bayesian classification.
• Experiments on UCI datasets are performed for the proposed and existing algorithms.
• The applicability of the algorithm to flow meter diagnostics is also demonstrated.
摘要
•We propose a supervised linear dimensionality reduction algorithm.•The algorithm reduces the dimensionality of data to K−1 for the K-class problem.•The linearly reduced data is well-suited for Bayesian classification.•Experiments on UCI datasets are performed for the proposed and existing algorithms.•The applicability of the algorithm to flow meter diagnostics is also demonstrated.
论文关键词：Linear dimensionality reduction,LDA,Heteroscedasticity,Bayes error,Flow meter diagnostics
论文评审过程：Received 4 July 2017, Revised 6 September 2017, Accepted 9 September 2017, Available online 9 September 2017, Version of Record 12 September 2017.
论文官网地址：https://doi.org/10.1016/j.eswa.2017.09.010
