Research Article
Data Mining for Material Feeding Optimization of Printed Circuit Board Template Production
Algorithm 1
Multivariate boxplot-based outlier detection of scrap rate.
Input: samples; categorical variable set | Output: Outlier frequency for each sample | Initialize: | for do | set as the values of feature | Plot a boxplot of scrap rate for each values in , and detect samples with scrap rate out of | for each boxplot; and outlier frequency of these samples are added by 1. | End for | Remove the samples corresponding to with , . Return |
|