A cost-sensitive convolution neural network learning for control chart pattern recognition

作者：

Highlights：

• We discussed practical challenges for control chart pattern recognition problem.

• We developed a convolutional neural network to address imbalancedness and scale.

• We studied the performance of our model on simulated and real-world data.

• We demonstrated its benefits over the conventional neural network models.

摘要

•We discussed practical challenges for control chart pattern recognition problem.•We developed a convolutional neural network to address imbalancedness and scale.•We studied the performance of our model on simulated and real-world data.•We demonstrated its benefits over the conventional neural network models.

论文关键词：Convolutional neural network,Time-series classification,Imbalanced data,Control chart pattern recognition

论文评审过程：Received 26 August 2019, Revised 11 December 2019, Accepted 2 February 2020, Available online 3 February 2020, Version of Record 19 February 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113275