Prediction measurement with mean acceptable error for proper inconsistency in noisy weldability prediction data
详细信息 查看全文
- 作者：Kyoung-Yun Kima ; kykim@eng.wayne.edu" class="auth_mail" title="E-mail the corresponding author ; Junheung Parka ; junheung@wayne.edu" class="auth_mail" title="E-mail the corresponding author ; Raj Sohmshettyb ; rsoshmshe@ford.com" class="auth_mail" title="E-mail the corresponding author
- 关键词：Weldability prediction ; Data inconsistency ; Proper inconsistency ; Mean acceptable error ; Prediction measurement
- 刊名：Robotics and Computer-Integrated Manufacturing
- 出版年：2017
- 出版时间：February 2017
- 年：2017
- 卷：43
- 期：Complete
- 页码：18-29
- 全文大小：386 K
文摘
- •
Mean acceptable error (MACE) measures noisy weldability data for prediction accuracy.
- •
The effect of noisy data on prediction accuracy is investigated using MACE.
- •
k nearest neighbor regression and generalized regression neural network are compared.
- •
Three different acceptance levels for MACE allow the level of acceptable prediction.