A novel stacked regression algorithm based on slice transform for small sample size problem in spectroscopic analysis | |
Yifan Wu1,2; Silong Peng1,2; Qiong Xie1; Quanjie Han1 | |
2018-05 | |
会议名称 | ICISCE 2018 : IEEE 5th International Conference on Information Science and Control Engineering |
会议日期 | July 20-22, 2018 |
会议地点 | Zhengzhou, China |
会议录编者/会议主办者 | Henan University of Science and Technology |
出版地 | America |
出版者 | IEEE |
摘要 | In spectroscopic data analysis, small sample size (SSS) problem occurs. A solution is to perform variable selection, which has been proved to be critical to improve the performance of the regression model, such as partial least squares (PLS) regression. Stacked moving window partial least squares (SMWPLS) aims to combine variable sets instead of selecting a subset to improve the model robustness. In this study, we proposed a novel weighting strategy to calculate the combination weights. Slice transform (SLT) is used to map the cross-validation (CV) weights to new weights in a piecewise linear manner. The parameters of SLT are optimized with the least-square criterion. Experiments on two near-infrared (NIR) data sets demonstrated the efficiency of the proposed SLT weighting. |
关键词 | Small Sample Size Problem Variable Selection Stacked Regression Slice Transform |
学科门类 | 工学 |
DOI | DOI 10.1109/ICISCE.2018.00026 |
URL | 查看原文 |
收录类别 | EI |
语种 | 英语 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/23537 |
专题 | 智能制造技术与系统研究中心_多维数据分析(彭思龙)-技术团队 |
通讯作者 | Silong Peng |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences, 100190, Beijing, China 2.University of Chinese Academy of Sciences, 100190, Beijing, China |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Yifan Wu,Silong Peng,Qiong Xie,et al. A novel stacked regression algorithm based on slice transform for small sample size problem in spectroscopic analysis[C]//Henan University of Science and Technology. America:IEEE,2018. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
A novel stacked regr(358KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论