Calibration transfer via an extreme learning machine auto-encoder
Calibration transfer via an extreme learning machine auto-encoder
复制标题
通过极限学习机自动编码器进行校准传输
DOI：
10.1039/c5an02243f
复制
发表时间：
2016-01-01
期刊：
影响因子：
4.2
通讯作者：
Liang, Yi-Zeng
中科院分区：
文献类型：
--
作者：
Chen, Wo-Ruo;Bin, Jun;Liang, Yi-Zeng
为了解决近红外光谱分析中的光谱标准化问题，提出了一种基于极端学习机的自动编码器转换方法。对TEAM、分段直接标准化（PDS）、广义最小二乘法（GLS）和基于典型相关分析（CCA）的校正传递方法进行了比较研究，并以玉米、烟草和药片光谱数据为基准对这些算法的性能进行了测试。结果表明，TEAM是一种稳定的方法，与PDS，GLS和CCA相比，可以显着降低预测误差。在大多数情况下，TEAM还可以使用少量校准集实现最佳RMSEP。TEAM是用Python语言实现的，可以在https：//github上作为开源包获得。com/zmzhang/TEAM.
In order to solve the spectra standardization problem in near-infrared (NIR) spectroscopy, a Transfer via Extreme learning machine Auto-encoder Method (TEAM) has been proposed in this study. A comparative study among TEAM, piecewise direct standardization (PDS), generalized least squares (GLS) and calibration transfer methods based on canonical correlation analysis (CCA) was conducted, and the performances of these algorithms were benchmarked with three spectral datasets: corn, tobacco and pharmaceutical tablet spectra. The results show that TEAM is a stable method and can significantly reduce prediction errors compared with PDS, GLS and CCA. TEAM can also achieve the best RMSEPs in most cases with a small number of calibration sets. TEAM is implemented in Python language and available as an open source package at https://github. com/zmzhang/TEAM.