Chen Wo-Ruo, Bin Jun, Lu Hong-Mei, Zhang Zhi-Min, Liang Yi-Zeng
College of Chemistry and Chemical Engineering, Central South University, Changsha 410083, China.
College of Bioscience and Biotechnology, Hunan Agriculture University, Changsha 410128, China.
Analyst. 2016 Mar 21;141(6):1973-80. doi: 10.1039/c5an02243f.
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.
为了解决近红外（NIR）光谱中的光谱标准化问题，本研究提出了一种基于极限学习机自动编码器的转移方法（TEAM）。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）的校准转移方法进行了比较研究，并使用三个光谱数据集（玉米、烟草和药片片剂光谱）对这些算法的性能进行了基准测试。结果表明，TEAM是一种稳定的方法，与PDS、GLS和CCA相比，能显著降低预测误差。在大多数情况下，TEAM使用少量校准集也能实现最佳的预测均方根误差（RMSEPs）。TEAM用Python语言实现，并作为开源包可在https://github.com/zmzhang/TEAM获取。
Zotero 插件