Click on “Download PDF” for the PDF version or on the title for the HTML version.
If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.
Maintaining the predictive abilities of tea moisture content models on different environment based on Visible and Near-Infrared spectroscopy technique
Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org
Citation: 2019 ASABE Annual International Meeting 1901013.(doi:10.13031/aim.201901013)
Authors: Zhen xiong Huang, Hai yun Li, Lang Liu, Xiao li Li, Da peng Ye
Keywords: Direct standardization, Moisture content, Tea leaves, Visible and Near-Infrared spectroscopy.
Abstract. The objective of this work is to study the role of transfer calibration correction (TCC) in eliminating the influence of detection environment on tea moisture content model. Spectrum of 6 days samples, including two tea varieties and each variety lasts three days, were divided into modeling set and prediction set in the ratio of 2:1, and used to establish moisture content model by partial least squares regression (PLSR) after multiplicative scatter correction (MSC) pre-treatment. The result showed that the moisture content of tea leaves which can be determined quickly and non-destructively by Visible and Near-Infrared (Vis/NIR) spectroscopy with the determination coefficients () were greater than 0.9209 and the root-mean-square error (RMSEC) were less than 0.0411. Direct standardization (DS) algorithm was utilized to model transfer in the same species of different days. The results show that DS algorithm can eliminate the influence of environment on spectral modeling, especially when the environmental difference tremendously, the effect of DS algorithm was obviously. Through this study, ideas were provided for the establishment of a stable tea moisture content detection model.
(Download PDF) (Export to EndNotes)