[2020]The research findings of Zhang Xiaowen published in “Infrared Physics &Technology.”


Zhang Xiaowen, Master’s student from the Class of 2020, has had her paper titled “Rapid detection of lignin content in corn straw based on Laplacian Eigenmaps” published in the journal Infrared Physics & Technology , which is covered by SCI Zone 2 of the Chinese Academy of Sciences and with an IF=3.3. The paper was completed under the guidance of Professor Chen Zhengguang. During her graduate studies, Zhang Xiaowen published 4 SCIs, 3 of which were included in the CAS Zone 2 SCI . This paper is the final achievement of her graduate studies.

The abstract of the paper is as follows:

Lignin is an essential components ofcorn stalk and has a wide range of application. To realize the rapiddetection of lignin content in corn straw and increase the detectionaccuracy, we initially preprocess the gathered corn strawnear-infrared spectral data with Standard Normal Variabletransformation (SNV). After that, the nonlinear dimensionalityreduction method Laplacian Eigenmaps (LE) and Local Tangent SpaceAlignment (LTSA) are applied independently to reduce the dimension ofspectral data. principal component analysis (PCA), a lineardimensionality reduction method, is also utilized for spectral datadimensionality reduction. Finally, models for Partial Least SquaresRegression (PLSR) and Support Vector Regression (SVR) areconstructed. According to the model findings, LE-SVR model offers thebest prediction accuracy and stability. The determination coefficientand root mean square error of the training and tests sets are 97.17%,0.1875 and 96.25%, 0.2718 respectively. Furthermore, the relativeanalytical error is 5.0776. In addition, the study findings show thatthe number of neighbor points k has no discernible effect on themodel performance. According to the findings, nonlinear modelingusing LE-SVR for NIR spectral data of corn stover can lower modelcomplexity, while improving model prediction accuracy and stability.NIR spectroscopy may be used to determine lignin content in cornstraw. At the same time, the technique in this work offers a novelapproach for the rapidly detecting lignin content in other cropsstraw.

The DOI of the paperhttps://doi.org/10.1016/j.infrared.2023.104787