Key Variables Screening of Near-Infrared Models for Simultaneous Determination of Quality Parameters in Traditional Chinese Food “Fuzhu”

Jiahua Wang,Jingjing Cheng,Qingyu Li,Xiaowei Zhang,Jun Wang

doi:10.1155/2018/3136516

Abstract

The traditional Chinese food Fuzhu is a dried soy protein-lipid film formed during the heating of soymilk. This study investigates whether a simple and accurate model can nondestructively determine the quality parameters of intact Fuzhu. The diffused reflectance spectra (1000–2499 nm) of intact Fuzhu were collected by a commercial near-infrared (NIR) spectrometer. Among various preprocessing methods, the derivative by wavelet transform method optimally enhanced the characteristic signals of Fuzhu spectra. Uninformative variable elimination based on Monte Carlo (MC-UVE), random frog (RF), and competitive adaptive reweighted sampling (CARS) were proposed to select key variables for partial least squares (PLS) calculation. The strong performance of the developed models is attributed to the high ratios of prediction to deviation values (3.32–3.51 for protein, 3.62–3.89 for lipid, and 4.27–4.55 for moisture). The prediction set was used to assess the performances of the best models of protein (CARS-PLS), lipid (RF-PLS), and moisture (CARS-PLS), which resulted in greater coefficients of determination of 0.958, 0.966, and 0.976, respectively, and lower root mean square errors of prediction of 0.656%, 0.442%, and 0.123%, respectively. Combined with chemometrics methods, the NIR technique is promising for simultaneous testing of quality parameters of intact Fuzhu.

Highlights

The Chinese traditional soybean food “Fuzhu” originates from the Tang Dynasty in ancient China and has long been considered a luxury in China and Japan
The protein, lipid, and moisture contents of intact Fuzhu were determined simultaneously by NIR spectroscopy in diffused reflectance mode
The efficiencies of various preprocessing methods were assessed by the root mean squared error of cross-validation (RMSECV) value computed by Monte Carlo cross-validation (MCCV)

Summary

Introduction

The Chinese traditional soybean food “Fuzhu” originates from the Tang Dynasty in ancient China and has long been considered a luxury in China and Japan. Used preprocessing methods are Savitzky Golay (SG) smoothing [7], the Norris derivative filter (NDF), firstorder derivative (1D) or second-order derivative (2D), multiplicative scatter correction (MSC), and the standard normal variate (SNV) [8] These methods, respectively, filter the highfrequency noises, improve the signal-to-noise ratio, enhance the spectroscopy resolution, resolve the overlapping peaks, correct the baseline, and eliminate scatter. To our knowledge, key variables selection by NIR modeling for simultaneous determination of the quality parameters in Fuzhu has never been reported. The present work applies NIR spectroscopy to the simultaneous determination of protein, lipid, and moisture contents in intact Fuzhu. The specific objectives were (1) to determine a suitable pretreatment method for spectral processing; (2) to select the key variables for protein, lipid, and moisture analyses by MC-UVE, FR, and CARS; (3) to develop PLS models and inspect their practical performances

Materials and Methods

Chemometrics

Results and Discussion

Screening for Key Wavelengths

Conclusion