Nondestructive determination of IMP content in chilled chicken based on hyperspectral data combined with chemometrics

This study was conducted to investigate the potential of hyperspectral imaging technique (900-1700 nm) for nondestructive determination inosinic acid (IMP) in chicken. Hyperspectral images chicken flesh samples were acquired, and their mean spectra within extracted. The quantitative relationship between reference IMP value fitted by partial least squares (PLS) regression algorithm. A PLS model (MAS-PLS) built with moving average smoothing (MAS) showed better performance predicting content, leading correlation coefficients (RP) 0.951, root square error (RMSEP) 0.046 mg/g, residual predictive deviation (RPD) 3.152. Regression coefficient (RC), successive projections algorithm (SPA), stepwise, competitive adaptive reweighted sampling (CARS), uninformative variable elimination (UVE) used select optimal wavelengths optimize MAS-PLS model. Based on 18 (907.14, 917.02, 918.67, 926.90, 930.20, 936.78, 956.54, 1004.28, 1135.89, 1211.56, 1302.07, 1367.94, 1397.60, 1488.31, 1680.17, 1683.49, 1686.80 1695.10 selected from MAS SPA, MAS-SPA-PLS RP 0.920, RMSEP 0.056 mg/g RPD 3.220, which similar overall indicated that 900-1700 nm range combined SPA could be predict content flesh. Keywords: near-infrared imaging, chicken, acid, squares, DOI: 10.25165/j.ijabe.20221501.6612 Citation: Wang Y Y, He H J, Jiang S Q, Ma J. Nondestructive chilled based data chemometrics. Int J Agric & Biol Eng, 2022; 15(1): 277–284.