A deep learning based feature extraction method on hyperspectral images for nondestructive prediction of TVB-N content in Pacific white shrimp (Litopenaeus vannamei)

Abstract

Hyperspectral imaging (HSI) technique with spectral range of 900–1700 nm was implemented to predict total volatile basic nitrogen (TVB-N) content in Pacific white shrimp. Successive projections algorithm (SPA) and deep-learning-based stacked auto-encoders (SAEs) algorithm were comparatively used for spectral feature extraction. Least-squares support vector machine (LS-SVM), partial least squares regression (PLSR) and multiple linear regression (MLR) were used for prediction. The results demonstrated that the SAEs-based prediction models (SAEs-LS-SVM, SAEs-MLR and SAEs-PLSR) performed better than either full wavelengths-based or SPA-based prediction models. The SAEs-LS-SVM was considered to be the best model with RP2 value of 0.921, RMSEP value of 6.22 mg N [100 g]−1, RPD value of 3.58 and computational time of 3.9 ms for predicting TVB-N in prediction set. The results of this study indicated that SAEs has a high potential in the multivariate analysis of hyperspectral images for shrimp quality inspections.