Prediction of various freshness indicators in fish fillets by one multispectral imaging system

Abstract

In current study, a simple multispectral imaging (430–1010 nm) system along with linear and non-linear regressions were used to assess the various fish spoilage indicators during 12 days storage at 4 ± 2 °C. The indicators included Total-Volatile Basic Nitrogen (TVB-N) and Psychrotrophic Plate Count (PPC) and sensory score in fish fillets. immediately, after hyperspectral imaging, the reference values (TVB-N, PPC and sensory score) of samples were obtained by traditional method. To simplify the calibration models, nine optimal wavelengths were selected by genetic algorithm. The prediction performance of various chemometric models including partial least-squares regression (PLSR), multiple-linear regression (MLR), least-squares support vector machine (LS-SVM) and back-propagation artificial neural network (BP-ANN) were compared. All models showed acceptable performance for simultaneous predicting of PPC, TVB-N and sensory score (R2P ≥ 0.853 and RPD ≥ 2.603). Non-linear models were considered better quantitative model to predict all of three freshness indicators in fish fillets. Among the three spoilage indices, the best predictive power was obtained for PPC value and the weakest one was acquired for TVB-N content prediction. The best model for prediction TVB-N (R2p = 0.862; RMSEP = 3.542 and RPD = 2.678) and sensory score (R2p = 0.912; RMSEP = 1.802 and RPD = 3.33) belonged to GA-LS-SVM and for prediction of PPC value was BP-ANN (R2p = 0.921; RMSEP = 0.504 and RPD = 3.64). Therefore, developing multispectral imaging system based on LS-SVM model seems to be suitable for simultaneous prediction of all three indicators (R2P > 0.862 and RPD > 2.678). Further studies needed to improve the accuracy and applicability of HSI system for predicting freshness of rainbow-trout fish.

Evaluation of the total volatile basic nitrogen (TVB-N) content in fish fillets using hyperspectral imaging coupled with deep learning neural network and meta-analysis

“…Based on Table 3 and Fig. 3, the performance of LDNN model was comparable with the results of previous works established for prediction of TVB-N value of various meat and seafood products based on hyperspectral imaging systems [5][6][7]33 . Figure 3a,b showed the effect of various chemometric algorithms on the predictive power of hyperspectral imaging system.…”

“…A mean spectrum for each fish fillet was obtained and used as input data for evaluation TVB-N values of the samples based on a trained deep learning algorithm. Savitzky-Golay (S-G) algorithm was used to decline the noises of extracted average spectrum (by: Unscrambler 10.4; CAMO, Trondheim, Norway) 5 .…”

“…Generally, a suitable prediction model can be introduced based on the following principles: (i) high value of determination coefficient (poor model: R 2 < 0.82; good model: 0.82 ≤ R 2 ≤ 0.9; and excellent model: R 2 > 0.9); (ii) high RPD value (RPD < 1.5: very poor model; 1.5 < RPD < 2.0: poor model; 2 < RPD < 2.5: fair model; 2.5 < RPD < 2.5: good model; RPD > 3: very good model and R > 5: excellent model) (iii) low RMSEs values and (iv) a small difference between RMSEC and RMSEP value 1,44,45 . The building, validation, and evaluation processes of LDNN model were carried out in MATLAB R2016a (The Mathworks Inc., Natick, MA, USA) 5,32 .…”

Sensing Technology for Fish Freshness and Safety: A Review

“…The model created with only fat tissue spectra obtained the best results, with an R 2 CV (in cross-validation) of 0.89 (RMSECV = 2.7 days). More recently, Khoshnoudi-Nia et al [ 110 ] studied the assessment of TVB-N, psychotropic plate count (PPC), and sensory score in rainbow trout fillets. Four different multivariate analyses were developed: PLSR, MLR, LS-SVM, and back propagation neural network (BP-NN), each of which used six optimal wavelengths determined by GA, coming from the original range of 430–1010 nm.…”

Image Analysis and Computer Vision Applications in Animal Sciences: An Overview

“…Since these earlier studies, there has been an increasing interest in the use of computer vision for prediction of the most diverse meat quality traits, not only for beef but also for fish, poultry, and pork ( Table 2). There are applications focused on imaging technologies for determination of not only meat crude protein and fat content but also more refined chemical characteristics like fatty acids profile, freshness (50,57), as well as prediction of meat quality, palatability, tenderness, and other traits normally evaluated by a panel of trained experts (45,46,51) or even automatic sorting and weighing cuts and viscera which is normally performed manually (48,52). Again, different devices and imaging technologies have been used, with several predictive approaches evaluated.…”