Nondestructive Prediction of Moisture and Sodium Chloride in Cold Smoked Atlantic Salmon (Salmo salar)

Salt and moisture contents in cold-smoked salmon were determined using short-wavelength near-infrared (SW-NIR) reflectance spectroscopy (600 to 1100 nm). Partial least square (PLS) regression models yielded the best results among 3 linear regression methods tested. Back-propagation neural networks (...

Full description

Saved in:
Bibliographic Details
Published in:Journal of food science 2002-09, Vol.67 (7), p.2543-2547
Main Authors: Huang, Y, Cavinato, A.G, Mayes, D.M, Bledsoe, G.E, Rasco, B.A
Format: Article
Language:English
Subjects:
artificial neural networks
Biological and medical sciences
cold
fish
Fish and seafood industries
Food industries
Food science
Fundamental and applied biological sciences. Psychology
linear models
linear regression
Moisture
near-infrared
Neural networks
nondestructive analysis
prediction
reflectance
Regression analysis
Salmo salar
Salmon
Salt
smoked salmon
sodium chloride
spectroscopy
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Salt and moisture contents in cold-smoked salmon were determined using short-wavelength near-infrared (SW-NIR) reflectance spectroscopy (600 to 1100 nm). Partial least square (PLS) regression models yielded the best results among 3 linear regression methods tested. Back-propagation neural networks (BPNN) exhibited a somewhat better capability to model salt and moisture concentrations (Salt: R(2)= 0.824, RMS = 0.55; Moisture: R(2)= 0.946, RMS = 2.44) than PLS (Salt: R(2)= 0.775, RMS = 0.63; Moisture: R(2)= 0.936, RMS = 2.65). Selection of samples from different axial locations on a fish did not affect the prediction error for salt or WPS but affected the prediction error for moisture.
ISSN:0022-1147
1750-3841
DOI:10.1111/j.1365-2621.2002.tb08773.x