Combining the genetic algorithm and successive projection algorithm for the selection of feature wavelengths to evaluate exudative characteristics in frozen–thawed fish muscle

•Hyperspectral imaging was used to predict drip loss in frozen–thawed fish.•Five key wavelengths were selected by combination of GA and SPA.•GA–SPA–LS-SVM and GA–SPA–MLR models showed satisfactory performances.•The distribution maps of drip loss were generated. The potential use of feature wavelengt...

Full description

Saved in:
Bibliographic Details
Published in:Food chemistry Vol. 197; no. Pt A; pp. 855 - 863
Main Authors: Cheng, Jun-Hu, Sun, Da-Wen, Pu, Hongbin
Format: Journal Article
Language:English
Published: England Elsevier Ltd 15.04.2016
Subjects:
Algorithms
Animals
Carps
chemometrics
Ctenopharyngodon idella
drip loss
Equipment Design
exudation
fish
Food Analysis - instrumentation
Food Analysis - methods
Food Preservation
Food Quality
Frozen–thawed
Grass carp
hyperspectral imagery
least squares
Least-Squares Analysis
Linear Models
LS-SVM
Models, Theoretical
multispectral imagery
Multispectral imaging
Multivariate Analysis
muscles
Muscles - chemistry
prediction
Seafood - analysis
Seafood - standards
selection methods
Spectroscopy, Near-Infrared
Support Vector Machine
support vector machines
Variable selection
wavelengths
Multispectral imaging
Grass carp
LS-SVM
Frozen–thawed
Variable selection
ISSN:0308-8146, 1873-7072
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Hyperspectral imaging was used to predict drip loss in frozen–thawed fish.•Five key wavelengths were selected by combination of GA and SPA.•GA–SPA–LS-SVM and GA–SPA–MLR models showed satisfactory performances.•The distribution maps of drip loss were generated. The potential use of feature wavelengths for predicting drip loss in grass carp fish, as affected by being frozen at −20°C for 24h and thawed at 4°C for 1, 2, 4, and 6days, was investigated. Hyperspectral images of frozen–thawed fish were obtained and their corresponding spectra were extracted. Least-squares support vector machine and multiple linear regression (MLR) models were established using five key wavelengths, selected by combining a genetic algorithm and successive projections algorithm, and this showed satisfactory performance in drip loss prediction. The MLR model with a determination coefficient of prediction (R2P) of 0.9258, and lower root mean square error estimated by a prediction (RMSEP) of 1.12%, was applied to transfer each pixel of the image and generate the distribution maps of exudation changes. The results confirmed that it is feasible to identify the feature wavelengths using variable selection methods and chemometric analysis for developing on-line multispectral imaging.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0308-8146
1873-7072
DOI:10.1016/j.foodchem.2015.11.019