Loading…

Developing a multispectral imaging for simultaneous prediction of freshness indicators during chemical spoilage of grass carp fish fillet

This study investigated the feasibility of developing a multispectral imaging method using key wavelengths from hyperspectral images for modeling and simultaneously predicting total volatile basic nitrogen (TVB-N), thiobarbituric acid reactive substances (TBARS) and K value in grass carp fillet duri...

Full description

Saved in:
Bibliographic Details
Published in:Journal of food engineering 2016-08, Vol.182, p.9-17
Main Authors: Cheng, Jun-Hu, Sun, Da-Wen, Qu, Jia-Huan, Pu, Hong-Bin, Zhang, Xiao-Chao, Song, Zhongxiang, Chen, Xinghai, Zhang, Hong
Format: Article
Language:English
Subjects:
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!
cited_by cdi_FETCH-LOGICAL-c448t-d20adcd7c3c2895f27f5cb9d387e51636c58b8807e91f395b00fa0141781f2a93
cites cdi_FETCH-LOGICAL-c448t-d20adcd7c3c2895f27f5cb9d387e51636c58b8807e91f395b00fa0141781f2a93
container_end_page 17
container_issue
container_start_page 9
container_title Journal of food engineering
container_volume 182
creator Cheng, Jun-Hu
Sun, Da-Wen
Qu, Jia-Huan
Pu, Hong-Bin
Zhang, Xiao-Chao
Song, Zhongxiang
Chen, Xinghai
Zhang, Hong
description This study investigated the feasibility of developing a multispectral imaging method using key wavelengths from hyperspectral images for modeling and simultaneously predicting total volatile basic nitrogen (TVB-N), thiobarbituric acid reactive substances (TBARS) and K value in grass carp fillet during chemical spoilage. The established least-squares support vector machine (LS-SVM) and multiple linear regression (MLR) models using five successive projection algorithm (SPA)-selected and six genetic algorithm (GA)-selected wavelengths showed excellent performances for predicting TVB-N and K value with R2P > 0.900 and RPD > 3.000, and poor results for TBARS value prediction. The LS-SVM model using six GA-selected wavelengths showed good reliability and was considered the best for simultaneous determination of TVB-N, TBARS and K value. The distribution maps of chemical spoilage changes were generated using image processing algorithms. The results demonstrated the feasibility of developing a rapid and on-line multispectral imaging system using the feature wavelengths and chemometrics analysis. •The spectral information was extracted from hyperspectral images in fish fillet.•Five and six key wavelengths were selected using SPA and GA.•LS-SVM and MLR models showed good performances for predicting TVB-N and K value.•The established models failed to predict the TBARS value.•The distribution maps of chemical spoilage were generated.
doi_str_mv 10.1016/j.jfoodeng.2016.02.004
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1816049632</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S026087741630036X</els_id><sourcerecordid>1816049632</sourcerecordid><originalsourceid>FETCH-LOGICAL-c448t-d20adcd7c3c2895f27f5cb9d387e51636c58b8807e91f395b00fa0141781f2a93</originalsourceid><addsrcrecordid>eNqFkc1u1DAUha0KJIbSV6i8ZJNw7fzY2RUVCpUqdQNry-NcZzzyxME3U4lH4K1xNLDuxpaPzznSvR9jtwJqAaL_dKyPPqUR56mW5V2DrAHaK7YTWjVVpxS8YTuQPVRaqfYde090BIAOpNyxP1_wBWNawjxxy0_nuAZa0K3ZRh5Odtp0nzKnsP3ZGdOZ-JJxDG4NaebJc5-RDjMS8TAX2a4pEx_PeYu6A56KFDktKUQ74RaYsi1mZ_PCfaBDOWLE9QN7620kvPl3X7OfD19_3H-vnp6_Pd5_fqpc2-q1GiXY0Y3KNU7qofNS-c7th7HRCjvRN73r9F5rUDgI3wzdHsBbEK1QWnhph-aafbz0Ljn9OiOt5hTIYYyX4YzQood26Bv5ulUNMPSia7fW_mJ1ORFl9GbJZX_5txFgNkzmaP5jMhsmA9IUTCV4dwlimfklYDbkAs6ubDgXDmZM4bWKv5X9ogE</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1790961549</pqid></control><display><type>article</type><title>Developing a multispectral imaging for simultaneous prediction of freshness indicators during chemical spoilage of grass carp fish fillet</title><source>ScienceDirect Freedom Collection</source><creator>Cheng, Jun-Hu ; Sun, Da-Wen ; Qu, Jia-Huan ; Pu, Hong-Bin ; Zhang, Xiao-Chao ; Song, Zhongxiang ; Chen, Xinghai ; Zhang, Hong</creator><creatorcontrib>Cheng, Jun-Hu ; Sun, Da-Wen ; Qu, Jia-Huan ; Pu, Hong-Bin ; Zhang, Xiao-Chao ; Song, Zhongxiang ; Chen, Xinghai ; Zhang, Hong</creatorcontrib><description>This study investigated the feasibility of developing a multispectral imaging method using key wavelengths from hyperspectral images for modeling and simultaneously predicting total volatile basic nitrogen (TVB-N), thiobarbituric acid reactive substances (TBARS) and K value in grass carp fillet during chemical spoilage. The established least-squares support vector machine (LS-SVM) and multiple linear regression (MLR) models using five successive projection algorithm (SPA)-selected and six genetic algorithm (GA)-selected wavelengths showed excellent performances for predicting TVB-N and K value with R2P &gt; 0.900 and RPD &gt; 3.000, and poor results for TBARS value prediction. The LS-SVM model using six GA-selected wavelengths showed good reliability and was considered the best for simultaneous determination of TVB-N, TBARS and K value. The distribution maps of chemical spoilage changes were generated using image processing algorithms. The results demonstrated the feasibility of developing a rapid and on-line multispectral imaging system using the feature wavelengths and chemometrics analysis. •The spectral information was extracted from hyperspectral images in fish fillet.•Five and six key wavelengths were selected using SPA and GA.•LS-SVM and MLR models showed good performances for predicting TVB-N and K value.•The established models failed to predict the TBARS value.•The distribution maps of chemical spoilage were generated.</description><identifier>ISSN: 0260-8774</identifier><identifier>EISSN: 1873-5770</identifier><identifier>DOI: 10.1016/j.jfoodeng.2016.02.004</identifier><language>eng</language><publisher>Elsevier Ltd</publisher><subject>Algorithms ; Carp ; Chemical spoilage ; Ctenopharyngodon idella ; Fillets ; Freshness ; Freshwater ; Grass carp ; Grasses ; Imaging ; LS-SVM ; Mathematical models ; Multispectral imaging ; Spoilage ; Wavelengths</subject><ispartof>Journal of food engineering, 2016-08, Vol.182, p.9-17</ispartof><rights>2016 Elsevier Ltd</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c448t-d20adcd7c3c2895f27f5cb9d387e51636c58b8807e91f395b00fa0141781f2a93</citedby><cites>FETCH-LOGICAL-c448t-d20adcd7c3c2895f27f5cb9d387e51636c58b8807e91f395b00fa0141781f2a93</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Cheng, Jun-Hu</creatorcontrib><creatorcontrib>Sun, Da-Wen</creatorcontrib><creatorcontrib>Qu, Jia-Huan</creatorcontrib><creatorcontrib>Pu, Hong-Bin</creatorcontrib><creatorcontrib>Zhang, Xiao-Chao</creatorcontrib><creatorcontrib>Song, Zhongxiang</creatorcontrib><creatorcontrib>Chen, Xinghai</creatorcontrib><creatorcontrib>Zhang, Hong</creatorcontrib><title>Developing a multispectral imaging for simultaneous prediction of freshness indicators during chemical spoilage of grass carp fish fillet</title><title>Journal of food engineering</title><description>This study investigated the feasibility of developing a multispectral imaging method using key wavelengths from hyperspectral images for modeling and simultaneously predicting total volatile basic nitrogen (TVB-N), thiobarbituric acid reactive substances (TBARS) and K value in grass carp fillet during chemical spoilage. The established least-squares support vector machine (LS-SVM) and multiple linear regression (MLR) models using five successive projection algorithm (SPA)-selected and six genetic algorithm (GA)-selected wavelengths showed excellent performances for predicting TVB-N and K value with R2P &gt; 0.900 and RPD &gt; 3.000, and poor results for TBARS value prediction. The LS-SVM model using six GA-selected wavelengths showed good reliability and was considered the best for simultaneous determination of TVB-N, TBARS and K value. The distribution maps of chemical spoilage changes were generated using image processing algorithms. The results demonstrated the feasibility of developing a rapid and on-line multispectral imaging system using the feature wavelengths and chemometrics analysis. •The spectral information was extracted from hyperspectral images in fish fillet.•Five and six key wavelengths were selected using SPA and GA.•LS-SVM and MLR models showed good performances for predicting TVB-N and K value.•The established models failed to predict the TBARS value.•The distribution maps of chemical spoilage were generated.</description><subject>Algorithms</subject><subject>Carp</subject><subject>Chemical spoilage</subject><subject>Ctenopharyngodon idella</subject><subject>Fillets</subject><subject>Freshness</subject><subject>Freshwater</subject><subject>Grass carp</subject><subject>Grasses</subject><subject>Imaging</subject><subject>LS-SVM</subject><subject>Mathematical models</subject><subject>Multispectral imaging</subject><subject>Spoilage</subject><subject>Wavelengths</subject><issn>0260-8774</issn><issn>1873-5770</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2016</creationdate><recordtype>article</recordtype><recordid>eNqFkc1u1DAUha0KJIbSV6i8ZJNw7fzY2RUVCpUqdQNry-NcZzzyxME3U4lH4K1xNLDuxpaPzznSvR9jtwJqAaL_dKyPPqUR56mW5V2DrAHaK7YTWjVVpxS8YTuQPVRaqfYde090BIAOpNyxP1_wBWNawjxxy0_nuAZa0K3ZRh5Odtp0nzKnsP3ZGdOZ-JJxDG4NaebJc5-RDjMS8TAX2a4pEx_PeYu6A56KFDktKUQ74RaYsi1mZ_PCfaBDOWLE9QN7620kvPl3X7OfD19_3H-vnp6_Pd5_fqpc2-q1GiXY0Y3KNU7qofNS-c7th7HRCjvRN73r9F5rUDgI3wzdHsBbEK1QWnhph-aafbz0Ljn9OiOt5hTIYYyX4YzQood26Bv5ulUNMPSia7fW_mJ1ORFl9GbJZX_5txFgNkzmaP5jMhsmA9IUTCV4dwlimfklYDbkAs6ubDgXDmZM4bWKv5X9ogE</recordid><startdate>20160801</startdate><enddate>20160801</enddate><creator>Cheng, Jun-Hu</creator><creator>Sun, Da-Wen</creator><creator>Qu, Jia-Huan</creator><creator>Pu, Hong-Bin</creator><creator>Zhang, Xiao-Chao</creator><creator>Song, Zhongxiang</creator><creator>Chen, Xinghai</creator><creator>Zhang, Hong</creator><general>Elsevier Ltd</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7ST</scope><scope>C1K</scope><scope>F1W</scope><scope>H95</scope><scope>L.G</scope><scope>SOI</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope></search><sort><creationdate>20160801</creationdate><title>Developing a multispectral imaging for simultaneous prediction of freshness indicators during chemical spoilage of grass carp fish fillet</title><author>Cheng, Jun-Hu ; Sun, Da-Wen ; Qu, Jia-Huan ; Pu, Hong-Bin ; Zhang, Xiao-Chao ; Song, Zhongxiang ; Chen, Xinghai ; Zhang, Hong</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c448t-d20adcd7c3c2895f27f5cb9d387e51636c58b8807e91f395b00fa0141781f2a93</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2016</creationdate><topic>Algorithms</topic><topic>Carp</topic><topic>Chemical spoilage</topic><topic>Ctenopharyngodon idella</topic><topic>Fillets</topic><topic>Freshness</topic><topic>Freshwater</topic><topic>Grass carp</topic><topic>Grasses</topic><topic>Imaging</topic><topic>LS-SVM</topic><topic>Mathematical models</topic><topic>Multispectral imaging</topic><topic>Spoilage</topic><topic>Wavelengths</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Cheng, Jun-Hu</creatorcontrib><creatorcontrib>Sun, Da-Wen</creatorcontrib><creatorcontrib>Qu, Jia-Huan</creatorcontrib><creatorcontrib>Pu, Hong-Bin</creatorcontrib><creatorcontrib>Zhang, Xiao-Chao</creatorcontrib><creatorcontrib>Song, Zhongxiang</creatorcontrib><creatorcontrib>Chen, Xinghai</creatorcontrib><creatorcontrib>Zhang, Hong</creatorcontrib><collection>CrossRef</collection><collection>Environment Abstracts</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ASFA: Aquatic Sciences and Fisheries Abstracts</collection><collection>Aquatic Science &amp; Fisheries Abstracts (ASFA) 1: Biological Sciences &amp; Living Resources</collection><collection>Aquatic Science &amp; Fisheries Abstracts (ASFA) Professional</collection><collection>Environment Abstracts</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology &amp; Engineering</collection><collection>Engineering Research Database</collection><jtitle>Journal of food engineering</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Cheng, Jun-Hu</au><au>Sun, Da-Wen</au><au>Qu, Jia-Huan</au><au>Pu, Hong-Bin</au><au>Zhang, Xiao-Chao</au><au>Song, Zhongxiang</au><au>Chen, Xinghai</au><au>Zhang, Hong</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Developing a multispectral imaging for simultaneous prediction of freshness indicators during chemical spoilage of grass carp fish fillet</atitle><jtitle>Journal of food engineering</jtitle><date>2016-08-01</date><risdate>2016</risdate><volume>182</volume><spage>9</spage><epage>17</epage><pages>9-17</pages><issn>0260-8774</issn><eissn>1873-5770</eissn><abstract>This study investigated the feasibility of developing a multispectral imaging method using key wavelengths from hyperspectral images for modeling and simultaneously predicting total volatile basic nitrogen (TVB-N), thiobarbituric acid reactive substances (TBARS) and K value in grass carp fillet during chemical spoilage. The established least-squares support vector machine (LS-SVM) and multiple linear regression (MLR) models using five successive projection algorithm (SPA)-selected and six genetic algorithm (GA)-selected wavelengths showed excellent performances for predicting TVB-N and K value with R2P &gt; 0.900 and RPD &gt; 3.000, and poor results for TBARS value prediction. The LS-SVM model using six GA-selected wavelengths showed good reliability and was considered the best for simultaneous determination of TVB-N, TBARS and K value. The distribution maps of chemical spoilage changes were generated using image processing algorithms. The results demonstrated the feasibility of developing a rapid and on-line multispectral imaging system using the feature wavelengths and chemometrics analysis. •The spectral information was extracted from hyperspectral images in fish fillet.•Five and six key wavelengths were selected using SPA and GA.•LS-SVM and MLR models showed good performances for predicting TVB-N and K value.•The established models failed to predict the TBARS value.•The distribution maps of chemical spoilage were generated.</abstract><pub>Elsevier Ltd</pub><doi>10.1016/j.jfoodeng.2016.02.004</doi><tpages>9</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0260-8774
ispartof Journal of food engineering, 2016-08, Vol.182, p.9-17
issn 0260-8774
1873-5770
language eng
recordid cdi_proquest_miscellaneous_1816049632
source ScienceDirect Freedom Collection
subjects Algorithms
Carp
Chemical spoilage
Ctenopharyngodon idella
Fillets
Freshness
Freshwater
Grass carp
Grasses
Imaging
LS-SVM
Mathematical models
Multispectral imaging
Spoilage
Wavelengths
title Developing a multispectral imaging for simultaneous prediction of freshness indicators during chemical spoilage of grass carp fish fillet
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T04%3A04%3A19IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Developing%20a%20multispectral%20imaging%20for%20simultaneous%20prediction%20of%20freshness%20indicators%20during%20chemical%20spoilage%20of%20grass%20carp%20fish%20fillet&rft.jtitle=Journal%20of%20food%20engineering&rft.au=Cheng,%20Jun-Hu&rft.date=2016-08-01&rft.volume=182&rft.spage=9&rft.epage=17&rft.pages=9-17&rft.issn=0260-8774&rft.eissn=1873-5770&rft_id=info:doi/10.1016/j.jfoodeng.2016.02.004&rft_dat=%3Cproquest_cross%3E1816049632%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c448t-d20adcd7c3c2895f27f5cb9d387e51636c58b8807e91f395b00fa0141781f2a93%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1790961549&rft_id=info:pmid/&rfr_iscdi=true