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

Abstract Recently, hyperspectral-imaging (HSI), as a rapid and non-destructive technique, has generated much interest due to its unique potential to monitor food quality and safety. The specific aim of the study is to investigate the potential of the HSI (430–1010 nm) coupled with Linear Deep Neural...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Marzieh Moosavi-Nasab, Sara Khoshnoudi-Nia, Zohreh Azimifar, Shima Kamyab
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/a747cbff8b844f3387d4838f0832f720
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:a747cbff8b844f3387d4838f0832f720
record_format dspace
spelling oai:doaj.org-article:a747cbff8b844f3387d4838f0832f7202021-12-02T13:30:11ZEvaluation of the total volatile basic nitrogen (TVB-N) content in fish fillets using hyperspectral imaging coupled with deep learning neural network and meta-analysis10.1038/s41598-021-84659-y2045-2322https://doaj.org/article/a747cbff8b844f3387d4838f0832f7202021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-84659-yhttps://doaj.org/toc/2045-2322Abstract Recently, hyperspectral-imaging (HSI), as a rapid and non-destructive technique, has generated much interest due to its unique potential to monitor food quality and safety. The specific aim of the study is to investigate the potential of the HSI (430–1010 nm) coupled with Linear Deep Neural Network (LDNN) to predict the TVB-N content of rainbow trout fillet during 12 days storage at 4 ± 2 °C. After the acquisition of hyperspectral images, the TVB-N content of fish fillets was obtained by a conventional method (micro-Kjeldahl distillation). To simplify the calibration models, nine optimal wavelengths were selected by the successive projections algorithm. A seven layers LDNN was designed to estimate the TVB-N content of samples. The LDNN model showed acceptable performance for prediction of TVB-N content of fish fillet (R2p = 0.853; RSMEP = 3.159 and RDP = 3.001). The performance of LDNN model was comparable with the results of previous works. Although, the results of the meta-analysis did not show any significant difference between various chemometric models. However, the least-squares support vector machine algorithm showed better prediction results as compared to the other models (RMSEP: 2.63 and R2 p = 0.897). Further studies are required to improve the prediction power of the deep learning model for prediction of rainbow-trout fish quality.Marzieh Moosavi-NasabSara Khoshnoudi-NiaZohreh AzimifarShima KamyabNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Marzieh Moosavi-Nasab
Sara Khoshnoudi-Nia
Zohreh Azimifar
Shima Kamyab
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
description Abstract Recently, hyperspectral-imaging (HSI), as a rapid and non-destructive technique, has generated much interest due to its unique potential to monitor food quality and safety. The specific aim of the study is to investigate the potential of the HSI (430–1010 nm) coupled with Linear Deep Neural Network (LDNN) to predict the TVB-N content of rainbow trout fillet during 12 days storage at 4 ± 2 °C. After the acquisition of hyperspectral images, the TVB-N content of fish fillets was obtained by a conventional method (micro-Kjeldahl distillation). To simplify the calibration models, nine optimal wavelengths were selected by the successive projections algorithm. A seven layers LDNN was designed to estimate the TVB-N content of samples. The LDNN model showed acceptable performance for prediction of TVB-N content of fish fillet (R2p = 0.853; RSMEP = 3.159 and RDP = 3.001). The performance of LDNN model was comparable with the results of previous works. Although, the results of the meta-analysis did not show any significant difference between various chemometric models. However, the least-squares support vector machine algorithm showed better prediction results as compared to the other models (RMSEP: 2.63 and R2 p = 0.897). Further studies are required to improve the prediction power of the deep learning model for prediction of rainbow-trout fish quality.
format article
author Marzieh Moosavi-Nasab
Sara Khoshnoudi-Nia
Zohreh Azimifar
Shima Kamyab
author_facet Marzieh Moosavi-Nasab
Sara Khoshnoudi-Nia
Zohreh Azimifar
Shima Kamyab
author_sort Marzieh Moosavi-Nasab
title 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
title_short 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
title_full 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
title_fullStr 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
title_full_unstemmed 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
title_sort 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
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/a747cbff8b844f3387d4838f0832f720
work_keys_str_mv AT marziehmoosavinasab evaluationofthetotalvolatilebasicnitrogentvbncontentinfishfilletsusinghyperspectralimagingcoupledwithdeeplearningneuralnetworkandmetaanalysis
AT sarakhoshnoudinia evaluationofthetotalvolatilebasicnitrogentvbncontentinfishfilletsusinghyperspectralimagingcoupledwithdeeplearningneuralnetworkandmetaanalysis
AT zohrehazimifar evaluationofthetotalvolatilebasicnitrogentvbncontentinfishfilletsusinghyperspectralimagingcoupledwithdeeplearningneuralnetworkandmetaanalysis
AT shimakamyab evaluationofthetotalvolatilebasicnitrogentvbncontentinfishfilletsusinghyperspectralimagingcoupledwithdeeplearningneuralnetworkandmetaanalysis
_version_ 1718392992901890048