Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 May 21;10(6):1161.
doi: 10.3390/foods10061161.

Artificial Intelligence Empowered Multispectral Vision Based System for Non-Contact Monitoring of Large Yellow Croaker (Larimichthys crocea) Fillets

Shengnan Wang  1 , Avik Kumar Das  2 , Jie Pang  1 , Peng Liang  1
Affiliations

Artificial Intelligence Empowered Multispectral Vision Based System for Non-Contact Monitoring of Large Yellow Croaker (Larimichthys crocea) Fillets

Shengnan Wang et al. Foods. .

Abstract

A non-contact method was proposed to monitor the freshness (based on TVB-N and TBA values) of large yellow croaker fillets (Larimichthys crocea) by using a visible and near-infrared hyperspectral imaging system (400-1000 nm). In this work, the quantitative calibration models were built by using feed-forward neural networks (FNN) and partial least squares regression (PLSR). In addition, it was established that using a regression coefficient on the data can be further compressed by selecting optimal wavelengths (35 for TVB-N and 18 for TBA). The results validated that FNN has higher prediction accuracies than PLSR for both cases using full and selected reflectance spectra. Moreover, our FNN based model has showcased excellent performance even with selected reflectance spectra with rp = 0.978, R2p = 0.981, and RMSEP = 2.292 for TVB-N, and rp = 0.957, R2p = 0.916, and RMSEP = 0.341 for TBA, respectively. This optimal FNN model was then utilized for pixel-wise visualization maps of TVB-N and TBA contents in fillets.

Keywords: feed-forward neural networks; freshness; hyperspectral imaging technology; large yellow croaker.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
(a) Large yellow croaker fillet samples, (b) hyperspectral image acquisition, and (c) schematic diagram of three-dimensional hyperspectral image.
Figure 2
Figure 2
(a) Average spectral curves of the examined large yellow croaker fillet after 8 days’ storage; (b) Distribution of optimal wavelengths in full reflectance spectra.
Figure 3
Figure 3
Scatter plots of predicted versus measured TVB-N (a) and TBA (b) obtained by FNN-simplified model based on the optimal wavelengths.
Figure 4
Figure 4
Distribution maps of TVB-N (a–c) and TBA (d–f) contents in large yellow croaker fillets after 8-day storage at three low-temperature treatments.
See this image and copyright information in PMC

References

    1. Sun X.H., Xiao L., Lan W.Q., Liu S.C., Wang Q., Yang X.H., Zhang W.J., Xie J. Effects of temperature fluctuation on quality changes of large yellow croaker (Pseudosciaena crocea) with ice storage during logistics process. J. Food Process. Pres. 2018;42:e13505. doi: 10.1111/jfpp.13505. - DOI
    1. Zhao J., Lv W., Wang J., Li J., Liu X., Zhu J. Effects of tea polyphenols on the post-mortem integrity of large yellow croaker (Pseudosciaena crocea) fillet proteins. Food Chem. 2013;141:2666–2674. doi: 10.1016/j.foodchem.2013.04.126. - DOI - PubMed
    1. Grienke U., Silke J., Tasdemir D. Bioactive compounds from marine mussels and their effects on human health. Food Chem. 2014;142:48–60. doi: 10.1016/j.foodchem.2013.07.027. - DOI - PubMed
    1. Zhou G.H., Xu X.L., Liu Y. Preservation technologies for fresh meat—A review. Meat Sci. 2010;86:119–128. doi: 10.1016/j.meatsci.2010.04.033. - DOI - PubMed
    1. Shi J., Zhang L.T., Lu H., Shen H.X., Yu X.P., Luo Y.K. Protein and lipid changes of mud shrimp (Solenocera melantho) during frozen storage: Chemical properties and their prediction. Int. J. Food Prop. 2017;20:2043–2056. doi: 10.1080/10942912.2017.1361973. - DOI

LinkOut - more resources