Nondestructive determination of freshness indicators for tilapia fillets stored at various temperatures by hyperspectral imaging coupled with RBF neural networks

Ce Shi; Jianping Qian; Wenying Zhu; Huan Liu; Shuai Han; Xinting Yang

doi:10.1016/j.foodchem.2018.09.092

Nondestructive determination of freshness indicators for tilapia fillets stored at various temperatures by hyperspectral imaging coupled with RBF neural networks

Food Chem. 2019 Mar 1:275:497-503. doi: 10.1016/j.foodchem.2018.09.092. Epub 2018 Sep 15.

Authors

Ce Shi¹, Jianping Qian¹, Wenying Zhu¹, Huan Liu¹, Shuai Han¹, Xinting Yang²

Affiliations

¹ Beijing Research Center for Information Technology in Agriculture, Beijing Academy of Agricultural and Forestry Sciences, Beijing 100097, China; National Engineering Research Center for Information Technology in Agriculture, Beijing Academy of Agricultural and Forestry Sciences, Beijing 100097, China; National Engineering Laboratory for Agri-product Quality Traceability, Beijing Academy of Agricultural and Forestry Sciences, Beijing 100097, China.
² Beijing Research Center for Information Technology in Agriculture, Beijing Academy of Agricultural and Forestry Sciences, Beijing 100097, China; National Engineering Research Center for Information Technology in Agriculture, Beijing Academy of Agricultural and Forestry Sciences, Beijing 100097, China; National Engineering Laboratory for Agri-product Quality Traceability, Beijing Academy of Agricultural and Forestry Sciences, Beijing 100097, China. Electronic address: yangxt@nercita.org.cn.

PMID: 30724225
DOI: 10.1016/j.foodchem.2018.09.092

Abstract

This study develops a reliable radial basis function neural networks (RBFNNs) to estimate freshness for tilapia fillets stored under non-isothermal conditions by using optimal wavelengths from hyperspectral imaging (HSI). The results show that, for tilapia fillet stored at -3, 0, 4, 10, and 15 °C and non-isothermal conditions, total volatile basic nitrogen (TVB-N), total aerobic counts (TAC), and the K value increase whereas sensory scores decrease with increasing storage time. To simplify the models, nine optimal wavelengths were selected by using the successive projections algorithm (SPA), following which SPA-RBFNN models were built based on the selected wavelengths and the values of TVB-N, TAC, K, and sensory evaluations for tilapia fillets store isothermally. The ability of the models based on HSI to predict the freshness indicators were verified for tilapia fillets stored under non-isothermal conditions. HSI thus has an excellent potential for nondestructive determination of freshness in tilapia fillets.

Keywords: Freshness; Hyperspectral imaging; Non-isothermal conditions; Reliable radial basis function neural networks; Tilapia fillets.

MeSH terms

Animals
Food Quality*
Food Storage / methods*
Neural Networks, Computer*
Nitrogen / analysis
Seafood* / analysis
Seafood* / microbiology
Temperature*
Tilapia* / microbiology

Substances

Nitrogen