Freshness Discrimination of Chilled Pork with Fluorescent Indicator Labels Based on Lightweight Convolutional Neural Network
, Lin WANG1 (
), Abstract
Color indications of fluorescent labels for freshness provide an important tool for monitoring meat quality in real time. This study developed a fluorescent label based on a zein film modified with rhodamine B (RhB) and fluorescein isothiocyanate (FITC). In the label, green fluorescence from FITC acted as a response signal, and red fluorescence from RhB as a reference signal. This fluorescent label exhibited dual emission responses when exposed to amines, FITC fluorescence increased whilst the fluorescence of RhB was undisturbed. The fluorescent label presented a clearly distinguishable color transition from pink to yellow-green, indicating significantly enhanced sensitivity and accuracy. Furthermore, convolutional neural network (CNN) was used to intelligently distinguish the color changes of the fluorescent label to reduce human visual errors. Lightweight CNN EfficientNetb0 was found to be superior to two other lightweight CNN (MobileNetv2 and ShuffleNetv2) and two non-lightweight CNN (ResNet50 and VGG16) in terms of discriminant effectiveness, with a recognition accuracy of 95.6%. The parameters and floating-point operations per second (FLOPs) of the EfficientNetb0 model were 4.01 MB and 0.398 GMACs, respectively, which achieved the best balance between FLOPs and accuracy. Therefore, this model can meet the need for the fast, accurate and nondestructive identification of chilled pork freshness. The research results provide a theoretical reference for the intelligent grading of the freshness of chilled pork using fluorescent indicator labels during cold storage and cold-chain transportation.
References
BEKHIT A, HOLMAN, GITERU S, et al. Total volatile basic nitrogen (TVB-N) and its role in meat spoilage: a review[J]. Trends in Food Science and Technology, 2021, 109: 280-302. DOI:10.1016/j.tifs.2021.01.006.
QU F F, REN D, HE Y, et al. Predicting pork freshness using multiindex statistical information fusion method based on near infrared spectroscopy[J]. Meat Science, 2018, 146: 59-67. DOI:10.1016/j.meatsci.2018.07.023.
CHENG J H, SUN J, YAO K S, et al. A decision fusion method based on hyperspectral imaging and electronic nose techniques for moisture content prediction in frozen-thawed pork[J]. LWT-Food Science and Technology, 2022, 165: 113778. DOI:10.1016/j.lwt.2022.113778.
LI H Y, WANG Y, ZHANG J X, et al. Prediction of the freshness of horse mackerel (Trachurus japonicus) using E-nose, E-tongue, and colorimeter based on biochemical indexes analyzed during frozen storage of whole fish[J]. Food Chemistry, 2023, 402: 134325. DOI:10.1016/j.foodchem.2022.134325.
CHE S Y, PAN S L, SHAO X S, et al. Portable and reversible smart labels for non-destructive detection of seafood freshness via amineresponse fluorescent ionic liquids[J]. Food Chemistry, 2024, 430: 136946. DOI:10.1016/j.foodchem.2023.136946.
FANG S L, GUAN Z H, SU C, et al. Accurate fish-freshness prediction label based on red cabbage anthocyanins[J]. Food Control, 2022, 138: 109018. DOI:10.1016/j.foodcont.2022.109018.
HAN T T, XIA C Y, HUANG Y, et al. An electrospun sensing label based on poly(vinyl alcohol)-Ag-grape seed anthocyanidin nanofibers for smart, real-time meat freshness monitoring[J]. Sensors and Actuators B: Chemical, 2023, 376: 132975. DOI:10.1016/j.snb.2022.132975.
ZHANG D D, ZHU L, JIANG Q W, et al. Real-time and rapid prediction of TVB-N of livestock and poultry meat at three depths for freshness evaluation using a portable fluorescent film sensor[J]. Food Chemistry, 2023, 400: 134041. DOI:10.1016/j.foodchem.2022.134041.
JIA R N, TIAN W W, BAI H T, et al. Amine-responsive cellulosebased ratiometric fluorescent materials for real-time and visual detection of shrimp and crab freshness[J]. Nature Communications, 2019, 10: 795. DOI:10.1038/s41467-019-08675-3.
QUAN Z Y, HE H, ZHOU H, et al. Designing an intelligent nanofiber ratiometric fluorescent sensor sensitive to biogenic amines for detecting the freshness of shrimp and pork[J]. Sensors and Actuators B:Chemical, 2021, 333: 129535. DOI:10.1016/j.snb.2021.129535.
ZHAN Y J, YANG J, GUO L H, et al. Targets regulated formation of boron nitride quantum dots-gold nanoparticles nanocomposites for ultrasensitive detection of acetylcholinesterase activity and its inhibitors[J]. Sensors and Actuators B: Chemical, 2019, 279: 61-68. DOI:10.1016/j.snb.2018.09.097.
PU H B, YU J X, SUN D W, et al. Distinguishing fresh and frozenthawed beef using hyperspectral imaging technology combined with convolutional neural networks[J]. Microchemical Journal, 2023, 189: 108559. DOI:10.1016/j.microc.2023.108559.
MOHAMMADI LALABADI H, SADEGHI M, MIREEI S A. Fish freshness categorization from eyes and gills color features using multi-class artificial neural network and support vector machines[J]. Aquacultural Engineering, 2020, 90: 102076. DOI:10.1016/j.aquaeng.2020.102076.
SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. Computer Vision and Pattern Recognition, 2014, 2014: 1409. DOI:10.48550/arXiv.1409.1556.
SERDAROGLU M, CAN H, SARI B, et al. Effects of natural nitrite sources from arugula and barberry extract on quality characteristic of heat-treated fermented sausages[J]. Meat Science, 2023, 198: 109090. DOI:10.1016/j.meatsci.2022.109090.
KOCHKINA N E, LUKIN N D. Structure and properties of biodegradable maize starch/chitosan composite films as affected by PVA additions[J]. International Journal of Biological Macromolecules, 2020, 157: 377-384. DOI:10.1016/j.ijbiomac.2020.04.154.
BUENO J N, CORRADINI E, SOUZA P R, et al. Films based on mixtures of zein, chitosan, and PVA: development with perspectives for food packaging application[J]. Polymer Testing, 2021, 101: 107279. DOI:10.1016/j.polymertesting.2021.107279.
CHEN X, XIAO J, CAI J Y, et al. Phase separation behavior in zeing-elatin composite film and its modulation effects on retention and release of multiple bioactive compounds[J]. Food Hydrocolloids, 2020, 109: 106105. DOI:10.1016/j.foodhyd.2020.106105.
KARIM M, FATHI M, SOLEIMANIAN-ZAD S. Incorporation of zein nanofibers produced by needle-less electrospinning within the casted gelatin film for improvement of its physical properties[J]. Food and Bioproducts Processing, 2020, 122: 193-204. DOI:10.1016/j.fbp.2020.04.006.
AHAMMED S, LIU F, KHIN M N, et al. Improvement of the water resistance and ductility of gelatin film by zein[J]. Food Hydrocolloids, 2020, 105: 105804. DOI:10.1016/j.foodhyd.2020.105804.
VAHEDIKIA N, GARAVAND F, TAJEDDIN B, et al. Biodegradable zein film composites reinforced with chitosan nanoparticles and cinnamon essential oil: physical, mechanical, structural and antimicrobial attributes[J]. Colloids and Surfaces B: Biointerfaces, 2019, 177: 25-32. DOI:10.1016/j.colsurfb.2019.01.045.
WANG L, MU R J, LI Y Z, et al. Characterization and antibacterial activity evaluation of curcumin loaded konjac glucomannan and zein nanofibril films[J]. LWT-Food Science and Technology, 2019, 113: 108293. DOI:10.1016/j.lwt.2019.108293.
HAN Y Y, YU M, WANG L J. Soy protein isolate nanocomposites reinforced with nanocellulose isolated from licorice residue: water sensitivity and mechanical strength[J]. Industrial Crops and Products, 2018, 117: 252-259. DOI:10.1016/j.indcrop.2018.02.028.
CHEN S, LI H Q, MCCLEMENTS D J, et al. Co-delivery of curcumin and piperine in zein-carrageenan core-shell nanoparticles:formation, structure, stability and in vitro gastrointestinal digestion[J]. Food Hydrocolloids, 2020, 99: 105334. DOI:10.1016/j.foodhyd.2019.105334.
LIU Q Y, CHEN J J, QIN Y, et al. Zein/fucoidan-based composite nanoparticles for the encapsulation of pterostilbene: preparation, characterization, physicochemical stability, and formation mechanism[J]. International Journal of Biological Macromolecules, 2020, 158: 461-470. DOI:10.1016/j.ijbiomac.2020.04.128.
YAN F, FAN K Q, BAI Z J, et al. Fluorescein applications as fluorescent probes for the detection of analytes[J]. Trends in Analytical Chemistry, 2017, 97: 15-35. DOI:10.1016/j.trac.2017.08.013
京公网安备11010802044758号