Detection of Pork Freshness Using NIR Hyperspectral Imaging Based on Genetic Algorithm and Deep Neural Network

XIE Anguo; JI Siyuan; LI Yueling; WANG Mansheng; ZHANG Yu

doi:10.13386/j.issn1002-0306.2023120096

Volume 45 Issue 17

Aug. 2024

Turn off MathJax

Article Contents

Abstract

References

Supplements

Science and Technology of Food Industry > 2024 > 45(17): 345-351. > DOI: 10.13386/j.issn1002-0306.2023120096

XIE Anguo, JI Siyuan, LI Yueling, et al. Detection of Pork Freshness Using NIR Hyperspectral Imaging Based on Genetic Algorithm and Deep Neural Network[J]. Science and Technology of Food Industry, 2024, 45(17): 345−351. (in Chinese with English abstract). doi: 10.13386/j.issn1002-0306.2023120096.

Citation:

PDF (1609 KB)

Detection of Pork Freshness Using NIR Hyperspectral Imaging Based on Genetic Algorithm and Deep Neural Network

1.
Zhang Zhongjing School of Chinese Medicine, Nanyang Institute of Technology, Nanyang 473004, China
2.
Institute of Bast Fiber Crops, Chinese Academy of Agricultural Sciences, Changsha 410205, China
3.
School of Intelligent Manufacturing, Nanyang Institute of Technology, Nanyang 473004, China

More Information

Received Date: December 10, 2023
Available Online: June 30, 2024

Graphical Abstract

Abstract

Abstract

To evaluate the effectiveness of a deep learning which is based intelligent assisted hyperspectral imaging system on the detection of pork freshness indicators, volatile basic nitrogen (TVB-N), total viable count (TVC), and 900~2500 nm near-infrared spectral data were collected from pork which were refrigerated at 4 ℃ for 12 days. Based on Python's TensorFlow and Keras platform, hyperspectral data was processed and a quantitative detection model of deep neural network was also established. And the characteristic spectral bands related to pork freshness were selected by genetic algorithm (GA). The results showed that the performance of the spectral model could be improved significantly by selecting the band of genetic algorithm. When the number of spectral bands reached 35 and 50, the prediction accuracy of GA+ANN model was higher than that of full-band linear regression model. The predictive performance of TVC was better than that of TVB-N, and the best R_p² and RMSEP of TVC were 0.877 and 0.575, respectively. The best R_p² and RMSEP for TVB-N were 0.826 and 1.01, respectively. In addition, it was also found that the NIR band selected by genetic algorithm had a high coincidence with the molecular vibration absorption bands of meat, such as O-H, N-H, C=O and so on. This study provides a new method which can be used for processing the near-infrared and hyperspectral data, and also provides a technical reference for rapid nondestructive testing of pork and other meat freshness.
- pork quality,
- freshness,
- hyperspectral image (HSI),
- near infrared (NIR),
- TensorFlow,
- genetic algorithm,
- neural network

FullText(HTML)

References (30)

References

[1]	WÓJCIAK K M, HALAGARDA M, ROHN S, et al. Selected nutrients determining the quality of different cuts of organic and conventional pork[J]. European Food Research and Technology,2021,247:1389−1400. doi: 10.1007/s00217-021-03716-y
[2]	KUCHA C T, NGADI M O. Rapid assessment of pork freshness using miniaturized NIR spectroscopy[J]. Journal of Food Measurement and Characterization,2020,14:1105−1115. doi: 10.1007/s11694-019-00360-9
[3]	SOHAIB M, ANJUM F M, ARSHAD M S, et al. Postharvest intervention technologies for safety enhancement of meat and meat based products; a critical review[J]. Journal of Food Science and Technology,2016,53:19−30. doi: 10.1007/s13197-015-1985-y
[4]	XIE A G, SUN J, WANG T, et al. Visualized detection of quality change of cooked beef with condiments by hyperspectral imaging technique[J]. Food Science and Biotechnology,2022,31(10):1257−1266. doi: 10.1007/s10068-022-01115-x
[5]	ZAREEF M, CHEN Q, HASSAN M M, et al. An overview on the applications of typical non-linear algorithms coupled with NIR spectroscopy in food analysis[J]. Food Engineering Reviews,2020,12:173−190. doi: 10.1007/s12393-020-09210-7
[6]	XIE A G, SUN D W, ZHU Z, et al. Nondestructive measurements of freezing parameters of frozen porcine meat by NIR hyperspectral imaging[J]. Food and Bioprocess Technology,2016,9:1444−1454. doi: 10.1007/s11947-016-1766-2
[7]	王彩霞, 王松磊, 贺晓光, 等. 高光谱图谱融合检测羊肉中饱和脂肪酸含量[J]. 光谱学与光谱分析,2020,409(2):595−601. [WANG C X, WANG S L, HE X G, et al. Detection of saturated fatty acid content in mutton by using the fusion of hyperspectral spectrum and image information[J]. Spectroscopy and Spectral Analysis,2020,409(2):595−601.] WANG C X, WANG S L, HE X G, et al. Detection of saturated fatty acid content in mutton by using the fusion of hyperspectral spectrum and image information[J]. Spectroscopy and Spectral Analysis, 2020, 409（2）: 595−601.
[8]	ZHANG J, LIU G, LI Y, et al. Rapid identification of lamb freshness grades using visible and near-infrared spectroscopy (Vis-NIR)[J]. Journal of Food Composition and Analysis,2022,111:104590. doi: 10.1016/j.jfca.2022.104590
[9]	ERNA K H, ROVINA K, MANTIHAL S. Current detection techniques for monitoring the freshness of meat-based products:A review[J]. Journal of Packaging Technology and Research,2021,5(3):127−141. doi: 10.1007/s41783-021-00120-5
[10]	GÓRSKA-HORCZYCZAK E, HORCZYCZAK M, GUZEK D, et al. Chromatographic fingerprints supported by artificial neural network for differentiation of fresh and frozen pork[J]. Food Control,2017,73:237−244. doi: 10.1016/j.foodcont.2016.08.010
[11]	HASSOUN A, AÏT-KADDOUR A, SAHAR A, et al. Monitoring thermal treatments applied to meat using traditional methods and spectroscopic techniques:A review of advances over the last decade[J]. Food and Bioprocess Technology,2021,14:195−208. doi: 10.1007/s11947-020-02510-0
[12]	NGUYEN G, DLUGOLINSKY S, BOBÁK M, et al. Machine learning and deep learning frameworks and libraries for large-scale data mining:A survey[J]. Artificial Intelligence Review,2019,52:77−124. doi: 10.1007/s10462-018-09679-z
[13]	Geatpy–The genetic and evolutionary algorithm toolbox for Python with high performance[EB/OL]. http://geatpy.com/index.php/home/.
[14]	MAHMUD M, KAISER M S, MCGINNITY T M, et al. Deep learning in mining biological data[J]. Cognitive Computation,2021,13:1−33. doi: 10.1007/s12559-020-09773-x
[15]	DONG K, GUAN Y, WANG Q, et al. Non-destructive prediction of yak meat freshness indicator by hyperspectral techniques in the oxidation process[J]. Food Chemistry:X,2023,17:100541.
[16]	CASABURI A, PIOMBINO P, NYCHAS G J, et al. Bacterial populations and the volatilome associated to meat spoilage[J]. Food Microbiology,2015,45:83−102. doi: 10.1016/j.fm.2014.02.002
[17]	LUO X, DONG K, LIU L, et al. Proteins associated with quality deterioration of prepared chicken breast based on differential proteomics during refrigerated storage[J]. Journal of the Science of Food and Agriculture,2021,101:3489−3499. doi: 10.1002/jsfa.10980
[18]	BÜNING-PFAUE H. Analysis of water in food by near infrared spectroscopy[J]. Food Chemistry,2003,82(1):107−115. doi: 10.1016/S0308-8146(02)00583-6
[19]	HEIMAN A, LICHT S. Fundamental baseline variations in aqueous near-infrared analysis[J]. Analytica Chimica Acta,1999,394(2):135−147.
[20]	WANG P, WANG P, WANG H W, et al. Mapping lipid and collagen by multispectral photoacoustic imaging of chemical bond vibration[J]. Journal of Biomedical Optics,2012,17(9):96010−96011.
[21]	谢安国, 王满生, 石晓微, 等. 牛肉加热过程中低场核磁驰豫信号与品质特征的动态分析[J]. 食品与机械,2020,36(7):23−27,71. [XIE A G, WANG M S, SHI X W, et al. Dynamic analysis of LF-NMR relaxation signals and quality characteristics during heating beef[J]. Food & Machinery,2020,36(7):23−27,71.] XIE A G, WANG M S, SHI X W, et al. Dynamic analysis of LF-NMR relaxation signals and quality characteristics during heating beef[J]. Food & Machinery, 2020, 36（7）: 23−27,71.
[22]	胡黄水, 赵思远, 刘清雪, 等. 基于动量因子优化学习率的BP神经网络PID参数整定算法[J]. 吉林大学学报(理学版),2020,58(6):1415−1420. [HU H S, ZHAO S Y, LIU Q X, et al. BP neural network PID parameter tuning algorithm based on momentum factor optimized learning rate[J]. Journal of Jilin University(Science Edition),2020,58(6):1415−1420.] HU H S, ZHAO S Y, LIU Q X, et al. BP neural network PID parameter tuning algorithm based on momentum factor optimized learning rate[J]. Journal of Jilin University（Science Edition）, 2020, 58（6）: 1415−1420.
[23]	SUN H, SHEN L, ZHONG Q, et al. AdaSAM:Boosting sharpness-aware minimization with adaptive learning rate and momentum for training deep neural networks[J]. Neural Networks,2024,169:506−519. doi: 10.1016/j.neunet.2023.10.044
[24]	CHANDRA B, SHARMA R K. Deep learning with adaptive learning rate using laplacian score[J]. Expert Systems with Applications,2016,63:1−7. doi: 10.1016/j.eswa.2016.05.022
[25]	ZHENG S, GUO W, LI C, et al. Application of machine learning and deep learning methods for hydrated electron rate constant prediction[J]. Environmental Research,2023,231:115996. doi: 10.1016/j.envres.2023.115996
[26]	WORKMAN J, WEYER L. Practical guide to interpretive near-infrared spectroscopy[M]. CRC Press, 2007, 47:4620-4629.
[27]	何鸿举, 王洋洋, 王魏, 等. NIR高光谱成像技术联用SPA算法快速检测五花肉的过氧化值[J]. 食品工业科技,2020,41(8):236−241. [HE H J, WANG Y Y, WANG W, et al. NIR hyperspectral imaging combined with SPA algorithm for the rapid detection of peroxidation value of pork belly[J]. Science and Technology of Food Industry,2020,41(8):236−241.] HE H J, WANG Y Y, WANG W, et al. NIR hyperspectral imaging combined with SPA algorithm for the rapid detection of peroxidation value of pork belly[J]. Science and Technology of Food Industry, 2020, 41（8）: 236−241.
[28]	XU J L, ESQUERRE C, SUN D W. Methods for performing dimensionality reduction in hyperspectral image classification[J]. Journal of Near Infrared Spectroscopy,2018,26(1):61−75. doi: 10.1177/0967033518756175
[29]	李艳坤, 董汝南, 张进, 等. 光谱数据解析中的变量筛选方法[J]. 光谱学与光谱分析, 2021, 41(11):3331-3338. [LI Y K, DONG R N, ZHANG J, et al. Variable selection methods in spectral data analysis[J]. Spectroscopy and Spectral Analysis, 2021, 41(11):3331.] LI Y K, DONG R N, ZHANG J, et al. Variable selection methods in spectral data analysis[J]. Spectroscopy and Spectral Analysis, 2021, 41（11）: 3331.
[30]	CHENG W W, SUN D W, PU H B, et al. Characterization of myofibrils cold structural deformation degrees of frozen pork using hyperspectral imaging coupled with spectral angle mapping algorithm[J]. Food Chemistry,2018,239:1001−1008. doi: 10.1016/j.foodchem.2017.07.011

Supplements (1)

Supplements
Other Related Supplements

Get Citation

PDF

XML

Article Metrics

Article views (85) PDF downloads (17)

Science and Technology of Food Industry

Detection of Pork Freshness Using NIR Hyperspectral Imaging Based on Genetic Algorithm and Deep Neural Network

Abstract

References

Supplements

Other Related Supplements

Catalog

Article Metrics

Export File

Citation

Format

Content