Research on storage quality detection method of blueberry based on ensemble learning and near-infrared spectroscopy

ZHANG Chen; ZHU Yujie; FENG Guohong

doi:10.13995/j.cnki.11-1802/ts.035198

Food and Fermentation Industries >

2023 , Vol. 49 >Issue 18: 306 - 314

DOI: https://doi.org/10.13995/j.cnki.11-1802/ts.035198

Research on storage quality detection method of blueberry based on ensemble learning and near-infrared spectroscopy

ZHANG Chen ,
ZHU Yujie ,
FENG Guohong

Expand

(College of Engineering and Technology, Northeast Forestry University, Harbin 150040, China)

Received date: 2023-02-19

Revised date: 2023-04-20

Online published: 2023-10-25

Fold

Abstract

A non-destructive detection method based on ensemble learning and near-infrared spectroscopy technology was proposed to address the complex process and high-cost issues of traditional chemical methods for determining blueberry storage quality. Using 150 Rika blueberries and 30 Green Emerald blueberries from Dandong as the research objects, near-infrared reflection spectra of Rika blueberries with different storage times and Green Emerald blueberries with different maturity levels were collected using a near-infrared spectrometer. The sample set partitioning based on the joint X-Y distance (SPXY) method was used to divide Rika blueberries samples into training and validation sets at a ratio of 4∶1, and Green Emerald blueberries samples were used as the test set. The preprocessing effects of one or several combinations of standard normal variate transformation (SNV), Z-score standardization, first derivative (1st-D), and second derivative (2nd-D) on the original spectra were compared using partial least squares regression (PLSR). The competitive adaptive reweighted sampling (CARS) method was used to select the characteristic wavelengths of blueberry near-infrared spectra, and support vector regression (SVR), extreme gradient boosting (XGBoost), and multilayer perceptron (MLP) were used as base models. A stacking ensemble learning model was established using the stacking integration strategy. Vitamin C, soluble solids content (SSC), and anthocyanins, which were most related to blueberry storage quality, were used as labels to train four prediction models. The stacking ensemble model was the best, with test set correlation coefficients (R²) of 0.872 6, 0.881 4, and 0.905 5 for vitamin C, SSC, and anthocyanins, respectively. The root mean square error (RMSE) was 0.566 4, 0.696 3, and 1.693 9, and the relative percent deviation (RPD) was 2.801 6, 2.903 7, and 3.253. Results showed that the stacking ensemble learning model proposed in this study had the advantages of high accuracy, good stability, and strong generalization ability by integrating SVR, XGBoost, and MLP, providing new ideas for the non-destructive detection of blueberries.

Key words： near infrared spectrum; ensemble learning; blueberries; non-destructive testing; support vector regression; extreme gradient boosting; multilayer perceptron

Cite this article

ZHANG Chen , ZHU Yujie , FENG Guohong . Research on storage quality detection method of blueberry based on ensemble learning and near-infrared spectroscopy[J]. Food and Fermentation Industries, 2023 , 49(18) : 306 -314 . DOI: 10.13995/j.cnki.11-1802/ts.035198

References

[1] KALT W, CASSIDY A, HOWARD L R, et al.Recent research on the health benefits of blueberries and their anthocyanins[J].Advances in Nutrition, 2020, 11(2):224-236.
[2] QIAO S C, TIAN Y W, WANG Q H, et al.Nondestructive detection of decayed blueberry based on information fusion of hyperspectral imaging (HSI) and low-Field nuclear magnetic resonance (LF-NMR)[J].Computers and Electronics in Agriculture, 2021,184:106100.
[3] 翁海勇, 许金钗, 陶铸, 等.高EGCG含量茶树品种光谱识别模型构建[J].中国农机化学报, 2021, 42(6):111-117.
WENG H Y, XU J C, TAO Z, et al.Construction of spectral screening model for tea cultivars with high EGCG content[J].Journal of Chinese Agricultural Mechanization, 2021, 42(6):111-117.
[4] 王冬, 王坤, 吴静珠, 等.基于光谱及成像技术的种子品质无损速测研究进展[J].光谱学与光谱分析, 2021, 41(1):52-59.
WANG D, WANG K, WU J Z, et al.Progress in research on rapid and non-destructive detection of seed quality based on spectroscopy and imaging technology[J].Spectroscopy and Spectral Analysis, 2021, 41(1):52-59.
[5] 金文玲, 曹乃亮, 朱明东, 等.基于近红外超连续激光光谱的水稻种子活力无损分级检测研究[J].中国光学, 2020, 13(5):1032-1043.
JIN W L, CAO N L, ZHU M D, et al.Nondestructive grading test of rice seed activity using near infrared super-continuum laser spectrum[J].Chinese Optics, 2020, 13(5):1032-1043.
[6] 阚相成, 李耀翔, 王立海, 等.基于光谱预处理的低温水曲柳原木含水率检测[J].中南林业科技大学学报, 2022, 42(11):154-163.
KAN X C, LI Y X, WANG L H, et al.Moisture content detection of Fraxinus mandshurica logs at low temperatures based on different spectrum pretreatments[J].Journal of Central South University of Forestry & Technology, 2022, 42(11):154-163.
[7] 陈博文, 胡娟, 金咏琪, 等.基于傅里叶红外光谱预测翅荚木顺纹抗压强度[J].西南林业大学学报(自然科学), 2022, 42(4):178-183.
CHEN B W, HU J, JIN Y Q, et al.Prediction for compressive strength parallel to grain of Zenia insignis plantation based on Fourier infrared spectroscopy[J].Journal of Southwest Forestry University (Natural Sciences), 2022, 42(4):178-183.
[8] 汪紫阳, 尹世逵, 李颖, 等.基于可见/近红外光谱识别东北地区常见木材[J].浙江农林大学学报, 2019, 36(1):162-169.
WANG Z Y, YIN S K, LI Y, et al.Identification of common wood species in northeast China using Vis/NIR spectroscopy[J].Journal of Zhejiang A & F University, 2019, 36(1):162-169.
[9] 李倩, 斯乐婷, 何衍钦, 等.基于近红外光谱技术的藿香正气口服液质量透瓶快速检测方法研究[J].药学学报, 2022, 57(2):453-459.
LI Q, SI L T, HE Y Q, et al.A study on the rapidly non-destructive detection method of Huoxiang Zhengqi oral liquid using near infrared spectroscopy[J].Acta Pharmaceutica Sinica, 2002, 57(2):453-459.
[10] 曲正义, 逄世峰, 王兆森, 等.基于近红外光谱技术的大力参含水量快速无损检测[J].时珍国医国药, 2020, 31(11):2653-2655.
QU Z Y, PANG S F, WANG Z S, et al.Rapid nondestructive testing of water content of Ginseng based on near infrared spectroscopy[J].Lishizhen Medicine and Materia Medica Research, 2020, 31(11):2653-2655.
[11] 孙晓荣, 郑冬钰, 刘翠玲, 等.小麦粉品质在线无损快速检测系统设计与实现[J].食品与机械, 2022, 38(12):87-91.
SUN X R, ZHENG D Y, LIU C L, et al.Design and implementation of on-line nondestructive rapid testing system for wheat flour quality[J].Food & Machinery, 2022, 38(12):87-91.
[12] 刘翠玲, 闻世震, 孙晓荣, 等.京郊鲜食杏白利糖度的便携式光谱快速无损检测方法研究[J].食品安全质量检测学报, 2022, 13(24):7981-7988.
LIU C L, WEN S Z, SUN X R, et al.Research on the Brix content of fresh Armeniaca in suburbs of Beijing based on portable spectroscopic rapid non-destructive detection method[J].Journal of Food Safety and Quality, 2022, 13(24):7981-7988.
[13] 汤文涛, 徐佳锋, 胡栋, 等.基于近红外光谱的山核桃蛋白质、脂肪含量的测定[J].粮食与油脂, 2022, 35(12):158-162.
TANG W T, XU J F, HU D, et al.Determination of protein and fat content in pecan based on near infrared spectroscopy[J].Cereals & Oils, 2022, 35(12):158-162.
[14] 关晔晴, 王冬, 李楠, 等.基于近红外技术无损检测深州蜜桃果实内部品质[J].现代食品科技, 2022, 38(10):290-296.
GUAN Y Q, WANG D, LI N, et al.Near-infrared technology-based non-destructive detection of the internal quality of Shenzhou peaches[J].Modern Food Science and Technology, 2022, 38(10):290-296.
[15] 朱金艳, 朱玉杰, 冯国红, 等.基于深度信念网络与混合波长选择方法的蓝莓糖度近红外检测模型优化[J].光谱学与光谱分析, 2022, 42(12):3775-3782.
ZHU J Y, ZHU Y J, FENG G H, et al.Optimization of near-infrared detection model of blueberry sugar content based on deep belief network and hybrid wavelength selection method[J].Spectroscopy and Spectral Analysis, 2022, 42(12):3775-3782.
[16] 陈雅, 姜凯译, 李耀翔, 等.基于近红外的PE包装蓝莓新鲜度无损检测[J].包装工程, 2022, 43(7):1-10.
CHEN Y, JIANG K Y, LI Y X, et al.Nondestructive detection of freshness of PE packaged blueberries based on NIR[J].Packaging Engineering, 2022, 43(7):1-10.
[17] 曾明飞, 朱玉杰, 冯国红, 等.基于可见/近红外光谱的蓝莓新鲜度快速评价[J].食品与发酵工业, 2022, 48(20):252-259.
ZENG M F, ZHU Y J, FENG G H, et al.Rapid evaluation of blueberry freshness based on visible/near-infrared spectroscopy[J].Food and Fermentation Industries, 2022, 48(20):252-259.
[18] 朱金艳, 朱玉杰, 冯国红, 等.基于近红外光谱技术联合极限学习机的蓝莓贮藏品质定量模型建立[J].食品与发酵工业, 2022, 48(16):270-276.
ZHU J Y, ZHU Y J, FENG G H, et al.Establishment of quantitative models for blueberry storage quality based on near infrared spectroscopy combined with extreme learning machine[J].Food and Fermentation Industries, 2022, 48(16):270-276.
[19] 张丽娟, 夏其乐, 陈剑兵, 等.近红外光谱的三种蓝莓果渣花色苷含量测定[J].光谱学与光谱分析, 2020, 40(7):2246-2252.
ZHANG L J, XIA Q L, CHEN J B, et al.Prediction of anthocyanin content in three types of blueberry pomace by near-infrared spectroscopy[J].Spectroscopy and Spectral Analysis, 2020, 40(7):2246-2252.
[20] 王姗姗. 蓝莓可溶性固形物、总酚和花青素近红外光谱检测技术研究[D].北京:北京林业大学, 2012.
WANG S S.Research on near infrared spectroscopy for rapid measurements of SSC, total phenols, and anthocyanins in blueberry[D].Beijing:Beijing Forestry University, 2012.
[21] 李洋, 张茜, 陈业莉, 等.贮运过程中振动损伤对蓝莓品质的影响[J].林业科学, 2020, 56(9):40-50.
LI Y, ZHANG X, CHEN Y L, et al.Effect of vibration damage on blueberry quality during storage and transportation[J].Scientia Silvae Sinicae, 2020, 56(9):40-50.
[22] 常明娟, 楚宗艳, 杜玉倍, 等.高温胁迫下小麦生理指标的主成分分析及综合评价[J].湖南农业大学学报(自然科学版), 2023, 49(1):1-11.
CHANG M J, CHU Z Y, DU Y B, et al.Principal component analysis and comprehensive evaluation of the physiological indices in wheat under high temperature resistance[J].Journal of Hunan Agricultural University (Natural Sciences), 2023, 49(1):1-11.
[23] 冯方剑, 宋敏, 陈全家, 等.棉花苗期抗旱相关指标的主成分分析及综合评价[J].新疆农业大学学报, 2011, 34(3):211-217.
FENG F J, SONG M, CHEN Q J, et al.Analysis and comprehensive evaluation on principal component of relative indices of drought resistance at the seedling stage of cotton[J].Journal of Xinjiang Agricultural University, 2011, 34(3):211-217.

Options

Outlines

模态框（Modal）标题

Abstract

Cite this article

References