Non-destructive detection of polysaccharides and moisture in Ganoderma lucidum using near-infrared spectroscopy and machine learning algorithm

被引：21

作者：

Ni, Hongfei ^{[1
]}

Fu, Weiliang ^{[1
]}

Wei, Jing ^{[2
]}

Zhang, Yiwei ^{[1
]}

Chen, Dan ^{[1
]}

Tong, Jie ^{[3
]}

Chen, Yong ^{[1
,4
]}

Liu, Xuesong ^{[1
,4
]}

Luo, Yingjie ^{[1
]}

Xu, Tengfei ^{[1
,4
]}

机构：

[1] Zhejiang Univ, Innovat Inst Artificial Intelligence Med, Coll Pharmaceut Sci, Hangzhou 310058, Zhejiang, Peoples R China

[2] Air Force Hosp Western Theater Command, Chengdu 610000, Sichuan, Peoples R China

[3] Yale Sch Med, PET Ctr, Dept Radiol & Biomed Imaging, New Haven, CT 06520 USA

[4] Zhejiang Univ, Coll Pharmaceut Sci, Key Lab Adv Drug Delivery Syst Zhejiang Prov, Hangzhou 310058, Zhejiang, Peoples R China

来源：

LWT-FOOD SCIENCE AND TECHNOLOGY | 2023年 / 184卷

关键词：

Near-infrared spectroscopy; Ganoderma lucidum; Non-destructive detection; Machine learning; SUPPORT VECTOR MACHINE; PROTEIN;

D O I：

10.1016/j.lwt.2023.115001

中图分类号：

TS2 [食品工业];

学科分类号：

0832 ;

摘要：

Ganoderma lucidum, the fruiting body of the Poraceae fungi G. lucidum or Ganoderma sinense, has a long history of use in promoting health and longevity in Asian countries. However, traditional methods for detecting poly-saccharides and moisture in G. lucidum are complicated, time-consuming, and damaging (to the sample). In this study, rapid and nondestructive near-infrared (NIR) spectroscopy (700-2500 nm) was uesd to directly scan the back of the G. lucidum cap without powdering. Thereafter, we used synergy interval partial least squares to select the performing band and the ant lion optimization (ALO) algorithm to optimize the least squares support vector machine (LSSVM) model for these two components. The results showed that the ALO-LSSVM model could predict the total polysaccharide and moisture content with high accuracy. The correlation coefficient for calibration were both >0.9 and their ratio of prediction to deviation (RPD) values of prediction were 2.6 and 3.6, respec-tively, indicating the non-destructive determination of polysaccharides and moisture in G. lucidum will provide great convenience for on-site testing by procurement personnel. This shows the combination of NIR spectroscopy and the ALO-LSSVM algorithm has potential applications for the rapid and nondestructive analysis of natural products.

引用

页数：11

共 39 条

[1] Promoting rainwater harvesting for improving water security: Analysis of drivers and barriers in Ghana [J].

Akuffobea-Essilfie, Mavis ;

Williams, Portia Adade ;

Asare, Roland ;

Damman, Sigrid ;

Essegbey, George Owusu .

AFRICAN JOURNAL OF SCIENCE TECHNOLOGY INNOVATION & DEVELOPMENT, 2020, 12 (04) :443-451

[2] Benchtop NIR method development for continuous manufacturing scale to enable efficient PAT application for solid oral dosage form [J].

Alam, Md Anik ;

Liu, Yang Angela ;

Dolph, Stephanie ;

Pawliczek, Marcin ;

Peeters, Elisabeth ;

Palm, Andrew .

INTERNATIONAL JOURNAL OF PHARMACEUTICS, 2021, 601

[3] Modeling of cetane number of biodiesel from fatty acid methyl ester (FAME) information using GA-, PSO-, and HGAPSO- LSSVM models [J].

Bemani, Amin ;

Xiong, Qingang ;

Baghban, Alireza ;

Habibzadeh, Saijad ;

Mohammadi, Amir H. ;

Doranehgard, Mohammad Hossein .

RENEWABLE ENERGY, 2020, 150 :924-934

[4] Bio-inspired algorithm for variable selection in i-PLSR to determine physical properties, thorium and rare earth elements in soils from Brazilian semiarid region [J].

Bernardino Oliveira, Danubio Leonardo ;

de Souza Pereira, Lavinia Hannah ;

Schneider, Mateus Pires ;

Agra Bezerra Silva, Ygor Jacques ;

Araujo Nascimento, Clistenes Williams ;

van Straaten, Peter ;

Agra Bezerra Silva, Yuri Jacques ;

Gomes, Adriano de Araujo ;

Veras, Germano .

MICROCHEMICAL JOURNAL, 2021, 160

[5] Vis-NIR hyperspectral imaging for the classification of bacterial foodborne pathogens based on pixel-wise analysis and a novel CARS-PSO-SVM model [J].

Bonah, Ernest ;

Huang, Xingyi ;

Yi, Ren ;

Aheto, Joshua Harrington ;

Yu, Shanshan .

INFRARED PHYSICS & TECHNOLOGY, 2020, 105

[6] Least-squares support vector machines and near infrared spectroscopy for quantification of common adulterants in powdered milk [J].

Borin, Alessandra ;

Ferrao, Marco Flores ;

Mello, Cesar ;

Maretto, Danilo Althmann ;

Poppi, Ronei Jesus .

ANALYTICA CHIMICA ACTA, 2006, 579 (01) :25-32

[7] Non-destructive determination of total sugar content in tobacco filament based on calibration transfer with parameter free adjustment [J].

Geng, Yingrui ;

Shen, Huanchao ;

Ni, Hongfei ;

Tian, Yunong ;

Zhao, Zhenjie ;

Chen, Yong ;

Liu, Xuesong .

MICROCHEMICAL JOURNAL, 2022, 181

[8] Quantitative assessment of zearalenone in maize using multivariate algorithms coupled to Raman spectroscopy [J].

Guo, Zhiming ;

Wang, Mingming ;

Wu, Jingzhu ;

Tao, Feifei ;

Chen, Quansheng ;

Wang, Qingyan ;

Ouyang, Qin ;

Shi, Jiyong ;

Zou, Xiaobo .

FOOD CHEMISTRY, 2019, 286 :282-288

[9] Spectrum-effect relationship of immunologic activity of Ganoderma lucidum by UPLC-MS/MS and component knock-out method [J].

Li, Changqin ;

Cui, Yiping ;

Lu, Jie ;

Meng, Lijun ;

Ma, Changyang ;

Liu, Zhenhua ;

Zhang, Yan ;

Kang, Wenyi .

FOOD SCIENCE AND HUMAN WELLNESS, 2021, 10 (03) :278-288

[10] Rapid monitoring of black tea fermentation quality based on a solution-phase sensor array combined with UV-visible spectroscopy [J].

Li, Luqing ;

Li, Menghui ;

Cui, Qingqing ;

Liu, Ying ;

Chen, Yuyu ;

Wang, Yujie ;

Zhang, Zhengzhu ;

Chen, Quansheng ;

Ning, Jingming .

FOOD CHEMISTRY, 2022, 377

← 1 2 3 4 →