1
|
Zhu Y, Fan S, Zuo M, Zhang B, Zhu Q, Kong J. Discrimination of New and Aged Seeds Based on On-Line Near-Infrared Spectroscopy Technology Combined with Machine Learning. Foods 2024; 13:1570. [PMID: 38790869 PMCID: PMC11120509 DOI: 10.3390/foods13101570] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/19/2024] [Revised: 05/09/2024] [Accepted: 05/14/2024] [Indexed: 05/26/2024] Open
Abstract
The harvest year of maize seeds has a significant impact on seed vitality and maize yield. Therefore, it is vital to identify new seeds. In this study, an on-line near-infrared (NIR) spectra collection device (899-1715 nm) was designed and employed for distinguishing maize seeds harvested in different years. Compared with least squares support vector machine (LS-SVM), k-nearest neighbor (KNN), and extreme learning machine (ELM), the partial least squares discriminant analysis (PLS-DA) model has the optimal recognition performance for maize seed harvest years. Six different preprocessing methods, including Savitzky-Golay smoothing (SGS), standard normal variate transformation (SNV), multiplicative scatter correction (MSC), Savitzky-Golay 1 derivative (SG-D1), Savitzky-Golay 2 derivative (SG-D2), and normalization (Norm), were used to improve the quality of the spectra. The Monte Carlo cross-validation uninformative variable elimination (MC-UVE), competitive adaptive reweighted sampling (CARS), bootstrapping soft shrinkage (BOSS), successive projections algorithm (SPA), and their combinations were used to obtain effective wavelengths and decrease spectral dimensionality. The MC-UVE-BOSS-PLS-DA model achieved the classification with an accuracy of 88.75% using 93 features based on Norm preprocessed spectral data. This study showed that the self-designed NIR collection system could be used to identify the harvested years of maize seed.
Collapse
Affiliation(s)
- Yanqiu Zhu
- Key Laboratory for Theory and Technology of Intelligent Agricultural Machinery and Equipment of Jiangsu University, Zhenjiang 212013, China;
| | - Shuxiang Fan
- College of Technology, Beijing Forestry University, Beijing 100083, China;
| | - Min Zuo
- National Engineering Research Center for Agri-Product Quality Traceability, Beijing Technology and Business University, Beijing 100048, China;
| | - Baohua Zhang
- College of Artificial Intelligence, Nanjing Agricultural University, Nanjing 210095, China;
| | - Qingzhen Zhu
- Key Laboratory for Theory and Technology of Intelligent Agricultural Machinery and Equipment of Jiangsu University, Zhenjiang 212013, China;
| | - Jianlei Kong
- National Engineering Research Center for Agri-Product Quality Traceability, Beijing Technology and Business University, Beijing 100048, China;
| |
Collapse
|
2
|
Fu L, Sun J, Wang S, Xu M, Yao K, Cao Y, Tang N. Identification of maize seed varieties based on stacked sparse autoencoder and near‐infrared hyperspectral imaging technology. J FOOD PROCESS ENG 2022. [DOI: 10.1111/jfpe.14120] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Affiliation(s)
- Lvhui Fu
- School of Electrical and Information Engineering Jiangsu University Zhenjiang China
| | - Jun Sun
- School of Electrical and Information Engineering Jiangsu University Zhenjiang China
| | - Simin Wang
- School of Electrical and Information Engineering Jiangsu University Zhenjiang China
| | - Min Xu
- School of Electrical and Information Engineering Jiangsu University Zhenjiang China
| | - Kunshan Yao
- School of Electrical and Information Engineering Jiangsu University Zhenjiang China
| | - Yan Cao
- School of Electrical and Information Engineering Jiangsu University Zhenjiang China
| | - Ningqiu Tang
- School of Electrical and Information Engineering Jiangsu University Zhenjiang China
| |
Collapse
|
3
|
Identification of Maize with Different Moldy Levels Based on Catalase Activity and Data Fusion of Hyperspectral Images. Foods 2022; 11:foods11121727. [PMID: 35741924 PMCID: PMC9223184 DOI: 10.3390/foods11121727] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/06/2022] [Revised: 06/04/2022] [Accepted: 06/10/2022] [Indexed: 12/10/2022] Open
Abstract
Maize is susceptible to mold infection during growth and storage due to its large embryo and high moisture content. Therefore, it is essential to distinguish the moldy sample from healthy groups to prevent the spread of mold and avoid huger economic losses. Catalase is a metabolite in the growth of microorganisms; hence, all maize samples were accurately divided into four moldy grades (health, mild, moderate, and severe levels) by determining their catalase activity. The visible and shortwave near-infrared (Vis-SWNIR) and longwave near-infrared (LWNIR) hyperspectral images were investigated to jointly identify the moldy levels of maize. Spectra and texture information of each maize sample were extracted and used to build the classification models of maize with different moldy levels in pixel-level fusion and feature-level fusion. The result showed that the feature-level fusion of spectral and texture within Vis-SWNIR and LWNIR regions achieved the best results, overall prediction accuracy reached 95.00% for each moldy level, all healthy maize was correctly classified, and none of the moldy samples were misclassified as healthy level. This study illustrated that two hyperspectral image systems, with complementary spectral ranges, combined with feature selection and data fusion strategies, could be used synergistically to improve the classification accuracy of maize with different moldy levels.
Collapse
|
4
|
Wang Z, Huang W, Tian X, Long Y, Li L, Fan S. Rapid and Non-destructive Classification of New and Aged Maize Seeds Using Hyperspectral Image and Chemometric Methods. FRONTIERS IN PLANT SCIENCE 2022; 13:849495. [PMID: 35620676 PMCID: PMC9127793 DOI: 10.3389/fpls.2022.849495] [Citation(s) in RCA: 15] [Impact Index Per Article: 7.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 01/06/2022] [Accepted: 04/05/2022] [Indexed: 06/15/2023]
Abstract
The aged seeds have a significant influence on seed vigor and corn growth. Therefore, it is vital for the planting industry to identify aged seeds. In this study, hyperspectral reflectance imaging (1,000-2,000 nm) was employed for identifying aged maize seeds using seeds harvested in different years. The average spectra of the embryo side, endosperm side, and both sides were extracted. The support vector machine (SVM) algorithm was used to develop classification models based on full spectra to evaluate the potential of hyperspectral imaging for maize seed detection and using the principal component analysis (PCA) and ANOVA to reduce data dimensionality and extract feature wavelengths. The classification models achieved perfect performance using full spectra with an accuracy of 100% for the prediction set. The performance of models established with the first three principal components was similar to full spectrum models, but that of PCA loading models was worse. Compared to other spectra, the two-band ratio (1,987 nm/1,079 nm) selected by ANOVA from embryo-side spectra achieved a better classification accuracy of 95% for the prediction set. The image texture features, including histogram statistics (HS) and gray-level co-occurrence matrix (GLCM), were extracted from the two-band ratio image to establish fusion models. The results demonstrated that the two-band ratio selected from embryo-side spectra combined with image texture features achieved the classification of maize seeds harvested in different years with an accuracy of 97.5% for the prediction set. The overall results indicated that combining the two wavelengths with image texture features could detect aged maize seeds effectively. The proposed method was conducive to the development of multi-spectral detection equipment.
Collapse
Affiliation(s)
- Zheli Wang
- Intelligent Equipment Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, China
- College of Information and Electrical Engineering, China Agricultural University, Beijing, China
| | - Wenqian Huang
- Intelligent Equipment Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, China
| | - Xi Tian
- Intelligent Equipment Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, China
| | - Yuan Long
- Intelligent Equipment Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, China
| | - Lianjie Li
- Intelligent Equipment Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, China
| | - Shuxiang Fan
- Intelligent Equipment Research Center, Beijing Academy of Agriculture and Forestry Sciences, Beijing, China
| |
Collapse
|
5
|
Nascimento MC, Marcarini WD, Folli GS, da Silva Filho WG, Barbosa LL, Paulo EH, Vassallo PF, Mill JG, Barauna V, Martin FL, de Castro ER, Romão W, Filgueiras PR. Noninvasive Diagnostic for COVID-19 from Saliva Biofluid via FTIR Spectroscopy and Multivariate Analysis. Anal Chem 2022; 94:2425-2433. [PMID: 35076208 PMCID: PMC8805707 DOI: 10.1021/acs.analchem.1c04162] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/24/2021] [Accepted: 01/13/2022] [Indexed: 01/22/2023]
Abstract
Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused the worst global health crisis in living memory. The reverse transcription polymerase chain reaction (RT-qPCR) is considered the gold standard diagnostic method, but it exhibits limitations in the face of enormous demands. We evaluated a mid-infrared (MIR) data set of 237 saliva samples obtained from symptomatic patients (138 COVID-19 infections diagnosed via RT-qPCR). MIR spectra were evaluated via unsupervised random forest (URF) and classification models. Linear discriminant analysis (LDA) was applied following the genetic algorithm (GA-LDA), successive projection algorithm (SPA-LDA), partial least squares (PLS-DA), and a combination of dimension reduction and variable selection methods by particle swarm optimization (PSO-PLS-DA). Additionally, a consensus class was used. URF models can identify structures even in highly complex data. Individual models performed well, but the consensus class improved the validation performance to 85% accuracy, 93% sensitivity, 83% specificity, and a Matthew's correlation coefficient value of 0.69, with information at different spectral regions. Therefore, through this unsupervised and supervised framework methodology, it is possible to better highlight the spectral regions associated with positive samples, including lipid (∼1700 cm-1), protein (∼1400 cm-1), and nucleic acid (∼1200-950 cm-1) regions. This methodology presents an important tool for a fast, noninvasive diagnostic technique, reducing costs and allowing for risk reduction strategies.
Collapse
Affiliation(s)
- Márcia
H. C. Nascimento
- Chemometrics
Laboratory of the Center of Competence in Petroleum Chemistry −
NCQP, Universidade Federal do Espírito
Santo (UFES), Vitória, Espírito Santo 29075-910, Brazil
| | - Wena D. Marcarini
- Department
of Physiological Sciences, Universidade
Federal do Espírito Santo (UFES), Vitória, Espírito Santo 29040-090, Brazil
| | - Gabriely S. Folli
- Chemometrics
Laboratory of the Center of Competence in Petroleum Chemistry −
NCQP, Universidade Federal do Espírito
Santo (UFES), Vitória, Espírito Santo 29075-910, Brazil
| | - Walter G. da Silva Filho
- Department
of Physiological Sciences, Universidade
Federal do Espírito Santo (UFES), Vitória, Espírito Santo 29040-090, Brazil
| | - Leonardo L. Barbosa
- Department
of Physiological Sciences, Universidade
Federal do Espírito Santo (UFES), Vitória, Espírito Santo 29040-090, Brazil
| | - Ellisson Henrique
de Paulo
- Chemometrics
Laboratory of the Center of Competence in Petroleum Chemistry −
NCQP, Universidade Federal do Espírito
Santo (UFES), Vitória, Espírito Santo 29075-910, Brazil
| | - Paula F. Vassallo
- Clinical
Hospital, Universidade Federal de Minas
Gerais, Belo Horizonte, Minas Gerais 31270-901, Brazil
| | - José G. Mill
- Department
of Physiological Sciences, Universidade
Federal do Espírito Santo (UFES), Vitória, Espírito Santo 29040-090, Brazil
| | - Valério
G. Barauna
- Department
of Physiological Sciences, Universidade
Federal do Espírito Santo (UFES), Vitória, Espírito Santo 29040-090, Brazil
| | | | - Eustáquio
V. R. de Castro
- Chemometrics
Laboratory of the Center of Competence in Petroleum Chemistry −
NCQP, Universidade Federal do Espírito
Santo (UFES), Vitória, Espírito Santo 29075-910, Brazil
| | - Wanderson Romão
- Instituto
Federal de Educação, Ciência
e Tecnologia do Espírito Santo, Vila Velha 29106-010, Brazil
| | - Paulo R. Filgueiras
- Chemometrics
Laboratory of the Center of Competence in Petroleum Chemistry −
NCQP, Universidade Federal do Espírito
Santo (UFES), Vitória, Espírito Santo 29075-910, Brazil
| |
Collapse
|
6
|
El-Zeiny MB, Zawbaa HM, Serag A. An evaluation of different bio-inspired feature selection techniques on multivariate calibration models in spectroscopy. SPECTROCHIMICA ACTA. PART A, MOLECULAR AND BIOMOLECULAR SPECTROSCOPY 2021; 246:119042. [PMID: 33065451 DOI: 10.1016/j.saa.2020.119042] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/06/2020] [Revised: 09/05/2020] [Accepted: 10/01/2020] [Indexed: 06/11/2023]
Abstract
Herein, two new swarm intelligence based algorithms namely; grey wolf optimization (GWO) and antlion optimization (ALO) algorithms were presented, for the first time, as variable selection tools in spectroscopic data analysis. In order to assess the performance of these algorithms, they were applied along with the recently introduced firefly algorithm (FFA) and the well-established genetic algorithm (GA) and particle swarm optimization (PSO) algorithm on four different spectroscopic datasets of varying sizes and nature (UV and IR). Partial least squares (PLS) regression models were built using the selected variables by these algorithms along with the full spectral data as the reference models. The obtained results prove that the ALO and GWO optimization algorithms select variables in most cases less than GA and PSO while keeping the PLS performance almost the same. Accordingly, these algorithms can be successfully used for variable selection in spectroscopic data analysis.
Collapse
Affiliation(s)
- Mohamed B El-Zeiny
- Analytical Chemistry Department, Faculty of Pharmacy, Modern University for Technology and Information (MTI), Egypt.
| | - Hossam M Zawbaa
- Faculty of Computers and Information, Beni-Suef University, Egypt; Faculty of Mathematics and Computer Science, Babes-Bolyai University, Romania
| | - Ahmed Serag
- Pharmaceutical Analytical Chemistry Department, Faculty of Pharmacy, Al-Azhar University, Cairo 11751, Egypt.
| |
Collapse
|
7
|
Near-Infrared Spectroscopy Evaluations for the Differentiation of Carbapenem-Resistant from Susceptible Enterobacteriaceae Strains. Diagnostics (Basel) 2020; 10:diagnostics10100736. [PMID: 32977503 PMCID: PMC7598181 DOI: 10.3390/diagnostics10100736] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/18/2020] [Revised: 09/11/2020] [Accepted: 09/21/2020] [Indexed: 11/24/2022] Open
Abstract
Antimicrobial Resistance (AMR) caused by Carbapenem-Resistant Enterobacteriaceae (CRE) is a global threat. Accurate identification of these bacterial species with associated AMR is critical for their management. While highly accurate methods to detect CRE are available, they are costly, timely and require expert skills, making their application infeasible in low-resource settings. Here, we investigated the potential of Near-Infrared Spectroscopy (NIRS) for a range of applications: (i) the detection and differentiation of isolates of two pathogenic Enterobacteriaceae species, Klebsiella pneumoniae and Escherichia coli, and (ii) the differentiation of carbapenem resistant and susceptible K. pneumoniae. NIRS has successfully differentiated between K. pneumoniae and E. coli isolates with a predictive accuracy of 89.04% (95% CI; 88.7–89.4%). K. pneumoniae isolates harbouring carbapenem-resistance determinants were differentiated from susceptible K. pneumoniae strains with an accuracy of 85% (95% CI; 84.2–86.1%). To our knowledge, this is the largest proof of concept demonstration for the utility and feasibility of NIRS to rapidly differentiate between K. pneumoniae and E. coli as well as carbapenem-resistant K. pneumoniae from susceptible strains.
Collapse
|
8
|
Variety Identification of Single Rice Seed Using Hyperspectral Imaging Combined with Convolutional Neural Network. APPLIED SCIENCES-BASEL 2018. [DOI: 10.3390/app8020212] [Citation(s) in RCA: 88] [Impact Index Per Article: 14.7] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/26/2023]
|
9
|
Zhao Y, Zhu S, Zhang C, Feng X, Feng L, He Y. Application of hyperspectral imaging and chemometrics for variety classification of maize seeds. RSC Adv 2018; 8:1337-1345. [PMID: 35540920 PMCID: PMC9077125 DOI: 10.1039/c7ra05954j] [Citation(s) in RCA: 40] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/27/2017] [Accepted: 12/22/2017] [Indexed: 11/21/2022] Open
Abstract
Hyperspectral imaging provides an effective way for seed variety classification for assessing variety purity and increasing crop yield.
Collapse
Affiliation(s)
- Yiying Zhao
- College of Biosystems Engineering and Food Science
- Zhejiang University
- Hangzhou 310058
- China
| | - Susu Zhu
- College of Biosystems Engineering and Food Science
- Zhejiang University
- Hangzhou 310058
- China
| | - Chu Zhang
- College of Biosystems Engineering and Food Science
- Zhejiang University
- Hangzhou 310058
- China
| | - Xuping Feng
- College of Biosystems Engineering and Food Science
- Zhejiang University
- Hangzhou 310058
- China
| | - Lei Feng
- College of Biosystems Engineering and Food Science
- Zhejiang University
- Hangzhou 310058
- China
| | - Yong He
- College of Biosystems Engineering and Food Science
- Zhejiang University
- Hangzhou 310058
- China
| |
Collapse
|
10
|
Esteki M, Nouroozi S, Amanifar S, Shahsavari Z. A Simple and Highly Sensitive Method for Quantitative Detection of Methyl Paraben and Phenol in Cosmetics Using Derivative Spectrophotometry and Multivariate Chemometric Techniques. J CHIN CHEM SOC-TAIP 2017. [DOI: 10.1002/jccs.201600104] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/12/2022]
Affiliation(s)
- Mahnaz Esteki
- Department of Chemistry; University of Zanjan; Zanjan 45195-313 Iran
| | - Siavash Nouroozi
- Department of Chemistry; University of Zanjan; Zanjan 45195-313 Iran
| | - Setareh Amanifar
- Department of Agriculture; University of Zanjan; Zanjan 45195-313 Iran
| | - Zahra Shahsavari
- Department of Chemistry; University of Zanjan; Zanjan 45195-313 Iran
| |
Collapse
|
11
|
Determination of Geographical Origin and Anthocyanin Content of Black Goji Berry (Lycium ruthenicum Murr.) Using Near-Infrared Spectroscopy and Chemometrics. FOOD ANAL METHOD 2016. [DOI: 10.1007/s12161-016-0666-4] [Citation(s) in RCA: 17] [Impact Index Per Article: 2.1] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/20/2022]
|