Detection of paralytic shellfish toxins by near-infrared spectroscopy based on a near-Bayesian SVM classifier with unequal misclassification costs.
imbalanced classification
near-Bayesian SVM
near-infrared spectroscopy
paralytic shellfish toxins
unequal misclassification costs
Journal
Journal of the science of food and agriculture
ISSN: 1097-0010
Titre abrégé: J Sci Food Agric
Pays: England
ID NLM: 0376334
Informations de publication
Date de publication:
29 Oct 2023
29 Oct 2023
Historique:
revised:
25
09
2023
received:
12
04
2023
accepted:
30
10
2023
pubmed:
30
10
2023
medline:
30
10
2023
entrez:
30
10
2023
Statut:
aheadofprint
Résumé
Paralytic shellfish poisoning caused by human consumption of shellfish fed on toxic algae is a public health hazard. It is essential to implement shellfish monitoring programs to minimize the possibility of shellfish contaminated by paralytic shellfish toxins (PST) reaching the marketplace. This paper proposes a rapid detection method for PST in mussels using near-infrared spectroscopy (NIRS) technology. Spectral data in the wavelength range of 950-1700 nm for PST-contaminated and non-contaminated mussel samples were used to build the detection model. Near-Bayesian support vector machines (NBSVM) with unequal misclassification costs (u-NBSVM) were applied to solve a classification problem arising from the fact that the quantity of non-contaminated mussels was far less than that of PST-contaminated mussels in practice. The u-NBSVM model performed adequately on imbalanced datasets by combining unequal misclassification costs and decision boundary shifts. The detection performance of the u-NBSVM did not decline as the number of PST samples decreased due to adjustments to the misclassification costs. When the number of PST samples was 20, the G-mean and accuracy reached 0.9898 and 0.9944, respectively. Compared with the traditional support vector machines (SVMs) and the NBSVM, the u-NBSVM model achieved better detection performance. The results of this study indicate that NIRS technology combined with the u-NBSVM model can be used for rapid and non-destructive PST detection in mussels. © 2023 Society of Chemical Industry.
Sections du résumé
BACKGROUND
BACKGROUND
Paralytic shellfish poisoning caused by human consumption of shellfish fed on toxic algae is a public health hazard. It is essential to implement shellfish monitoring programs to minimize the possibility of shellfish contaminated by paralytic shellfish toxins (PST) reaching the marketplace.
RESULTS
RESULTS
This paper proposes a rapid detection method for PST in mussels using near-infrared spectroscopy (NIRS) technology. Spectral data in the wavelength range of 950-1700 nm for PST-contaminated and non-contaminated mussel samples were used to build the detection model. Near-Bayesian support vector machines (NBSVM) with unequal misclassification costs (u-NBSVM) were applied to solve a classification problem arising from the fact that the quantity of non-contaminated mussels was far less than that of PST-contaminated mussels in practice. The u-NBSVM model performed adequately on imbalanced datasets by combining unequal misclassification costs and decision boundary shifts. The detection performance of the u-NBSVM did not decline as the number of PST samples decreased due to adjustments to the misclassification costs. When the number of PST samples was 20, the G-mean and accuracy reached 0.9898 and 0.9944, respectively.
CONCLUSION
CONCLUSIONS
Compared with the traditional support vector machines (SVMs) and the NBSVM, the u-NBSVM model achieved better detection performance. The results of this study indicate that NIRS technology combined with the u-NBSVM model can be used for rapid and non-destructive PST detection in mussels. © 2023 Society of Chemical Industry.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Subventions
Organisme : National Natural Science Foundation of China
Organisme : Open Project of Mangrove Institute of Lingnan Normal University
Informations de copyright
© 2023 Society of Chemical Industry.
Références
Humpage AR, Magalhaes VF and Froscio SM, Comparison of analytical tools and biological assays for detection of paralytic shellfish poisoning toxins. Anal Bioanal Chem 397:1655-1671 (2010).
Reis Costa P, Impact and effects of paralytic shellfish poisoning toxins derived from harmful algal blooms to marine fish. Fish Fish 17:226-248 (2016).
Harrison K, Johnson S and Turner AD, Application of rapid test kits for the determination of paralytic shellfish poisoning (PSP) toxins in bivalve molluscs from Great Britain. Toxicon 119:352-361 (2016).
Knaack JS, Porter KA, Jacob JT, Sullivan K, Forester M, Wang RY et al., Case diagnosis and characterization of suspected paralytic shellfish poisoning in Alaska. Harmful Algae 57:45-50 (2016).
Okumura M, Tsuzuki H and Tomita B-I, A rapid detection method for paralytic shellfish poisoning toxins by cell bioassay. Toxicon 46:93-98 (2005).
Mattarozzi M, Bianchi F, Milioli M, Cavazza A and Careri M, An innovative method based on quick, easy, cheap, effective, rugged, and safe extraction coupled to desorption electrospray ionization-high resolution mass spectrometry for screening the presence of paralytic shellfish toxins in clams. Talanta 147:416-421 (2016).
Teye E, Huang XY and Afoakwa N, Review on the potential use of near infrared spectroscopy (NIRS) for the measurement of chemical residues in food. Am J Food Sci Technol 1:1-8 (2013).
Nicolaï BM, Beullens K, Bobelyn E, Peirs A, Saeys W, Theron KI et al., Nondestructive measurement of fruit and vegetable quality by means of NIR spectroscopy: a review. Postharvest Biol Technol 46:99-118 (2007).
Wei C and Li X, A near-infrared spectroscopy method for the detection of texture profile analysis of Litopeneo vannamei based on partial least squares regression. J Food Process Eng 45:e14140 (2022).
Piarulli S, Sciutto G, Oliveri P, Malegori C, Prati S, Mazzeo R et al., Rapid and direct detection of small microplastics in aquatic samples by a new near infrared hyperspectral imaging (NIR-HSI) method. Chemosphere 260:127655 (2020).
Guévélou E, Carnegie RB, Whitefleet-Smith L, Small JM and Allen SK, Near infrared reflectance spectroscopy to quantify Perkinsus marinus infecting Crassostrea virginica. Aquaculture 533:736063 (2021).
Currò S, Fasolato L, Serva L, Boffo L, Ferlito JC, Novelli E et al., Use of a portable near-infrared tool for rapid on-site inspection of freezing and hydrogen peroxide treatment of cuttlefish (Sepia officinalis). Food Control 132:108524 (2022).
Liu Y, Xu L, Zeng S, Qiao F, Jiang W and Xu Z, Rapid detection of mussels contaminated by heavy metals using near-infrared reflectance spectroscopy and a constrained difference extreme learning machine. Spectrochim Acta A Mol Biomol Spectrosc 269:120776 (2022).
Ghidini S, Varrà MO and Zanardi E, Approaching authenticity issues in fish and seafood products by qualitative spectroscopy and chemometrics. Molecules 24:1812 (2019).
Zhou J, Yu L, Ding Q and Wang R, Textile fiber identification using near-infrared spectroscopy and pattern recognition. Autex Res J 19:201-209 (2019).
Liu P, Wang J, Li Q, Gao J, Tan X and Bian X, Rapid identification and quantification of Panax notoginseng with its adulterants by near infrared spectroscopy combined with chemometrics. Spectrochim Acta A Mol Biomol Spectrosc 206:23-30 (2019).
Lima ABSD, Batista AS, Jesus JCD, Silva JDJ, Araújo ACMD and Santos LS, Fast quantitative detection of black pepper and cumin adulterations by near-infrared spectroscopy and multivariate modeling. Food Control 107:106802 (2020).
Zeng J, Guo Y, Han Y, Li Z, Yang Z, Chai Q et al., A review of the discriminant analysis methods for food quality based on near-infrared spectroscopy and pattern recognition. Molecules 26:749 (2021).
Datta S and Das S, Near-bayesian support vector machines for imbalanced data classification with equal or unequal misclassification costs. Neural Netw 70:39-52 (2015).
Zhang Y, Fu P, Liu W and Chen G, Imbalanced data classification based on scaling kernel-based support vector machine. Neural Comput Appl 25:927-935 (2014).
Wu Q and Zhou D-X, SVM soft margin classifiers: linear programming versus quadratic programming. Neural Comput 17:1160-1187 (2005).
Liu Y, Qiao F, Xu L, Wang R, Jiang W and Xu Z, Fast detection of diarrhetic shellfish poisoning toxins in mussels using NIR spectroscopy and improved twin support vector machines. Front Mar Sci 9:907378 (2022).
Ouyang Q, Zhao J, Pan W and Chen Q, Real-time monitoring of process parameters in rice wine fermentation by a portable spectral analytical system combined with multivariate analysis. Food Chem 190:135-141 (2016).
Zhao Z and Wang X, Cost-sensitive SVDD models based on a sample selection approach. Appl Intell 48:4247-4266 (2018).
Tang J, Li J, Xu W, Tian Y, Ju X and Zhang J, Robust cost-sensitive kernel method with Blinex loss and its applications in credit risk evaluation. Neural Netw 143:327-344 (2021).
Zhao Z, Zhong P and Zhao Y, Learning SVM with weighted maximum margin criterion for classification of imbalanced data. Math Comput Modell 54:1093-1099 (2011).
Mishra P, Rutledge DN, Roger J-M, Wali K and Khan HA, Chemometric pre-processing can negatively affect the performance of near-infrared spectroscopy models for fruit quality prediction. Talanta 229:122303 (2021).
Baranowski P, Mazurek W and Pastuszka-Woźniak J, Supervised classification of bruised apples with respect to the time after bruising on the basis of hyperspectral imaging data. Postharvest Biol Technol 86:249-258 (2013).
Ye D, Sun L, Tan W, Che W and Yang M, Detecting and classifying minor bruised potato based on hyperspectral imaging. Chemom Intel Lab Syst 177:129-139 (2018).
Barnes RJ, Dhanoa MS and Lister SJ, Standard normal variate transformation and de-trending of near-infrared diffuse reflectance spectra. Appl Spectrosc 43:772-777 (1989).
Wu D, Chen X, Cao F, Sun D-W, He Y and Jiang Y, Comparison of infrared spectroscopy and nuclear magnetic resonance techniques in tandem with multivariable selection for rapid determination of ω-3 polyunsaturated fatty acids in fish oil. Food Bioprocess Technol 7:1555-1569 (2014).
Jafarigol E and Trafalis T, Imbalanced learning with parametric linear programming support vector machine for weather data application. SN Comput Sci 1:360 (2020).
Mirzaei B, Rahmati F and Nezamabadi-pour H, A score-based preprocessing technique for class imbalance problems. Pattern Anal Appl 25:913-931 (2022).