Classification of freshwater fish species by linear discriminant analysis based on near infrared reflectance spectroscopy

Abstract

Near infrared reflectance spectroscopy was used to discriminate different species of freshwater fish samples. Samples from seven freshwater fish species of the family Cyprinidae (black carp (Mylopharyngodon piceus), grass carp (Ctenopharyngodon idellus), silver carp (Hypophthalmichthys molitrix), bighead carp (Aristichthys nobilis), common carp (Cyprinus carpio), crucian (Carassius auratus), and bream (Parabramis pekinensis)) were scanned by near infrared reflectance spectroscopy from 1000 nm to 1799 nm. Linear discriminant analysis models were built for the classification of species. We inspected the effect of partial least square, principal component analysis, competitive adaptive reweighted sampling, and fast Fourier transform on linear discriminant analysis. The results showed that the dimension reduction methods worked very well for this example. Linear discriminant analysis models which were combined with principal component analysis and fast Fourier transform could classify accurately all the samples under multiplicative scatter correction pre-processing. According to the loadings in principal component analysis,

Fraud in Animal Origin Food Products: Advances in Emerging Spectroscopic Detection Methods over the Past Five Years

“…DNA analysis and MS methods are among the most commonly used techniques in this regard [126,145,146,184,185]. Seven freshwater fish species Species identification NIR (1000-1799 nm) PCA, LDA [190] Fish surimi; white croaker, hairtail, red coat Species identification FT-IR (2500-25000 nm) PCR [191] Fish surimi; white croaker, hairtail, red coat Species identification NIR (1000-2500 nm) DA [192] Freshwater shrimps Addition adulterant LF-NMR, MRI PCA, PLSR [193] Tilapia Detection of thawed fish NIR (1000-2500 nm) PCA [194] Crucian carp Detection of thawed fish VIS/NIR HSI (400-1000 nm) PLS-DA [195] Grass carp Detection of thawed fish VIS/NIR HIS (400-1000 nm) SIMCA, PLS-DA, LS-SVM, and PNN [196] Shelled shrimp Detection of thawed products VIS/NIR HSI (400-1000 nm) SIMCA, RF [197] PCA Several spectroscopic techniques in conjunction with chemometric tools have been used to identify fish species and detect fraud. Alamprese and Casiraghi used FT-NIR and FT-MIR data coupled with two classification techniques (i.e., SIMCA and linear discriminant analyses (LDA)) in order to discriminate valuable fish species (i.e., red mullet and plaice) substituted with cheaper ones, namely Atlantic mullet and flounder [76].…”

How Fishy Is Your Fish? Authentication, Provenance and Traceability in Fish and Seafood by Means of Vibrational Spectroscopy

“…A study by Lv and collaborators, utilised NIR spectroscopy to discriminate different species of freshwater fish including black carp (Mylopharyngodon piceus), grass carp (Ctenopharyngodon idellus), silver carp (Hypophthalmichthys molitrix), bighead carp (Aristichthys nobilis), common carp (Cyprinus carpio), crucian (Carassius auratus), and bream (Parabramis pekinensis) [74]. The authors evaluated several chemometric techniques including PLS-DA, PCA, competitive adaptive reweighted sampling, and fast Fourier transform (FT) applied to LDA to classify and monitor the origin of the samples [74]. The authors concluded that the developed methodology was effective in distinguishing between freshwater fish species [74].…”

“…The authors evaluated several chemometric techniques including PLS-DA, PCA, competitive adaptive reweighted sampling, and fast Fourier transform (FT) applied to LDA to classify and monitor the origin of the samples [74]. The authors concluded that the developed methodology was effective in distinguishing between freshwater fish species [74].…”

Approaching Authenticity Issues in Fish and Seafood Products by Qualitative Spectroscopy and Chemometrics

“…Different species of freshwater fish of the Cyprinidae family, namely black carp ( Mylopharyngodon piceus ), grass carp ( Ctenopharyngodon idellus ), silver carp ( Hypophthalmichthys molitrix ), bighead carp ( Aristichthys nobilis ), common carp ( Cyprinus carpio ), crucian ( Carassius auratus ), and bream ( Parabramis pekinensis ), were also investigated by NIR spectroscopy [53]. Fish samples were scanned in the 1000–1799 nm region, MSC pre-treated, and pre-reduced in dimensionality by different methods, including PCA, PLS, and fast Fourier transform (FFT).…”

“…Fish samples were scanned in the 1000–1799 nm region, MSC pre-treated, and pre-reduced in dimensionality by different methods, including PCA, PLS, and fast Fourier transform (FFT). In this case, LDA models were built by using only nine pre-selected spectra wavelengths from the entire spectrum and results obtained showed a good prediction ability of the adopted strategy: PCA-LDA and FFT-LDA models, in fact, showed 100% accuracy, specificity, sensitivity, and precision, even if most of the information was not taken into account by calculation [53].…”