Fourier Transform Near-infrared Research Articles

The future of fish age estimation: deep machine learning coupled with Fourier transform near-infrared spectroscopy of otoliths

Our novel approach for fish age prediction uses quantitative analysis of Fourier transform near-infrared (FT-NIR) spectra of otoliths by means of multimodal convolutional neural networks (MMCNN). We integrate two key data modalities that are related to fish ages: the entire range of wavenumbers of FT-NIR spectra and corresponding biological and geospatial data for nearly 9000 walleye pollock ( Gadus chalcogrammus) specimens. The proposed model extracts informative spectral features automatically and elucidates hidden structural relationships associated with fish growth to improve age predictions. Absorbance associated with 7000 to 4000 cm−1 wavenumbers had the highest influence on model predictions followed by fish length, latitude, depth, and temperature. The optimal model resulted in good overall performance with an R2 of 0.93 and RMSE of 0.83 for training data set and R2 of 0.92 and RMSE of 0.91 for test data set. MMCNN's age predictions were comparable to microscope-based ages yielding as good or slightly better precision. Moreover, the model outperformed classical partial least squares analysis of otolith spectra and remedied prediction bias at older ages of fish.

Rapid and Accurate Authentication of Porcini Mushroom Species Using Fourier Transform Near-Infrared Spectra Combined with Machine Learning and Chemometrics.

Porcini mushrooms have high nutritional value and great potential, but different species are easily confused, so it is essential to identify them rapidly and precisely. The diversity of nutrients in stipe and cap will lead to differences in spectral information. In this research, Fourier transform near-infrared (FT-NIR) spectral information about imparity species of porcini mushroom stipe and cap was collected and combined into four data matrices. FT-NIR spectra of four data sets were combined with chemometric methods and machine learning for accurate evaluation and identification of different porcini mushroom species. From the results: (1) improved visualization level of t-distributed stochastic neighbor embedding (t-SNE) results after the second derivative preprocessing compared with raw spectra; (2) after using multiple pretreatment combinations to process the four data matrices, the model accuracies based on support vector machine and partial least-square discriminant analysis (PLS-DA) under the best preprocessing method were 98.73-99.04% and 98.73-99.68%, respectively; (3) by comparing the modeling results of FT-NIR spectra with different data matrices, it was found that the PLS-DA model based on low-level data fusion has the highest accuracy (99.68%), but residual neural network (ResNet) model based on the stipe, cap, and average spectral data matrix worked better (100% accuracy). The above results suggest that distinct models should be selected for dissimilar spectral data matrices of porcini mushrooms. Additionally, FT-NIR spectra have the advantages of being nondevastate and fast; this method is expected to be a promising analytical tool in food safety control.

Rapid metabolic fingerprinting with the aid of chemometric models to identify authenticity of natural medicines: Turmeric, Ocimum, and Withania somnifera study

Herbal medicines are popular natural medicines that have been used for decades. The use of alternative medicines continues to expand rapidly across the world. The World Health Organization suggests that quality assessment of natural medicines is essential for any therapeutic or health care applications, as their therapeutic potential varies between different geographic origins, plant species, and varieties. Classification of herbal medicines based on a limited number of secondary metabolites is not an ideal approach. Their quality should be considered based on a complete metabolic profile, as their pharmacological activity is not due to a few specific secondary metabolites but rather a larger group of bioactive compounds. A holistic and integrative approach using rapid and nondestructive analytical strategies for the screening of herbal medicines is required for robust characterization. In this study, a rapid and effective quality assessment system for geographical traceability, species, and variety-specific authenticity of the widely used natural medicines turmeric, Ocimum, and Withania somnifera was investigated using Fourier transform near-infrared (FT-NIR) spectroscopy-based metabolic fingerprinting. Four different geographical origins of turmeric, five different Ocimum species, and three different varieties of roots and leaves of Withania somnifera were studied with the aid of machine learning approaches. Extremely good discrimination (R2 > 0.98, Q2 > 0.97, and accuracy = 1.0) with sensitivity and specificity of 100% was achieved using this metabolic fingerprinting strategy. Our study demonstrated that FT-NIR-based rapid metabolic fingerprinting can be used as a robust analytical method to authenticate several important medicinal herbs.

Rapid Determination of the Total Petroleum Hydrocarbon Content of Soils by Handheld Fourier Transform Near-Infrared Spectroscopy.

For successful soil remediation and hydrocarbon exploration operations, determining the total petroleum hydrocarbon (TPH) content of soils is an indispensable process step. This paper reports on the performance of a handheld Fourier transform near-infrared (FT-NIR) spectrometer for rapid and quantitative determination of TPH content of soils from two different sites by diffuse reflection measurements. For rapid decisions for exploration work or environmental site assessment projects, a quick─preferably on-site─determination of TPH content is valuable. Diffuse reflection NIR spectra were recorded from soil samples of two different sites with TPH reference values ranging from 350 to 30,000 ppm, as determined by capillary gas chromatography and flame ionization detection with hydrocarbon fingerprinting C1-C44. However, this paper not only addresses the development of site-specific partial-least squares (PLS) calibrations but also demonstrates the locally-weighted PLS (LW-PLS) technique, which can be used to develop global, site-independent PLS calibrations without significant penalty in calibration performance. As a first step, the diffuse reflection spectra were used to develop conservative, site-specific PLS calibration models with root-mean-square calibration/cross-validation errors (RMSEC/RMSECV) of 1043/1106 and 741/785 ppm TPH, respectively, and the average absolute prediction errors for samples not contained in the calibration set were 451 and 293 ppm for the two sites, respectively. In a further step, significant degradation of the RMSE values of a conservative PLS model based on the NIR spectra of both sites was then compared to the application of the LW-PLS method, with only a slight loss of the prediction accuracy relative to the site-independent models. This study confirms the ability of next-generation portable FT-NIR spectrometers to predict low TPH levels in various soil types through both─soil-specific and site-independent─calibrations, giving these spectrometers the potential to become rapid screening tools in the field.

Analysis of Near-Infrared Spectral Properties and Quantitative Detection of Rose Oxide in Wine

This study aims to investigate the near-infrared spectral properties of Rose Oxide (4-Methyl-2-(2-methyl-1-propenyl) tetrahydropyran) in wine, establish a quantitative detection, and build relationships between the chemical groups of Rose Oxide and near-infrared characteristic bands, so as to provide ideas and references for the near-infrared detection of a low-content aroma substance in wine. In total, 133 samples with different wine matrices were analyzed using Fourier transform–near-infrared (FT-NIR) spectroscopy. Min–max normalization (MMN), principal component analysis (PCA), and synergy interval partial least squares regression (Si-PLSR) were used for pre-processing, outlier rejection, analysis of spectral properties, and modeling. Finally, the quantitative detection model was established using the PLSR method and the wine sample containing Rose Oxide was verified externally. Eight subintervals (4000–4400 cm−1, 4400–4800 cm−1, 5600–6000 cm−1, 6000–6400 cm−1, 6400–6800 cm−1, 6800–7200 cm−1, 7200–7600 cm−1, 8400–8800 cm−1) were determined as the characteristic band intervals of Rose Oxide in the NIR region. Among them, 5600–6000 cm−1 was assigned to the first overtone C–H stretching in tetrahydropyran ring and methyl as well as the combination C–H stretching of the CH3 function groups, 6000–6400 cm−1 was assigned to the first overtone C–H stretching of the C–H=group and the combination C=C stretching in isobutyl, and 8400–8800 cm−1 was assigned to the second overtone C–H stretching and C–O stretching in tetrahydropyran ring as well as the C–H stretching vibration in methyl. In addition, 4000–4800 cm−1, 6400–6800 cm−1, and 7200–7600 cm−1 were assigned to the C–H stretching vibration, while 6400–7600 cm−1 was assigned to the C–O stretching vibration. The training result showed that the calibration model (rcv2 of 0.96 and RMSECV of 2.33) and external validation model (rcv2 of 0.84 and RMSECV of 2.72) of Rose Oxide in wine were acceptable, indicating a good predictive ability. The spectral assignment of Rose Oxide provides a new way for the NIR study of other terpenes in wine, and the use of the established Si-PLSR model for the rapid determination of Rose Oxide content in wine is feasible.

Quality Monitoring of Biodiesel and Diesel/Biodiesel Blends: A Comparison between Benchtop FT-NIR versus a Portable Miniaturized NIR Spectroscopic Analysis

A methodology such as near-infrared (NIR) spectroscopy, which enables in situ and in real-time analysis, is crucial to perform quality control of biodiesel, since it is blended into diesel fuel and the presence of contaminants can hinder its performance. This work aimed to compare the performance of a benchtop Fourier Transform (FT) NIR spectrometer with a prototype of a portable, miniaturized near-infrared spectrometer (miniNIR) to detect and quantify contaminants in biodiesel and biodiesel in diesel. In general, good models based on principal component analysis-linear discriminant analysis (PCA-LDA) of FT-NIR spectra were obtained, predicting with high accuracies biodiesel contaminants and biodiesel in diesel (between 75% to 95%), as well as good partial least square (PLS) regression models to predict contaminants concentration in biodiesel and biodiesel concentration in diesel/biodiesel blends, with high coefficients of determination (between 0.83 and 0.99) and low prediction errors. The miniNIR prototype’s PCA-LDA models enabled the prediction of target contaminants with good accuracies (between 66% and 86%), and a PLS model enabled the prediction of biodiesel concentration in diesel with a reasonable coefficient of determination (0.68), pointing to the device’s potential for preliminary analysis of biodiesel which, associated with its potential low cost and portability, could increase biodiesel quality control.

Monitoring Chemical Changes of Coffee Beans During Roasting Using Real-time NIR Spectroscopy and Chemometrics

Variations occurring in coffee beans during roasting are ascribable to several chemical-physical phenomena: to quickly track the whole process and to ensure its reproducibility, a process analytical technology (PAT) approach is needed.In this study, a method combining in-line Fourier transform near-infrared (FT-NIR) spectroscopy and chemometric modelling was investigated to get real-time and practical knowledge about the roasting effects on coffee’s chemical-physical composition. In-line spectra were acquired by inserting a NIR probe into a laboratory coffee roaster, running twenty-four roasting experiments, planned spanning different coffee species (Arabica and Robusta), four roasting temperature settings (TS1–TS4) and times (650–1580 s).Multivariate curve resolution-alternate least squares (MCR-ALS) was used to model the chemical-physical changes occurring during the roasting process, and information about maximum rate, acceleration and deceleration of the process was obtained, also highlighting potential effects due to the different roasting temperatures and coffee varieties.The proposed approach provides the groundwork for direct real-time implementation of rapid, non-invasive automated monitoring of the roasting process at industrial scale.

Crop Seed Phenomics: Focus on Non-Destructive Functional Trait Phenotyping Methods and Applications

Seeds play a critical role in ensuring food security for the earth's 8 billion people. There is great biodiversity in plant seed content traits worldwide. Consequently, the development of robust, rapid, and high-throughput methods is required for seed quality evaluation and acceleration of crop improvement. There has been considerable progress in the past 20 years in various non-destructive methods to uncover and understand plant seed phenomics. This review highlights recent advances in non-destructive seed phenomics techniques, including Fourier Transform near infrared (FT-NIR), Dispersive-Diode Array (DA-NIR), Single-Kernel (SKNIR), Micro-Electromechanical Systems (MEMS-NIR) spectroscopy, Hyperspectral Imaging (HSI), and Micro-Computed Tomography Imaging (micro-CT). The potential applications of NIR spectroscopy are expected to continue to rise as more seed researchers, breeders, and growers successfully adopt it as a powerful non-destructive method for seed quality phenomics. It will also discuss the advantages and limitations that need to be solved for each technique and how each method could help breeders and industry with trait identification, measurement, classification, and screening or sorting of seed nutritive traits. Finally, this review will focus on the future outlook for promoting and accelerating crop improvement and sustainability.

Rapid detection of pork gelatin in ice cream samples by using non-destructive FT-NIR spectroscopy and Partial least squares-discriminant analysis

This study aimed at developing a fast and low-cost detection method to discriminate between ice cream samples containing pork or non-pork gelatin by using Fourier Transform Near Infrared (FT-NIR) spectroscopy and Partial Least Squares Discriminant Analysis (PLS-DA). Forty two samples of ice cream were used, among which twenty three samples were adulterated with different levels i.e. 1%, 5%, 10%, and 20 % of pork gelatin (Non-Halal). Whereas, the remaining nineteen samples containing only cow gelatin (Halal) were used as a control. All the ice cream samples were measured with the FT-NIR spectrophotometer in the reflection mode. Spectra were collected in the wavenumber range from 10000 to 4000 cm−1 (1000 to 2500 nm). The results show that the PLS-DA model with Unit Vector Normalization (UVN) spectral transformations for 1% pork gelatin adulteration is the optimal one which was based on a compromise between the lowest value of root mean square error of cross validation (RMSECV) for the calibration set. The lowest value of root mean square error of prediction (RMSEP) for the test set, the least number of factors and the percentage of correctly classified samples, the Halal and Non-Halal, for both calibration and test sets. This newly developed method is fast, involves simple sample preparation and is low cost.

Sustaining low-impact practices in horticulture through non-destructive approach to provide more information on fresh produce history and quality: the SUS&LOW project

The general aim of the project SUS&LOW is to increase the sustainability of fresh produce by testing and implementing low-input agricultural practices (LIP) with positive impact on product quality with the support of non-destructive (ND) tools for real-time quality assessment and for product discrimination. Additionally, new marketing strategies are generated to better support the added value of the products and to satisfy the final consumers’ preferences. The SUS&LOW project consists of three work packages (WP) and the adopted methodology used two model crops: rocket salad and tomato. The WP1, focused on the reduction of agricultural inputs, showed that sensor-based fertigation management might improve sustainability of soilless cultivation. Results coming from WP2, aimed to the evaluation of ND techniques, outlined the high potentiality of hyperspectral imaging (HSI) and Fourier transformed-near infrared (FT-NIR) techniques for the authentication of sustainable growing methods. Moreover, project activities’ proved computer vision system (CVS) as an effective tool for evaluating the product quality also through the bag. The WP3, dealing with marketing strategies, indicated a positive approach of consumers compared to LIP products certified through a visual storytelling platform.

In vitro propagation of Codonopsis pilosula (Franch.) Nannf. using apical shoot segments and phytochemical assessments of the maternal and regenerated plants

BackgroundCodonopsis pilosula (Franch.) Nannf. is a medicinal plant traditionally used in China, Korea, and Japan to treat many diseases including poor gastrointestinal function, low immunity, gastric ulcers, and chronic gastritis. The increasing therapeutic and preventive use of C. pilosula has subsequently led to depletion of the natural populations of this species thus necessitating propagation of this important medicinal plant. Here, we developed an efficient and effective in vitro propagation protocol for C. pilosula using apical shoot segments. We tested various plant tissue culture media for the growth of C. pilosula and evaluated the effects of plant growth regulators on the shoot proliferation and rooting of regenerated C. pilosula plants. Furthermore, the tissues (roots and shoots) of maternal and in vitro-regenerated C. pilosula plants were subjected to Fourier-transform near-infrared (FT-NIR) spectrometry, Gas chromatography-mass spectrometry (GC–MS), and their total flavonoids, phenolics, and antioxidant capacity were determined and compared.ResultsFull-strength Murashige and Skoog (MS) medium augmented with vitamins and benzylaminopurine (1.5 mg·L−1) regenerated the highest shoot number (12 ± 0.46) per explant. MS medium augmented with indole-3-acetic acid (1.0 mg·L−1) produced the highest root number (9 ± 0.89) and maximum root length (20.88 ± 1.48 mm) from regenerated C. pilosula shoots. The survival rate of in vitro-regenerated C. pilosula plants was 94.00% after acclimatization. The maternal and in vitro-regenerated C. pilosula plant tissues showed similar FT-NIR spectra, total phenolics, total flavonoids, phytochemical composition, and antioxidant activity. Randomly amplified polymorphic DNA (RAPD) test confirmed the genetic fidelity of regenerated C. pilosula plants.ConclusionsThe proposed in vitro propagation protocol may be useful for the rapid mass multiplication and production of high quality C. pilosula as well as for germplasm preservation to ensure sustainable supply amidst the ever-increasing demand.

Support vector machine-based rapid detection and quantification of butter yellow adulteration in mustard oil using NIR spectra

Butter yellow (BY; 3′-methyl-4-dimethyl-aminoazobenzene) is a carcinogenic adulterant of edible mustard oil. In this study, Fourier-transform near-infrared (FT-NIR) spectral data was combined with multivariate data analysis to both detect and quantify BY adulteration in mustard oil. Fifteen pure mustard oil and one hundred fifty mustard oil samples with BY (0.1–1% w/v) as the adulterant were evaluated. It was observed that sonication- based processing of adulterated samples provides sensitive fingerprints during FT-NIR analysis when compared to heat- based processing. Principal component analysis (PCA) of spectral regions 6000–6064 cm−1 showed well-defined discrimination of pure and adulterated mustard oil with 100% variability. For quantification of BY both NIPALS (non-linear iterative partial least squares) based partial least square (PLS) and LS-SVM (least squares support vector machine) were carried for full-spectrum as well as selected fingerprints using RCGA (real coded genetic algorithm), a variable selection method. Overall, RCGA-LS-SVM model showed best calibration and prediction model with high precision and accuracy based on low root mean square error of cross validation (RMSECV = 0.0073) and prediction (RMSEP = 0.0060). RCGA has indeed lowered the number of variables to mere 30 variables to predict BY in the range of (0.1–1% w/v) with a correlation coefficient of calibration (RC2 = 0.9997) and prediction (RP2 = 0.9996). The key fingerprints detect CH3 and CH functional groups (1st overtone) of BY. This study demonstrated that FT-NIR spectroscopy, combined with selected 30 variables using RCGA-PLS procedure could be a robust technique for the rapid quantification of butter yellow in mustard oil samples. The study would certainly help in quality control and quality assurance of mustard oil and could be emulated for other edible oils.

FT-NIR online detection performance improvement and evaluation for 2,6-dimethylphenol purity

In this paper, Fourier transform near-infrared (FT-NIR) spectroscopy was used to online detect the 2,6-dimethylphenol(2,6-DMP) purity of different rectifying columns in the distillation separation process. Considering the similarity of spectral data between different columns, transfer learning could be introduced to improve the online detection performance of 2,6-DMP purity by reusing the spectral data from other columns. Furthermore, in order to analyze the effect of the quantity and quality of the FT-NIR spectra on the detection accuracy, the influence function was used to construct the quantitative relationship between the detection accuracy and the spectral information to be transferred. The effectiveness of the approach was analyzed on the FT-NIR spectral datasets from the distillation purification process in the 2,6-DMP monomer separation section. By transferring more favorable spectral data to avoid negative transfer, the detection accuracy will be obviously increased.

Predicting proximate composition of mutton by fourier transform-near infrared spectroscopy

A study was conducted to predict the proximate composition viz., moisture, crude protein, crude fat and total ash contents of mutton by Fourier transform-near infrared (FT-NIR) spectroscopy.Atotal of 200 longissimus dorsi muscle samples of mutton were collected from the retail meat outlets in and around Chennai in of September, 2020. The correlation coefficient ((R2)between true (conventional) and prediction (FT-NIR) values for moisture, crude protein, crude fat and total ash in mutton were 0.98, 0.98, 0.89, and 0.84, respectively. The root mean square errors of cross-validation (RMSECV) were 0.106, 0.095, 0.188 and 0.034, respectively. Ratios of prediction to deviation (RPD) were 7.80, 8.08, 3.15 and 2.53, respectively. Nonsignificant (P>0.05) difference was observed between the true and predicted values for all the proximate composition. It was concluded that FT-NIR spectroscopy canbeusedas a promisingtoolforassessing theproximate composition of mutton.

Releasing fast and slow: Non-destructive prediction of density and drug release from SLS 3D printed tablets using NIR spectroscopy

Selective laser sintering (SLS) 3D printing is a revolutionary 3D printing technology that has been found capable of creating drug products with varied release profiles by changing the laser scanning speed. Here, SLS 3D printed formulations (printlets) loaded with a narrow therapeutic index drug (theophylline) were produced using SLS 3D printing at varying laser scanning speeds (100–180 mm/s). The use of reflectance Fourier Transform – Near Infrared (FT-NIR) spectroscopy was evaluated as a non-destructive approach to predicting 3D printed tablet density and drug release at 2 h and 4 h. The printed drug products formulated with a higher laser speed exhibited an accelerated drug release and reduced density compared with the slower laser scanning speeds. Univariate calibration models were developed based on a baseline shift in the spectra in the third overtone region upon changing physical properties. For density prediction, the developed univariate model had high linearity (R2 value = 0.9335) and accuracy (error < 0.029 mg/mm3). For drug release prediction at 2 h and 4 h, the developed univariate models demonstrated a linear correlation (R2 values of 0.9383 and 0.9167, respectively) and accuracy (error < 4.4%). The predicted vs. actual dissolution profiles were found to be statistically similar (f2 > 50) for all of the test printlets. Overall, this article demonstrates the feasibility of SLS 3D printing to produce drug products containing a narrow therapeutic index drug across a range of drug release profiles, as well as the potential for FT-NIR spectroscopy to predict the physical characteristics of SLS 3D printed drug products (drug release and density) as a non-destructive quality control method at the point-of-care.

Rapid quality assessment of Succus Bambusae oral liquid based on near infrared spectroscopy and chemometrics

In this study, a rapid quality assessment method of SBOL was established by fourier-transform near infrared (FT-NIR) spectroscopy combined with chemometric analysis. Combined with Hotelling T 2 and DModX statistics, warning limits and control limits were set for SBOL samples quality of different manufacturers. The contents of volatile components (4-hydroxybenzaldehyde, vanillin, syringaldehyde, acetylsyringone and methyl syringate) in 100 samples of SBOL were determined by gas chromatography-Mass spectrometry (GC-MS). Partial least-squares-discriminant analysis (PLS-DA), data-driven soft independent modeling of class analogy (DD-SIMCA) and random forest (RF) algorithms were used to establish the qualitative models of SBOLs based on NIR spectroscopy, which in terms of error rate and accuracy were satisfactory. Partial least squares regression (PLSR) algorithm was used to establish a quantitative calibration model. In this case, NIR showed a good performance with the effective discrimination of SBOL from different manufacturers, but the rapid quantitative model of quality markers (Q-markers) with moderate performance. • Near-infrared spectroscopy was applied for the quality control of Succus Bambusae oral liquid (SBOL). • SBOL from different manufacturers were accurately distinguished using Chemometrics. • Partial least squares models were used for the rapid determination of active compounds in SBOL with moderate performance.

The beneficial effect of leaf removal during fruit set on physiological, biochemical, and qualitative indices and volatile organic compound profile of the Cypriot reference cultivar 'Xynisteri'.

'Xynisteri' is the reference Cypriot white cultivar that, despite its significant societal and economic impact, is poorly characterized regarding its qualitative properties, while scarce information exists regarding its aroma profile. In the current study, the effect of leaf removal during fruit set (BBCH 71) on 6-year cordon-trained, spur-pruned grapevines was assessed and an array of physiological, biochemical, and qualitative indices were monitored during successive developmental stages (BBCH 75, BBCH 85, BBCH 87, and BBCH 89). Grapes were additionally monitored for the volatile organic compounds (VOCs) profile during the advanced on-vine developmental stages (BBCH 85-BBCH 89) with the employment of gas chromatography-mass spectrometry (GC-MS), Fourier-transform near infrared (FT-NIR) spectra and electronic nose (E-nose) techniques. Grape berries from the vines subjected to leaf removal were characterized by higher solid soluble sugars (SSC), titratable acidity (TA), tartaric acid, and ammonium nitrogen contents, while this was not the case for assimilable amino nitrogen (primary amino nitrogen). A total of 75 compounds were identified and quantified, including aliphatic alcohols, benzenic compounds, phenols, vanillins, monoterpenes, and C13 -norisoprenoids. Leaf removal led to enhanced amounts of glycosylated aroma compounds, mainly monoterpenes, and C13 -norisoprenoids. Chemometric analysis, used through FT-NIR and E-nose, showed that the aromatic patterns detected were well associated to the grape ripening trend and differences between leaf removal-treated and control grapes were detectable during fully ripe stage. Leaf removal at fruit set resulted in an overall induction of secondary metabolism, with special reference to glycosylated aroma compounds, namely monoterpenes and C13 -norisoprenoids. © 2022 The Authors. Journal of The Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

ResNet and MaxEnt modeling for quality assessment of Wolfiporia cocos based on FT-NIR fingerprints.

As a fungus with both medicinal and edible value, Wolfiporia cocos (F. A. Wolf) Ryvarden & Gilb. has drawn more public attention. Chemical components' content fluctuates in wild and cultivated W. cocos, whereas the accumulation ability of chemical components in different parts is different. In order to perform a quality assessment of W. cocos, we proposed a comprehensive method which was mainly realized by Fourier transform near-infrared (FT-NIR) spectroscopy and ultra-fast liquid chromatography (UFLC). A qualitative analysis means was built a residual convolutional neural network (ResNet) to recognize synchronous two-dimensional correlation spectroscopy (2DCOS) images. It can rapidly identify samples from wild and cultivated W. cocos in different parts. As a quantitative analysis method, UFLC was used to determine the contents of three triterpene acids in 547 samples. The results showed that a simultaneous qualitative and quantitative strategy could accurately evaluate the quality of W. cocos. The accuracy of ResNet models combined synchronous FT-NIR 2DCOS in identifying wild and cultivated W. cocos in different parts was as high as 100%. The contents of three triterpene acids in Poriae Cutis were higher than that in Poria, and the one with wild Poriae Cutis was the highest. In addition, the suitable habitat plays a crucial role in the quality of W. cocos. The maximum entropy (MaxEnt) model is a common method to predict the suitable habitat area for W. cocos under the current climate. Through the results, we found that suitable habitats were mostly situated in Yunnan Province of China, which accounted for approximately 49% of the total suitable habitat area of China. The research results not only pave the way for the rational planting in Yunnan Province of China and resource utilization of W. cocos, but also provide a basis for quality assessment of medicinal fungi.

Prediction of mango firmness by near infrared spectroscopy tandem with machine learning

The firmness of the mango fruit is one of the internal physical properties that can show its quality. Unfortunately, non-destructive methods to measure this are not yet available. In the current study, we develop a calibration model using near infrared spectroscopy to predict the physical properties (firmness) of the mango cultivar Arumanis (Mangifera indica cv. Arumanis) via machine learning. Spectral data were acquired using the fourier transform near-infrared (FTNIR) benchtop with a wavelength range of 1000 to 2500 nm. Multivariate spectra analysis based on machine learning, including principal component regression (PCR), partial least squares regression (PLSR), and support vector machine regression (SVMR), was utilized and compared to estimate the firmness of fresh mangos. The results obtained show that the prediction of machine learning by PLSR is better than that of SVMR and PCR for the prediction of mango firmness. The coefficient correlation of calibration (rc) and validation (rcv), the root means square error of calibration (RMSE-C) and validation (RMSE-CV), and the ratio of prediction to deviation (RPD) were 0.941, 0.382 kgf, 0.920, 0.472 kgf, and 2.556, respectively. The general results satisfactorily indicate that near infrared spectroscopy technology integrated with an appropriate machine learning algorithm has optimistic results in determining the firmness of mango non-destructively.

Prediction of mango firmness by near infrared spectroscopy tandem with machine learning

The firmness of the mango fruit is one of the internal physical properties that can show its quality. Unfortunately, non-destructive methods to measure this are not yet available. In the current study, we develop a calibration model using near infrared spectroscopy to predict the physical properties (firmness) of the mango cultivar Arumanis (Mangifera indica cv. Arumanis) via machine learning. Spectral data were acquired using the fourier transform near-infrared (FTNIR) benchtop with a wavelength range of 1000 to 2500 nm. Multivariate spectra analysis based on machine learning, including principal component regression (PCR), partial least squares regression (PLSR), and support vector machine regression (SVMR), was utilized and compared to estimate the firmness of fresh mangos. The results obtained show that the prediction of machine learning by PLSR is better than that of SVMR and PCR for the prediction of mango firmness. The coefficient correlation of calibration (rc) and validation (rcv), the root means square error of calibration (RMSE-C) and validation (RMSE-CV), and the ratio of prediction to deviation (RPD) were 0.941, 0.382 kgf, 0.920, 0.472 kgf, and 2.556, respectively. The general results satisfactorily indicate that near infrared spectroscopy technology integrated with an appropriate machine learning algorithm has optimistic results in determining the firmness of mango non-destructively.