Fruit quality evaluation using spectroscopy technology: a review

Determination of sugar content in Lingwu jujube by NIR-hyperspectral imaging

Near infrared hyperspectral imaging (NIR-HSI) with a spectral range of 900 to 1700 nm was for the first time used to predict the changes of sugar content in Lingwu jujube during storage. Monte Carlo method was adopted to detect outliers, and multiple scattering correction (MSC), standard normal variate transformation (SNV), and Baseline were used to optimize modeling. Competitive adaptive reweighted sampling (CARS), interval variable iterative space shrinkage approach (iVISSA), and interval random frog (IRF) were used to select optimal wavelengths. In addition, partial least square regression (PLSR) and support vector machine (SVM) modeling based on optimal wavelengths were compared. The results showed that 30, 30, and 24 wavelengths were selected by CARS; 106, 87, and 112 feature wavelengths were selected by iVISSA; and 96, 71, and 83 optimal wavelengths were selected by IRF for sucrose, fructose, and glucose, respectively. The CARS-PLSR models provided the best results for fructose and glucose, and iVISSA-SVM model was better for sucrose. The results indicated that NIR-HSI model may be used as a rapid and nondestructive method for the determination of sugar content in jujubes.

Nondestructive evaluation of soluble solids content in tomato with different stage by using Vis/NIR technology and multivariate algorithms

In this study Vis/NIR spectroscopy was applied to evaluate soluble solids content (SSC) of tomato. A total of 168 tomato samples with five different maturity stages, were measured by two developed systems with the wavelength ranges of 500-930 nm and 900-1400 nm, respectively. The raw spectral data were pre-processed by first derivative and standard normal variate (SNV), respectively, and then the effective wavelengths were selected using competitive adaptive reweighted sampling (CARS) and random frog (RF). Partial least squares (PLS) and least square-support vector machines (LS-SVM) were employed to build the prediction models to evaluate SSC in tomatoes. The prediction results revealed that the best performance was obtained using the PLS model with the optimal wavelengths selected by CARS in the range of 900-1400 nm (Rp = 0.820 and RMSEP = 0.207 °Brix). Meanwhile, this best model yielded desirable results with Rp and RMSEP of 0.830 and 0.316 °Brix, respectively, in 60 samples of the independent set. The method proposed from this study can provide an effective and quick way to predict SSC in tomato.

Rapid detection of seven indexes in sheep serum based on Raman spectroscopy combined with DOSC-SPA-PLSR-DS model

Hepatic fascioliasis, ketosis of pregnancy, toxemia of pregnancy and other common sheep diseases will directly affect the concentration (/enzymatic activity) of seven indicators, such as cortisol and high-density lipoprotein cholesterol (HDL-C) in sheep serum. Whether the concentrations (/enzymatic activity) of these indicators can be detected quickly will directly affect the prevention of sheep diseases and the targeted adjustment of breeding methods, thereby affecting the economic benefits of sheep breeding. In this research, we established partial least square regression (PLSR), support vector regression based on genetic algorithm optimization (GA-SVR) and extreme learning machine (ELM) models. Due to the large differences in the content of different substances, it is difficult to directly use the RMSE to evaluate the quantitative effect of the model. This study is the first to propose conducting deviation standardization (DS) for the determination results of various substances. To further improve the performance of the model, we use the successive projections algorithm (SPA) to optimize feature extraction and combine it with the better-performing PLSR model for training. The results show that the optimized DOSC-SPA-PLSR-DS quantitative model has better determination results for 101 sheep serum samples. The average RMSE_p* of the concentration of the six substances decreased from 0.0408 to 0.0387, the R_p² increased from 0.9758 to 0.9846, and the running time was reduced from 0.1659 to 0.0008 s. And the determination performance of lipase (LPS) enzymatic activity has also been improved. The results of this research show that sheep serum Raman spectroscopy combined with DOSC-SPA-PLSR-DS optimization can efficiently monitor the concentration (/enzyme activity) of seven indicators in real time and provide a new strategy for future intelligent supervision of animal husbandry.

Remote Sensing and Machine Learning in Crop Phenotyping and Management, with an Emphasis on Applications in Strawberry Farming

Measurement of plant characteristics is still the primary bottleneck in both plant breeding and crop management. Rapid and accurate acquisition of information about large plant populations is critical for monitoring plant health and dissecting the underlying genetic traits. In recent years, high-throughput phenotyping technology has benefitted immensely from both remote sensing and machine learning. Simultaneous use of multiple sensors (e.g., high-resolution RGB, multispectral, hyperspectral, chlorophyll fluorescence, and light detection and ranging (LiDAR)) allows a range of spatial and spectral resolutions depending on the trait in question. Meanwhile, computer vision and machine learning methodology have emerged as powerful tools for extracting useful biological information from image data. Together, these tools allow the evaluation of various morphological, structural, biophysical, and biochemical traits. In this review, we focus on the recent development of phenomics approaches in strawberry farming, particularly those utilizing remote sensing and machine learning, with an eye toward future prospects for strawberries in precision agriculture. The research discussed is broadly categorized according to strawberry traits related to (1) fruit/flower detection, fruit maturity, fruit quality, internal fruit attributes, fruit shape, and yield prediction; (2) leaf and canopy attributes; (3) water stress; and (4) pest and disease detection. Finally, we present a synthesis of the potential research opportunities and directions that could further promote the use of remote sensing and machine learning in strawberry farming.

ALTERNATIVE OPTICAL METHODS FOR QUALITATIVE DETECTION OF VITAMIN B6 AND B12 OF BANANA

Bananas are known to contain fiber and vitamins essential for human body. Thus, the ability to detect these of vitamin in bananas is crucial. Information in the vitamin content of can affect procedures for harverst and post-harvest process. Methods to determine the nutrition content of foods are usually carried out using High Performance Liquid Chromatography (HPLC). However, this method requires complex sample preparation and chemical reaction processes. Due to this weakness, alternative techniques are needed to detect vitamin in simple ways. In this study, a simple, easy and fast methods to determine the vitamin content of banana was developed. Using reflectance and photoluminence spectroscopy, the vitamin of bananas from five different species were able to be identified. From the reflectance spectra results, two peaks were observed, the first peak at a wavelength of 325 nm is the absorption peak of vitamin B6 and the second peak at 450 nm is the absorption peak of vitamin B12. From the photoluminence spectra using excitation wavelength at 325 nm, an emission peak was found at wavelength 450 nm which is the peak emission from vitamin B6. These results proved that by using the methods proposed, the detection of vitamins in bananas can be done in an easy and simple ways.

A Portable Spectrometric System for Quantitative Prediction of the Soluble Solids Content of Apples with a Pre-calibrated Multispectral Sensor Chipset

A portable spectrometric system for nondestructive assessment of the soluble solids content (SSC) of fruits for practical applications has been proposed and its performance has been examined by an experiment on quantitative prediction of the SSC of apples. Although the spectroscopic technique is a powerful tool for predicting the internal qualities of fruits, its practical applications are limited due to its high cost and complexity. In the proposed system, the spectra of apples were collected by a simple optical setup with a cheap pre-calibrated multispectral chipset. An optimal multiple linear regression model with five wavebands at 900, 760, 730, 680, and 535 nm revealed the best performance with the coefficient of determination of prediction and the root mean square error of prediction of 0.861 and 0.403 °Brix, respectively, which was comparable to that of the previous studies using dispersive spectrometers. Compared with previously reported systems using discrete filters or light emitting diodes, the proposed system was superior in terms of manufacturability and reproducibility. The experimental results confirmed that the proposed system had a considerable potential for practical, cost-effective applications of the SSC prediction, not only for apples but also for other fruits.

Application of hyperspectral imaging for spatial prediction of soluble solid content in sweet potato

Visible and near infrared (Vis-NIR) hyperspectral imaging was used for fast detection and visualization of soluble solid content (SSC) in ‘Beijing 553’ and ‘Red Banana’ sweet potatoes. Hyperspectral images were acquired from 420 ROIs of each cultivar of sliced sweet potatoes. There were 8 and 10 outliers removed from ‘Beijing 553’ and ‘Red Banana’ sweet potatoes by Monte Carlo partial least squares (MCPLS). The optimal spectral pretreatments were determined to enhance the performance of the prediction model. Successive projections algorithm (SPA) and competitive adaptive reweighted sampling (CARS) were employed to select characteristic wavelengths. SSC prediction models were developed using partial least squares regression (PLSR), support vector regression (SVR) and multivariate linear regression (MLR). The more effective prediction performances emerged from the SPA–SVR model with R_p² of 0.8581, RMSEP of 0.2951 and RPD_p of 2.56 for ‘Beijing 553’ sweet potato, and the CARS–MLR model with R_p² of 0.8153, RMSEP of 0.2744 and RPD_p of 2.09 for ‘Red Banana’ sweet potato. Spatial distribution maps of SSC were obtained in a pixel-wise manner using SPA–SVR and CARS–MLR models for quantifying the SSC level in a simple way. The overall results illustrated that Vis-NIR hyperspectral imaging was a powerful tool for spatial prediction of SSC in sweet potatoes.

Visible and near infrared (Vis-NIR) hyperspectral imaging was used for fast detection and visualization of soluble solid content (SSC) in ‘Beijing 553’ and ‘Red Banana’ sweet potatoes.

The Potential of High Voltage Discharges for Green Solvent Extraction of Bioactive Compounds and Aromas from Rosemary (Rosmarinus officinalis L.)-Computational Simulation and Experimental Methods

Rosemary (Rosmarinus officinalis L.) is a Mediterranean medicinal and aromatic plant widely used due to valuable bioactive compounds (BACs) and aromas. The aim of the study was to evaluate the extraction of intracellular compounds from rosemary combining experimental procedure by means of high voltage electrical discharge (HVED), with a theoretical approach using two computational simulation methods: conductor-like screening model for real solvents and Hansen solubility parameters. The optimal HVED parameters were as follows: frequency 100 Hz, pulse width 400 ns, gap between electrodes 15 mm, liquid to solid ratio 50 mL/g, voltage 15 and 20 kV for argon, and 20 and 25 kV for nitrogen gas. Green solvents were used, water and ethanol (25% and 50%). The comparison was done with modified conventional extraction (CE) extracted by magnetic stirring and physicochemical analyses of obtained extracts were done. Results showed that HVED extracts in average 2.13-times higher total phenol content compared to CE. Furthermore, nitrogen, longer treatment time and higher voltage enhanced higher yields in HVED extraction. HVED was confirmed to have a high potential for extraction of BACs from rosemary. The computational stimulation methods were confirmed by experimental study, ethanol had higher potential of solubility of BACs and aromas from rosemary compared to water.

The Sample, the Spectra and the Maths-The Critical Pillars in the Development of Robust and Sound Applications of Vibrational Spectroscopy

The last two decades have witnessed an increasing interest in the use of the so-called rapid analytical methods or high throughput techniques. Most of these applications reported the use of vibrational spectroscopy methods (near infrared (NIR), mid infrared (MIR), and Raman) in a wide range of samples (e.g., food ingredients and natural products). In these applications, the analytical method is integrated with a wide range of multivariate data analysis (MVA) techniques (e.g., pattern recognition, modelling techniques, calibration, etc.) to develop the target application. The availability of modern and inexpensive instrumentation together with the access to easy to use software is determining a steady growth in the number of uses of these technologies. This paper underlines and briefly discusses the three critical pillars-the sample (e.g., sampling, variability, etc.), the spectra and the mathematics (e.g., algorithms, pre-processing, data interpretation, etc.)-that support the development and implementation of vibrational spectroscopy applications.

Accurate non-destructive prediction of peach fruit internal quality and physiological maturity with a single scan using near infrared spectroscopy

The development of precise and reliable near infrared spectroscopy (NIRS)-based non-destructive tools to assess physicochemical properties of fleshy fruit has been challenging. A novel crop load × fruit developmental stage protocol for multivariate NIRS-based prediction models calibration to non-destructively assess peach internal quality and maturity was followed. Regression statistics of the prediction models highlighted that dry matter content (DMC, R² = 0.98, RMSEP = 0.41%), soluble solids concentration (SSC, R² = 0.96, RMSEP = 0.58%) and index of absorbance difference (I_AD, R² = 0.96, RMSEP = 0.08) could be estimated accurately with a single scan during fruit growth and development. Thus, the impact of preharvest factors such as crop load and canopy position on peach quality and maturity was evaluated. Large-scale field validation showed that heavier crop loads reduced peach quality (DMC, SSC) and delayed maturity (I_AD) and upper canopy position advanced both mainly in the moderate crop loads. This calibration protocol can enhance NIRS adaptation across tree fruit supply chain.

Performance of new low-cost handheld NIR spectrometers for nondestructive analysis of umbu (Spondias tuberosa Arruda) quality

The objective of this study was to evaluate the analytical performance of two new low-cost handheld NIR spectrometers for the determination of umbu fruit (Spondias tuberosa Arruda) quality. A third handheld spectrometer, representing a proven good performance for fruit quality analysis, was used as reference instrument. Multivariate calibration models were built using Partial Least Squares regression to determine dry matter (DM), soluble solids (SS), flesh firmness (FF) and skin color (SC). No significant statistical difference was found among the analytical performances of all three spectrometers. The average of the relative root mean square error of prediction (RMSEPr) obtained with the three spectrometers were 5.2 ± 0.9% for DM, 8.4 ± 1.5% for SS, 27.6 ± 2.0% for FF and 8.0 ± 0.6% for SC. According to these results, the new low-cost handheld NIR spectrometers can be used to monitor umbu fruit quality during ripening with suitable accuracy.

Determination of pesticide residual levels in strawberry (Fragaria) by near-infrared spectroscopy

BACKGROUND

In this study, an infrared-based prediction method was developed for easy, fast and non-destructive detection of pesticide residue levels measured by reference analysis in strawberry (Fragaria × ananassa Duch, cv. Albion) samples using near-infrared spectroscopy and demonstrating its potential alternative or complementary use instead of traditional pesticide determination methods. Strawberries of Albion variety, which were supplied directly from greenhouses, were used as the study material. A total of 60 batch sample groups, each consisting of eight strawberries, was formed, and each group was treated with a commercial pesticide at different concentrations (26.7% boscalid + 6.7% pyraclostrobin) and varying residual levels were obtained in strawberry batches. The strawberry samples with pesticide residuals were used both to collect near-infrared spectra and to determine reference pesticide levels, applying QuEChERS (quick, easy, cheap, rugged, safe) extraction, followed by liquid chromatographic-mass spectrometric analysis.

RESULTS AND CONCLUSION

Partial least squares regression (PLSR) models were developed for boscalid and pyraclostrobin active substances. During model development, the samples were randomly divided into two groups as calibration (n = 48) and validation (n = 12) sets. A calibration model was developed for each active substance, and then the models were validated using cross-validation and external sets. Performance evaluation of the PLSR models was evaluated based on the residual predictive deviation (RPD) of each model. An RPD of 2.28 was obtained for boscalid, while it was 2.31 for pyraclostrobin. These results indicate that the developed models have reasonable predictive power. © 2019 Society of Chemical Industry.

Performance Evaluation of Two Commercially Available Portable Spectrometers to Non-Invasively Determine Table Grape and Peach Quality Attributes

Near-infrared (NIR) spectroscopy has been used to non-destructively and rapidly evaluate the quality of fresh agricultural produce. In this study, two commercially available portable spectrometers (F-750: Felix Instruments, WA, USA; and SCiO: Consumer Physics, Tel Aviv, Israel) were evaluated in the wavelength range between 740 and 1070 nm to non-invasively predict quality attributes, including the dry matter (DM), and total soluble solids (TSS) content of three fresh table grape cultivars (‘Autumn Royal’, ‘Timpson’, and ‘Sweet Scarlet’) and one peach cultivar (‘Cassie’). Prediction models were developed using partial least-square regression (PLSR) to correlate the NIR absorbance spectra with the invasive quality measurements. In regard to grapes, the best DM prediction models yielded an R2 of 0.83 and 0.81, a ratio of standard error of performance to standard deviation (RPD) of 2.35 and 2.29, and a root mean square error of prediction (RMSEP) of 1.40 and 1.44; and the best TSS prediction models generated an R2 of 0.97 and 0.95, an RPD of 5.95 and 4.48, and an RMSEP of 0.53 and 0.70 for the F-750 and SCiO spectrometers, respectively. Overall, PLSR prediction models using both spectrometers were promising to predict table grape quality attributes. Regarding peach, the PLSR prediction models did not perform as well as in grapes, as DM prediction models resulted in an R2 of 0.81 and 0.67, an RPD of 2.24 and 1.74, and an RMSEP of 1.28 and 1.66; and TSS resulted in an R2 of 0.62 and 0.55, an RPD of 1.55 and 1.48, and an RMSEP of 1.19 and 1.25 for the F-750 and SCiO spectrometers, respectively. Overall, the F-750 spectrometer prediction models performed better than those generated by using the SCiO spectrometer data.

Phenotypic techniques and applications in fruit trees: a review

Phenotypic information is of great significance for irrigation management, disease prevention and yield improvement. Interest in the evaluation of phenotypes has grown with the goal of enhancing the quality of fruit trees. Traditional techniques for monitoring fruit tree phenotypes are destructive and time-consuming. The development of advanced technology is the key to rapid and non-destructive detection. This review describes several techniques applied to fruit tree phenotypic research in the field, including visible and near-infrared (VIS-NIR) spectroscopy, digital photography, multispectral and hyperspectral imaging, thermal imaging, and light detection and ranging (LiDAR). The applications of these technologies are summarized in terms of architecture parameters, pigment and nutrient contents, water stress, biochemical parameters of fruits and disease detection. These techniques have been shown to play important roles in fruit tree phenotypic research.

Quantitative Analysis of Gas Phase IR Spectra Based on Extreme Learning Machine Regression Model

Advanced chemometric analysis is required for rapid and reliable determination of physical and/or chemical components in complex gas mixtures. Based on infrared (IR) spectroscopic/sensing techniques, we propose an advanced regression model based on the extreme learning machine (ELM) algorithm for quantitative chemometric analysis. The proposed model makes two contributions to the field of advanced chemometrics. First, an ELM-based autoencoder (AE) was developed for reducing the dimensionality of spectral signals and learning important features for regression. Second, the fast regression ability of ELM architecture was directly used for constructing the regression model. In this contribution, nitrogen oxide mixtures (i.e., N₂O/NO₂/NO) found in vehicle exhaust were selected as a relevant example of a real-world gas mixture. Both simulated data and experimental data acquired using Fourier transform infrared spectroscopy (FTIR) were analyzed by the proposed chemometrics model. By comparing the numerical results with those obtained using conventional principle components regression (PCR) and partial least square regression (PLSR) models, the proposed model was verified to offer superior robustness and performance in quantitative IR spectral analysis.

Broadband Time Domain Diffuse Optical Reflectance Spectroscopy: A Review of Systems, Methods, and Applications

This review presents recent developments and a wide overview of broadband time domain diffuse optical spectroscopy (TD-DOS). Various topics including physics of photon migration, advanced instrumentation, methods of analysis, applications covering multiple domains (tissue chromophore, in vivo studies, food, wood, pharmaceutical industry) are elaborated. The key role of standardization and recent studies in that direction are discussed. Towards the end, a brief outlook is presented on the current status and future trends in broadband TD-DOS.

Non-destructive determination of strawberry fruit and juice quality parameters using ultraviolet, visible, and near-infrared spectroscopy

BACKGROUND

The development of rapid methods for the determination of the soluble solids content (SSC) and total phenolic content (TPC) in fruit juices is of great interest. Soluble solids content is related to sensory attributes, whereas TPC is related to the antioxidant capacity of juices. The aim of this study was to develop and optimize the calibration models for the prediction of the SSC and TPC of strawberry juices from the spectra of fruit and juices.

RESULTS

Near infrared (NIR) spectra were measured for strawberry fruit and ultraviolet (UV), visible (VIS), and NIR spectra were measured for juices. The partial least squares regression models were validated using the test sample set and their predictive ability was evaluated on the basis of determination coefficients (R² _P ) and root mean square error of prediction (RMSEP). For SSC the models with high predictive ability were obtained using spectra of fruit (R² _P = 0.929, RMSEP = 0.46%) or juices (R² _P = 0.979, RMSEP = 0.25%) in the NIR range. The optimal models for TPC were obtained using NIR spectra of fruit (R² _P = 0.834, RMSEP = 130.8 mg GA L^-1 ) or UV-VIS-NIR spectra of juices (R² _P = 0.844, RMSEP = 126.7 mg GA L^-1 ).

CONCLUSION

The results show the potential of spectroscopy for predicting quality parameters of strawberry juices from the juice spectra itself or non-destructively from the fruit spectra. They may contribute to the development of fruit sorting systems to optimize their use in juice production, as well as fast-screening methods for quality control of juices. © 2019 Society of Chemical Industry.

P-Wave Visible-Shortwave-Near-Infrared (Vis-SW-NIR) Detection System for the Prediction of Soluble Solids Content and Firmness on Wax Apples

A nondestructive system for measuring the soluble solids content (SSC) and firmness of wax apples was developed using 670, 850, 880, 940, and 980 nm visible-shortwave-near-infrared (Vis-SW-NIR) light-emitting diode (LED) light sources and a silicon (Si) photodetector. These specified wavelengths are highly correlated with the SSC and the firmness of fruit. An LED light source was incident onto the fruit as parallel-polarized waves (P-wave) at the Brewster angle (θ_B) to minimize the interfacial reflection and maximize the C-H and O-H bonds absorption signals from the fruit. Partial least squares (PLS) regression is used to build calibration modes and analyze the prediction of the correlation (rp2) and the root mean square error for prediction (RMSEP) of the reflected optical signals with SSC and firmness. This resulted in rp2 and RMSEP values of 0.87 and 0.66 °Bx, respectively, in SSC measurements and 0.80 and 1.16 N/cm², respectively, in firmness measurements. Therefore, the result shows rp2 of SSC and firmness are 6.4% and 9% higher and the RMSEP are 14% and 20% lower, respectively, than those obtained using non-polarized LED light sources.

Optimizing genetic algorithm-partial least squares model of soluble solids content in Fukumoto navel orange based on visible-near-infrared transmittance spectroscopy using discrete wavelet transform

BACKGROUND

The thick rind of Fukumoto navel orange is a great barrier to light penetration, which makes it difficult to evaluate the internal quality of Fukumoto navel orange accurately by visible-near-infrared (Vis-NIR) transmittance spectroscopy. The information carried by the transmission spectrum is limited. Thus, the application of genetic algorithm (GA) for variable selection may not reach the expected results, and selected variables may contain redundancy. In this paper, we present the use of discrete wavelet transforms for optimizing a GA-partial least squares (PLS) model based on Vis-NIR transmission spectra of Fukumoto navel orange. Haar, Db, Sym, Coif and Bior wavelets were used to compress the spectral data selected by GA. Then a PLS model was established based on the variables compressed by each wavelet function.

RESULTS

The use of Db4, Sym4, Coif2 and Bior3.5 succeeded in further simplification of the GA-PLS model by reducing the number of variables by 40-44% without decreasing the prediction accuracy. The application of Bior3.5 not only could reduce the number of variables in the GA-PLS model by 40%, but also increase the value of correlation coefficient of prediction by 1% and decrease the value of root mean square error of prediction by 3%.

CONCLUSIONS

The results indicated that the combination of GA and discrete wavelet transforms for variable selection in the internal quality assessment of Fukumoto navel orange by Vis-NIR transmittance spectroscopy was feasible. © 2019 Society of Chemical Industry.

Quantitatively determining the total bacterial count of raw goat milk using dielectric spectra

The objective of this study was to evaluate dielectric spectra as a means of quantitatively determining total bacterial count (TBC) of raw goat milk. The dielectric spectra, including dielectric constant (ε') spectra and dielectric loss factor (ε″) spectra, and TBC of 154 raw goat milk samples were measured using network analyzer and plate count methods, respectively. Owing to the poor linear relationship between TBC in logarithm and permittivities at a single frequency, chemometrics was used to reduce noise, identify outliers, select effective variables, and divide sample sets. Several linear models, such as multiple linear regression, ridge regression, and least absolute shrinkage and selection operator, were established to determine TBC based on the effective spectra of ε', ε″, and their combination (ε'+ε″). The results indicated that the models built using the spectra of ε'+ε″ and ε' had excellent TBC prediction performance. The best model was multiple linear regression based on ε'+ε″ spectra with the residual predictive deviation of 3.26. This study shows that the dielectric spectra had great potential to quantitatively and rapidly determine TBC of raw milk.

Innovative and rapid analysis for rice authenticity using hand-held NIR spectrometry and chemometrics

Rice is the second most important food staple worldwide and the demand will continue to increase with the growth of the world population. As reports grow that frauds is prevalent in many supply chains there is the need for an effective and rapid technique for monitoring the authenticity and quality of rice. This study investigated the novel application of hand-held NIR spectrometry coupled to chemometric for the estimation of rice authenticity and quality in real time. A total of 520 rice samples from different quality grades (high quality, mid quality and low quality) and different countries (Ghana, Thailand, and Vietnam) of origin were used. Among the pre-processing methods used multiplicative scatter correction (MSC) was found to be superior. Principal component analysis (PCA) was used to extract relevant information from the spectral data set and the results showed that rice samples of different categories could be clearly clustered under the first three PCs using the MSC preprocessing method. The performance of K-nearest neighbor (KNN) revealed that for authentication of rice quality grades, the classification rate gave 91.62% and 91.81% in training set and prediction set respectively while identification rate based on different country of origin was 90.84% and 90.64% in both training set and prediction set respectively. For the differentiation of local rice from the imported, KNN and SVM all had 100% in both the training set and prediction set. These gives very strong evidence that hand-held spectrometry coupled with MSC-PCA-KNN could successfully be used to provide rapid and nondestructive classification of rice samples according to different quality grades, geographical origin and imported versus locally produced rice. This technique could enhance the work of quality control inspectors both from industry and regulatory perspectives for the rapid detection of rice integrity and fraud issues.

Pattern recognition-based optical technique for non-destructive detection of Ectomyelois ceratoniae infestation in pomegranates during hidden activity of the larvae

In this research, the feasibility of utilizing visible/near-infrared (Vis/NIR) spectroscopy as an optical non-destructive technique combined with both supervised and unsupervised pattern recognition methods was assessed for detection of Ectomyelois ceratoniae, carob moth, infestation in pomegranates during hidden activity of the larvae. To this end, some fruits were artificially contaminated to the carob moth larvae. Vis/NIR spectra of the blank samples and the contaminated pomegranates without and with external visual symptoms of larvae infestation were analyzed one and two weeks after contaminating the samples as three groups of "Healthy", "Unhealthy-A" and "Unhealthy-B", respectively. Principal component analysis (PCA) as unsupervised pattern recognition method was used to verify the possibility of clustering of the pomegranate samples into the three groups. Discriminant analysis (DA) based on PCA was also used as a powerful supervised pattern recognition method to classify the samples. The calibration models of linear, quadratic and Mahalanobis discriminant analyses were developed based on different spectral pre-processing techniques. The best PCA-DA model was obtained using Mahalanobis distance method and first derivative (D1) pre-processing. The total percentage of correctly classified samples with the best calibration model was 97.9%. The developed model could also predict unknown samples with total percentage of correctly classified samples of 90.6%. It was concluded that Vis/NIR spectroscopy combined with pattern recognition method of PCA-DA can be an appropriate and rapid technology for non-destructively screening the pomegranates for detection of carob moth infestation during hidden activity of the larvae.

Method Development of Near-Infrared Spectroscopy Approaches for Nondestructive and Rapid Estimation of Total Protein in Brown Rice Flour

Rice varietal development and improvement programs are constantly seeking means to shorten the breeding cycle in order to deliver new, consumer-acceptable rice varieties to farmers and to consumers. Advances in molecular biology technologies have enabled breeders to use high-throughput genotyping to screen breeding lines. However, current phenotyping technologies, particularly for rice cooking and eating properties, have yet to match the efficiency of genotyping methodologies. A high-throughput and cost-effective phenotyping suite is essential because without phenotype, the value of genotypic information cannot be maximized. In this book chapter, we explore the application of near-infrared spectroscopy (NIRS), a high-throughput and nondestructive approach in characterizing rice grains, primarily describing method development and validation, instrument calibration, upgrading, and maintenance. We then focus on estimating protein content (PC) in brown rice as a case study because (1) PC is an attribute that contributes to the cooking behavior and the eating properties of cooked rice; and (2) proteins contain chemical bonds that can easily be detected by NIRS.

PLS, iPLS, GA-PLS models for soluble solids content, pH and acidity determination in intact dovyalis fruit using near-infrared spectroscopy

BACKGROUND

Dovyalis species Dovyalis abyssinica Warb. and Dovyalis hebecarpa Warb. were introduced into Brazil, but the fruit quality of these species is not appropriate for fresh consumption due to their high titratable acidity (TA) and low soluble solids content (SSC). With the selection of new D. abyssinica clones with lower acidity and the hybridization of these two dovyalis species (D. abyssinica and D. hebecarpa) the fruit quality improved and the better physical-chemical characteristics make them more suitable for fresh consumption. The objective of this study was to develop partial least squares (PLS) models using near infrared spectroscopy (NIRS) for the determination of SSC, TA and pH in intact dovyalis hybrid fruit (D. abyssinica Warb. × D. hebecarpa Warb.).

RESULTS

The best SSC prediction model was developed with PLS regression (root mean square error of prediction (RMSE_P ) of 0.71 °Brix, prediction data set (R_P ² ) of 0.74 and residual predictive deviation (RPD) of 2.82). Although interval PLS was tested, genetic algorithm PLS performed better for TA (RMSE_P of 4.8 g kg^-1 , R_P ² of 0.40, and RPD of 1.67), and for pH (RMSE_P of 0.03, R_P ² of 0.90, and RPD of 6.67).

CONCLUSION

NIRS can be used as a non-destructive method to determine quality parameters in intact dovyalis hybrid fruit. © 2018 Society of Chemical Industry.

Variety Identification of Raisins Using Near-Infrared Hyperspectral Imaging

Different varieties of raisins have different nutritional properties and vary in commercial value. An identification method of raisin varieties using hyperspectral imaging was explored. Hyperspectral images of two different varieties of raisins (Wuhebai and Xiangfei) at spectral range of 874–1734 nm were acquired, and each variety contained three grades. Pixel-wise spectra were extracted and preprocessed by wavelet transform and standard normal variate, and object-wise spectra (sample average spectra) were calculated. Principal component analysis (PCA) and independent component analysis (ICA) of object-wise spectra and pixel-wise spectra were conducted to select effective wavelengths. Pixel-wise PCA scores images indicated differences between two varieties and among different grades. SVM (Support Vector Machine), k-NN (k-nearest Neighbors Algorithm), and RBFNN (Radial Basis Function Neural Network) models were built to discriminate two varieties of raisins. Results indicated that both SVM and RBFNN models based on object-wise spectra using optimal wavelengths selected by PCA could be used for raisin variety identification. The visualization maps verified the effectiveness of using hyperspectral imaging to identify raisin varieties.

Detection of Sclerotinia Stem Rot on Oilseed Rape (Brassica napus L.) Leaves Using Hyperspectral Imaging

Hyperspectral imaging was explored to detect Sclerotinia stem rot (SSR) on oilseed rape leaves with chemometric methods, and the influences of variable selection, machine learning, and calibration transfer methods on detection performances were evaluated. Three different sample sets containing healthy and infected oilseed rape leaves were acquired under different imaging acquisition parameters. Four discriminant models were built using full spectra, including partial least squares-discriminant analysis (PLS-DA), support vector machine (SVM), soft independent modeling of class analogies (SIMCA), and k-nearest neighbors (KNN). PLS-DA and SVM models were also built with the optimal wavelengths selected by principal component analysis (PCA) loadings, second derivative spectra, competitive adaptive reweighted sampling (CARS), and successive projections algorithm (SPA). The optimal wavelengths selected for each sample set by different methods were different; however, the optimal wavelengths selected by PCA loadings and second derivative spectra showed similarity between different sample sets. Direct standardization (DS) was successfully applied to reduce spectral differences among different sample sets. Overall, the results demonstrated that using hyperspectral imaging with chemometrics for plant disease detection can be efficient and will also help in the selection of optimal variable selection, machine learning, and calibration transfer methods for fast and accurate plant disease detection.

Prediction Models for Assessing Lycopene in Open-Field Cultivated Tomatoes by Means of a Portable Reflectance Sensor: Cultivar and Growing-Season Effects

Reflectance spectroscopy represents a useful tool for the nondestructive assessment of tomato lycopene, even in the field. For this reason, a compact, low-cost, light emitting diode-based sensor has been developed to measure reflectance in the 400-750 nm spectral range. It was calibrated against wet chemistry and evaluated by partial least squares (PLS) regression analyses. The lycopene prediction models were defined for two open-field cultivated red-tomato varieties: the processing oblong tomatoes of the cv. Calista (average weight: 76 g) and the fresh-consumption round tomatoes of the cv. Volna (average weight: 130 g), over a period of two consecutive years. The lycopene prediction models were dependent on both cultivar and season. The lycopene root mean square error of prediction produced by the 2014 single-cultivar calibrations validated on the 2015 samples was large (33 mg kg^-1) in the Calista tomatoes and acceptable (9.5 mg kg^-1) in the Volna tomatoes. A more general bicultivar and biyear model could still explain almost 80% of the predicted lycopene variance, with a relative error in red tomatoes of less than 20%. In 2016, the in-field applications of the multiseasonal prediction models, built with the 2014 and 2015 data, showed significant ( P < 0.001) differences in the average lycopene estimated in the crop on two sampling dates that were 20 days apart: on August 19 and September 7, 2016, the lycopene was 98.9 ± 9.3 and 92.2 ± 10.8 mg kg^-1 FW for cv. Calista and 54.6 ± 13.2 and 60.8 ± 6.8 mg kg^-1 FW for cv. Volna. The sensor was also able to monitor the temporal evolution of lycopene accumulation on the very same fruits attached to the plants. These results indicated that a simple, compact reflectance device and PLS analysis could provide adequately precise and robust (through-seasons) models for the nondestructive assessment of lycopene in whole tomatoes. This technique could guarantee tomatoes with the highest nutraceutical value from the production, during storage and distribution, and finally to consumers.

Integration of Artificial Neural Network Modeling and Hyperspectral Data Preprocessing for Discrimination of Colla Corii Asini Adulteration

The study of hyperspectral imaging in tandem with spectral preprocessing and neural network techniques was conducted to realize Colla Corii Asini (CCA, E’jiao) adulteration discrimination. CCA was adulterated with pig skin gelatin (PSG) in the range of 5–95% (w/w) at 5% increments. Three methods were used to pretreat the original spectra, which are multiplicative scatter correction (MSC), Savitzky-Golay (SG) smoothing, and the combination of MSC and SG (MSC-SG). SPA was employed to select the characteristic wavelengths (CWs) to reduce the high dimension. Colour and texture features of CWs were extracted as input of prediction model. Two kinds of artificial neural network (ANN) with three spectral preprocessing methods were applied to establish the prediction models. The prediction model of generalized regression neural network (GRNN) in tandem with the MSC-SG preprocessed method presented satisfactory performance with the correct classification rate value of 92.5%. The results illustrated that the integration of preprocessing methods, hyperspectral imaging features, and ANN modeling had a great potential and feasibility for CCA adulteration discrimination.

Non-destructive Determination of Shikimic Acid Concentration in Transgenic Maize Exhibiting Glyphosate Tolerance Using Chlorophyll Fluorescence and Hyperspectral Imaging

The development of transgenic glyphosate-tolerant crops has revolutionized weed control in crops in many regions of the world. The early, non-destructive identification of superior plant phenotypes is an important stage in plant breeding programs. Here, glyphosate-tolerant transgenic maize and its parental wild-type control were studied at 2, 4, 6, and 8 days after glyphosate treatment. Visible and near-infrared hyperspectral imaging and chlorophyll fluorescence imaging techniques were applied to monitor the performance of plants. In our research, transgenic maize, which was highly tolerant to glyphosate, was phenotyped using these high-throughput non-destructive methods to validate low levels of shikimic acid accumulation and high photochemical efficiency of photosystem II as reflected by maximum quantum yield and non-photochemical quenching in response to glyphosate. For hyperspectral imaging analysis, the combination of spectroscopy and chemometric methods was used to predict shikimic acid concentration. Our results indicated that a partial least-squares regression model, built on optimal wavelengths, effectively predicted shikimic acid concentrations, with a coefficient of determination value of 0.79 for the calibration set, and 0.82 for the prediction set. Moreover, shikimic acid concentration estimates from hyperspectral images were visualized on the prediction maps by spectral features, which could help in developing a simple multispectral imaging instrument for non-destructive phenotyping. Specific physiological effects of glyphosate affected the photochemical processes of maize, which induced substantial changes in chlorophyll fluorescence characteristics. A new data-driven method, combining mean fluorescence parameters and featuring a screening approach, provided a satisfactory relationship between fluorescence parameters and shikimic acid content. The glyphosate-tolerant transgenic plants can be identified with the developed discrimination model established on important wavelengths or sensitive fluorescence parameters 6 days after glyphosate treatment. The overall results indicated that both hyperspectral imaging and chlorophyll fluorescence imaging techniques could provide useful tools for stress phenotyping in maize breeding programs and could enable the detection and evaluation of superior genotypes, such as glyphosate tolerance, with a non-destructive high-throughput technique.

Hyperspectral Imaging for Predicting the Internal Quality of Kiwifruits Based on Variable Selection Algorithms and Chemometric Models

We investigated the feasibility and potentiality of determining firmness, soluble solids content (SSC), and pH in kiwifruits using hyperspectral imaging, combined with variable selection methods and calibration models. The images were acquired by a push-broom hyperspectral reflectance imaging system covering two spectral ranges. Weighted regression coefficients (BW), successive projections algorithm (SPA) and genetic algorithm-partial least square (GAPLS) were compared and evaluated for the selection of effective wavelengths. Moreover, multiple linear regression (MLR), partial least squares regression and least squares support vector machine (LS-SVM) were developed to predict quality attributes quantitatively using effective wavelengths. The established models, particularly SPA-MLR, SPA-LS-SVM and GAPLS-LS-SVM, performed well. The SPA-MLR models for firmness (R _pre  = 0.9812, RPD = 5.17) and SSC (R _pre  = 0.9523, RPD = 3.26) at 380-1023 nm showed excellent performance, whereas GAPLS-LS-SVM was the optimal model at 874-1734 nm for predicting pH (R _pre  = 0.9070, RPD = 2.60). Image processing algorithms were developed to transfer the predictive model in every pixel to generate prediction maps that visualize the spatial distribution of firmness and SSC. Hence, the results clearly demonstrated that hyperspectral imaging has the potential as a fast and non-invasive method to predict the quality attributes of kiwifruits.

Design of a simple non-destructive detection system using P-wave lasers for determining the soluble solids content of apples

The simple and nondestructive detection system studied in this work uses a near-infrared (NIR) detector and parallel-polarized (P-wave) NIR lasers to determine the soluble solids content (SSC) of apples. The P-wave NIR laser in this system is incident into the apple's pulp at the Brewster angle to minimize the interference caused by interfacial reflections. After the apple has been illuminated by four P-wave NIR lasers that correspond to the specified wavelengths of the SSC chemical bonds (880, 940, 980, and 1064 nm), the prediction of correlation (rp2) and the root-mean-square error for prediction (RMSEP) of the SSC are determined via partial least square regression analysis of the reflectance. Our results indicate that the use of P-wave lasers at the Brewster angle (as the angle of incidence) and the above specified wavelengths for the prediction set measurement of the SSC of apples obtained an rp2 of 0.88 and an RMSEP of 0.47°Brix. These rp2 are 6% higher, and the RMSEPs are 9% lower, than those obtained using non-polarized lasers.