A comparative investigation of two handheld near-ir spectrometers for direct forensic examination of fibres in-situ
Rashed, Hamad S. ; Mishra, Puneet ; Nordon, Alison ; Palmer, David S. ; Baker, Matthew J. - \ 2021
Vibrational Spectroscopy 113 (2021). - ISSN 0924-2031
Chemometrics - Crime scene - Handheld spectrometers - Near-IR - Textile fibres - Vibrational spectroscopy
Fibres comparison in forensic science play a significant role in solving different crimes. Worldwide the most common textile fibre materials (fabrics) found at crimes scenes are cotton, polyester, denim, polypropylene, polycotton, and viscose. These fabrics are the focus of this study. The textile fabrics were examined by two handheld near-infrared (NIR) spectrometers, SCIO® by Consumer Physics and NIRscan Nano by Texas Instruments, for in situ comparisons of fibres, demonstrating capability at a crime scene. Spectral differences were apparent between both spectrometers due to the complementary wavelengths, SCIO interrogates the third overtone region (740–1070 nm) and NIRscan Nano interrogates the first and second overtone regions (900–1700 nm). A SCIO and NIRscan Nano data were pre-processed to eliminate noise and smooth the data for input to machine learning classifiers. The data were pre-processed and modelled by PRFFECTv2 software, and showed good predictive accuracy, with accuracy, sensitivity and specificity in the range 78–100 % for the best binary classification models (one class versus others) and within the range 65–100 % for the best multi-class classification models. This paper presents for the first time the use of small handheld spectrometers coupled with the Random Forest (RF) algorithm to classify fibre material for forensic comparison purposes in a fast, rapid, and non-destructive manner that is ideally suited for direct analysis at the crime scene.
Improved prediction of potassium and nitrogen in dried bell pepper leaves with visible and near-infrared spectroscopy utilising wavelength selection techniques
Mishra, Puneet ; Herrmann, Ittai ; Angileri, Mariagiovanna - \ 2021
Talanta 225 (2021). - ISSN 0039-9140
Chemometrics - Green chemistry - Multivariate - Non-destructive - Plants - Spectral phenotyping
Wet chemistry analysis of agricultural plant materials such as leaves is widely performed to quantify key chemical components to understand plant physiological status. Visible and near-infrared (Vis-NIR) spectroscopy is an interesting tool to replace the wet chemistry analysis, often labour intensive and time-consuming. Hence, this study accesses the potential of Vis-NIR spectroscopy to predict nitrogen (N) and potassium (K) concentration in bell pepper leaves. In the chemometrics perspective, the study aims to identify key Vis-NIR wavelengths that are most correlated to the N and K, and hence, improves the predictive performance for N and K in bell pepper leaves. For wavelengths selection, six different wavelength selection techniques were used. The performances of several wavelength selection techniques were compared to identify the best technique. As a baseline comparison, the partial least-square (PLS) regression analysis was used. The results showed that the Vis-NIR spectroscopy has the potential to predict N and K in pepper leaves with root mean squared error of prediction (RMSEP) of 0.28 and 0.44%, respectively. The wavelength selection in general improved the predictive performance of models for both K and N compared to the PLS regression. With wavelength selection, the RMSEP's were decreased by 19% and 15% for N and K, respectively, compared to the PLS regression. The results from the study can support the development of protocols for non-destructive prediction of key plant chemical components such as K and N without wet chemistry analysis.
Identifying key wavenumbers that improve prediction of amylose in rice samples utilizing advanced wavenumber selection techniques
Mishra, Puneet ; Woltering, Ernst J. - \ 2021
Talanta 224 (2021). - ISSN 0039-9140
Chemometrics - Feature selection - Food chemistry - Multi-spectral
This study utilizes advanced wavenumber selection techniques to improve the prediction of amylose content in grounded rice samples with near-infrared spectroscopy. Four different wavenumber selection techniques, i.e. covariate selection (CovSel), variable combination population analysis (VCPA), bootstrapping soft shrinkage (BOSS) and variable combination population analysis-iteratively retains informative variables (VCPA-IRIV), were used for model optimization and key wavenumbers selection. The results of the several wavenumber selection techniques were compared with the predictions reported previously on the same data set. All the four wavenumber selection techniques improved the predictive performance of amylose in rice samples. The best performance was obtained with VCPA, where, with only 11 wavenumbers-based model, the prediction error was reduced by 19% compared to what reported previously on the same data set. The selected wavenumbers can help in development of low-cost multi-spectral sensors for amylose prediction in rice samples.
Improved prediction of tablet properties with near-infrared spectroscopy by a fusion of scatter correction techniques
Mishra, Puneet ; Nordon, Alison ; Roger, Jean Michel - \ 2021
Journal of Pharmaceutical and Biomedical Analysis 192 (2021). - ISSN 0731-7085
Fusion - Multiblock - Multivariate - Pre-processing - Spectroscopy
Near-infrared (NIR) spectra of pharmaceutical tablets get affected by light scattering phenomena, which mask the underlying peaks related to chemical components. Often the best performing scatter correction technique is selected from a pool of pre-selected techniques. However, the data corrected with different techniques may carry complementary information, hence, use of a single scatter correction technique is sub-optimal. In this study, the aim is to prove that NIR models related to pharmaceuticals can directly benefit from the fusion of complementary information extracted from multiple scatter correction techniques. To perform the fusion, sequential and parallel pre-processing fusion approaches were used. Two different open source NIR data sets were used for the demonstration where the assay uniformity and active ingredient (AI) content prediction was the aim. As a baseline, the fusion approach was compared to partial least-squares regression (PLSR) performed on standard normal variate (SNV) corrected data, which is a commonly used scatter correction technique. The results suggest that multiple scatter correction techniques extract complementary information and their complementary fusion is essential to obtain high-performance predictive models. In this study, the prediction error and bias were reduced by up to 15 % and 57 % respectively, compared to PLSR performed on SNV corrected data.
Improved prediction of fuel properties with near-infrared spectroscopy using a complementary sequential fusion of scatter correction techniques
Mishra, Puneet ; Marini, Federico ; Biancolillo, Alessandra ; Roger, Jean Michel - \ 2021
Talanta 223 (2021)Part 1. - ISSN 0039-9140
Data fusion - Fuel - Multi-block data analysis - Multivariate analysis - Preprocessing - Spectroscopy
Near-infrared (NIR) spectroscopy of fuels can suffer from scattering effects which may mask the signals corresponding to key analytes in the spectra. Therefore, scatter correction techniques are often used prior to any modelling so to remove scattering and improve predictive performances. However, different scatter correction techniques may carry complementary information so that, if jointly used, both model stability and performances could be improved. A solution to that is the fusion of complementary information from differently scatter corrected data. In the present work, the use of a preprocessing fusion approach called sequential preprocessing through orthogonalization (SPORT) is demonstrated for predicting key quality parameters in diesel fuels. In particular, the possibility of predicting four different key properties, i.e., boiling point (°C), density (g/mL), aromatic mass (%) and viscosity (cSt), was considered. As a comparison, standard partial least-squares (PLS) regression modelling was performed on data pretreated by SNV and 2nd derivative (which is a widely used preprocessing combination). The results showed that the SPORT models, based on the fusion of scatter correction techniques, outperformed the standard PLS models in the prediction of all the four properties, suggesting that selection and use of a single scatter correction technique is often not sufficient. Up to complete bias removal with 50% reduction in prediction error was obtained. The R2P was increased by up to 8%. The sequential scatter fusion approach (SPORT) is not limited to NIR data but can be applied to any other spectral data where a preprocessing optimization step is required.
Improving moisture and soluble solids content prediction in pear fruit using near-infrared spectroscopy with variable selection and model updating approach
Mishra, Puneet ; Woltering, Ernst ; Brouwer, Bastiaan ; Hogeveen-van Echtelt, Esther - \ 2021
Postharvest Biology and Technology 171 (2021). - ISSN 0925-5214
Chemometric - Covariate selection - Fruit-quality - Interval partial least-squares regression - Non-destructive
To obtain robust near-infrared (NIR) spectroscopy data calibration models, variable selection and model updating with recalibration approaches were used for predicting quality parameters in pear fruit. For variables selection, interval partial least-squares regression and covariate selection approaches were used and compared. Model updating with recalibration was performed by incorporating a few new samples in the calibration set of existing batch data. The interaction of variable selection and model updating was also explored. The results showed that with variable selection, the model performance when tested on a new independent batch of fruit was greatly improved. Further, the model updating with only a few new samples resulted in a reduction of the bias when tested on the new batch. In the case of MC prediction, the variable selection reduced the bias from 1.31 % to 0.19 % and the RMSEP from 1.44 % to 0.58 %, compared to the standard partial least-squares regression (PLS2R). In the case of SSC prediction, the variable selection reduced the bias from -0.62 % to 0.07 % and the RMSEP from 0.90 % to 0.63 %, compared to the standard PLS2R. With a combination of variable selection and model updating the bias and RMSEP were further reduced. The interval-based method performed better compared to the filter-based method. As few as only 10 samples from the new batch already lead to a significant improvement in model performance. In the case of MC, spectral regions of 749-759 nm and 879-939 nm were identified as the most important region. In the case of the SSC, 709-759 nm and 789-999 nm were found to be important spectral regions. Robust models made on selected variables combined with model updating strategy can support to make NIR spectroscopy a preferred choice for non-destructive assessment of quality features of fresh fruit.
FRUITNIR-GUI: A graphical user interface for correcting external influences in multi-batch near infrared experiments related to fruit quality prediction
Mishra, Puneet ; Roger, Jean Michel ; Marini, Federico ; Biancolillo, Alessandra ; Rutledge, Douglas N. - \ 2020
Postharvest Biology and Technology (2020). - ISSN 0925-5214
Chemometrics - Fruit quality - Non-destructive - User-interface
Near infrared (NIR) spectroscopy is widely used for non-destructive prediction of fruit traits. Common traits such as dry matter (DM) and soluble solids contents (SSC) can be predicted with reliable accuracy. However, the main problem with NIR spectroscopy is that a model developed on one batch may not perform very well when tested on other batches. Reasons for that are the physical, chemical and environmental differences between the experiments performed in different batches. To deal with these issues, approaches such as variables selection, dynamic orthogonal projection (DOP) and transfer component analysis (TCA) can be used. However, the techniques are known but it is rarely possible for a new user or non-specialist to implement them in the practical situations. To overcome this limitation, for the first time, a graphical user interface-based toolbox (FRUITNIR-GUI) for basic chemometric data processing (regression and variable selection) is developed and presented. The GUI allows performing model adaption and maintenance in the context of multi-batch NIR spectroscopic experiments related to fruit. Furthermore, a case-study demonstrating its effectiveness in correcting for seasonality when predicting DM in apples is presented. The toolbox provides a push-button approach to build chemometric models of varying complexity for the characterization of fruit quality. Moreover, approaches such as variable selection and batch correction with DOP and TCA can improve the model performances on new batches. FRUITNIR-GUI can be freely downloaded at https://github.com/puneetmishra2/FRUITNIR and run using the password “welovenirs” (without quotation marks).
A conceptual model of the social–ecological system of nature-based solutions in urban environments
Tzoulas, Konstantinos ; Galan, Juanjo ; Venn, Stephen ; Dennis, Matthew ; Pedroli, Bas ; Mishra, Himansu ; Haase, Dagmar ; Pauleit, Stephan ; Niemelä, Jari ; James, Philip - \ 2020
Ambio (2020). - ISSN 0044-7447
Multifunctionality - Polycentric governance - Relational values - Sustainable urban planning - Transdisciplinarity
This article provides a perspective on nature-based solutions. First, the argument is developed that nature-based solutions integrate social and ecological systems. Then, theoretical considerations relating to relational values, multifunctionality, transdisciplinarity, and polycentric governance are briefly outlined. Finally, a conceptual model of the social–ecological system of nature-based solutions is synthesised and presented. This conceptual model comprehensively defines the social and ecological external and internal systems that make up nature-based solutions, and identifies theoretical considerations that need to be addressed at different stages of their planning and implementation The model bridges the normative gaps of existing nature-based solution frameworks and could be used for consistent, comprehensive, and transferable comparisons internationally. The theoretical considerations addressed in this article inform practitioners, policymakers, and researchers about the essential components of nature-based solutions. The conceptual model can facilitate the identification of social and ecological interconnections within nature-based solutions and the range of stakeholders and disciplines involved.
Partial least square regression versus domain invariant partial least square regression with application to near-infrared spectroscopy of fresh fruit
Mishra, Puneet ; Nikzad-Langerodi, Ramin - \ 2020
Infrared Physics & Technology 111 (2020). - ISSN 1350-4495
Calibration transfer - di-PLS - Domain adaptation - Near-infrared - Robust
Calibration models required for near-infrared (NIR) spectroscopy-based analysis of fresh fruit frequently fail to extrapolate adequately to conditions not encountered during initial data acquisition. Such different conditions can be due to physical, chemical or environmental effects and might be encountered for instance when measurements are carried out on a new instrument, at a different sensor operating temperature or if the model is applied to samples harvested under different seasonal conditions. To cope with such changes efficiently, for the first time, this study investigates the application of domain-invariant partial least square (di-PLS) regression to obtain calibration models that maintain the performance when used on a new condition. In particular, di-PLS allows unsupervised adaptation of a calibration model to a new condition, i.e. without the need to have access to reference measurements (e.g. dry matter contents) for the samples analyzed under the new condition. The potential of di-PLS for compensation of instrumental/seasonal and sensor temperature changes is demonstrated on four different use cases in the realm of NIR-based fruit quality assessment. The results showed that di-PLS regression outperformed standard PLS regression when tested on data affected by the aforementioned factors. The prediction R2 increased by up to 67 % with a 46 % and 80 % decrease in RMSEP and prediction bias, respectively. The main limitation of di-PLS is that, to operate efficiently, it requires that the distribution of the response variables to be similar in the data from the different conditions.
Sequential fusion of information from two portable spectrometers for improved prediction of moisture and soluble solids content in pear fruit
Mishra, Puneet ; Marini, Federico ; Brouwer, Bastiaan ; Roger, Jean Michel ; Biancolillo, Alessandra ; Woltering, Ernst ; Hogeveen van Echtelt, Esther - \ 2020
Talanta 223 (2020)Part 2. - ISSN 0039-9140
Chemometrics - Miniature near infrared (NIR) spectrometers - Multi-block data analysis - Multivariate analysis - Pear (Pyrus communis L.) - Sequential data fusion
Near infrared (NIR) spectroscopy allows rapid estimation of quality traits in fresh fruit. Several portable spectrometers are available in the market as a low-cost solution to perform NIR spectroscopy. However, portable spectrometers, being lower in cost than a benchtop counterpart, do not cover the complete near infrared (NIR) spectral range. Often portable sensors either use silicon-based visible and NIR detector to cover 400–1000 nm, or InGaAs-based short wave infrared (SWIR) detector covering the 900–1700 nm. However, these two spectral regions carry complementary information, since the 400–1000 nm interval captures the color and 3rd overtones of most functional group vibrations, while the 1st and the 2nd overtones of the same transitions fall in the 1000–1700 nm range. To exploit such complementarity, sequential data fusion strategies were used to fuse the data from two portable spectrometers, i.e., Felix F750 (~400–1000 nm) and the DLP NIR Scan Nano (~900–1700 nm). In particular, two different sequential fusion approaches were used, namely sequential orthogonalized partial-least squares (SO-PLS) regression and sequential orthogonalized covariate selection (SO-CovSel). SO-PLS improved the prediction of moisture content (MC) and soluble solids content (SSC) in pear fruit, leading to an accuracy which was not obtainable with models built on any of the two spectral data set individually. Instead, SO-CovSel was used to select the key wavelengths from both the spectral ranges mostly correlated to quality parameters of pear fruit. Sequential fusion of the data from the two portable spectrometers led to an improved model prediction (higher R2 and lower RMSEP) of MC and SSC in pear fruit: compared to the models built with the DLP NIR Scan Nano (the worst individual block) where SO-PLS showed an increase in R2p up to 56% and a corresponding 47% decrease in RMSEP. Differences were less pronounced to the use of Felix data alone, but still the R2p was increased by 2.5% and the RMSEP was reduced by 6.5%. Sequential data fusion is not limited to NIR data but it can be considered as a general tool for integrating information from multiple sensors.
New data preprocessing trends based on ensemble of multiple preprocessing techniques
Mishra, Puneet ; Biancolillo, Alessandra ; Roger, Jean Michel ; Marini, Federico ; Rutledge, Douglas N. - \ 2020
TrAC : Trends in Analytical Chemistry 132 (2020). - ISSN 0165-9936
Chemometrics - Ensemble learning - Multi-block analysis - Multivariate calibration - Preprocessing
Data generated by analytical instruments, such as spectrometers, may contain unwanted variation due to measurement mode, sample state and other external physical, chemical and environmental factors. Preprocessing is required so that the property of interest can be predicted correctly. Different correction methods may remove specific types of artefacts while still leaving some effects behind. Using multiple preprocessing in a complementary way can remove the artefacts that would be left behind by using only one technique. This article summarizes the recent developments in new data preprocessing strategies and specifically reviews the emerging ensemble approaches to preprocessing fusion in chemometrics. A demonstration case is also presented. In summary, ensemble preprocessing allows the selection of several techniques and their combinations that, in a complementary way, lead to improved models. Ensemble approaches are not limited to spectral data but can be used in all cases where preprocessing is needed and identification of a single best option is not easily done.
Close-range hyperspectral imaging of whole plants for digital phenotyping : Recent applications and illumination correction approaches
Mishra, Puneet ; Lohumi, Santosh ; Ahmad Khan, Haris ; Nordon, Alison - \ 2020
Computers and Electronics in Agriculture 178 (2020). - ISSN 0168-1699
Digital - High throughput - Non-destructive - Phenotyping - Spectroscopy
Digital plant phenotyping is emerging as a key research domain at the interface of information technology and plant science. Digital phenotyping aims to deploy high-end non-destructive sensing techniques and information technology infrastructures to automate the extraction of both structural and physiological traits from plants under phenotyping experiments. One of the promising sensor technologies for plant phenotyping is hyperspectral imaging (HSI). The main benefit of utilising HSI compared to other imaging techniques is the possibility to extract simultaneously structural and physiological information on plants. The use of HSI for analysis of parts of plants, e.g. plucked leaves, has already been demonstrated. However, there are several significant challenges associated with the use of HSI for extraction of information from a whole plant, and hence this is an active area of research. These challenges are related to data processing after image acquisition. The hyperspectral data acquired of a plant suffers from variations in illumination owing to light scattering, shadowing of plant parts, multiple scattering and a complex combination of scattering and shadowing. The extent of these effects depends on the type of plants and their complex geometry. A range of approaches has been introduced to deal with these effects, however, no concrete approach is yet ready. In this article, we provide a comprehensive review of recent studies of close-range HSI of whole plants. Several studies have used HSI for plant analysis but were limited to imaging of leaves, which is considerably more straightforward than imaging of the whole plant, and thus do not relate to digital phenotyping. In this article, we discuss and compare the approaches used to deal with the effects of variation in illumination, which are an issue for imaging of whole plants. Furthermore, future possibilities to deal with these effects are also highlighted.
Two standard-free approaches to correct for external influences on near-infrared spectra to make models widely applicable
Mishra, Puneet ; Roger, Jean Michel ; Rutledge, Douglas N. ; Woltering, Ernst - \ 2020
Postharvest Biology and Technology 170 (2020). - ISSN 0925-5214
Chemometrics - Model adaption - Multivariate - Scalable spectroscopy
In near-infrared (NIR) spectroscopy of fresh fruit often the external influences due to differences in physical, chemical and environmental conditions lead to model failure. Correction methods are required where standard samples are measured covering all different conditions and then remodeling is performed. However, in the real-world, it is often difficult to measure standard samples. To deal with this, two different approaches to correct for external influences without standard sample measurements i.e., dynamic orthogonalization projection (DOP) and domain adaption (DA), are presented, and for the first time are applied to NIR spectroscopy of fresh fruit. Four different case studies, chosen based on their importance and their frequency of occurrences in the NIR spectroscopy domain, were used for the demonstration. The first case was an adaption to maintain the predictive performance of a model when used on a spectra from a second similar instrument. The second case was the correction of the temperature effects due to sensor heating. The third and fourth cases were about maintaining the model performance for multi-season fruit quality prediction models for mangos and for apples. In all of the cases, the aim was to solve the challenges without resorting to new measurement of standards. The results showed that for all the cases, both DOP and DA improved model performances. Up to 31% increase in R2p, and 98% and 66% reduction in prediction bias and root mean squared error (RMSE) of prediction were noted, respectively. The main benefit of the DOP and DA techniques in NIR spectroscopy is the limited need for standard measurements, providing general-purpose tools to complement the NIR spectroscopy and make the models scalable, transferable, and reusable.
MBA-GUI: A chemometric graphical user interface for multi-block data visualisation, regression, classification, variable selection and automated pre-processing
Mishra, Puneet ; Roger, Jean Michel ; Rutledge, Douglas N. ; Biancolillo, Alessandra ; Marini, Federico ; Nordon, Alison ; Jouan-Rimbaud-Bouveresse, Delphine - \ 2020
Chemometrics and Intelligent Laboratory Systems 205 (2020). - ISSN 0169-7439
Chemometrics - Data fusion - Graphical user interface - Multi-sensor
In recent years, due to advances in sensor technology, multi-modal measurement of process and products properties has become easier. However, multi-modal measurements are only of use if the data from adding new sensors is worthwhile, especially in the case of industrial applications where financial justification is needed for new sensor purchase and integration, and if the multi-modal data generated can be properly utilised. Several multi-block methods have been developed to do this; however, their use is largely limited to chemometricians, and non-experts have little experience with such methods. To deal with this, we present the first version of a MATLAB-based graphical user interface (GUI) for multi-block data analysis (MBA), capable of performing data visualisation, regression, classification and variable selection for up to 4 different sensors. The MBA-GUI can also be used to implement a recent technique called sequential pre-processing through orthogonalization (SPORT). Data sets are supplied to demonstrate how to use the MBA-GUI. In summary, the developed GUI makes the implementation of multi-block data analysis easier, so that it could be used also by practitioners with no programming skills or unfamiliar with the MATLAB environment. The fully functional GUI can be downloaded from (https://github.com/puneetmishra2/Multi-block.git) and can be either installed to run in the MATLAB environment or as a standalone executable program. The GUI can also be used for analysis of a single block of data (standard chemometrics).
Improved prediction of ‘Kent’ mango firmness during ripening by near-infrared spectroscopy supported by interval partial least square regression
Mishra, Puneet ; Woltering, Ernst ; Harchioui, Najim El - \ 2020
Infrared Physics & Technology 110 (2020). - ISSN 1350-4495
Fruit quality - iPLSR - Non-destructive - Variable selection
Mangoes (Mangifera indica L.) are tropical fruits, which are sourced worldwide to supply the consumer market in Europe. Often mangoes are transported over sea in refrigerated containers at 8–10 °C and in some cases under controlled atmosphere conditions. At arrival in European countries, a vast amount of fruit is ripened under specified conditions to deliver 'Ready to Eat' fruit to consumers. The latter is a challenge due to great variability in fruit maturity stage at arrival. There are currently no good methodologies to rapidly and nondestructively monitor and control the ripening process of mangoes. A major indicator of mango ripeness is fruit firmness. In the present study, a portable visible near-infrared (400–1130 nm) (VNIR) spectrometer was used to predict the firmness of individual mango undergoing ripening. Ripening of ‘Kent’ mango was for 10 days monitored at 20 °C and relative humidity (RH) of 85%. Every other day fruit firmness (measured with AWETA acoustic firmness analyzer) and NIR spectrum were determined on 2 opposite sides of the fruit. Interval partial-least square (iPLSR) regression was used for identifying the important wavelengths responsible for predicting firmness in mangoes. Results showed a change in the VNIR spectra with the change in firmness of mangoes. The model based on selected wavelengths performed significantly better compared to PLSR without pre-selecting wavelengths. iPLSR based regression provided a correlation of calibration and prediction as R2c = 0.75 and R2p = 0.75, and root means squared error of calibration and prediction as 6.02 Hz2g2/3 and 5.92 Hz2g2/3 respectively. The iPLSR model outperformed the standard PLSR model by over 12% in R2p and 14% reduction in prediction error. The predictions by the model provided an evolution of the firmness during the complete ripening experiment. Non-destructive access to mango firmness during ripening can assist in optimizing the process to better meet the market demand.
Utilising variable sorting for normalisation to correct illumination effects in close-range spectral images of potato plants
Mishra, Puneet ; Polder, Gerrit ; Gowen, Aoife ; Rutledge, Douglas N. ; Roger, Jean Michel - \ 2020
Biosystems Engineering 197 (2020). - ISSN 1537-5110 - p. 318 - 323.
Illumination - Non-destructive - Phenotyping - Spectroscopy
Visible and near-infrared spectral imaging is a key non-destructive technique for rapid assessment of biophysical traits of plants. A major challenge with close-range spectral imaging of plants is spectral variation arising from illumination effects, which may mask the signals due to physiochemical differences. In the present work, we describe a new scatter correction technique called variable sorting for normalisation (VSN) and compare its efficiency with that of the commonly used standard normal variate (SNV) technique for the removal of unwanted illumination effects. Spectral images of potato plants were used for testing the correction. The results showed that the VSN outperformed SNV in removing illumination effects from the images of plants. The results show that the VSN approach to illumination correction can support high-throughput plant phenotyping where spectral imaging is used as a continuous monitoring tool.
SPORT pre-processing can improve near-infrared quality prediction models for fresh fruits and agro-materials
Mishra, Puneet ; Roger, Jean Michel ; Rutledge, Douglas N. ; Woltering, Ernst - \ 2020
Postharvest Biology and Technology 168 (2020). - ISSN 0925-5214
Chemometric - Data-fusion - Multi-block - Scatter correction - SOPLS
Near-infrared spectroscopy (NIRS) is a key non-destructive technique for rapid assessment of the chemical properties of food materials. However, a major challenge with NIRS is the mixed physicochemical phenomena captured by the interaction of the light with the matter. The interaction often results in both absorption and scattering of the light. The overall NIRS signal therefore contains information related to the two phenomena mixed. To predict chemical properties such as dry matter, Brix and lipids, light refelction/absorption is used. Therefore, when the aim of the data analysis is to predict chemical components, it is necessary to remove as much as possible the scattering effects from the spectra. Several pre-processing techniques are available to do this, but it is often difficult to decide which one to choose. In this article we present the use of a recently developed pre-processing approach, sequential pre-processing through orthogonalization (SPORT), to improve the predictive power of multivariate models based on NIR spectra of food materials. The SPORT approach utilizes sequential orthogonalized partial least square regression (SOPLS) for the fusion of data blocks corresponding to several spectral preprocessing techniques. The results were compared with commonly used pre-processing techniques in the analysis of food materials by NIRS. The comparison was made by analyzing 5 different datasets comprised of apples, apricots, olive oils and grapes associated with chemical properties such as dry matter (DM), Brix, lipids and citric acid. The datasets were from both reflection and transmission measurements. The results showed that the fusion-based pre-processing methodology is an ideal choice for pre-processing of NIRS data. For four out of five datasets, the prediction accuracies (high R2pred and low RMSEP) were improved. The improvement led to as much as a 20 % increase in R2pred and a 25 % decrease in RMSEP compared to the standard 2nd derivative pre-processing. The pre-processing fusion was more effective for the reflection mode compared to the transmission mode. Multiple pre-processing techniques provided complementary information, and therefore, their fusion using the SPORT approach improved the model performance. The methodology is not only applicable to food materials but can in fact be used as a general pre-processing approach for all types of modeling of spectral data.
Non-destructive measurement of internal browning in mangoes using visible and near-infrared spectroscopy supported by artificial neural network analysis
Gabriëls, Suzan H.E.J. ; Mishra, Puneet ; Mensink, Manon G.J. ; Spoelstra, Patrick ; Woltering, Ernst J. - \ 2020
Postharvest Biology and Technology 166 (2020). - ISSN 0925-5214
Artificial neural networks - Internal browning - Internal defects - Multivariate analyses - Near infrared spectroscopy
Visible and near infrared spectroscopy (VNIRS) (400−1000 nm) is a key emerging non-destructive technique for fruit quality assessment. This, because it is a unique method which allows rapid access to fruit pigments and chemical properties linked to fruit quality. In the present work, VNIRS has been used to predict the internal browning in ‘Keitt’ mangoes halves. The reference analysis was performed by cutting individual mango into halves and quantifying the extent of internal browning with a standardized color imaging (CI) cabinet as a browning index (BI). The CI provided a value for the “browning index” for each mango reflecting the presence and severity of internal browning. The data modelling involved both regression and classification analysis. The regression was performed to link the VNIR spectra with the BI values obtained from the internal color analysis. The classification analysis was performed for binary classification of mango into healthy or brown. Two different analysis techniques i.e. artificial neural network (ANN) and partial least square (PLS) were utilized. The study shows that VNIRS combined with ANN can classify mangoes as healthy or having internal brown with an accuracy of over 80 %. A robust and reliable classification system can potentially improve quality decisions through the mango supply chain, thereby reducing post-harvest losses.
Exploring potential of non-destructive and non-invasive sensors in food supply chains
Bouzembrak, Y. ; Chauhan, A. ; Daniels, F.M.J. ; Gavai, Anand ; Gonzales Rojas, Jose ; Kamphuis, C. ; Marvin, H.J.P. ; Meesters, Lydia ; Mishra, Puneet ; Müller-Maatsch, Judith ; Ouweltjes, W. ; Paillart, M.J.M. ; Petie, R. ; Petropoulou, Anna ; Plantenga, F.D.M. ; Rijgersberg, H. ; Top, J.L. ; Tsafaras, I. ; Ummels, Meeke ; Breukelen, Anouk van; Weesepoel, Y.J.A. - \ 2020
- 1 p.
|Exploring potential of non-destructive and non-invasive sensors in food supply chains
Chauhan, Aneesh ; Bouzembrak, Yamine ; Daniels, Freek ; Gavai, Anand ; Gonzales Rojas, Jose ; Kamphuis, J. ; Marvin, Hans ; Meesters, Lydia ; Mishra, Puneet ; Mueller-Maatsch, J. ; Ouweltjes, J. ; Paillart, Maxence ; Petie, Ronald ; Petropoulou, Anna ; Plantenga, Faline ; Rijgersberg, Hajo ; Top, Jan ; Tsafaras, Ilias ; Ummels, Meeke ; Breukelen, Anouk van; Weesepoel, Yannick - \ 2020