scholarly journals Assessment of internal quality attributes of mandarin fruit. 2. NIR calibration model robustness

2005 ◽  
Vol 56 (4) ◽  
pp. 417 ◽  
Author(s):  
J. A. Guthrie ◽  
D. J. Reid ◽  
K. B. Walsh
Keyword(s):  
Near Infrared ◽  
Model Updating ◽  
Multivariate Calibration ◽  
Mean Squared Error ◽  
Sample Selection ◽  
Model Performance ◽  
Soluble Solids ◽  
Internal Quality ◽  
Calibration Model ◽  
Validation Population

The robustness of multivariate calibration models, based on near infrared spectroscopy, for the assessment of total soluble solids (TSS) and dry matter (DM) of intact mandarin fruit (Citrus reticulata cv. Imperial) was assessed. TSS calibration model performance was validated in terms of prediction of populations of fruit not in the original population (different harvest days from a single tree, different harvest localities, different harvest seasons). Of these, calibration performance was most affected by validation across seasons (signal to noise statistic on root mean squared error of prediction of 3.8, compared with 20 and 13 for locality and harvest day, respectively). Procedures for sample selection from the validation population for addition to the calibration population (‘model updating’) were considered for both TSS and DM models. Random selection from the validation group worked as well as more sophisticated selection procedures, with approximately 20 samples required. Models that were developed using samples at a range of temperatures were robust in validation for TSS and DM.

Calibration Transfer between Miniature Photodiode Array-Based Spectrometers in the near Infrared Assessment of Mandarin Soluble Solids Content

2002 ◽  
Vol 10 (1) ◽  
pp. 27-35 ◽  
Author(s):  
C.V. Greensill ◽  
K.B. Walsh
Keyword(s):  
Near Infrared ◽  
Model Updating ◽  
Soluble Solids ◽  
Soluble Solid Content ◽  
Calibration Model ◽  
Calibration Transfer ◽  
Orthogonal Signal Correction ◽  
Significant Difference ◽  
Photodiode Array ◽  
Direct Standardisation

The transfer of predictive models among photodiode array based, short wave near infrared spectrometers using the same illumination/detection optical geometry has been attempted using various chemometric techniques, including slope and bias correction (SBC), direct standardisation (DS), piecewise direct standardisation (PDS), double window PDS (DWPDS), orthogonal signal correction (OSC), finite impulse transform (FIR) and wavelet transform (WT). Additionally, an interpolation and photometric response correction method, a wavelength selection method and a model updating method were assessed. Calibration transfer was attempted across two populations of mandarin fruit. Model performance was compared in terms of root mean squared error of prediction ( RMSEP), using Fearn's significance testing, for calibration transfer (standardisation) between pairs of spectrometers from a group of four spectrometers. For example, when a calibration model (Root Mean Square Error of Cross-Validation [ RMSECV = 0.26% soluble solid content (SSC)], developed on one spectrometer, was used with spectral data collected on another spectrometer, a poor prediction resulted ( RMSEP = 2.5% SSC). A modified WT method performed significantly better (e.g. RMSEP = 0.25% SSC) than all other standardisation methods (10 of 12 cases), and almost on a par with model updating (MU) (nine cases with no significant difference, one case and two cases significantly better for WT and MU, respectively).

scholarly journals NIR model development and robustness in prediction of melon fruit total soluble solids

2006 ◽  
Vol 57 (4) ◽  
pp. 411 ◽  
Author(s):  
J. A. Guthrie ◽  
C. J. Liebenberg ◽  
K. B. Walsh
Keyword(s):  
Near Infrared ◽  
Multivariate Calibration ◽  
Mean Squared Error ◽  
Scatter Correction ◽  
Model Development ◽  
Equatorial Region ◽  
Soluble Solids ◽  
Eating Quality ◽  
Spectral Window ◽  
Total Soluble Solids

Near infrared spectroscopy (NIRS) can be used for the on-line, non-invasive assessment of fruit for eating quality attributes such as total soluble solids (TSS). The robustness of multivariate calibration models, based on NIRS in a partial transmittance optical geometry, for the assessment of TSS of intact rockmelons (Cucumis melo) was assessed. The mesocarp TSS was highest around the fruit equator and increased towards the seed cavity. Inner mesocarp TSS levels decreased towards both the proximal and distal ends of the fruit, but more so towards the proximal end. The equatorial region of the fruit was chosen as representative of the fruit for near infrared assessment of TSS. The spectral window for model development was optimised at 695–1045 nm, and the data pre-treatment procedure was optimised to second-derivative absorbance without scatter correction. The ‘global’ modified partial least squares (MPLS) regression modelling procedure of WINISI (ver. 1.04) was found to be superior with respect to root mean squared error of prediction (RMSEP) and bias for model predictions of TSS across seasons, compared with the ‘local’ MPLS regression procedure. Updating of the model with samples selected randomly from the independent validation population demonstrated improvement in both RMSEP and bias with addition of approximately 15 samples.

Quality Analysis of Stored Bell Peppers Using Near-Infrared Hyperspectral Imaging

2018 ◽  
Vol 61 (4) ◽  
pp. 1199-1207 ◽  
Author(s):  
Anisur Rahman ◽  
Mohammad Akbar Faqeerzada ◽  
Rahul Joshi ◽  
Santosh Lohumi ◽  
Lalit Mohan Kandpal ◽  
...  
Keyword(s):  
Hyperspectral Imaging ◽  
Near Infrared ◽  
Multivariate Calibration ◽  
Bell Pepper ◽  
Soluble Solids ◽  
Quality Analysis ◽  
Calibration Model ◽  
Pls Regression ◽  
Quality Properties ◽  
Bell Peppers

Abstract. The objective of this study was to predict the moisture content (MC), soluble solids content (SSC), and titratable acidity (TA) content in bell peppers during storage (18°C, 85% relative humidity) over 12 days, based on near-infrared hyperspectral imaging (NIR-HSI) in the 1000-1500 nm wavelength range. The mean spectra of 148 mature bell peppers were extracted from the hyperspectral images, and multivariate calibration models were built using partial least squares (PLS) regression with different preprocessing spectra techniques. The most effective wavelengths were selected using the variable importance in projection (VIP) technique, which selected optimal variables for the target quality parameters of bell peppers from a full set of variables. Subsequently the selected variables were used to develop a PLS-VIP model for simplifying the prediction model. The MC, SSC, and TA content in bell peppers during storage changed from 90.7% to 93.0%, from 6.1%Brix to 7.3%Brix, and from 0.222% to 0.334%, respectively. The PLS regression model with MC, SSC, and TA content resulted in coefficients of determination (R2pred) of 0.83, 0.85, and 0.7, with standard errors of prediction (SEP) of 0.08%, 0.075%Brix, and 0.013%, respectively, using SNV preprocessed spectra for MC and TA content and Savitzky-Golay (S-G) second-order derivatives preprocessed spectra for SSC of bell peppers. By contrast, the prediction results yielded R2pred of 0.69, 0.75, and 0.68, respectively, with SEP values of 0.103%, 0.107%Brix, and 0.011% when the PLS-VIP model was employed. The PLS-VIP model simplified the calibration model by selecting the most important variables in terms of their responsiveness to bell pepper quality properties. The results revealed that HSI coupled with multivariate analysis can be used successfully to predict the MC, SSC, and TA content in bell peppers. Keywords: Fruit quality, Hyperspectral imagery, Image analysis, Spectral analysis, Stored bell pepper.

Measuring The Tensile Strain of Wood By Visible And Near-Infrared Spatially Resolved Spectroscopy

2021 ◽  
Author(s):  
Ma Te ◽  
Tetsuya Inagaki ◽  
Masato Yoshida ◽  
Mayumi Ichino ◽  
Satoru Tsuchikawa
Keyword(s):  
Light Scattering ◽  
Prediction Accuracy ◽  
Tensile Strain ◽  
Near Infrared ◽  
Mean Squared Error ◽  
Calibration Model ◽  
Spatially Resolved ◽  
Squared Error ◽  
Stiffness Evaluation ◽  
Spatially Resolved Spectroscopy

Abstract Wood has various mechanical properties, so stiffness evaluation is critical for quality management. Using conventional strain gauges constantly is high cost, also challenging to measure precious wood materials due to the use of strong adhesive. This study demonstrates the correlation between light scattering changes inside the wood cell walls and tensile strain. A multifiber-based visible-near-infrared (Vis–NIR) spatially resolved spectroscopy (SRS) system was designed to rapidly and conventiently acquire such light scattering changes. For the preliminary experiment, samples with different thicknesses were measured to evaluate the influence of thickness. The differences in Vis–NIR SRS spectral data diminish with an increase in sample thickness, which suggests that the SRS method can successfully measure the whole strain (i.e., surface and inside) of wood samples. Then, for the primary experiment, 18 wood samples with the same thickness (2 mm) were tested to construct a strain calibration model. The prediction accuracy was characterized by a determination coefficient (R2) of 0.86 with a root mean squared error (RMSE) of 297.89 με for five-fold cross-validation; for test validation, The prediction accuracy was characterized by an R2 of 0.82 and an RMSE of 345.44 με.

scholarly journals Sample-Specific Prediction Error Measures in Spectroscopy

2020 ◽  
Vol 74 (7) ◽  
pp. 791-798
Author(s):  
Carl Emil Eskildsen ◽  
Tormod Næs
Keyword(s):  
Chemical Reaction ◽  
Multivariate Calibration ◽  
Mean Squared Error ◽  
Predictive Performance ◽  
Calibration Model ◽  
Prediction Errors ◽  
Prediction Ability ◽  
Spectroscopic Measurements ◽  
Error Measures ◽  
Specific Prediction

In applied spectroscopy, the purpose of multivariate calibration is almost exclusively to relate analyte concentrations and spectroscopic measurements. The multivariate calibration model provides estimates of analyte concentrations based on the spectroscopic measurements. Predictive performance is often evaluated based on a mean squared error. While this average measure can be used in model selection, it is not satisfactory for evaluating the uncertainty of individual predictions. For a calibration, the uncertainties are sample specific. This is especially true for multivariate calibration, where interfering compounds may be present. Consider in-line spectroscopic measurements during a chemical reaction, production, etc. Here, reference values are not necessarily available. Hence, one should know the uncertainty of a given prediction in order to use that prediction for telling the state of the chemical reaction, adjusting the process, etc. In this paper, we discuss the influence of variance and bias on sample-specific prediction errors in multivariate calibration. We compare theoretical formulae with results obtained on experimental data. The results point towards the fact that bias contribution cannot necessarily be neglected when assessing sample-specific prediction ability in practice.

Prediction of Soluble Solids Content and Post-Storage Internal Quality of Bulida Apricots Using near Infrared Spectroscopy

2007 ◽  
Vol 15 (3) ◽  
pp. 179-188 ◽  
Author(s):  
Marena Manley ◽  
Elizabeth Joubert ◽  
Lindie Myburgh ◽  
Ester Lotz ◽  
Martin Kidd
Keyword(s):  
Cold Storage ◽  
Regression Models ◽  
Near Infrared ◽  
Storage Period ◽  
Multivariate Adaptive Regression Splines ◽  
Soluble Solids ◽  
Internal Quality ◽  
Soluble Solids Content ◽  
Classification Rate ◽  
Solids Content

The development of internal breakdown of South African Bulida apricots during cold storage, rendering the fruit unsuitable for canning, causes significant post-harvest losses. Regression models to predict internal post-storage quality using near infrared (NIR) spectroscopy and multivariate classification techniques were developed using NIR spectra of the intact fruit collected prior to storage and subjective quality evaluations performed after a cold storage period of four weeks. A correct classification rate of 69% was obtained using multivariate adaptive regression splines (MARS) compared to 50% obtained by soft independent modelling by class analogy (SIMCA). NIR regression models developed for soluble solids content (SSC) of intact fruit as well as for direct NIR measurements on the exposed fruit tissue gave similar results, thus confirming sufficient NIR light penetration into the intact fruit. The best prediction results were obtained when two spectral measurements per fruit (one on each half of the fruit), compared to single measurements, were used.

scholarly journals Near-Infrared Spectroscopy Combined with Multivariate Calibration to Predict the Yield of Sesame Oil Produced by Traditional Aqueous Extraction Process

2017 ◽  
Vol 2017 ◽  
pp. 1-5
Author(s):  
Yong-Dong Xu ◽  
Yan-Ping Zhou ◽  
Jing Chen
Keyword(s):  
Near Infrared ◽  
Multivariate Calibration ◽  
Nir Spectroscopy ◽  
Extraction Process ◽  
Sesame Oil ◽  
Aqueous Extraction ◽  
Oil Yield ◽  
Support Vector ◽  
Calibration Model ◽  
Aqueous Extraction Process

Sesame oil produced by the traditional aqueous extraction process (TAEP) has been recognized by its pleasant flavor and high nutrition value. This paper developed a rapid and nondestructive method to predict the sesame oil yield by TAEP using near-infrared (NIR) spectroscopy. A collection of 145 sesame seed samples was measured by NIR spectroscopy and the relationship between the TAEP oil yield and the spectra was modeled by least-squares support vector machine (LS-SVM). Smoothing, taking second derivatives (D2), and standard normal variate (SNV) transformation were performed to remove the unwanted variations in the raw spectra. The results indicated that D2-LS-SVM (4000–9000 cm−1) obtained the most accurate calibration model with root mean square error of prediction (RMSEP) of 1.15 (%, w/w). Moreover, the RMSEP was not significantly influenced by different initial values of LS-SVM parameters. The calibration model could be helpful to search for sesame seeds with higher TAEP oil yields.

Limitations to the measurement of intact melon total soluble solids using near infrared spectroscopy

2006 ◽  
Vol 57 (4) ◽  
pp. 403 ◽  
Author(s):  
Robert L. Long ◽  
Kerry B. Walsh
Keyword(s):  
Near Infrared ◽  
Model Performance ◽  
Nir Spectroscopy ◽  
Quality Standard ◽  
Sampling Procedure ◽  
Performance Model ◽  
Soluble Solids ◽  
Fruit Storage ◽  
Total Soluble Solids ◽  
Fruit Maturity

The imposition of a minimum total soluble solids (TSS) value as a quality standard for orange-flesh netted melon fruit (Cucumis melo L. reticulatus group) requires either a batch sampling procedure (i.e. the estimation of the mean and standard deviation of a population), or the individual assessment of fruit [e.g. using a non-destructive procedure such as near infrared (NIR) spectroscopy]. Several potential limitations to the NIR assessment of fruit, including the variation in TSS within fruit and the effect of fruit storage conditions on the robustness of calibration models, were considered in this study. Outer mesocarp TSS was 3 TSS units higher at the stylar end of the fruit compared with the stem end, and the TSS of inner mesocarp was higher than outer tissue and more uniform across spatial positions. The linear relationship between the outer 10 mm and the subsequent middle 10 mm of tissue varied with fruit maturity [e.g. 42 days before harvest (DBH), r 2 = 0.8; 13 DBH, r 2 = 0.4; 0 DBH, r 2 = 0.7], and with cultivars (at fruit maturity, Eastern Star 2001 r 2 = 0.88; Malibu 2001 r 2 = 0.59). This relationship notably affected NIR calibration performance (e.g. based on inner mesocarp TSS; R c 2 = 0.80, root mean standard error of cross-validation (RMSECV) = 0.65, and R c 2 = 0.41, RMSECV = 0.88 for mature Eastern Star and Malibu fruit, respectively). Cold storage of fruit (0–14 days at 5°C) did not affect NIR model performance. Model performance was equivalent when based on either that part of the fruit in contact with the ground or equatorial positions; however, it was improved when based on the stylar end of the fruit.

scholarly journals Time-of-flight Near-infrared Spectroscopy for Nondestructive Measurement of Internal Quality in Grapefruit

2013 ◽  
Vol 138 (3) ◽  
pp. 225-228 ◽  
Author(s):  
Yohei Kurata ◽  
Tomoe Tsuchida ◽  
Satoru Tsuchikawa
Keyword(s):  
Infrared Spectroscopy ◽  
Near Infrared Spectroscopy ◽  
Prediction Accuracy ◽  
Near Infrared ◽  
Time Of Flight ◽  
Soluble Solids ◽  
Internal Quality ◽  
Citrus Paradisi ◽  
Least Squares Regression ◽  
Time Resolved

We proposed a technique combining time-of-flight (TOF) and near-infrared spectroscopy (NIRS), termed TOF-NIRS, capable of measuring the time-resolved profiles of near-infrared (NIR) light with nanosecond resolution. Analysis of the variation in time-resolved profiles was used to estimate soluble solids concentration (SSC) and acidity in grapefruit (Citrus paradisi), and the prediction accuracy was compared with the conventional NIR measurement device. In data processing, the cross-correlation function, which evaluated the similarity between the reference and transmitted beams, was introduced as an explanatory variable for partial least squares regression. TOF-NIRS predicted both SSC and acidity in grapefruit with higher precision than the conventional NIR measurement with respective r values of 0.72 and 0.85. Specifically, the superiority of TOF-NIRS was attributed to measurement time and prediction accuracy in determining acidity.

Sign in / Sign up

Export Citation Format

Share Document