Short wave near infrared (NIR) spectroscopy operated in a partial or full transmission geometry and a point spectroscopy mode has been increasingly adopted for evaluation of quality of intact fruit, both on-tree and on-packing lines. The evolution in hardware has been paralleled by an evolution in the modelling techniques employed. This review documents the range of spectral pre-treatments and modelling techniques employed for this application. Over the last three decades, there has been a shift from use of multiple linear regression to partial least squares regression. Attention to model robustness across seasons and instruments has driven a shift to machine learning methods such as artificial neural networks and deep learning in recent years, with this shift enabled by the availability of large and diverse training and test sets.
NorrisKH. Instrumental techniques for measuring quality of agricultural crops. In: Post-harvest Physiology and Crop Preservation. Springer, 1983, pp. 471–484.
2.
NorrisK. Direct spectrophotometric determination of moisture content of grain and seeds. In: Proc of the 1963 international symposium on humidity and moisture, Washington, USA, 20–23 May 1965, p. 19.
3.
WalshKBMcGloneVAHanDH. The uses of near infra-red spectroscopy in postharvest decision support: A review. Postharvest Biol Tech2020; 163: 111139. DOI: 10.1016/j.postharvbio.2020.111139
4.
AndersonN. Forecasting of the Mango Crop: Quantity and quality. Masters Thesis. Central Queensland University, 2018.
5.
WilliamsPKarlH. Norris. The father of near-infrared spectroscopy. NIR News2019; 30: 25–27. DOI: 10.1177/0960336019875883
6.
WoldHOA. Nonlinear estimation by iterative least square procedures. In: Research Papers in Statistics. New York, USA: Wiley, 1968.
7.
SaeysWNguyen Do TrongN, et al.Multivariate calibration of spectroscopic sensors for postharvest quality evaluation: A review. Postharvest Biol Tech2019; 158: 110981. DOI: 10.1016/j.postharvbio.2019.110981
8.
WalshKBBlascoJZude-SasseM, et al.Visible-NIR 'point' spectroscopy in postharvest fruit and vegetable assessment: The science behind three decades of commercial use. Postharvest Biol Tech2020; 168: 111246. DOI: 10.1016/j.postharvbio.2020.111246
RongDWangHYingY, et al.Peach variety detection using VIS-NIR spectroscopy and deep learning. Comput Electro Agric2020; 175: 105553. DOI: 10.1016/j.compag.2020.105553
11.
MishraPPassosD. Realizing transfer learning for updating deep learning models of spectral data to be used in new scenarios. Chemometrics Intell Lab Syst2021; 212: 104283. DOI: 10.1016/j.chemolab.2021.104283
12.
PeirsATirryJVerlindenB, et al. Effect of biological variability on the robustness of NIR models for soluble solids content of apples. Postharvest Biol Tech2003; 28: 269–280. DOI: 10.1016/S0925-5214(02)00196-5
13.
SubediPPWalshKBOwensG. Prediction of mango eating quality at harvest using short-wave near infrared spectrometry. Postharvest Biol Tech2007; 43: 326–334. DOI: 10.1016/j.postharvbio.2006.09.012
14.
BobelynESerbanA-SNicuM, et al.Postharvest quality of apple predicted by NIR-spectroscopy: Study of the effect of biological variability on spectra and model performance. Postharvest Biology Technology2010; 55: 133–143, DOI: 10.1016/j.postharvbio.2009.09.006
15.
WeddingBBWrightCGraufS, et al.Effects of seasonal variability on FT-NIR prediction of dry matter content for whole Hass avocado fruit. Postharvest Biology Technology2013; 75: 9–16. DOI: 10.1016/j.postharvbio.2012.04.016
16.
ShenGLesnoffMBaetenV, et al.Local partial least squares based on global PLS scores. J Chemometrics2019; 33: e3117. DOI: 10.1002/cem.3117
17.
WangHPengJXieC, et al.Fruit quality evaluation using spectroscopy technology: a review. Sensors2015; 15: 11889–11927, DOI: 10.3390/s150511889
18.
LiuYSunXOuyangA. Nondestructive measurement of soluble solid content of navel orange fruit by visible-NIR spectrometric technique with PLSR and PCA-BPNN. LWT - Food Sci Tech2010; 43: 602–607, DOI: 10.1016/j.lwt.2009.10.008.. DOI:
19.
Pérez-MarínDPazPGuerreroJ-E, et al.Miniature handheld NIR sensor for the on-site non-destructive assessment of post-harvest quality and refrigerated storage behavior in plums. J Food Engineering2010; 99: 294–302, DOI: 10.1016/j.jfoodeng.2010.03.002
20.
MoghimiAAghkhaniMHSazgarniaA, et al.Vis/NIR spectroscopy and chemometrics for the prediction of soluble solids content and acidity (pH) of kiwifruit. Biosyst Engineering2010; 106: 295–302, DOI: 10.1016/j.biosystemseng.2010.04.002
21.
WuYLiLLiuL, et al.Nondestructive measurement of internal quality attributes of apple fruit by using NIR spectroscopy. Multimedia Tools Appl2019; 78: 4179–4195, DOI: 10.1007/s11042-017-5388-0
22.
LuoXYeZXuH, et al.Robustness improvement of NIR-based determination of soluble solids in apple fruit by local calibration. Postharvest Biol Tech2018; 139: 82–90. DOI: 10.1016/j.postharvbio.2018.01.019
23.
NturambirweJFINieuwoudtHHPeroldWJ, et al.Non-destructive measurement of internal quality of apple fruit by a contactless NIR spectrometer with genetic algorithm model optimization. Scientific Afr2019; 3: e00051. DOI: 10.1016/j.sciaf.2019.e00051
24.
NicolaïBMBeullensKBobelynE, et al. Nondestructive measurement of fruit and vegetable quality by means of NIR spectroscopy: a review. Postharvest Biology Technology2007; 46: 99–118. DOI: 10.1016/j.postharvbio.2007.06.024
25.
ZudeM.. Non-destructive prediction of banana fruit quality using VIS/NIR spectroscopy. Fruits2003; 58: 135–142. DOI: 10.1051/fruits:2003001
26.
NicolaïBMVerlindenBEDesmetM, et al.Time-resolved and continuous wave NIR reflectance spectroscopy to predict soluble solids content and firmness of pear. Postharvest Biol Tech2008; 47: 68–74, DOI: 10.1016/j.postharvbio.2007.06.001
27.
WeddingBBWhiteRDGraufS, et al.Non-destructive prediction of 'Hass' avocado dry matter via FT-NIR spectroscopy. J Sci Food Agric2011; 91: 233–238, DOI: 10.1002/jsfa.4175
28.
ChoiJ-HChenP-ALeeB, et al.Portable, non-destructive tester integrating VIS/NIR reflectance spectroscopy for the detection of sugar content in Asian pears. Scientia Horticulturae2017; 220: 147–153, DOI: 10.1016/j.scienta.2017.03.050
29.
KhodabakhshianREmadiBKhojastehpourM, et al.A comparative study of reflectance and transmittance modes of Vis/NIR spectroscopy used in determining internal quality attributes in pomegranate fruits. J Food Meas Characterization2019; 13: 3130–3139, DOI: 10.1007/s11694-019-00235-z
30.
PeirsA. Measurement of Apple Quality and Maturity by Means of NIR Spectroscopy and imagingPhD Thesis. Leuven, Belgium: Catholic University of Leuven, 2002.
31.
AndersonNTWalshKBSubediPP, et al.Achieving robustness across season, location and cultivar for a NIRS model for intact mango fruit dry matter content. Postharvest Biol Tech2020; 168: 111202, DOI: 10.1016/j.postharvbio.2020.111202
32.
HollandJH. Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence. Michigan, USA: University of Michigan Press, 1975.
33.
LiHLiangYXuQ, et al.Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibration. Analytica Chimica Acta2009; 648: 77–84, DOI: 10.1016/j.aca.2009.06.046
AndrewAFearnT. Transfer by orthogonal projection: making near-infrared calibrations robust to between-instrument variation. Chemometrics Intell Lab Syst2004; 72: 51–56. DOI: 10.1016/j.chemolab.2004.02.004
36.
RogerJ-MChauchardFBellon-MaurelV. EPO-PLS external parameter orthogonalisation of PLS application to temperature-independent measurement of sugar content of intact fruits. Chemometrics Intell Lab Syst2003; 66: 191–204. DOI: 10.1016/S0169-7439(03)00051-0
37.
ZeaiterMRogerJMBellon-MaurelV. Dynamic orthogonal projection. A new method to maintain the on-line robustness of multivariate calibrations. Application to NIR-based monitoring of wine fermentations. Chemometrics Intell Lab Syst2006; 80: 227–235. DOI: 10.1016/j.chemolab.2005.06.011
38.
MishraPRogerJMRutledgeDN, et al.Two standard-free approaches to correct for external influences on near-infrared spectra to make models widely applicable. Postharvest Biol Tech2020; 170: 111326. DOI: 10.1016/j.postharvbio.2020.111326
39.
PanSJTsangIWKwokJT, et al.Domain adaptation via transfer component analysis. IEEE Trans Neural Networks2011; 22: 199–210. DOI: 10.1109/TNN.2010.2091281.
40.
IgneBDardennePHonigsD, et al.The 2010 IDRC software shoot-out at a glance. NIR News2010; 21: 14–16. DOI: 10.1255/nirn.1216
41.
NorrisKH. Understanding and correcting the factors which affect diffuse transmittance spectra. NIR News2001; 12: 6–9, DOI: 10.1255/nirn.613
42.
GuthrieJWeddingBWalshK. Robustness of NIR calibrations for soluble solids in intact melon and pineapple. J Near Infrared Spectrosc1998; 6: 259–265, DOI: 10.1255/jnirs.145
43.
SaranwongSKawanoS. On-tree harvesting quality evaluation of mango fruit with a hand-held NIR instrument. In: Japan-Thailand Joint Symposium on Nondestructive Evaluation Technology Bangkok, Thailand, 18–21 May 2004, pp. 18–21.
44.
LerudRM. Sensors And Portable Instruments For Postharvest Agriculture. PhD Thesis. Portland State University, 2019.
45.
RogerJMPalagosBBertrandD, et al.CovSel: Variable selection for highly multivariate and multi-response calibration. Chemometrics Intell Lab Syst2011; 106: 216–223, DOI: 10.1016/j.chemolab.2010.10.003
46.
KhatiwadaBPSubediPPHayesC, et al.Assessment of internal flesh browning in intact apple using visible-short wave near infrared spectroscopy. Postharvest Biol Tech2016; 120: 103–111. DOI: 10.1016/j.postharvbio.2016.06.001.. DOI:
NørgaardLSaudlandAWagnerJ, et al.Interval partial least-squares regression (iPLS): A comparative chemometric study with an example from near-infrared spectroscopy. Appl Spectrosc2000; 54: 413–419. DOI: 10.1366/0003702001949500
49.
MishraPMariniFBrouwerB, et al.Sequential fusion of information from two portable spectrometers for improved prediction of moisture and soluble solids content in pear fruit. Talanta2021; 223: 121733. DOI: 10.1016/j.talanta.2020.121733
DaviesAMCBritcherHVFranklinJG, et al. The application of fourier-transformed near-infrared spectra to quantitative analysis by comparison of similarity indices (CARNAC). Mikrochimica Acta1988; 94: 61–64. DOI: 10.1007/BF01205839
52.
ShenkJSWesterhausMOBerzaghiP. Investigation of a LOCAL calibration procedure for near infrared instruments. J Near Infrared Spectrosc1997; 5: 223–232, DOI: 10.1255/jnirs.115
53.
NaesTIsakssonTKowalskiB. Locally weighted regression and scatter correction for near-infrared reflectance data. Anal Chem1990; 62: 664–673. DOI: 10.1021/ac00206a003
54.
Ramirez-LopezLBehrensTSchmidtK, et al.The spectrum-based learner: A new local approach for modeling soil vis-NIR spectra of complex datasets. Geoderma2013; 195-196: 268–279. DOI: 10.1016/j.geoderma.2012.12.014
55.
MarianiNCTde Almeida TeixeiraGHde LimaKMG, et al.NIRS and iSPA-PLS for predicting total anthocyanin content in jaboticaba fruit. Food Chem2015; 174: 643–648. DOI: 10.1016/j.foodchem.2014.11.008
56.
MishraPNikzad-LangerodiR. Partial least square regression versus domain invariant partial least square regression with application to near-infrared spectroscopy of fresh fruit. Infrared Phys Tech2020; 111: 103547. DOI: 10.1016/j.infrared.2020.103547
57.
BlancoMCoelloJIturriagaH, et al.NIR calibration in non-linear systems: different PLS approaches and artificial neural networks. Chemometrics Intell Lab Syst2000; 50: 75–82, DOI: 10.1016/S0169-7439(99)00048-9
58.
XudongSHailiangZYandeL. Nondestructive assessment of quality of Nanfeng mandarin fruit by a portable near infrared spectroscopy. Int J Agric Biol Eng2009; 21: 65–71. DOI: 10.3965/j.issn.1934-6344.2009.01.065-071
59.
YibinYYandeLXiapingF, et al.Application of principal component regression and artificial neural network in FT-NIR soluble solids content determination of intact pear fruit. In: Optical sensors and sensing systems for natural resources and food safety and quality Boston, USA, 23–26 October 2005.
60.
GuoYNiYKokotS. Evaluation of chemical components and properties of the jujube fruit using near infrared spectroscopy and chemometrics. Spectrochimica Acta A: Mol Biomol Spectrosc2016; 153: 79–86. DOI: 10.1016/j.saa.2015.08.006
61.
ChauchardFCogdillRRousselS, et al.Application of LS-SVM to non-linear phenomena in NIR spectroscopy: development of a robust and portable sensor for acidity prediction in grapes. Chemometrics Intell Lab Syst2004; 71: 141–150. DOI: 10.1016/j.chemolab.2004.01.003
62.
MukarevMIWalshKB. Prediction of Brix Values of Intact Peaches with Least Squares-Support Vector Machine Regression Models. J Near Infrared Spectrosc2012; 20: 647–655. DOI: 10.1255/jnirs.1026
63.
LiMPullanagariRRPranamornkithT, et al.Quantitative prediction of post storage 'Hayward' kiwifruit attributes using at harvest Vis-NIR spectroscopy. J Food Eng2017; 202: 46–55, DOI: 10.1016/j.jfoodeng.2017.01.002
64.
MalegoriCNascimento MarquesEJde FreitasST, et al.Comparing the analytical performances of Micro-NIR and FT-NIR spectrometers in the evaluation of acerola fruit quality, using PLS and SVM regression algorithms. Talanta2017; 165: 112–116, DOI: 10.1016/j.talanta.2016.12.035
65.
NealR. Bayesian Learning for Neural Networks. New York, USA: Springer, 1996.
66.
ChenC-CJohnsonJTSatoM, et al.Foreword to the special issue on subsurface sensing using ground-penetrating radar (GPR). IEEE Trans Geosci Remote Sensing2007; 45: 2419–2421. DOI: 10.1109/TGRS.2007.902827
67.
CuiCFearnT. Comparison of partial least squares regression, least squares support vector machines, and Gaussian process regression for a near infrared calibration. J Near Infrared Spectrosc2017; 25: 5–14. DOI: 10.1177/0967033516678515
68.
AndersonNTWalshKBFlynnJR, et al.Achieving robustness across season, location and cultivar for a NIRS model for intact mango fruit dry matter content. II. Local PLS and nonlinear models. Postharvest Biol Tech2021; 171: 111358. DOI: 10.1016/j.postharvbio.2020.111358
69.
MinasnyBMcBratneyAB. Regression rules as a tool for predicting soil properties from infrared reflectance spectroscopy. Chemometrics Intell Lab Syst2008; 94: 72–79. DOI: 10.1016/j.chemolab.2008.06.003
70.
KoiralaAWalshKBWangZ, et al.Deep learning - Method overview and review of use for fruit detection and yield estimation. Comput Electronics Agriculture2019; 162: 219–234, DOI: 10.1016/j.compag.2019.04.017
71.
CuiCFearnT. Modern practical convolutional neural networks for multivariate regression: Applications to NIR calibration. Chemometrics Intell Lab Syst2018; 182: 9–20. DOI: 10.1016/j.chemolab.2018.07.008
72.
SchootMKapperCvan KollenburgGH, et al.Investigating the need for preprocessing of near-infrared spectroscopic data as a function of sample size. Chemometrics Intell Lab Syst2020; 204: 104105, DOI: 10.1016/j.chemolab.2020.104105
73.
MishraPPassosD. A synergistic use of chemometrics and deep learning improved the predictive performance of near-infrared spectroscopy models for dry matter prediction in mango fruit. Chemometrics Intell Lab Syst2021; 212: 104287. DOI: 10.1016/j.chemolab.2021.104287
74.
SteinbrenerJPoschKLeitnerR. Hyperspectral fruit and vegetable classification using convolutional neural networks. Comput Electro Agric2019; 162: 364–372. DOI: 10.1016/j.compag.2019.04.019
75.
YuXLuHWuD. Development of deep learning method for predicting firmness and soluble solid content of postharvest Korla fragrant pear using Vis/NIR hyperspectral reflectance imaging. Postharvest Biol Tech2018; 141: 39–49. DOI: 10.1016/j.postharvbio.2018.02.013
76.
GaoZShaoYXuanG, et al.Real-time hyperspectral imaging for the in-field estimation of strawberry ripeness with deep learning. Artif Intelligence Agric2020; 4: 31–38, DOI: 10.1016/j.aiia.2020.04.003
77.
WangZHuMZhaiG. Application of deep learning architectures for accurate and rapid detection of internal mechanical damage of blueberry using hyperspectral transmittance data. Sensors2018; 18: 1126. DOI: 10.3390/s18041126
78.
AndersonNWalshKSubediP. Mango DMC and Spectra. Mendley data, 2020. DOI: 10.17632/46htwnp833.1
79.
MishraPRutledgeDNRogerJ-M, et al.Chemometric pre-processing can negatively affect the performance of near-infrared spectroscopy models for fruit quality prediction. Talanta2021; 229: 122303. DOI: 10.1016/j.talanta.2021.122303
80.
Puneet MishraPPassosD. Deep multiblock predictive modelling using parallel input convolutional neural networks. Analytica Chim Acta2021; 1163: 338520. DOI: 10.1016/j.aca.2021.338520
81.
CaruanaRNiculescu-MizilACrewG, et al.Ensemble selection from libraries of models. In: 21st international conference on machine learning Banff, Canada, 4 July 2004, p. 18.
JanikLJCozzolinoDDambergsR, et al.The prediction of total anthocyanin concentration in red-grape homogenates using visible-near-infrared spectroscopy and artificial neural networks. Analytica Chim Acta2007; 594: 107–118, DOI: 10.1016/j.aca.2007.05.019
85.
BalabinRMSafievaRZLomakinaEI. Near-infrared (NIR) spectroscopy for motor oil classification: From discriminant analysis to support vector machines. Microchemical J2011; 98: 121–128, DOI: 10.1016/j.microc.2010.12.007
MishraPRogerJMMariniF, et al.FRUITNIR-GUI: A graphical user interface for correcting external influences in multi-batch near infrared experiments related to fruit quality prediction. Postharvest Biol Tech2021; 175: 111414, DOI: 10.1016/j.postharvbio.2020.111414
