Optimisation of vibrational spectroscopy instruments and pre-processing for classification problems across various decision parameters

Abstract

Vibrational spectroscopy is a green, rapid, and affordable analytical tool for analysing the quality, safety, and origin of biological materials in agri-food sectors. Pre-processing spectral data is crucial to removing instrumental interferences and physical artifacts when developing a classification model. However, there has yet to be a consensus on which spectral pre-processing method, settings, and decision parameters to use to optimise pre-processing for different spectroscopy tools. Using an arbitrary criterion poses a risk of applying the wrong type or too severe pre-processing that removes valuable information or affects the model's performance for prediction studies. Matthew's Correlation Coefficient (MCC) - a statistic for parameterising classification performance, accounts for data set imbalance and improved decisions on model selection to express uncertainty on future predictions. Four vibrational spectroscopy instruments [near-infrared (NIR), hyperspectral (HSI), mid-infrared (FTIR), and Raman] were compared using different pre-processing methods to understand the performance using MCC to classify coffee from four countries (Indonesia, Ethiopia, Brazil and Rwanda). Key decision parameters were evaluated for the development of reliable classification models. The best pre-processing for NIR was extended multiplicative scatter correction with mean centering (MNCN), and for HSI, Savitzky-Golay (1 ^st derivative, 15 points) with MNCN. NIR performed the best across all four instruments, with FTIR performing the worst. Raman showed potential for coffee origin classification using the right pre-processing. Pre-processing with weighted least squares, normalisation, and MNCN eliminated the fluorescence effect on Raman spectral data. These findings show the feasibility of using MCC for classification problems.

Keywords

Vibrational spectroscopy / Chemometrics / Pre-processing / Model optimisation / Decision parameters

References

[1] Zhang L, Henson MJ, Sekulic SS. Multivariate data analysis for Raman imaging of a model pharmaceutical tablet Analytica Chimica Acta. 2005, 545, 262-78

[2] Khandasammy SR, Fikiet MA, Mistek E, Ahmed Y, Halámková L, et al. Bloodstains, paintings, and drugs: Raman spectroscopy applications in forensic science Forensic Chemistry. 2018, 8, 111-33

[3] Mcgoverin CM, Clark ASS, Holroyd SE, Gordon KC. Raman spectroscopic quantification of milk powder constituents Analytica Chimica Acta. 2010, 673, 26-32

[4] Beć KB, Grabska J, Bonn GK, Popp M, Huck CW. Principles and applications of vibrational spectroscopic imaging in plant science: A review Frontiers in Plant Science. 2020, 11, 1226

[5] Barnes RJ, Dhanoa MS, Lister SJ. Standard normal variate transformation and de-trending of near-infrared diffuse reflectance spectra Applied Spectroscopy. 1989, 43, 772-77

[6] Rinnan Å, Berg FVD, Engelsen SB. Review of the most common pre-processing techniques for near-infrared spectra Trends in Analytical Chemistry. 2009, 28, 1201-22

[7] Karoui R, Downey G, Blecker C. Mid-infrared spectroscopy coupled with chemometrics: A tool for the analysis of intact food systems and the exploration of their molecular structure−Quality relationships − A review Chemical Reviews. 2010, 110, 6144-68

[8] Lv Z, Zhang P, Sun W, Lei T, Benediktsson JA, et al. Sample iterative enhancement approach for improving classification performance of hyperspectral imagery IEEE Geoscience and Remote Sensing Letters. 2023, 21, 2500605

[10] Zhao N, Wu ZS, Zhang Q, Shi XY, Ma Q, et al. Optimization of Parameter Selection for Partial Least Squares Model Development Scientific Reports. 2015, 5, 11647

[13] Dhanoa MS, Lister SJ, Sanderson R, Barnes RJ. The link between multiplicative scatter correction (MSC) and standard normal variate (SNV) transformations of NIR spectra Journal of Near Infrared Spectroscopy. 1994, 2, 43-47

[14] Martens H, Stark E. Extended multiplicative signal correction and spectral interference subtraction: New preprocessing methods for near infrared spectroscopy Journal of Pharmaceutical and Biomedical Analysis. 1991, 9, 625-35

[15] Newey WK, Powell JL. Asymmetric least squares estimation and testing Econometrica. 1987, 55 4 819-47

[16] Chicco D, Jurman G. The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation BMC Genomics. 2020, 21, 6

[17] Powers DMW. Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation Journal of Machine Learning Technology. 2011, 2 1 37-63

[18] Lee LC, Liong CY, Jemain AA. A contemporary review on data preprocessing (DP) practice strategy in ATR-FTIR spectrum Chemometrics and Intelligent Laboratory Systems. 2017, 163, 64-75

[19] Norris KH, Williams PC. Optimisation of mathematical treatments of raw near-infrared signal in the measurement of protein in hard red spring wheat I. influence of particle Cereal Chemistry. 1984, 61 2 158-65

[20] Keidel A, Von Stetten D, Rodrigues C, Máguas C, Hildebrandt P. Discrimination of green arabica and robusta coffee beans by Raman spectroscopy Journal of Agricultural and Food Chemistry. 2010, 58, 11187-92

[21] Wermelinger T, D'Ambrosio L, Klopprogge B, Yeretzian C. Quantification of the robusta fraction in a coffee blend via Raman spectroscopy: Proof of principle Journal of Agricultural and Food Chemistry. 2011, 59, 9074-79

[22] Figueiredo LP, Borém FM, Almeida MR, Oliveira LFC, Alves APDC, et al. Raman spectroscopy for the differentiation of arabic coffee genotypes Food Chemistry. 2019, 288, 262-67

[23] Abreu GF, Borém FM, Oliveira LFC, Almeida MR, Alves APC. Raman spectroscopy: A new strategy for monitoring the quality of green coffee beans during storage Food Chemistry. 2019, 287, 241-48

[24] Dias RCE, Yeretzian C. Investigating coffee samples by Raman spectroscopy for quality control- Preliminary study International Journal of Experimental Spectroscopic Techniques. 2016, 1, 006

[25] Marquetti I, Link JV, Lemes ALG, dos Santos Scholz MB, Valderrama P, et al. Partial least square with discriminant analysis and near infrared spectroscopy for evaluation of geographic and genotypic origin of arabica coffee Computers and Electronics in Agriculture. 2016, 121, 313-19

[26] Moghimi A, Aghkhani MH, Sazgarnia A, Sarmad M. Vis/NIR spectroscopy and chemometrics for the prediction of soluble solids content and acidity (pH) of kiwifruit Biosystems Engineering. 2010, 106, 295-302

[27] Lasch P. Spectral pre-processing for biomedical vibrational spectroscopy and microspectroscopic imaging Chemometrics and Intelligent Laboratory Systems. 2012, 117, 100-14

[28] Liu Y, Huang J, Li M, Chen Y, Cui Q, et al. Rapid identification of the green tea geographical origin and processing month based on near-infrared hyperspectral imaging combined with chemometrics Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. 2022, 267, 120537

[29] Downey G, Briandet R, Wilson RH, Kemsley EK. Near- and mid-infrared spectroscopies in food authentication: Coffee varietal identification Journal of Agricultural and Food Chemistry. 1997, 45, 4357-61

[30] Obeidat SM, Hammoudeh AY, Alomary AA. Application of FTIR spectroscopy for assessment of green coffee beans according to their origin Journal of Applied Spectroscopy. 2018, 84, 1051-55

[31] Bona E, Marquetti I, Link JV, Makimori GYF, da Costa Arca V, et al. Support vector machines in tandem with infrared spectroscopy for geographical classification of green arabica coffee LWT - Food Science and Technology. 2017, 76, 330-36

[32] Medina J, Caro Rodríguez D, Arana VA, Bernal A, Esseiva P, et al. Comparison of attenuated total reflectance mid-infrared, near infrared, and ¹H-nuclear magnetic resonance spectroscopies for the determination of coffee's geographical origin International Journal of Analytical Chemistry. 2017, 2017, 7210463

[33] Cebi N, Yilmaz MT, Sagdic O. A rapid ATR-FTIR spectroscopic method for detection of sibutramine adulteration in tea and coffee based on hierarchical cluster and principal component analyses Food Chemistry. 2017, 229, 517-26

[34] Rubayiza AB, Meurens M. Chemical discrimination of arabica and robusta Coffees by Fourier transform Raman spectroscopy Journal of Agricultural and Food Chemistry. 2005, 53, 4654-59

[35] El-Abassy RM, Donfack P, Materny A. Discrimination between arabica and robusta green coffee using visible micro Raman spectroscopy and chemometric analysis Food Chemistry. 2011, 126, 1443-48

[36] Luna AS, Da Silva AP, Alves EA, Rocha RB, Lima ICA, De Gois JS. Evaluation of chemometric methodologies for the classification of coffea canephora cultivars via FT-NIR spectroscopy and direct sample analysis Analytical Methods. 2017, 9, 4255-60

[37] Giraudo A, Grassi S, Savorani F, Gavoci G, Casiraghi E, Geobaldo F. Determination of the geographical origin of green coffee beans using NIR spectroscopy and multivariate data analysis Food Control. 2019, 99, 137-45

RIGHTS & PERMISSIONS

2024 Editorial Office of Food Innovation and Advances