The impact of the order of derivative spectra on the performance of pattern recognition methods. Classification of medicinal plants according to the phylum.

Data pre-processing is an important strategy in chemometrics and related fields because in many cases the transformation of data has a great effect on the performance of the method (model). However, a careful examination of the literature clearly points out that only very few systematic studies are dedicated to the effect of the derivative spectra on the performance of the pattern recognition methods. This comprehensive study compares the impact of the order of derivative spectra and other data pre-processing procedures (normalization and standardization) on the performance of cluster analysis, principal component analysis and discriminant analysis applied for characterization and classification of medicinal plants according to their phylum using UV spectra. The efficiency of the pre-processing methods was estimated by comparing the accuracy of classification and prediction measured by internal cross-validation. Derivatization method (1st order) resulted in the best classification (100%) of medicinal plants according to their phylum (Pteridophyte, Magnoliophyte and Spermatophyte) as compared to other pre-processing methods (normalized spectra-71.4%, standardized spectra-76.2% and original spectra-78.6%).

[1]  M. Salem,et al.  Comparative study between derivative spectrophotometry and multivariate calibration as analytical tools applied for the simultaneous quantitation of Amlodipine, Valsartan and Hydrochlorothiazide. , 2013, Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy.

[2]  D. Skoog.  Fundamentals of analytical chemistry , 1963 .

[3]  M. Luca,et al.  Multivariate calibration techniques applied to derivative spectroscopy data for the analysis of pharmaceutical mixtures , 2009 .

[4]  J. Roger,et al.  Robustness of models developed by multivariate calibration. Part II: The influence of pre-processing methods , 2005 .

[5]  C. Bosch Ojeda,et al.  Recent applications in derivative ultraviolet/visible absorption spectrophotometry: 2009–2011: A review , 2012 .

[6]  C. Bosch Ojeda,et al.  Recent development in derivative ultraviolet/visible absorption spectrophotometry: 2004-2008: a review. , 2009, Analytica chimica acta.

[7]  Comparison of Chemometric Methods: Derivative Ratio Spectra and Multivariate Methods (CLS, PCR and PLS) for the Resolution of Ternary Mixtures of the Pesticides Carbofuran Carbaryl and Phenamifos After Their Extraction into Chloroform , 1997 .

[8]  A. El-Sayed,et al.  Recent Developments of Derivative Spectrophotometry and Their Analytical Applications , 2005, Analytical sciences : the international journal of the Japan Society for Analytical Chemistry.

[9]  Romà Tauler,et al.  Derivative FTIR spectroscopy for cluster analysis and classification of morocco olive oils , 2011 .

[10]  R. Anderssen,et al.  Molecular classification of barley (Hordeum vulgare L.) mutants using derivative NIR spectroscopy. , 2009, Journal of agricultural and food chemistry.

[11]  Evaluating the third and fourth derivatives of spectral data. , 2005, Talanta.

[12]  J. Riedl,et al.  Non-targeted detection of paprika adulteration using mid-infrared spectroscopy and one-class classification - Is it data preprocessing that makes the performance? , 2018, Food chemistry.

[13]  C. Sârbu,et al.  Use of TLC and UV–Visible Spectrometry for Fingerprinting of Dietary Supplements , 2015, Chromatographia.

[14]  C. Ojeda,et al.  Derivative ultraviolet-visible region absorption spectrophotometry and its analytical applications. , 1988, Talanta.

[15]  A. Krivchenko,et al.  Derivative Spectrophotometry and Electron Spin Resonance (ESR) Spectroscopy for Ecological and Biological Questions , 2013, Springer Vienna.

[16]  C. Bosch Ojeda,et al.  Recent development in derivative ultraviolet/visible absorption spectrophotometry: 2004-2008: a review. , 2009 .

[17]  Shweta Sharma,et al.  Derivative UV-vis absorption spectra as an invigorated spectrophotometric method for spectral resolution and quantitative analysis: Theoretical aspects and analytical applications: A review , 2016 .

[18]  O. Thomas,et al.  UV-visible spectrophotometry of water and wastewater , 2007 .

[19]  J. Karpińska.  Derivative spectrophotometry-recent applications and directions of developments. , 2004, Talanta.

[20]  David S. Moore,et al.  Handbook of spectroscopy , 2014 .

[21]  J. Namieśnik,et al.  Classification and fingerprinting of kiwi and pomelo fruits by multivariate analysis of chromatographic and spectroscopic data , 2012 .

[22]  V. Popovic,et al.  Analytical application of derivative spectrophotometry , 2000 .

[23]  G. Si,et al.  An improved ensemble model for the quantitative analysis of infrared spectra , 2015 .

[24]  Lalji Dixit,et al.  Quantitative Analysis by Derivative Electronic Spectroscopy , 1985 .

[25]  A. Moț,et al.  Multivariate analysis of reflectance spectra from propolis: geographical variation in Romanian samples. , 2010, Talanta.

[26]  E. Manzano,et al.  Raman spectroscopic discrimination of pigments and tempera paint model samples by principal component analysis on first-derivative spectra† , 2010 .

[27]  Ivo Leito,et al.  Uncertainty sources in UV-Vis spectrophotometric measurement , 2006 .

[28]  C. Ojeda,et al.  Recent developments in derivative ultraviolet/visible absorption spectrophotometery. , 1995, Talanta.

[29]  S. Kuś,et al.  DERIVATIVE UV-VIS SPECTROPHOTOMETRY IN ANALYTICAL CHEMISTRY , 1996 .

[30]  A. Savitzky,et al.  Smoothing and Differentiation of Data by Simplified Least Squares Procedures. , 1964 .