Data preprocessing methods of FT-NIR spectral data for the classification cooking oil

Abstract

This recent work describes the data pre-processing method of FT-NIR spectroscopy datasets of cooking oil and its quality parameters with chemometrics method. Pre-processing of near-infrared (NIR) spectral data has become an integral part of chemometrics modelling. Hence, this work is dedicated to investigate the utility and effectiveness of preprocessing algorithms namely row scaling, column scaling and single scaling process with Standard Normal Variate (SNV). The combinations of these scaling methods have impact on exploratory analysis and classification via Principle Component Analysis plot (PCA). The samples were divided into palm oil and non-palm cooking oil. The classification model was build using FT-NIR cooking oil spectra datasets in absorbance mode at the range of 4000cm -1 -14000cm -1 . Savitzky Golay derivative was applied before developing the classification model. Then, the data was separated into two sets which were training set and test set by using Duplex method. The number of each class was kept equal to 2/3 of the class that has the minimum number of sample. Then, the sample was employed t-statistic as variable selection method in order to select which variable is significant towards the classification models. The evaluation of data pre-processing were looking at value of modified silhouette width (mSW), PCA and also Percentage Correctly Classified (%CC). The results show that different data processing strategies resulting to substantial amount of model performances quality. The effects of several data pre-processing i.e. row scaling, column standardisation and single scaling process with Standard Normal Variate indicated by mSW and %CC. At two PCs model, all five classifier gave high %CC except Quadratic Distance Analysis.

Evaluation of solubility and histological effect of 11-keto-β-Boswellic acid on the diabetic mice liver using FTIR-PCA analysis and microscopy

“…FT-IR spectra demonstrated a prominent increase in the peak intensities in the wavenumber range from 950 to 1650 cm-1, and from 2009 to 3568 cm -1 as KBA doses were increased in relevance from group-1 to group-3 which indicated there was a clear effect of KBA solubility on treatments. The FTIR spectra of pure KBA gives characteristic peaks at 3437 cm1 (OH stretching), 2932 cm1 (C-H stretching), 1697 cm1 (C ¼ O stretching of aryl acid), 1453 cm1 (C-H bend), 1375 cm1 (COO symmetric stretching of carboxylates), 1240 cm1 (C-CO-C stretching of aryl ketone), 1025 cm1 and 988 cm1 (ring structures of cyclohexane) (Ruah et al, 2014).…”

Development of a quantitative method to evaluate the printability parameters of water-based ink using visible and near infrared spectroscopy

“…Commonly used spectral data preprocessing methods include meaning centering, normalization, smoothing, spectral derivatives, standard normal variate (SNV), and multivariate scattering correction (MSC). [11][12][13][14][15] Savitzky-Golay (SG) smoothing is a widely used spectral preprocessing method that can effectively remove spectral noises and is the key to choosing reasonable smoothing. 16 Vis-NIR spectra were preprocessed using MSC, SNV, and Savitzky-Golay in this study.…”

Principal Component Dan K-Means Cluster Analysis Untuk Data Spektrum Black Tea Grades Guna Penilaian Kualitas Alternatif

“…Metode yang melibatkan Near Infrared Spectroscopy (NIRS) dapat menjadi metode alternatif uji penilaian kualitas teh hitam guna memberikan solusi terhadap permasalahan atau kelemahan yang ada pada uji-uji lainnya karena metode yang melibatkan NIRS adalah relatif cepat, ramah lingkungan, serta memiliki penilaian yang obyektif [5,6]. NIRS memanfaatkan informasi hasil spectroscopy suatu bahan organik guna dapat dilakukan analisis kualitasnya [7]. Sampel teh hitam yang dilarutkan dalam air diletakan di dalam spektrometer guna ditembak oleh gelombang inframerah dengan panjang 10000 sampai dengan 4000 cm -1 yang mana hasil pengukuran dari spektrometer itu kemudian disebut sebagai data spektrum.…”