Different strategies for the use of random forest in NMR spectra

Abstract

Nuclear magnetic resonance (NMR) can provide a large amount of information about an analyzed sample; however, its spectra contain above 6000 variables, making it difficult for random forest (RF) applications. Reducing the size of the original dataset can minimize this problem. In this paper, we compared RF classification models obtained with full NMR spectral range and from the reduction of NMR variables, using principal component analysis (PCA) and the Fisher discriminant (FD). Then, the variables used in the construction of RF trees were analyzed and identified. Here, we used 1 H and 13 C NMR spectra obtained from 126 petroleum samples and values of their total acidy number (TAN), as measured by ASTM D664, ranging from 0.03 to 4.96 mg KOHÁ g −1 , to distinguish the oil samples from the TAN values. Of two classes that resulted, the first contained 78 samples with TAN values less than, or equal to, 0.3 mg KOHÁ g −1 , while the second contained 48 samples with TAN values higher than 0.3 mg KOHÁ g −1. The 1 H NMR results showed that the combination of FD and RF techniques provided the best accuracy (88%). For 13 C NMR data, the most accurate model was obtained by the association of PCA and RF (84%). The identification of variables used in RF allowed a better understanding of the important chemical data contained in the spectra and the relationship to TAN in petroleum. K E Y W O R D S fisher discriminant, NMR, PCA, random forest, reduction of variables 1 | INTRODUCTION Random forest (RF) is a machine learning method recognized for its efficiency in supervised classification of linear and nonlinear data, especially in the areas of genetic analysis, metabolomics, medical image analysis, food quality control, and crude oil. 1-4 The potential of the RF technique in classification is confirmed when associated with analytical methods that allow the acquisition of a large amount of information, such as chromatography, mass spectrometry, infrared spectroscopy, nuclear magnetic resonance of hydrogen (1 H NMR), and carbon (13 C NMR). 1-4 The NMR technique provides detailed information on functional groups, characterizing the sample at the molecular level; however, the number of variables generated may exceed 65 000, depending on the spectral range analyzed. In

Liu regression after random forest for prediction and modeling in high dimension

“…The RF has received increasing attention for efficient variable selection among other machine learning techniques. We refer to Afanador et al, 1 Behnamian et al, 2 Li et al, 3 Speiser et al, 4 and Lovatti et al, 5 to mention a few. However, to the best of our knowledge, this efficient machine learning technique for variable selection is not used with the Liu regression method in none of the related existing studies.…”

ESI(−)FT-ICR MS for the determination of best conditions for producing extract abundant in phenolic compounds from leaves of E. uniflora and FTIR-PCA as a sample screening method

“…Then, Fisher's discriminant analysis was used for variable selection to nd the spectral regions responsible for maximising the region separation or leaf collection times and minimising the sample separation from the same class. 53 Finally, the selected spectrum regions were submitted to principal component analysis (PCA) to identify the bands responsible for distinguishing the locations and leaf collection times of the day. The models were built using MATLAB R2015a (MathWorks Inc., Natick, MA, USA).…”

Comparison of feature extraction and auto-preprocessing for chili pepper (Capsicum Frutescens) quality classification using machine learning

“…RF is an algorithm that combines Classification and regression trees (CART) and bootstrapping aggregation (bagging) algorithms. RF applications to solve classification problems of large data and a larger sample set can generate a high computational cost in addition to requiring more time [27]. The detailed descriptions of the SVM, DT, and RF algorithms are described elsewhere and therefore not shown here.…”