Making wood inspection easier: FTIR spectroscopy and machine learning for Brazilian native commercial wood species identification.

The molecular structure of wood is mainly based on cellulose, lignin, and hemicellulose. However, low concentrations of lipids, phenolic compounds, terpenoids, fatty acids, resin acids, and waxes can also be found. In general, their color, smell, texture, quantity, and distribution of pores are used in human sensory analysis to identify native wood species, which may lead to erroneous classification, impairing quality control and inspection of commercialized wood. This study developed a fast and accurate method to discriminate Brazilian native commercial wood species using Fourier Transform Infrared Spectroscopy (FTIR) and machine learning algorithms. It not only solves the limitations of traditional methods but also goes beyond as it allows fast analyses to be obtained at low cost and high accuracy. In this work, we provide the identification of five Brazilian native wood species: Angelim-pedra (Hymenolobium petraeum Ducke), Cambara (Gochnatia polymorpha), Cedrinho (Erisma uncinatum), Champagne (Dipteryx odorata), and Peroba do Norte (Goupia glabra Aubl). The results showed the great potential of FTIR and multivariate analysis for wood sample classification; here, the Linear SVM differentiated the five wood species with an accuracy of 98%. The developed method allows industries, laboratories, companies, and control bodies to identify the nature of the wood product after being extracted and semi-manufactured.

Diagnosis of Cutaneous Leishmaniasis Using FTIR Spectroscopy and Machine Learning: An Animal Model Study.

Cutaneous leishmaniasis (CL) is a polymorphic and spectral skin disease caused by Leishmania spp. protozoan parasites. CL is difficult to diagnose because conventional methods are time-consuming, expensive, and low-sensitive. Fourier transform infrared spectroscopy (FTIR) with machine learning (ML) algorithms has been explored as an alternative to achieve fast and accurate results for many disease diagnoses. Besides the high accuracy demonstrated in numerous studies, the spectral variations between infected and noninfected groups are too subtle to be noticed. Since variability in sample set characteristics (such as sex, age, and diet) often leads to significant data variance and limits the comprehensive understanding of spectral characteristics and immune responses, we investigate a novel methodology for diagnosing CL in an animal model study. Blood serum, skin lesions, and draining popliteal lymph node samples were collected from Leishmania (Leishmania) amazonensis-infected BALB/C mice under experimental conditions. The FTIR method and ML algorithms accurately differentiated between infected (CL group) and noninfected (control group) samples. The best overall accuracy (∼72%) was obtained in an external validation test using principal component analysis and support vector machine algorithms in the 1800-700 cm-1 range for blood serum samples. The accuracy achieved in analyzing skin lesions and popliteal lymph node samples was satisfactory; however, notable disparities emerged in the validation tests compared to results obtained from blood samples. This discrepancy is likely attributed to the elevated sample variability resulting from molecular compositional differences. According to the findings, the successful functioning of prediction models is mainly related to data analysis rather than the differences in the molecular composition of the samples.