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.

Turning chaotic sample group clusterization into organized ones by feature selection: Application on photodiagnosis of Brucella abortus serological test.

Bovine brucellosis diagnosis is a major problem to be solved; the disease has a tremendous economic impact with significant losses in meat and dairy products, besides the fact that it can be transmitted to humans. The sanitary measures instituted in Brazil are based on disease control through diagnosis, animal sacrifice, and vaccination. Although the currently available diagnostic tests show suitable quality parameters, they are time-consuming, and the incidence of false-positive and/or false-negative results is still observed, hindering effective disease control. The development of a low-cost, fast, and accurate brucellosis diagnosis test remains a need for proper sanitary measures at a large-scale analysis. In this context, spectroscopy techniques associated with machine learning tools have shown great potential for use in diagnostic tests. In this study, bovine blood serum was investigated by UV-vis spectroscopy and machine learning algorithms to build a prediction model for Brucella abortus diagnosis. Here we first pre-treated the UV raw data by using Standard Normal Deviate method to remove baseline deviation, then apply principal component analysis - a clustering method - to observe the group formation tendency; the first results showed no clustering tendency with a messy sample score distribution, then we properly select the main principal components to improve clusterization. Finally, by using machine learning algorithms (SVM and KNN), the predicting models achieved a 92.5% overall accuracy. The present methodology provides a test result in an average time of 5 min, while the standard diagnosis, with the screening and confirmatory tests, can take up to 48 h. The present result demonstrates the method's viability for diagnosing bovine brucellosis, which can significantly contribute to disease control programs in Brazil and other countries.

Multi-resistant diarrheagenic Escherichia coli identified by FTIR and machine learning: a feasible strategy to improve the group classification.

The identification of multidrug-resistant strains from E. coli species responsible for diarrhea in calves still faces many laboratory limitations and is necessary for adequately monitoring the microorganism spread and control. Then, there is a need to develop a screening tool for bacterial strain identification in microbiology laboratories, which must show easy implementation, fast response, and accurate results. The use of FTIR spectroscopy to identify microorganisms has been successfully demonstrated in the literature, including many bacterial strains; here, we explored the FTIR potential for multi-resistant E. coli identification. First, we applied principal component analysis to observe the group formation tendency; the first results showed no clustering tendency with a messy sample score distribution; then, we improved these results by adequately selecting the main principal components which most contribute to group separation. Finally, using machine learning algorithms, a predicting model showed 75% overall accuracy, demonstrating the method's viability as a screaming test for microorganism identification.

Evaluation of Piezoresistive and Electrical Properties of Conductive Nanocomposite Based on Castor-Oil Polyurethane Filled with MWCNT and Carbon Black.

Flexible films of a conductive polymer nanocomposite-based castor oil polyurethane (PUR), filled with different concentrations of carbon black (CB) nanoparticles or multiwall carbon nanotubes (MWCNTs), were obtained by a casting method. The piezoresistive, electrical, and dielectric properties of the PUR/MWCNT and PUR/CB composites were compared. The dc electrical conductivity of both PUR/MWCNT and PUR/CB nanocomposites exhibited strong dependences on the concentration of conducting nanofillers. Their percolation thresholds were 1.56 and 1.5 mass%, respectively. Above the threshold percolation level, the electrical conductivity value increased from 1.65 × 10-12 for the matrix PUR to 2.3 × 10-3 and 1.24 × 10-5 S/m for PUR/MWCNT and PUR/CB samples, respectively. Due to the better CB dispersion in the PUR matrix, the PUR/CB nanocomposite exhibited a lower percolation threshold value, corroborated by scanning electron microscopy images. The real part of the alternating conductivity of the nanocomposites was in accordance with Jonscher's law, indicating that conduction occurred by hopping between states in the conducting nanofillers. The piezoresistive properties were investigated under tensile cycles. The nanocomposites exhibited piezoresistive responses and, thus, could be used as piezoresistive sensors.

Canine visceral leishmaniasis diagnosis by UV spectroscopy of blood serum and machine learning algorithms.

Visceral leishmaniasis (VL) is a zoonotic disease caused by the protozoan Leishmania infantum, and dogs are considered the main urban hosts for future disease transmission. The first and most effective control against the spread of disease relies on identifying infected animals, followed by their treatment or sacrifice, to reduce the protozoan reservoirs. Despite the availability of various diagnostic tests for VL in dogs the development of a quick and accurate diagnosis is essential from a public health and ethical point of view. Here we analyze the use of UV-Vis spectroscopy as an alternative diagnostic method for VL diagnosis by using the antigen-antibody interaction in canine blood serum and machine learning algorithms. The main UV spectra in the 220 to 280 nm range exhibit nine electronic absorption bands, but no significative difference could be identified between the positive and negative group spectra. Finally, UV pre-proceed spectra by SNV (standard normal variate) were submitted to principal component analysis followed by Linear SVM algorithm, the prediction model was tested in a leave-one-out cross-validation and external validation test reaching an overall accuracy of 75%.

Solvent modulation in peptide sub-microfibers obtained by solution blow spinning.

Peptides possess high chemical diversity at the amino acid sequence level, which further translates into versatile functions. Peptides with self-assembling properties can be processed into diverse formats giving rise to bio-based materials. Peptide-based spun fibers are an interesting format due to high surface-area and versatility, though the field is still in its infancy due to the challenges in applying the synthetic polymer spinning processes to protein fibers to peptides. In this work we show the use of solution blow-spinning to produce peptide fibers. Peptide fiber formation was assisted by the polymer poly (vinyl pyrrolidone) (PVP) in two solvent conditions. Peptide miscibility and further self-assembling propensity in the solvents played a major role in fiber formation. When employing acetic acid as solvent, peptide fibers (0.5 µm) are formed around PVP fibers (0.75 µm), whereas in isopropanol only one type of fibers are formed, consisting of mixed peptide and PVP (1 µm). This report highlights solvent modulation as a mean to obtain different peptide sub-microfibers via a single injection nozzle in solution blow spinning. We anticipate this strategy to be applied to other small peptides with self-assembly propensity to obtain multi-functional proteinaceous fibers.

Preparation and Phytotoxicity Evaluation of Cellulose Acetate Nanoparticles.

The use of biocompatible and low-cost polymeric matrices to produce non-phytotoxic nanoparticles for delivery systems is a promising alternative for good practices in agriculture management and biotechnological applications. In this context, there is still a lack of studies devoted to producing low-cost polymeric nanoparticles that exhibit non-phytotoxic properties. Among the different polymeric matrices that can be used to produce low-cost nanoparticles, we can highlight the potential application of cellulose acetate, a natural biopolymer with biocompatible and biodegradable properties, which has already been used as fibers, membranes, and films in different agricultural and biotechnological applications. Here, we provided a simple and low-cost route to produce cellulose acetate nanoparticles (CA-NPs), by modified emulsification solvent evaporation technique, with a main diameter of around 200 nm and a spherical and smooth morphology for potential use as agrochemical nanocarriers. The non-phytotoxic properties of the produced cellulose acetate nanoparticles were proved by performing a plant toxic test by Allium cepa assay. The cytotoxicity and genotoxicity tests allowed us to evaluate the mitotic process, chromosomal abnormalities, inhibition/delay in root growth, and micronucleus induction. In summary, the results demonstrated that CA-NPs did not induce phytotoxic, cytotoxic, or genotoxic effects, and they did not promote changes in the root elongation, germination or in the mitotic, chromosomal aberration, and micronucleus indices. Consequently, the present findings indicated that CA-NPs can be potentially used as environmentally friendly nanoparticles.

Laser-Induced Breakdown Spectroscopy Associated with the Design of Experiments and Machine Learning for Discrimination of Brachiaria brizantha Seed Vigor.

Laser-induced breakdown spectroscopy (LIBS) associated with machine learning algorithms (ML) was used to evaluate the Brachiaria seed physiological quality by discriminating the high and low vigor seeds. A 23 factorial design was used to optimize the LIBS experimental parameters for spectral analysis. A total of 120 samples from two distinct cultivars of Brachiaria brizantha seeds exhibiting high vigor (HV) and low vigor (LV) in standard tests were studied. The raw LIBS spectra were normalized and submitted to outlier verification, previously to the reduction data dimensionality from principal component analysis. Supervised machine learning algorithm parameters were chosen by leave-one-out cross-validation in the test samples, and it was tested by external validation using a new set of data. The overall accuracy in external validation achieved 100% for HV and LV discrimination, regardless of the cultivar or the classification algorithm.

Paracoccidioidomycosis screening diagnosis by FTIR spectroscopy and multivariate analysis.

Paracoccidioidomycosis (PCM) is a systemic mycosis with high incidence in Latin America, caused by species of the genus Paracoccidioides spp. Brazil is considered to be the endemic center of this disease, which is identified as the eighth cause of mortality from chronic infectious disease in the country. There are several specific diagnostic methods in PCM, such as microbiological, immunological, histopathological, and molecular. However, the standard laboratory diagnosis depends mostly on fungus direct observation - the gold standard of PCM diagnosis. The implementation of new technologies, such as Fourier Transform Infrared (FTIR), can contribute to the clinical diagnosis trial of this disease. Here, we evaluated a new strategy for the diagnosis of PCM by using blood serum FTIR spectra from 20 patients with PCM and 20 healthy individuals. Machine learning algorithms were able to provide an overall accuracy of 91.67% by using Cubic SVM in the PCA data from FTIR results.

PVDF/KNO3 Composite Sub-Microfibers Produced by Solution Blow Spinning as a Hydrophobic Matrix for Fertilizer Delivery System.

Nutrient supplementation is a common practice in agriculture to increase crop productivity in the field. This supplementation is usually excessive, causing nutrient leaching in periods of rainfall leading to environmental problems. To overcome such issues, many studies have been devoted to developing polymeric matrices for the controlled and continuous release of nutrients, reducing losses, and keeping plants nourished for as long as possible. However, the release mechanism of these matrices is based on water diffusion. They start immediately for swellable polymeric matrices, which is not interesting and also may cause some waste, because the plant only needs nutrition only after the germination process. Here, as proof of concept, we tested a hydrophobic polymeric matrix based on sub-microfibers mats, produced by solution blow spinning, filled with potassium nitrate (KNO3) for the controlled release of nutrients to plants. In this work, we used the polyvinylidene fluoride (PVDF) polymer to produce composite nanofibers containing pure potassium nitrate in the proportion of 10% weight. PVDF/KNO sub-microfibers mats were obtained with 370 nm average diameter and high occurrence of beads. We performed a release test using PVDF/KNO3 mats in a water bath. The release kinetic tests showed an anomalous delivery mechanism, but the composite polymeric fibrous mat showed itself to be a promising alternative to delay the nutrient delivery for the plants.

Simultaneous quantification of seven multi-class organic molecules by single-shot dilution differential pulse voltammetric calibration.

The contamination of water sources by anthropogenic activities is a topic of growing interest in the scientific community. Therefore, robust analytical techniques for the determination and quantification of multiple substances are needed, which often require complex and time-consuming procedures. In this context, we describe a univariate calibration method to determine emerging multi-class contaminants in different water sources. The instrumental setup is composed of a lab-made glass electrochemical cell with three electrodes: Pt counter, Ag/AgCl reference, and BDD working electrodes. With this system, we were able to simultaneously quantify tert-butylhydroquinone, acetaminophen, estrone, sulfamethoxazole, enrofloxacin, caffeine, and ibuprofen by differential pulse voltammetry. Only two calibration solutions are required for the Single-shot Dilution Differential Pulse Voltammetric Calibration (SSD-DP-VC) method described here, which can significantly improve sample throughput. Two robust univariate calibration strategies were also applied and compared with SSD-DP-VC. The new method is simple, fast, and comparable with traditional calibration methods, showing similar precision and accuracy for all determinations evaluated.

A new strategy for canine visceral leishmaniasis diagnosis based on FTIR spectroscopy and machine learning.

Visceral leishmaniasis is a neglected disease caused by protozoan parasites of the genus Leishmania. The successful control of the disease depends on its accurate and early diagnosis, which is usually made by combining clinical symptoms with laboratory tests such as serological, parasitological, and molecular tests. However, early diagnosis based on serological tests may exhibit low accuracy due to lack of specificity caused by cross-reactivities with other pathogens, and sensitivity issues related, among other reasons, to disease stage, leading to misdiagnosis. In this study was investigated the use of mid-infrared spectroscopy and multivariate analysis to perform a fast, accurate, and easy canine visceral leishmaniasis diagnosis. Canine blood sera of 20 noninfected, 20 Leishmania infantum, and eight Trypanosoma evansi infected dogs were studied. The data demonstrate that principal component analysis with machine learning algorithms achieved an overall accuracy above 85% in the diagnosis.

FTIR spectroscopy with machine learning: A new approach to animal DNA polymorphism screening.

Technological advances in recent decades, especially in molecular genetics, have enabled the detection of genetic DNA markers associated with productive characteristics in animals. However, the prospection of polymorphisms based on DNA sequencing is still expensive for the reality of many food-producing regions around the world, such as Brazil, demanding more accessible prospecting methods. In the present study, the Fourier transform infrared spectroscopy (FTIR) and machine learning algorithms were used to identify single nucleotide polymorphism (SNP) in animal DNA. The fragments of bovine DNA with well-known polymorphisms were used as a model. The DNA fragments were produced and genotyped by PCR-RFLP and classified according to the genotype (homozygous or heterozygous). FTIR spectra of DNA fragments were analyzed by principal component analysis (PCA) and machine learning algorithms. The best results exhibited 75-95% accuracy in the classification of bovine genotypes. Therefore, FTIR spectroscopy and multivariate analysis can be used as an alternative tool for prospecting polymorphisms in animal DNA. The method can contribute with studies to identify genetic markers associated with animal production and indirectly with food production itself, and reduce pressure on available natural resources.

Intraspecific differentiation of sandflies specimens by optical spectroscopy and multivariate analysis.

Lutzomyia longipalpis and Lutzomyia cruzi are the main sandflies species involved in the transmission of Leishmania infantum protozoan in Brazil. The morphological characteristics can be used for species identification of males specimens, while females are indistinguishable. Although, sandflies identification is essential to understand vectorial capacity, and susceptibility to infectious agents or insecticides, there is a lack of new strategies for specimen identification. In this study, Fourier transform infrared photoacoustic spectroscopy combined with multivariate analysis identified intraspecific differences between Lutzomyia populations. Successfully group clustering was achieved by principal component analysis. The main differences observed can be related to the protein content of the specimens. A classification with 100% accuracy was obtained using machine learning approach, allowing the identification of sandflies specimens.

Evaluation of rice varieties using LIBS and FTIR techniques associated with PCA and machine learning algorithms.

Laser-induced breakdown spectroscopy (LIBS) for atomic multi-elementary analyses, and Fourier transform infrared spectroscopy (FTIR) for molecular identification, are often suggested as the most versatile spectroscopic techniques. The present work aimed to evaluate the performance of both techniques, LIBS and FTIR, combined with principal component analysis (PCA) and machine learning (ML) algorithms in the detection of the composition analysis and differentiation of four different types of rice, white, brown, black, and red. The two techniques were primarily used to obtain the elemental and molecular qualitative characterization of rice samples. Then, LIBS and FTIR data sets were subjected to PCA and supervised ML analysis to investigate which main chemical features were responsible for nutritional differences for the white (milled) and colored rice samples. In particular, PCA data analysis suggested that protein, fatty acids, and magnesium were the highest contributors to the sample's differentiation. The ML analysis based on this information yielded a 100% level of accuracy, sensitivity, and specificity on sample classification. In conclusion, LIBS and FTIR coupled with multivariate analysis were confirmed as promising tools alternative to traditional analytical techniques for composition analysis and differentiation when subtle chemical variations were observed.

Soybean seed vigor discrimination by using infrared spectroscopy and machine learning algorithms.

A novel approach to distinguish soybean seed vigor based on Fourier transform infrared spectroscopy (FTIR) associated with chemometric methods is presented. Batches with high and low vigor soybean seeds were analyzed. Support vector machine (SVM), K-nearest neighbors (KNN), and discriminant analysis were applied to the raw spectral and reduced-dimensionality data from PCA (principal component analysis). Proteins, fatty acids, and amides were identified as the main molecules responsible for the discrimination of the batches. The cross-validation tests pointed out that high vigor soybean seeds were successfully discriminated from low vigor ones with an accuracy of 100%. These findings indicate FTIR spectroscopy associated with multivariate analysis as a new alternative approach to discriminate seed vigor.

Portland Cement/Acrocomia Aculeata Endocarp Bricks: Thermal Insulation and Mechanical Properties.

In the last few decades, Portland/residue composites have been researched due to their technological and environmental advantages. In this study, residues of Acrocomia aculeata (Jacq.) Lodd endocarp (AE) were introduced in the Portland cement-soil (PC) matrix in different concentrations (0, 5, 10, 15, 20, and 50 wt%) to produce PC/AE bricks. The characterization of the microstructures of the bricks indicate agglomerates of AE particles with increased humidity in small regions distributed throughout the matrix. Mid-infrared and laser-induced breakdown spectroscopy, along with thermogravimetry, indicated that AE contained mainly lignin and cellulose, as well as inorganic chemical elements such as Mg and Si. X-ray studies revealed that AE did not affect the crystallographic properties of the Portland/AE bricks. The findings indicate that the use of AE improved the thermal insulation capability of the composites with a small impact on the compressive strength.