Classification of Brazilian soils by using LIBS and variable selection in the wavelet domain

Pontes, Márcio José Coelho; Cortez, Juliana; Galvão, Roberto Kawakami Harrop; Pasquini, Célio; Araújo, Mário César Ugulino de; Coelho, Ricardo Marques; Chiba, Márcio Koiti; Abreu, Mônica Ferreira de; Madari, B. E.

doi:10.1016/j.aca.2009.03.001

Cited by 107 publications

(59 citation statements)

References 29 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Other options with inherent advantages for the determination of halogens in biological samples are direct sampling [136], electrothermal vaporization [204,205], and laser ablation coupled with ICP-MS [103,206,207]. Additionally, although few applications were found for determination of halogens, laser-induced-breakdown spectrometry can be considered a potential detection technique mainly regarding determination of halogens in pharmaceutical products [208] because it allows analysis almost free of a sample preparation step [209,210]. These methods have been less used probably owing to the low availability for many laboratories and also because they require greater expertise.…”

Section: Final Considerationsmentioning

confidence: 99%

Analytical methods for the determination of halogens in bioanalytical sciences: a review

et al. 2013

View full text Add to dashboard Cite

Fluorine, chlorine, bromine, and iodine have been studied in biological samples and other related matrices owing to the need to understand the biochemical effects in living organisms. In this review, the works published in last 20 years are covered, and the main topics related to sample preparation methods and analytical techniques commonly used for fluorine, chlorine, bromine, and iodine determination in biological samples, food, drugs, and plants used as food or with medical applications are discussed. The commonest sample preparation methods, as extraction and decomposition using combustion and pyrohydrolysis, are reviewed, as well as spectrometric and electroanalytical techniques, spectrophotometry, total reflection X-ray fluorescence, neutron activation analysis, and separation systems using chromatography and electrophoresis. On this aspect, the main analytical challenges and drawbacks are highlighted. A discussion related to the availability of certified reference materials for evaluation of accuracy is also included, as well as a discussion of the official methods used as references for the determination of halogens in the samples covered in this review.

show abstract

Section: Final Considerationsmentioning

confidence: 99%

Analytical methods for the determination of halogens in bioanalytical sciences: a review

et al. 2013

View full text Add to dashboard Cite

show abstract

“…10,[14][15][16][17][18]25 With the transformation by wavelet, the information contained in original spectra data can be represented by the wavelet coe±cients. Compression is achieved by suppressing the wavelet coe±cients that do not hold valuable information.…”

Section: Feature Selection In Wavelet Domainmentioning

confidence: 99%

Wavelet-based classification and influence matrix analysis method for the fast discrimination of Chinese herbal medicines according to the geographical origins with near infrared spectroscopy

Wenlong

2014

J. Innov. Opt. Health Sci.

View full text Add to dashboard Cite

A discriminant analysis technique using wavelet transformation (WT) and in°uence matrix analysis (CAIMAN) method is proposed for the near infrared (NIR) spectroscopy classi¯-cation. In the proposed methodology, NIR spectra are decomposed by WT for data compression and a forward feature selection is further employed to extract the relevant information from the wavelet coe±cients, reducing both classi¯cation errors and model complexity. A discriminant-CAIMAN (D-CAIMAN) method is utilized to build the classi¯cation model in wavelet domain on the basis of reduced wavelet coe±cients of spectral variables. NIR spectra data set of 265 salviae miltiorrhizae radix samples from 9 di®erent geographical origins is used as an example to test the classi¯cation performance of the algorithm. For a comparison, k-nearest neighbor (KNN), linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA) methods are also employed. D-CAIMAN with wavelet-based feature selection (WD-CAIMAN) method shows the best performance, achieving the total classi¯cation rate of 100% in both cross-validation set and prediction set. It is worth noting that the WD-CAIMAN classi¯er also shows improved sensitivity, selectivity and model interpretability in the classi¯cations.

show abstract

“…In order to reduce computational workload in the modelbuilding phase, a preliminary compression procedure was applied to the wavelet coefficients. Compression was carried out by discarding the smallest wavelet coefficients (in absolute value) while retaining 99% of the explained variance [18].…”

Section: Application Examplementioning

confidence: 99%

Combination of Models Obtained by Regression in the Wavelet Domain

Pinto¹,

Galvão²

2010

TEMA - Tendências Em Matemática Aplicada E Computacional

View full text Add to dashboard Cite

Abstract. The wavelet transform is a useful tool to preprocess and compress datasets for linear regression modelling. However, the prediction performance of the resulting model depends on the choice of wavelet filter and number of decomposition levels, which may not be a straightforward task. This paper proposes an alternative approach, which consists of combining models obtained from different wavelet decompositions of the dataset. For this purpose, a method is developed to convert wavelet regression models back to the original domain. The proposed approach is illustrated in a case study involving the determination of density in gasoline samples by using infrared spectroscopy. The results are favourably compared to those obtained by using individual wavelet decompositions.Keywords. Wavelet Transform, Combination of Models, Multiple Linear Regression. IntrodutionThe wavelet transform (WT) has been used in a variety of signal processing applications, such as filtering [10], compression [24] and classification [8]. In particular, the WT has become a popular tool in a field of Analytical Chemistry known as Multivariate Calibration (MC) [7,15]. The MC problem consists of building a mathematical model for estimation of physical or chemical properties of a sample from indirect measurements. Such measurements could be, for instance, emission, absorption or reflection intensities acquired over different wavelengths [20]. Applications of MC include determination of metals in steel alloys [16], analysis of composition of pharmaceutical formulae [5] and prediction of fuel properties [3], among many others.

show abstract

Classification of Brazilian soils by using LIBS and variable selection in the wavelet domain

Cited by 107 publications

References 29 publications

Analytical methods for the determination of halogens in bioanalytical sciences: a review

Analytical methods for the determination of halogens in bioanalytical sciences: a review

Wavelet-based classification and influence matrix analysis method for the fast discrimination of Chinese herbal medicines according to the geographical origins with near infrared spectroscopy

Combination of Models Obtained by Regression in the Wavelet Domain

Contact Info

Product

Resources

About