Selection of robust variables for transfer of classification models employing the successive projections algorithm

Milanez, Karla Danielle Tavares de Melo; Nóbrega, Thiago César Araújo; Nascimento, Danielle Silva Do; Galvão, Roberto Kawakami Harrop; Pontes, Márcio José Coelho

doi:10.1016/j.aca.2017.07.037

Cited by 25 publications

(12 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The (SPA) is an emerging band extraction method. Each selected band has the smallest linear relationship with the previously selected band ( Milanez, Araújo Nóbrega, Silva Nascimento, GalvãO, & Pontes, 2017 ). A band combination was selected to maximize the representation of the original data by minimizing the root mean square error (RMSE).…”

Section: Methodsmentioning

confidence: 99%

Application of spectral features for separating homochromatic foreign matter from mixed congee

et al. 2021

View full text Add to dashboard Cite

Highlights A method that can separate homochromatic FM in mixed congee was proposed. Spectral features of FM and mixed congee were extracted to build recognition model. The SVM model achieved high identification rates (99.17%) for homochromatic FM. The proposed method is better than computer vision in separating homochromatic FM.

show abstract

Section: Methodsmentioning

confidence: 99%

Application of spectral features for separating homochromatic foreign matter from mixed congee

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The response informative intervals were arranged in a matrix X, with m rows (sample number) and j columns (LIBS variables accounted j −1 column and Cd reference value accounted 1 column) corresponding to the samples and variables, respectively. The main procedures of SPA are summarized ( Liu et al, 2009 ; Milanez et al, 2017 ) that (1) set the maximum number of variables p to be selected, (2) one of j columns was yielded to calculate the projection of the remaining j −1 column (the process is expressed as projection operations in Figure 2 ), and the columns displaying the least collinearity and maximum projection value were projected onto the orthogonal subspace, (3) if total number of variables in the subspace of the previously selected variable = p , restarting (2) procedure from other columns of X, (4) the optimal initial variable and number of variables can be determined on the basis of the smallest RMSECV in a separate validation set.…”

Section: Methodsmentioning

confidence: 99%

Quantitative Analysis of Cadmium in Tobacco Roots Using Laser-Induced Breakdown Spectroscopy With Variable Index and Chemometrics

et al. 2018

View full text Add to dashboard Cite

The study investigated some new developed variable indices and chemometrics for the fast detection of cadmium (Cd) in tobacco root samples by laser-induced breakdown spectroscopy. The variables selection methods of interval partial least squares (iPLS), backward interval partial least squares (BiPLS), and successive projections algorithm (SPA) were used to locate the optimal Cd emission line for univariate analysis and to select the maximal relevant variables for multivariate analysis. iPLS and BiPLS located 10 Cd emission lines to establish univariate analysis models. Univariate analysis model based on Cd I (508.58 nm) performed best with the coefficient of determination of prediction (Rp2) of 0.9426 and root mean square error of prediction (RMSEP) of 1.060 mg g−1. We developed two new variable indices to remove negative effects for Cd content prediction, including Index1 = (I508.58 + I361.05)/2 × I466.23 and Index2 = I508.58/I466.23 based on Cd emission lines at 508.58, 361.05, and 466.23 nm. Univariate model based on Index2 obtained better result (Rp2 of 0.9502 and RMSEP of 0.988 mg g−1) than univariate analysis based on the best Cd emission line at 508.58 nm. PLS and support vector machines (SVM) were adopted and compared for multivariate analysis. The results of multivariate analysis outperformed univariate analysis and the best quantitative model was achieved by the iPLS-SVM model (Rc2 of 0.9820, RMSECV of 0.214 mg g−1, Rp2 of 0.9759, and RMSEP of 0.712 mg g−1) using the maximal relevant variables in the range of 474–526 nm. The results indicated that LIBS coupled with new developed variable index and chemometrics could provide a feasible, effective, and economical approach for fast detecting Cd in tobacco roots.

show abstract

“…Fluorescence spectroscopy has already been used in the detection 18 , structural investigation 19 , 20 and in the construction of a DNA biosensor for E. coli 21 . Chemometric methods such as Linear Discriminant Analysis (LDA) 22 , Quadratic Discriminant Analysis (QDA) 23 and Support Vector Machines (SVM) 24 , coupled with the dimensionality reduction algorithm: Principal Component Analysis (PCA) 25 , 26 ,and variable selection algorithms: Genetic Algorithm (GA) 27 and Successive Projections Algorithm (SPA) 28 , tend to enhance the spectroscopic techniques 29 – 31 .…”

Section: Introductionmentioning

confidence: 99%

Identification of resistance in Escherichia coli and Klebsiella pneumoniae using excitation-emission matrix fluorescence spectroscopy and multivariate analysis

Costa

Bezerra

Neto

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Klebsiella pneumoniae and Escherichia coli are part of the Enterobacteriaceae family, being common sources of community and hospital infections and having high antimicrobial resistance. This resistance profile has become the main problem of public health infections. Determining whether a bacterium has resistance is critical to the correct treatment of the patient. Currently the method for determination of bacterial resistance used in laboratory routine is the antibiogram, whose time to obtain the results can vary from 1 to 3 days. An alternative method to perform this determination faster is excitation-emission matrix (EEM) fluorescence spectroscopy combined with multivariate classification methods. In this paper, Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA) and Support Vector Machines (SVM), coupled with dimensionality reduction and variable selection algorithms: Principal Component Analysis (PCA), Genetic Algorithm (GA), and the Successive Projections Algorithm (SPA) were used. The most satisfactory models achieved sensitivity and specificity rates of 100% for all classes, both for E. coli and for K. pneumoniae. This finding demonstrates that the proposed methodology has promising potential in routine analyzes, streamlining the results and increasing the chances of treatment efficiency. The Enterobacteriaceae family is one of the most clinically prominent bacteria groups. One of the main gramnegative pathogen is Klebsiella pneumoniae (K. pneumoniae), which causes opportunistic infections, such as pneumonia, sepsis and inflammation of the urinary tract 1. Another gram-negative that compose the entereobacteriaceae family is Escherichia coli, which are not typically pathogenic to humans and have the ability to cause several diseases in different sites including gastrointestinal tract, the renal system and the central nervous system 2,3. Antibiotic therapy induces the selection of resistant bacteria 4 , which generate environmental and health hazards, and economical risk. Over the last decades, several bacterial strains have become progressively resistant to antimicrobial agents 5. Bacteria may have natural or acquired resistance. Among the genetic variations that confer resistance in bacteria, the main ones are extended spectrum betalactamases 6 (ESBL), AmpC production, Carbapenemases production 7 , KPC group and MBL group 5. Currently, the standard detection method is culture-based, which is time-consuming and labor intensive, providing a slow detection 8. Other methods can be used to obtain faster results, such as low cytometry 9 , electrochemical detection 10 , and polymerase chain reaction (PCR) 11. Near infrared (NIR) 12 , Raman 13 and Fourier transform infrared (FTIR) spectroscopy 14 have been also reported for these applications.

show abstract

Selection of robust variables for transfer of classification models employing the successive projections algorithm

Cited by 25 publications

References 44 publications

Application of spectral features for separating homochromatic foreign matter from mixed congee

Application of spectral features for separating homochromatic foreign matter from mixed congee

Quantitative Analysis of Cadmium in Tobacco Roots Using Laser-Induced Breakdown Spectroscopy With Variable Index and Chemometrics

Identification of resistance in Escherichia coli and Klebsiella pneumoniae using excitation-emission matrix fluorescence spectroscopy and multivariate analysis

Contact Info

Product

Resources

About