Genetic Algorithms as a Tool for Wavelength Selection in Multivariate Calibration

Jouan-Rimbaud, Delphine; Massart, D.L.; Leardi, Riccardo; Noord, Onno E. de

doi:10.1021/ac00119a015

Cited by 296 publications

(140 citation statements)

References 0 publications

Supporting

Mentioning

134

Contrasting

Unclassified

Order By: Relevance

“…"Mutations" are also produced which force the evaluation of new combinations avoiding saturation with similar sets of events and can further lower the number of variables and fitness values. The process continues until the difference in mean fitness level between successive generations is below a certain threshold, whereupon the GA is terminated to avoid over-training and avoid the risk of over fitting [101][102][103].…”

Section: Genetic Algorithmmentioning

confidence: 99%

Spectral pre and post processing for infrared and Raman spectroscopy of biological tissues and cells

et al. 2016

View full text Add to dashboard Cite

Vibrational Spectroscopy, both infrared absorption and Raman spectroscopy, have attracted increasing attention for biomedical applications, from in vivo and ex vivo disease diagnostics and screening, to in vitro screening of therapeutics. There remain, however, many challenges related to the accuracy of analysis of physically and chemically inhomogeneous samples, across heterogeneous sample sets. Data preprocessing is required to deal with variations in instrumental responses and intrinsic spectral backgrounds and distortions in order to extract reliable spectral data. Data postprocessing is required to extract the most reliable information from the sample sets, based on often very subtle changes in spectra associated with the targeted pathology or biochemical process. This review presents the current understanding of the factors influencing the quality of spectra recorded and the pre-processing steps commonly employed to improve on spectral quality. It further explores some of the most common techniques which have emerged for classification and analysis of the spectral data for biomedical applications. The importance of sample presentation and measurement conditions to yield the highest quality spectra in the first place is emphasised, as is the potential of model simulated datasets to validate both pre-and post-processing protocols.

show abstract

Section: Genetic Algorithmmentioning

confidence: 99%

Spectral pre and post processing for infrared and Raman spectroscopy of biological tissues and cells

et al. 2016

View full text Add to dashboard Cite

show abstract

“…By using this software tool, parallel implementations are presented for three computationally intensive chemometric procedures, namely the selection of variables using the successive projections algorithm (SPA) 16-27 and the genetic algorithm (GA), [16][17][18]22,24,26,28,29 and the use of leave-one-out cross-validation 30-32 for model order selection in partial least squares (PLS). 30,31,[33][34][35] Computational improvements in multivariate calibration and classification tasks are demonstrated.…”

Section: -14mentioning

confidence: 99%

“…24,28,29 In the present work, a genetic algorithm (GA) is employed to select variables for multivariate calibration using MLR (GA-MLR) and classification using LDA (GA-LDA). A standard GA formulation using binary chromosomes is adopted.…”

Section: Parallelization Of the Genetic Algorithmmentioning

confidence: 99%

“…24,28,29 As in SPA, the fitness is evaluated in a separate validation set, in order to avoid overfitting problems. In GA-MLR, the fitness is calculated as the inverse of the root-mean-square error of the MLR model in the validation set.…”

Section: Parallelization Of the Genetic Algorithmmentioning

confidence: 99%

“…[11][12][13][14] The present paper is concerned with the implementation of parallelism using the Matlab Parallel Computing Toolbox, 15 which requires only simple modifications to existing code in order to exploit the benefits of multicore processing. By using this software tool, parallel implementations are presented for three computationally intensive chemometric procedures, namely the selection of variables using the successive projections algorithm (SPA) [16][17][18][19][20][21][22][23][24][25][26][27] and the genetic algorithm (GA), [16][17][18]22,24,26,28,29 and the use of leave-one-out cross-validation [30][31][32] for model order selection in partial least squares (PLS). 30,31,[33][34][35] Computational improvements in multivariate calibration and classification tasks are demonstrated.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi-core computation in chemometrics: case studies of voltammetric and NIR spectrometric analyses

Soares¹,

Galvão²,

Araújo³

et al. 2010

J. Braz. Chem. Soc.

View full text Add to dashboard Cite

A aplicação de técnicas quimiométricas sofisticadas a grandes conjuntos de dados tem se tornado possível devido aos contínuos aprimoramentos tecnológicos em computadores comerciais. Recentemente, tais aprimoramentos têm sido obtidos principalmente através da introdução de processadores com múltiplos núcleos. Contudo, o uso eficiente de hardware com múltiplos núcleos requer o desenvolvimento de software apropriado para computação paralela. Este artigo trata da implementação de paralelismo empregando o Matlab Parallel Computing Toolbox, que requer somente pequenas modificações em códigos quimiométricos já existentes de modo a explorar os benefícios do processamento em múltiplos núcleos. Empregando essa ferramenta de software, mostra-se que implementações paralelas podem proporcionar expressivos ganhos computacionais. Em particular, considera-se o problema de seleção de variáveis empregando o algoritmo das projeções sucessivas e o algoritmo genético, bem como o uso de validação cruzada em mínimos quadrados parciais. Para ilustração, duas aplicações analíticas são apresentadas: determinação de proteína em trigo por espectrometria de reflectância no infravermelho próximo e classificação de óleos vegetais comestíveis por voltametria de onda quadrada. Empregando as implementações propostas para computação paralela, ganhos computacionais de até 204% foram obtidos.The application of sophisticated chemometrics techniques to large datasets has been made possible by continuing technological improvements in off-the-shelf computers. Recently, such improvements have been mainly achieved by the introduction of multi-core processors. However, the efficient use of multi-core hardware requires the development of software that properly address parallel computing. This paper is concerned with the implementation of parallelism using the Matlab Parallel Computing Toolbox, which requires only simple modifications to existing chemometrics code in order to exploit the benefits of multi-core processing. By using this software tool, it is shown that parallel implementations may provide substantial computational gains. In particular, the present study considers the problem of variable selection employing the successive projections algorithm and the genetic algorithm, as well as the use of cross-validation in partial least squares. For demonstration, two analytical applications are presented: determination of protein in wheat by near-infrared reflectance spectrometry and classification of edible vegetable oils by square-wave voltammetry. By using the proposed parallel computing implementations, computational gains of up to 204% were obtained.Keywords: parallel computation, successive projections algorithm, genetic algorithm, partial least squares, voltammetric analysis, near-infrared spectrometric analysis Soares et al. 1627 Vol. 21, No. 9, 2010 IntroductionModern techniques and instrumentation provide ever-growing amounts of data (in terms of variables and samples) that need to be processed for analytical purposes. Hyphenated methods 1 ...

show abstract

Pattern recognition approaches in biomedical and clinical magnetic resonance spectroscopy: a review

El‐Deredy

1997

NMR Biomed.

View full text Add to dashboard Cite

Genetic Algorithms as a Tool for Wavelength Selection in Multivariate Calibration

Cited by 296 publications

References 0 publications

Spectral pre and post processing for infrared and Raman spectroscopy of biological tissues and cells

Spectral pre and post processing for infrared and Raman spectroscopy of biological tissues and cells

Multi-core computation in chemometrics: case studies of voltammetric and NIR spectrometric analyses

Pattern recognition approaches in biomedical and clinical magnetic resonance spectroscopy: a review

Contact Info

Product

Resources

About