Sensitivity, Prediction Uncertainty, and Detection Limit for Artificial Neural Network Calibrations

Autores
Allegrini, Franco; Olivieri, Alejandro Cesar
Año de publicación
2016
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
With the proliferation of multivariate calibration methods based on artificial neural networks, expressions for the estimation of figures of merit such as sensitivity, prediction uncertainty, and detection limit are urgently needed. This would bring nonlinear multivariate calibration methodologies to the same status as the linear counterparts in terms of comparability. Currently only the average prediction error or the ratio of performance to deviation for a test sample set is employed to characterize and promote neural network calibrations. It is clear that additional information is required. We report for the first time expressions that easily allow one to compute three relevant figures: (1) the sensitivity, which turns out to be sample-dependent, as expected, (2) the prediction uncertainty, and (3) the detection limit. The approach resembles that employed for linear multivariate calibration, i.e., partial least-squares regression, specifically adapted to neural network calibration scenarios. As usual, both simulated and real (near-infrared) spectral data sets serve to illustrate the proposal.
Fil: Allegrini, Franco. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario. Instituto de Química Rosario. Universidad Nacional de Rosario. Facultad de Ciencias Bioquímicas y Farmacéuticas. Instituto de Química Rosario; Argentina. Universidad Nacional de Rosario. Facultad de Ciencias Bioquímicas y Farmacéuticas. Departamento de Química Analítica; Argentina
Fil: Olivieri, Alejandro Cesar. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario. Instituto de Química Rosario. Universidad Nacional de Rosario. Facultad de Ciencias Bioquímicas y Farmacéuticas. Instituto de Química Rosario; Argentina. Universidad Nacional de Rosario. Facultad de Ciencias Bioquímicas y Farmacéuticas. Departamento de Química Analítica; Argentina
Materia
Artifitial Neural Networks calibration
Sensitivity
Limit of detection
Prediction uncertainty
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/52696

id CONICETDig_ce37dbf4f36380c4cf1acdbcc1b5bc2c
oai_identifier_str oai:ri.conicet.gov.ar:11336/52696
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Sensitivity, Prediction Uncertainty, and Detection Limit for Artificial Neural Network CalibrationsAllegrini, FrancoOlivieri, Alejandro CesarArtifitial Neural Networks calibrationSensitivityLimit of detectionPrediction uncertaintyhttps://purl.org/becyt/ford/1.4https://purl.org/becyt/ford/1With the proliferation of multivariate calibration methods based on artificial neural networks, expressions for the estimation of figures of merit such as sensitivity, prediction uncertainty, and detection limit are urgently needed. This would bring nonlinear multivariate calibration methodologies to the same status as the linear counterparts in terms of comparability. Currently only the average prediction error or the ratio of performance to deviation for a test sample set is employed to characterize and promote neural network calibrations. It is clear that additional information is required. We report for the first time expressions that easily allow one to compute three relevant figures: (1) the sensitivity, which turns out to be sample-dependent, as expected, (2) the prediction uncertainty, and (3) the detection limit. The approach resembles that employed for linear multivariate calibration, i.e., partial least-squares regression, specifically adapted to neural network calibration scenarios. As usual, both simulated and real (near-infrared) spectral data sets serve to illustrate the proposal.Fil: Allegrini, Franco. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario. Instituto de Química Rosario. Universidad Nacional de Rosario. Facultad de Ciencias Bioquímicas y Farmacéuticas. Instituto de Química Rosario; Argentina. Universidad Nacional de Rosario. Facultad de Ciencias Bioquímicas y Farmacéuticas. Departamento de Química Analítica; ArgentinaFil: Olivieri, Alejandro Cesar. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario. Instituto de Química Rosario. Universidad Nacional de Rosario. Facultad de Ciencias Bioquímicas y Farmacéuticas. Instituto de Química Rosario; Argentina. Universidad Nacional de Rosario. Facultad de Ciencias Bioquímicas y Farmacéuticas. Departamento de Química Analítica; ArgentinaAmerican Chemical Society2016-08info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/52696Allegrini, Franco; Olivieri, Alejandro Cesar; Sensitivity, Prediction Uncertainty, and Detection Limit for Artificial Neural Network Calibrations; American Chemical Society; Analytical Chemistry; 88; 15; 8-2016; 7807-78120003-2700CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://pubs.acs.org/doi/10.1021/acs.analchem.6b01857info:eu-repo/semantics/altIdentifier/doi/10.1021/acs.analchem.6b01857info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T09:41:54Zoai:ri.conicet.gov.ar:11336/52696instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-29 09:41:54.886CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Sensitivity, Prediction Uncertainty, and Detection Limit for Artificial Neural Network Calibrations
title Sensitivity, Prediction Uncertainty, and Detection Limit for Artificial Neural Network Calibrations
spellingShingle Sensitivity, Prediction Uncertainty, and Detection Limit for Artificial Neural Network Calibrations
Allegrini, Franco
Artifitial Neural Networks calibration
Sensitivity
Limit of detection
Prediction uncertainty
title_short Sensitivity, Prediction Uncertainty, and Detection Limit for Artificial Neural Network Calibrations
title_full Sensitivity, Prediction Uncertainty, and Detection Limit for Artificial Neural Network Calibrations
title_fullStr Sensitivity, Prediction Uncertainty, and Detection Limit for Artificial Neural Network Calibrations
title_full_unstemmed Sensitivity, Prediction Uncertainty, and Detection Limit for Artificial Neural Network Calibrations
title_sort Sensitivity, Prediction Uncertainty, and Detection Limit for Artificial Neural Network Calibrations
dc.creator.none.fl_str_mv Allegrini, Franco
Olivieri, Alejandro Cesar
author Allegrini, Franco
author_facet Allegrini, Franco
Olivieri, Alejandro Cesar
author_role author
author2 Olivieri, Alejandro Cesar
author2_role author
dc.subject.none.fl_str_mv Artifitial Neural Networks calibration
Sensitivity
Limit of detection
Prediction uncertainty
topic Artifitial Neural Networks calibration
Sensitivity
Limit of detection
Prediction uncertainty
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.4
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv With the proliferation of multivariate calibration methods based on artificial neural networks, expressions for the estimation of figures of merit such as sensitivity, prediction uncertainty, and detection limit are urgently needed. This would bring nonlinear multivariate calibration methodologies to the same status as the linear counterparts in terms of comparability. Currently only the average prediction error or the ratio of performance to deviation for a test sample set is employed to characterize and promote neural network calibrations. It is clear that additional information is required. We report for the first time expressions that easily allow one to compute three relevant figures: (1) the sensitivity, which turns out to be sample-dependent, as expected, (2) the prediction uncertainty, and (3) the detection limit. The approach resembles that employed for linear multivariate calibration, i.e., partial least-squares regression, specifically adapted to neural network calibration scenarios. As usual, both simulated and real (near-infrared) spectral data sets serve to illustrate the proposal.
Fil: Allegrini, Franco. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario. Instituto de Química Rosario. Universidad Nacional de Rosario. Facultad de Ciencias Bioquímicas y Farmacéuticas. Instituto de Química Rosario; Argentina. Universidad Nacional de Rosario. Facultad de Ciencias Bioquímicas y Farmacéuticas. Departamento de Química Analítica; Argentina
Fil: Olivieri, Alejandro Cesar. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Rosario. Instituto de Química Rosario. Universidad Nacional de Rosario. Facultad de Ciencias Bioquímicas y Farmacéuticas. Instituto de Química Rosario; Argentina. Universidad Nacional de Rosario. Facultad de Ciencias Bioquímicas y Farmacéuticas. Departamento de Química Analítica; Argentina
description With the proliferation of multivariate calibration methods based on artificial neural networks, expressions for the estimation of figures of merit such as sensitivity, prediction uncertainty, and detection limit are urgently needed. This would bring nonlinear multivariate calibration methodologies to the same status as the linear counterparts in terms of comparability. Currently only the average prediction error or the ratio of performance to deviation for a test sample set is employed to characterize and promote neural network calibrations. It is clear that additional information is required. We report for the first time expressions that easily allow one to compute three relevant figures: (1) the sensitivity, which turns out to be sample-dependent, as expected, (2) the prediction uncertainty, and (3) the detection limit. The approach resembles that employed for linear multivariate calibration, i.e., partial least-squares regression, specifically adapted to neural network calibration scenarios. As usual, both simulated and real (near-infrared) spectral data sets serve to illustrate the proposal.
publishDate 2016
dc.date.none.fl_str_mv 2016-08
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/52696
Allegrini, Franco; Olivieri, Alejandro Cesar; Sensitivity, Prediction Uncertainty, and Detection Limit for Artificial Neural Network Calibrations; American Chemical Society; Analytical Chemistry; 88; 15; 8-2016; 7807-7812
0003-2700
CONICET Digital
CONICET
url http://hdl.handle.net/11336/52696
identifier_str_mv Allegrini, Franco; Olivieri, Alejandro Cesar; Sensitivity, Prediction Uncertainty, and Detection Limit for Artificial Neural Network Calibrations; American Chemical Society; Analytical Chemistry; 88; 15; 8-2016; 7807-7812
0003-2700
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://pubs.acs.org/doi/10.1021/acs.analchem.6b01857
info:eu-repo/semantics/altIdentifier/doi/10.1021/acs.analchem.6b01857
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
application/pdf
dc.publisher.none.fl_str_mv American Chemical Society
publisher.none.fl_str_mv American Chemical Society
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1844613321908551680
score 13.070432