Sensitivity and generalized analytical sensitivity expressions for quantitative analysis using convolutional neural networks

Standard

Sensitivity and generalized analytical sensitivity expressions for quantitative analysis using convolutional neural networks. / Shariat, Kourosh; Kirsanov, Dmitry; Olivieri, Alejandro C.; Parastar, Hadi.

в: Analytica Chimica Acta, Том 1192, 338697, 2022.

Результаты исследований: Научные публикации в периодических изданиях › статья › Рецензирование

BibTeX

@article{58cb3d04277b494d96afc6d192727756,

title = "Sensitivity and generalized analytical sensitivity expressions for quantitative analysis using convolutional neural networks",

abstract = "In recent years, convolutional neural networks and deep neural networks have been used extensively in various fields of analytical chemistry. The use of these models for calibration tasks has been highly effective; however, few reports have been published on their properties and characteristics of analytical figures of merit. Currently, most performance measures for these types of networks only incorporate some function of prediction error. While useful, these measures are incomplete and cannot be used as an objective comparison among different models. In this report, a new method for calculating the sensitivity of any type of neural network is proposed and studied on both simulated and real datasets. Generalized analytical sensitivity is defined and calculated for neural networks as an additional figure of merit. Moreover, the dependence of convolutional neural networks on regularization dataset size is studied and compared with other conventional calibration methods.",

keywords = "Analytical figures of merit, Convolutional neural networks, Deep learning, Sensitivity",

author = "Kourosh Shariat and Dmitry Kirsanov and Olivieri, {Alejandro C.} and Hadi Parastar",

note = "Publisher Copyright: {\textcopyright} 2021 Elsevier B.V.",

year = "2022",

doi = "10.1016/j.aca.2021.338697",

language = "English",

volume = "1192",

journal = "Analytica Chimica Acta",

issn = "0003-2670",

publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Sensitivity and generalized analytical sensitivity expressions for quantitative analysis using convolutional neural networks

AU - Shariat, Kourosh

AU - Kirsanov, Dmitry

AU - Olivieri, Alejandro C.

AU - Parastar, Hadi

PY - 2022

Y1 - 2022

N2 - In recent years, convolutional neural networks and deep neural networks have been used extensively in various fields of analytical chemistry. The use of these models for calibration tasks has been highly effective; however, few reports have been published on their properties and characteristics of analytical figures of merit. Currently, most performance measures for these types of networks only incorporate some function of prediction error. While useful, these measures are incomplete and cannot be used as an objective comparison among different models. In this report, a new method for calculating the sensitivity of any type of neural network is proposed and studied on both simulated and real datasets. Generalized analytical sensitivity is defined and calculated for neural networks as an additional figure of merit. Moreover, the dependence of convolutional neural networks on regularization dataset size is studied and compared with other conventional calibration methods.

AB - In recent years, convolutional neural networks and deep neural networks have been used extensively in various fields of analytical chemistry. The use of these models for calibration tasks has been highly effective; however, few reports have been published on their properties and characteristics of analytical figures of merit. Currently, most performance measures for these types of networks only incorporate some function of prediction error. While useful, these measures are incomplete and cannot be used as an objective comparison among different models. In this report, a new method for calculating the sensitivity of any type of neural network is proposed and studied on both simulated and real datasets. Generalized analytical sensitivity is defined and calculated for neural networks as an additional figure of merit. Moreover, the dependence of convolutional neural networks on regularization dataset size is studied and compared with other conventional calibration methods.

KW - Analytical figures of merit

KW - Convolutional neural networks

KW - Deep learning

KW - Sensitivity

UR - http://www.scopus.com/inward/record.url?scp=85107660467&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/fffd388e-5c6c-33ff-84c6-c655deda4cad/

U2 - 10.1016/j.aca.2021.338697

DO - 10.1016/j.aca.2021.338697

M3 - Article

AN - SCOPUS:85107660467

VL - 1192

JO - Analytica Chimica Acta

JF - Analytica Chimica Acta

SN - 0003-2670

M1 - 338697

ER -

ID: 85205549