Serveur d'exploration sur le LRGP

Attention, ce site est en cours de développement !
Attention, site généré par des moyens informatiques à partir de corpus bruts.
Les informations ne sont donc pas validées.

Neural network frames. Application to biochemical kinetic diagnosis

Identifieur interne : 002879 ( Main/Exploration ); précédent : 002878; suivant : 002880

Neural network frames. Application to biochemical kinetic diagnosis

Auteurs : O. Iordache [France] ; J. P. Corriou [France] ; L. Garrido-Sanchez [France, Mexique] ; C. Fonteix [France] ; Daniel Tondeur [France]

Source :

RBID : ISTEX:0FA91326A62B55830D3C6B1762335C017EFFB795

Descripteurs français

English descriptors

Abstract

Abstract: The diagnosis of chemical kinetics in chemical plants can be viewed as a process of classification. Recorded data can be associated with different types of kinetic models and the type of kinetics can be classified by comparison with previously recorded data. A new frame for a neural network (NN) is proposed in order to carry out the classification. The potentialities of this adaptive, hierarchized frame organized as a “polystochastic” model have been investigated here. The underlying approach is based on the use of distances between two paths of observed kinetic data. A matrix of distances results from a set of possible kinetic models, and algorithms for classifying models are developed using this matrix. Another type of distance, an informational type, is proposed between two matrices of distances so as to compare one classification with another or with a reference classification. Training the net by methods based on informational criteria is proposed and tested. By a fast adaptive procedure, the small number of resulting weights are adjusted to account for reference cases. The utility of the net is illustrated via the kinetic modeling of a fermentation process. A comparison with another conventional net is also made.

Url:
DOI: 10.1016/0098-1354(93)80091-Z


Affiliations:


Links toward previous steps (curation, corpus...)


Le document en format XML

<record>
<TEI wicri:istexFullTextTei="biblStruct">
<teiHeader>
<fileDesc>
<titleStmt>
<title>Neural network frames. Application to biochemical kinetic diagnosis</title>
<author>
<name sortKey="Iordache, O" sort="Iordache, O" uniqKey="Iordache O" first="O." last="Iordache">O. Iordache</name>
</author>
<author>
<name sortKey="Corriou, J P" sort="Corriou, J P" uniqKey="Corriou J" first="J. P." last="Corriou">J. P. Corriou</name>
</author>
<author>
<name sortKey="Garrido Sanchez, L" sort="Garrido Sanchez, L" uniqKey="Garrido Sanchez L" first="L." last="Garrido-Sanchez">L. Garrido-Sanchez</name>
</author>
<author>
<name sortKey="Fonteix, C" sort="Fonteix, C" uniqKey="Fonteix C" first="C." last="Fonteix">C. Fonteix</name>
</author>
<author>
<name sortKey="Tondeur, D" sort="Tondeur, D" uniqKey="Tondeur D" first="D." last="Tondeur">Daniel Tondeur</name>
<affiliation>
<country>France</country>
<placeName>
<settlement type="city">Nancy</settlement>
<region type="region" nuts="2">Grand Est</region>
<region type="region" nuts="2">Lorraine (région)</region>
</placeName>
<orgName type="laboratoire" n="5">Laboratoire réactions et génie des procédés</orgName>
<orgName type="university">Université de Lorraine</orgName>
<orgName type="institution">Centre national de la recherche scientifique</orgName>
</affiliation>
</author>
</titleStmt>
<publicationStmt>
<idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:0FA91326A62B55830D3C6B1762335C017EFFB795</idno>
<date when="1993" year="1993">1993</date>
<idno type="doi">10.1016/0098-1354(93)80091-Z</idno>
<idno type="url">https://api.istex.fr/document/0FA91326A62B55830D3C6B1762335C017EFFB795/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">000C70</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">000C70</idno>
<idno type="wicri:Area/Istex/Curation">000C70</idno>
<idno type="wicri:Area/Istex/Checkpoint">001030</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">001030</idno>
<idno type="wicri:doubleKey">0098-1354:1993:Iordache O:neural:network:frames</idno>
<idno type="wicri:Area/Main/Merge">002E57</idno>
<idno type="wicri:source">INIST</idno>
<idno type="RBID">Pascal:94-0034164</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">001018</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000F27</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">001007</idno>
<idno type="wicri:explorRef" wicri:stream="PascalFrancis" wicri:step="Checkpoint">001007</idno>
<idno type="wicri:doubleKey">0098-1354:1993:Iordache O:neural:network:frames</idno>
<idno type="wicri:Area/Main/Merge">002F87</idno>
<idno type="wicri:Area/Main/Curation">002879</idno>
<idno type="wicri:Area/Main/Exploration">002879</idno>
</publicationStmt>
<sourceDesc>
<biblStruct>
<analytic>
<title level="a">Neural network frames. Application to biochemical kinetic diagnosis</title>
<author>
<name sortKey="Iordache, O" sort="Iordache, O" uniqKey="Iordache O" first="O." last="Iordache">O. Iordache</name>
<affiliation wicri:level="3">
<country xml:lang="fr">France</country>
<wicri:regionArea>Laboratoire des Sciences du Génie Chimique, ENSIC, 1 rue Grandville, BP 451, 54001 Nancy Cedex</wicri:regionArea>
<placeName>
<region type="region" nuts="2">Grand Est</region>
<region type="old region" nuts="2">Lorraine (région)</region>
<settlement type="city">Nancy</settlement>
</placeName>
</affiliation>
</author>
<author>
<name sortKey="Corriou, J P" sort="Corriou, J P" uniqKey="Corriou J" first="J. P." last="Corriou">J. P. Corriou</name>
<affiliation></affiliation>
<affiliation wicri:level="3">
<country xml:lang="fr">France</country>
<wicri:regionArea>Laboratoire des Sciences du Génie Chimique, ENSIC, 1 rue Grandville, BP 451, 54001 Nancy Cedex</wicri:regionArea>
<placeName>
<region type="region" nuts="2">Grand Est</region>
<region type="old region" nuts="2">Lorraine (région)</region>
<settlement type="city">Nancy</settlement>
</placeName>
</affiliation>
</author>
<author>
<name sortKey="Garrido Sanchez, L" sort="Garrido Sanchez, L" uniqKey="Garrido Sanchez L" first="L." last="Garrido-Sanchez">L. Garrido-Sanchez</name>
<affiliation wicri:level="3">
<country xml:lang="fr">France</country>
<wicri:regionArea>Laboratoire des Sciences du Génie Chimique, ENSIC, 1 rue Grandville, BP 451, 54001 Nancy Cedex</wicri:regionArea>
<placeName>
<region type="region" nuts="2">Grand Est</region>
<region type="old region" nuts="2">Lorraine (région)</region>
<settlement type="city">Nancy</settlement>
</placeName>
</affiliation>
<affiliation wicri:level="1">
<country xml:lang="fr">Mexique</country>
<wicri:regionArea>CIATEJ, Normalistas 800, BP 451, 44270 Guadalajara</wicri:regionArea>
<wicri:noRegion>44270 Guadalajara</wicri:noRegion>
</affiliation>
</author>
<author>
<name sortKey="Fonteix, C" sort="Fonteix, C" uniqKey="Fonteix C" first="C." last="Fonteix">C. Fonteix</name>
<affiliation wicri:level="3">
<country xml:lang="fr">France</country>
<wicri:regionArea>Laboratoire des Sciences du Génie Chimique, ENSIC, 1 rue Grandville, BP 451, 54001 Nancy Cedex</wicri:regionArea>
<placeName>
<region type="region" nuts="2">Grand Est</region>
<region type="old region" nuts="2">Lorraine (région)</region>
<settlement type="city">Nancy</settlement>
</placeName>
</affiliation>
</author>
<author>
<name sortKey="Tondeur, D" sort="Tondeur, D" uniqKey="Tondeur D" first="D." last="Tondeur">Daniel Tondeur</name>
<affiliation wicri:level="3">
<country xml:lang="fr">France</country>
<wicri:regionArea>Laboratoire des Sciences du Génie Chimique, ENSIC, 1 rue Grandville, BP 451, 54001 Nancy Cedex</wicri:regionArea>
<placeName>
<region type="region" nuts="2">Grand Est</region>
<region type="old region" nuts="2">Lorraine (région)</region>
<settlement type="city">Nancy</settlement>
</placeName>
<placeName>
<settlement type="city">Nancy</settlement>
<region type="region" nuts="2">Grand Est</region>
<region type="region" nuts="2">Lorraine (région)</region>
</placeName>
<orgName type="laboratoire" n="5">Laboratoire réactions et génie des procédés</orgName>
<orgName type="university">Université de Lorraine</orgName>
<orgName type="institution">Centre national de la recherche scientifique</orgName>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series>
<title level="j">Computers and Chemical Engineering</title>
<title level="j" type="abbrev">CACE</title>
<idno type="ISSN">0098-1354</idno>
<imprint>
<publisher>ELSEVIER</publisher>
<date type="published" when="1993">1993</date>
<biblScope unit="volume">17</biblScope>
<biblScope unit="issue">11</biblScope>
<biblScope unit="page" from="1101">1101</biblScope>
<biblScope unit="page" to="1113">1113</biblScope>
</imprint>
<idno type="ISSN">0098-1354</idno>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt>
<idno type="ISSN">0098-1354</idno>
</seriesStmt>
</fileDesc>
<profileDesc>
<textClass>
<keywords scheme="KwdEn" xml:lang="en">
<term>Aberrant case</term>
<term>Academic press</term>
<term>Adaptive</term>
<term>Alarm state</term>
<term>Algorithm</term>
<term>Annealing methods</term>
<term>Biomass</term>
<term>Biomass concentration</term>
<term>Black pixel</term>
<term>Cbio</term>
<term>Cbio cbio</term>
<term>Classification</term>
<term>Classification algorithm</term>
<term>Classification index</term>
<term>Classification process</term>
<term>Coefficient</term>
<term>Complexity level</term>
<term>Complexity levels</term>
<term>Composition rule</term>
<term>Different classifications</term>
<term>Different conditioning levels</term>
<term>Different levels</term>
<term>Different paths</term>
<term>Different types</term>
<term>Dilution rate</term>
<term>Distance matrices</term>
<term>Distances results</term>
<term>Equal weight coefficients</term>
<term>Ergodic behaviour</term>
<term>Experimental data</term>
<term>Expert system</term>
<term>Fermentation</term>
<term>First step</term>
<term>General frame</term>
<term>Genetic algorithms</term>
<term>Good training example</term>
<term>Hierarchical</term>
<term>Hierarchical order</term>
<term>Hierarchical organization</term>
<term>Infinite memory</term>
<term>Information theory</term>
<term>Informational criteria</term>
<term>Informational type</term>
<term>Inhibition</term>
<term>Input layer</term>
<term>Investigation method</term>
<term>Iordache</term>
<term>Kinetic</term>
<term>Kinetic data</term>
<term>Kinetic diagnosis</term>
<term>Kinetic phenomenon</term>
<term>Kinetic regime</term>
<term>Kinetic regimes</term>
<term>Kinetics</term>
<term>Knowledge representation</term>
<term>Lactic acid production</term>
<term>Matrix</term>
<term>Minimum distance</term>
<term>Modeling method</term>
<term>Models</term>
<term>Neural</term>
<term>Neural network</term>
<term>Neural network frames</term>
<term>Neural network frames table</term>
<term>Neural networks</term>
<term>Neuron</term>
<term>Next cycle</term>
<term>Next level</term>
<term>Numerical experiments</term>
<term>Numerical information</term>
<term>Output functions</term>
<term>Pattern recognition</term>
<term>Permutation</term>
<term>Pixel</term>
<term>Polystochastic</term>
<term>Polystochastic frame</term>
<term>Polystochastic models</term>
<term>Possible conditions</term>
<term>Random iterations</term>
<term>Reference classification</term>
<term>Reference matrix</term>
<term>Residence time</term>
<term>Residence times</term>
<term>Same classification</term>
<term>Simulation</term>
<term>Stable matrix</term>
<term>Stochastic</term>
<term>Stochastic approximation procedures</term>
<term>Stochastic chains</term>
<term>Training data</term>
<term>Transition probabilities</term>
<term>Untrained data</term>
<term>Weight coefficient</term>
<term>Weight coefficients</term>
<term>White pixel</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr">
<term>Cinétique</term>
<term>Fermentation</term>
<term>Inhibition</term>
<term>Modèle</term>
<term>Méthode étude</term>
<term>Réseau neuronal</term>
</keywords>
<keywords scheme="Teeft" xml:lang="en">
<term>Aberrant case</term>
<term>Academic press</term>
<term>Adaptive</term>
<term>Alarm state</term>
<term>Algorithm</term>
<term>Annealing methods</term>
<term>Biomass</term>
<term>Biomass concentration</term>
<term>Black pixel</term>
<term>Cbio</term>
<term>Cbio cbio</term>
<term>Classification</term>
<term>Classification algorithm</term>
<term>Classification index</term>
<term>Classification process</term>
<term>Coefficient</term>
<term>Complexity level</term>
<term>Complexity levels</term>
<term>Composition rule</term>
<term>Different classifications</term>
<term>Different conditioning levels</term>
<term>Different levels</term>
<term>Different paths</term>
<term>Different types</term>
<term>Dilution rate</term>
<term>Distance matrices</term>
<term>Distances results</term>
<term>Equal weight coefficients</term>
<term>Ergodic behaviour</term>
<term>Experimental data</term>
<term>Expert system</term>
<term>First step</term>
<term>General frame</term>
<term>Genetic algorithms</term>
<term>Good training example</term>
<term>Hierarchical</term>
<term>Hierarchical order</term>
<term>Hierarchical organization</term>
<term>Infinite memory</term>
<term>Information theory</term>
<term>Informational criteria</term>
<term>Informational type</term>
<term>Input layer</term>
<term>Iordache</term>
<term>Kinetic</term>
<term>Kinetic data</term>
<term>Kinetic diagnosis</term>
<term>Kinetic phenomenon</term>
<term>Kinetic regime</term>
<term>Kinetic regimes</term>
<term>Kinetics</term>
<term>Knowledge representation</term>
<term>Lactic acid production</term>
<term>Matrix</term>
<term>Minimum distance</term>
<term>Modeling method</term>
<term>Neural</term>
<term>Neural network</term>
<term>Neural network frames</term>
<term>Neural network frames table</term>
<term>Neural networks</term>
<term>Neuron</term>
<term>Next cycle</term>
<term>Next level</term>
<term>Numerical experiments</term>
<term>Numerical information</term>
<term>Output functions</term>
<term>Pattern recognition</term>
<term>Permutation</term>
<term>Pixel</term>
<term>Polystochastic</term>
<term>Polystochastic frame</term>
<term>Polystochastic models</term>
<term>Possible conditions</term>
<term>Random iterations</term>
<term>Reference classification</term>
<term>Reference matrix</term>
<term>Residence time</term>
<term>Residence times</term>
<term>Same classification</term>
<term>Simulation</term>
<term>Stable matrix</term>
<term>Stochastic</term>
<term>Stochastic approximation procedures</term>
<term>Stochastic chains</term>
<term>Training data</term>
<term>Transition probabilities</term>
<term>Untrained data</term>
<term>Weight coefficient</term>
<term>Weight coefficients</term>
<term>White pixel</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr">
<term>Biomasse</term>
<term>Classification</term>
<term>Simulation</term>
</keywords>
</textClass>
<langUsage>
<language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front>
<div type="abstract" xml:lang="en">Abstract: The diagnosis of chemical kinetics in chemical plants can be viewed as a process of classification. Recorded data can be associated with different types of kinetic models and the type of kinetics can be classified by comparison with previously recorded data. A new frame for a neural network (NN) is proposed in order to carry out the classification. The potentialities of this adaptive, hierarchized frame organized as a “polystochastic” model have been investigated here. The underlying approach is based on the use of distances between two paths of observed kinetic data. A matrix of distances results from a set of possible kinetic models, and algorithms for classifying models are developed using this matrix. Another type of distance, an informational type, is proposed between two matrices of distances so as to compare one classification with another or with a reference classification. Training the net by methods based on informational criteria is proposed and tested. By a fast adaptive procedure, the small number of resulting weights are adjusted to account for reference cases. The utility of the net is illustrated via the kinetic modeling of a fermentation process. A comparison with another conventional net is also made.</div>
</front>
</TEI>
<affiliations>
<list>
<country>
<li>France</li>
<li>Mexique</li>
</country>
<region>
<li>Grand Est</li>
<li>Lorraine (région)</li>
</region>
<settlement>
<li>Nancy</li>
</settlement>
<orgName>
<li>Centre national de la recherche scientifique</li>
<li>Laboratoire réactions et génie des procédés</li>
<li>Université de Lorraine</li>
</orgName>
</list>
<tree>
<country name="France">
<region name="Grand Est">
<name sortKey="Iordache, O" sort="Iordache, O" uniqKey="Iordache O" first="O." last="Iordache">O. Iordache</name>
</region>
<name sortKey="Corriou, J P" sort="Corriou, J P" uniqKey="Corriou J" first="J. P." last="Corriou">J. P. Corriou</name>
<name sortKey="Fonteix, C" sort="Fonteix, C" uniqKey="Fonteix C" first="C." last="Fonteix">C. Fonteix</name>
<name sortKey="Garrido Sanchez, L" sort="Garrido Sanchez, L" uniqKey="Garrido Sanchez L" first="L." last="Garrido-Sanchez">L. Garrido-Sanchez</name>
<name sortKey="Tondeur, D" sort="Tondeur, D" uniqKey="Tondeur D" first="D." last="Tondeur">Daniel Tondeur</name>
</country>
<country name="Mexique">
<noRegion>
<name sortKey="Garrido Sanchez, L" sort="Garrido Sanchez, L" uniqKey="Garrido Sanchez L" first="L." last="Garrido-Sanchez">L. Garrido-Sanchez</name>
</noRegion>
</country>
</tree>
</affiliations>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/LrgpV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 002879 | SxmlIndent | more

Ou

HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 002879 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Wicri/Lorraine
   |area=    LrgpV1
   |flux=    Main
   |étape=   Exploration
   |type=    RBID
   |clé=     ISTEX:0FA91326A62B55830D3C6B1762335C017EFFB795
   |texte=   Neural network frames. Application to biochemical kinetic diagnosis
}}

Wicri

This area was generated with Dilib version V0.6.32.
Data generation: Sat Nov 11 15:47:48 2017. Site generation: Wed Mar 6 23:31:34 2024