Vis enkel innførsel

dc.contributor.authorKuchta, Miroslav
dc.contributor.authorWubshet, Sileshi Gizachew
dc.contributor.authorAfseth, Nils Kristian
dc.contributor.authorMardal, Kent-Andre
dc.contributor.authorLiland, Kristian Hovde
dc.date.accessioned2022-09-30T11:04:23Z
dc.date.available2022-09-30T11:04:23Z
dc.date.created2022-07-28T13:00:50Z
dc.date.issued2022
dc.identifier.citationJournal of Biophotonics. 2022, 1-18.
dc.identifier.issn1864-063X
dc.identifier.urihttps://hdl.handle.net/11250/3022853
dc.description.abstractIn the process of converting food-processing by-products to value-addedingredients, fine grained control of the rawmaterials, enzymes and process conditionsensures the best possible yield and eco-nomic return. However, when raw mate-rial batches lack good characterization andcontain high batch variation, online or at-line monitoring of the enzymatic reac-tions would be beneficial. We investigate the potential of deep neural networks inpredicting the future state of enzymatic hydrolysis as described by Fourier-trans-form infrared spectra of the hydrolysates. Combined with predictions of averagemolecular weight, this provides a flexible and transparent tool for process moni-toring and control, enabling proactive adaption of process parameters.
dc.language.isoeng
dc.subjectFTIR
dc.subjectFTIR
dc.subjectProcess control
dc.subjectProcess control
dc.subjectEnzymatic protein hydrolysis
dc.subjectEnzymatic protein hydrolysis
dc.subjectDeep learning
dc.subjectDeep learning
dc.subjectEncoder decoder
dc.subjectEncoder decoder
dc.titleEncoder–decoder neural networks for predicting future FTIR spectra – application to enzymatic protein hydrolysis
dc.title.alternativeEncoder–decoder neural networks for predicting future FTIR spectra – application to enzymatic protein hydrolysis
dc.typePeer reviewed
dc.typeJournal article
dc.description.versionpublishedVersion
dc.source.pagenumber1-18
dc.source.journalJournal of Biophotonics
dc.identifier.doi10.1002/jbio.202200097
dc.identifier.cristin2039937
dc.relation.projectNorges forskningsråd: 300305
dc.relation.projectNorges forskningsråd: 309259
dc.relation.projectNorges forskningsråd: 280709
dc.relation.projectNorges forskningsråd: 303362
dc.relation.projectNorges forskningsråd: 314111
cristin.ispublishedtrue
cristin.fulltextoriginal
cristin.qualitycode1


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel