Skip navigation
Please use this identifier to cite or link to this item: https://repository.esi-sba.dz/jspui/handle/123456789/336
Full metadata record
DC FieldValueLanguage
dc.contributor.authorLAMRI, MAya Chiraz-
dc.date.accessioned2022-11-09T13:08:17Z-
dc.date.available2022-11-09T13:08:17Z-
dc.date.issued2022-
dc.identifier.urihttps://repository.esi-sba.dz/jspui/handle/123456789/336-
dc.descriptionEncadreur : Melle ELOUALI Nadia Co-Encadreur : Melle DIF Nassimaen_US
dc.description.abstractIn this study, we present a method for evaluating the aesthetics of a website. We used convolutional neural networks, which are one of the most known deep learning research methodologies, to improve performance. Our method uses a screenshot of the website as input and then determines whether it is beautiful website on a scale of 1-9 based on user ratings. We present also a crowdsourcing service that will help gather more data automatically and put in display of researchers to improve their work and also helps us to take improve and take new approaches to solve the problem of quantifying website aesthetics.*** Dans cette ´etude, nous pr´esentons une m´ethode d’´evaluation de l’esth´etique d’un site web. Nous avons utilis´e des r´eseaux de neurones convolutifs, qui sont l’une des m´ethodologies de recherche en apprentissage profond les plus connues, pour am´eliorer les performances. Notre m´ethode utilise une capture d’´ecran du site Web comme entr´ee, puis d´etermine s’il s’agit d’une jollie interface sur une ´echelle de 1 `a 9 en fonction des ´evaluations des utilisateurs. Nous pr´esentons ´egalement un service de crowdsourcing qui aidera `a collecter automatiquement plus de donn´ees et `a afficher des chercheurs pour am´eliorer leur travail et nous aide ´egalement `a am´eliorer et `a adopter de nouvelles approches pour r´esoudre le probl`eme de la quantification de l’esth´etique du site Web.en_US
dc.language.isoenen_US
dc.subjectQuantificationen_US
dc.subjectWebpage,en_US
dc.subjectHuman Computer Interactionen_US
dc.subjectDeep Learningen_US
dc.subjectUsability Testingen_US
dc.subjectFirst Impressionen_US
dc.subjectAlexneten_US
dc.subjectMobileNeten_US
dc.subjectFlickren_US
dc.titleQuantifying The Aesthetics of Graphic Interfaces With Deep Learningen_US
dc.typeThesisen_US
Appears in Collections:Ingénieur

Files in This Item:
File Description SizeFormat 
lamri_pfe_final-1-1.pdf46,93 kBAdobe PDFView/Open
Show simple item record


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.