1. DSpace at Kasdi Merbah University Ouargla
  2. 3. Mémoires de Master
  3. 2. Faculté des nouvelles technologies de l’information et de la communication
  4. Département d'informatique et technologie de l'information - Master
Please use this identifier to cite or link to this item: https://dspace.univ-ouargla.dz/jspui/handle/123456789/35014
Full metadata record
DC FieldValueLanguage
dc.contributor.authorAmran, Laila-
dc.contributor.authorFerhi, Aya-
dc.date.accessioned2023-11-14T10:33:44Z-
dc.date.available2023-11-14T10:33:44Z-
dc.date.issued2023-
dc.identifier.urihttps://dspace.univ-ouargla.dz/jspui/handle/123456789/35014-
dc.description.abstractSoilplaysanimportantroleinthequalityofagriculturalcrops,especiallysinceweareinanera inwhichtheagriculturalsectoroccupiesagreatimportancenotonlyfromthesideoftheeconomy,butalsofromthesideofachievingfoodsufficiency,soifthetypeofthesoilisnotappropriate,thentheproductwillnotbeoftherequiredquality. Inourresearch,wewantedtohelpevery farmerandpeasantandeveryoneinterestedinthisfieldbydevelopingawebsitethatallowssoil classification(initiallyfivetypes)byincludingapictureofthesoiltoknowitstype. TheclassificationprocesswascarriedoutusingdeeplearningexactlyProposedCNNmodel,whichhadthe highestaccuracy(86%)aftercomparingitwith3othermodels,VGG(80%),ResNet(79%),and MobileNet(76%). Intheend,aftertheclassificationisdone,themostimportantcharacteristics (sixcharacteristics)ofthatsoilarepresented,whitchistemperature,Ph,Porosity,texture,color ,density.en_US
dc.language.isoenen_US
dc.publisherUNIVERSITY OF KASDI MERBAH OUARGLAen_US
dc.subjectArtificial Intelligenceen_US
dc.subjectDeep Learningen_US
dc.subject,CNNen_US
dc.subjectProposed CNNen_US
dc.subjectVGG16en_US
dc.subjectResNeten_US
dc.subjectMobile Neten_US
dc.titleSoil recognition and features measurement using AIen_US
dc.typeThesisen_US
Appears in Collections:Département d'informatique et technologie de l'information - Master

Files in This Item:
File Description SizeFormat 
FERHI.pdf3,43 MBAdobe PDFView/Open
Show simple item record


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