Please use this identifier to cite or link to this item: http://univ-bejaia.dz/dspace/123456789/24868
Full metadata record
DC FieldValueLanguage
dc.contributor.authorChakir, Melissa-
dc.contributor.authorAbdelghafour, Asma-
dc.contributor.authorEl Bouhissi Brahami, Houda ; promotrice-
dc.date.accessioned2024-12-08T10:36:44Z-
dc.date.available2024-12-08T10:36:44Z-
dc.date.issued2024-
dc.identifier.other004MAS/1304-
dc.identifier.urihttp://univ-bejaia.dz/dspace/123456789/24868-
dc.descriptionOption : systéme d’information avancésen_US
dc.description.abstractAfter evaluating the performance of our six models, it is evident that the ACO-LSTM model is the superior choice, achieving the highest accuracy of 97.1%. This model's remarkable performance underscores the potential of hybrid approaches that integrate swarm intelligence with deep learning techniques. The consistent high performance of the PSO-LSTM and ACO-GRU models further validates the efficacy of combining optimization algorithms with advanced neural networks. As we move forward, we are committed to refining these models, addressing their limitations, and expanding their applications to a broader range of medical conditions, thereby contributing to the advancement of predictive healthcare technologies.en_US
dc.language.isofren_US
dc.publisherUniversité Abderramane Mira-Bejaiaen_US
dc.subjectDiabetes : Mellitus Prediction : PSO-LSTM : ACO-GRUen_US
dc.titleDiabetes Mellitus Prediction.en_US
dc.typeThesisen_US
Appears in Collections:Mémoires de Master

Files in This Item:
File Description SizeFormat 
THESIS (5).pdf4.41 MBAdobe PDFView/Open


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