Skip navigation
Please use this identifier to cite or link to this item: https://repository.esi-sba.dz/jspui/handle/123456789/673
Full metadata record
DC FieldValueLanguage
dc.contributor.authorKERMAD, HAsna ABir-
dc.contributor.authorTAIBI, HAlima ZIneb AYat-
dc.date.accessioned2024-09-25T13:29:28Z-
dc.date.available2024-09-25T13:29:28Z-
dc.date.issued2024-
dc.identifier.urihttps://repository.esi-sba.dz/jspui/handle/123456789/673-
dc.descriptionSupervisor : Dr. Rabab BOUSMAHA Co-Supervisor :Pr. Sidi Mohammed BENSLIMANEen_US
dc.description.abstractParkinson’s disease (PD) is a progressive neurological disorder that affects millions worldwide, characterized by motor and non-motor symptoms, including tremors, bradykinesia, rigidity, and speech impairment. Early detection and monitoring of PD are crucial for effective management and intervention. Traditional diagnostic methods rely heavily on clinical assessments, which can be subjective and may not capture subtle changes in disease progression. In recent years, there has been growing interest in leveraging multimodal data analysis techniques, particularly combining handwriting and speech signals, to enhance PD detection and monitoring. The significance of this project lies in its potential to revolutionize PD diagnosis and monitoring by providing a non-invasive, cost-effective, and accessible method for early detection and longitudinal assessment. By combining handwriting and speech analysis, this approach offers a holistic perspective on motor and cognitive impairments associated with PD, facilitating timely interventions and personalized treatment strategies. Furthermore, the outcomes of this research have the potential to contribute significantly to the development of non-invasive and cost-effective methods for early PD detection, thus facilitating timely intervention and enhancing the quality of life for individuals affected by a neurodegenerative disorders like Parkinson’s disease. *** La maladie de Parkinson (MP) est un trouble neurologique progressif qui touche des millions de personnes dans le monde, caract´eris´e par des symptˆomes moteurs et non moteurs, notamment des tremblements, une bradykin´esie, une rigidit´e et des troubles de la parole. La d´etection pr´ecoce et la surveillance de la MP sont cruciales pour une gestion et une intervention efficaces. Les m´ethodes de diagnostic traditionnelles reposent fortement sur des ´evaluations cliniques, qui peuvent ˆetre subjectives et peuvent ne pas saisir les changements subtils dans la progression de la maladie. Ces derni`eres ann´ees, il y a eu un int´erˆet croissant pour l’utilisation de techniques d’analyse de donn´ees multimodales, en particulier la combinaison de signaux d’´ecriture manuscrite et de parole, pour am´eliorer la d´etection et la surveillance de la MP. L’importance de ce projet r´eside dans son potentiel `a r´evolutionner le diagnostic et la surveillance de la MP en fournissant une m´ethode non invasive, rentable et accessible pour la d´etection pr´ecoce et l’´evaluation longitudinale. En combinant l’analyse de l’´ecriture manuscrite et de la parole, cette approche offre une perspective holistique sur les d´eficiences motrices et cognitives associ´ees `a la MP, facilitant les interventions opportunes et les strat´egies de traitement personnalis´ees. De plus, les r´esultats de cette recherche ont le potentiel de contribuer de mani`ere significative au d´eveloppement de m´ethodes non invasives et rentables pour la d´etection pr´ecoce de la MP, facilitant ainsi une intervention rapide et am´eliorant la qualit´e de vie des personnes atteintes de troubles neurod´eg´en´eratifs comme la maladie de Parkinson.en_US
dc.language.isoenen_US
dc.subjectParkinson’s Disease (PD)en_US
dc.subjectFeature Extractionen_US
dc.subjectMachine Learning (ML)en_US
dc.subjectDeep Learning (DL)en_US
dc.subjectHandwriting Analysisen_US
dc.subjectSpeech Signalsen_US
dc.subjectMultimodal Analysisen_US
dc.subjectEarly Detectionen_US
dc.titleParkinson’s disease detection by multimodal analysis combining handwriting and speech signalsen_US
dc.typeThesisen_US
Appears in Collections:Ingénieur

Files in This Item:
File Description SizeFormat 
PFE_Taibi_Kermad-1-1.pdf69,99 kBAdobe PDFView/Open
Show simple item record


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