eprintid: 71151 rev_number: 11 eprint_status: archive userid: 2544 dir: disk0/00/07/11/51 datestamp: 2022-07-12 19:21:04 lastmod: 2022-07-12 19:21:04 status_changed: 2022-07-12 19:21:04 type: other metadata_visibility: show creators_name: Rojo Vicente, Mario contributors_name: Díaz Pérez, Francisco contributors_id: francisco.diazp@upm.es title: Exploration of Parkinson’s disease recognition space by artificial neural networks rights: by-nc-nd ispublished: unpub subjects: informatica subjects: medicina full_text_status: restricted keywords: Machine learning; Parkinson; Data sets abstract: This paper focuses on the objective a Machine Learning model to classify the advancement of Parkinson´s Disease on a patient given some audio recordings and general information, such as age and gender. For this we will utilize a dataset extracted from synapse to train the several proposed models and finally extract conclusions on the outcomes. This project focuses on the implementation of CNN models based of the VGG-16 architecture. The results ranges from a 30% accuracy to around a 60% on all three datasets (train, validation and test) depending on the model and its hyper parameters, as well as the processes applied on the data. In conclusion the project was lacking more instances of reliable data but shows the possibilities of implementing such models on bigger datasets with rather significant results. The final results of this paper allow us to define rules and procedures to be implemented in similar future projects. date_type: completed date: 2022-06 place_of_pub: Madrid institution: ETSI_Sistemas_Infor department: Sistemas_informaticos_2014 refereed: TRUE grado: Grado en Ingeniería del Software citation: Rojo Vicente, Mario (2022). Exploration of Parkinson’s disease recognition space by artificial neural networks. Proyecto Fin de Carrera / Trabajo Fin de Grado, E.T.S.I. de Sistemas Informáticos (UPM) , Madrid. document_url: https://oa.upm.es/71151/1/TFG_MARIO_ROJO_VICENTE.pdf