BCIs offer the opportunity, in patients with pathologies, to recover motor abilities through the decoding and conversion of brain activity into control signals. In parallel to neuroimaging techniques, which allow the acquisition of brain activity, machine learning algorithms offer systems for the extrapolation of neural information. The focus of this thesis is on the description and development of an asynchronous brain interface capable of discriminating two classes of events, with the presentation of visual feedback through the virtual reality environment. After an introduction to the concept of BCIs in the first chapters, the procedures performed for the development of the neural interface will be addressed, step by step, with a deep analytical treatment of the main integrated algorithms and of the code used for the development of the virtual environment.
Le BCI offrono l’opportunità, in pazienti con patologie, di recupero delle capacitàmotorie attraverso la decodifica e la conversione dell’attività cerebrale in segnalidi controllo. Parallelamente alle tecniche di neuroimaging, che permettono l’acqui-sizione dell’attività cerebrale, Gli algoritmi di machine learning offrono sistemi diestrapolazione dell’informazione neurale.Il focus di questa tesi è incentrato nella descrizione e nello sviluppo di un’interfaccianeurale asincrona capace di discriminare due classi di eventi, con presentazione delfeedback visivo attraverso l’ambiente di realtà virtuale.Dopo una introduzione al concetto delle BCI nei primi capitoli, verranno affrontate,passo dopo passo, le procedure svolte per lo sviluppo dell’interfaccia neurale, conapprofondita trattazione analitica dei principali algoritmi integrati e del codiceutilizzato per lo sviluppo dell’ambiente virtuale.
Paradigma delle BCI applicato ad un contesto di realtà virtuale.
BILANCIA, EDOARDO
2020/2021
Abstract
BCIs offer the opportunity, in patients with pathologies, to recover motor abilities through the decoding and conversion of brain activity into control signals. In parallel to neuroimaging techniques, which allow the acquisition of brain activity, machine learning algorithms offer systems for the extrapolation of neural information. The focus of this thesis is on the description and development of an asynchronous brain interface capable of discriminating two classes of events, with the presentation of visual feedback through the virtual reality environment. After an introduction to the concept of BCIs in the first chapters, the procedures performed for the development of the neural interface will be addressed, step by step, with a deep analytical treatment of the main integrated algorithms and of the code used for the development of the virtual environment.File | Dimensione | Formato | |
---|---|---|---|
Tesi_frontespizio_non_firmato (1).pdf
embargo fino al 27/10/2024
Dimensione
9.98 MB
Formato
Adobe PDF
|
9.98 MB | Adobe PDF |
I documenti in UNITESI sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/20.500.12075/1051