The new Semantic Communication (SC) paradigm has been revolutionizing the field of telecommunications with systems capable of understanding and extracting the meaning of messages, overcoming Shannon's theoretical limits. This project explores the application of these principles to input devices, particularly to mouse devices. The work consists of the gathering of data on the mouse movements imparted by an user, and of their processing through machine learning methods (both supervised and non-supervised) with the objective of building a model capable of reliably foreseeing the total displacement of the pointer given the smallest sub-sequence of the complete data. Even if the resulting model didn't satisfy the expectations, the research has unveiled promising alternatives to be explored by future projects to obtain a reliable prediction
Il nuovo paradigma della Comunicazione Semantica (Semantic Communication o SC) sta rivoluzionando il campo delle telecomunicazioni con sistemi che comprendono ed estraggono il significato dei messaggi, superando i limiti teorici di Shannon. Questo progetto esplora l’applicazione di questi principi all’utilizzo di dispositivi di input, in particolare ai mouse. Il lavoro consiste nella raccolta di dati di movimento del mouse impartiti da un utente e nella loro elaborazione attraverso metodi di apprendimento automatico, supervisionato e non, con l’obiettivo di costruire un modello capace di prevedere in modo affidabile lo spostamento del puntatore a partire da una sottosequenza minima dei dati completi. Anche se il modello risultante non ha soddisfatto le aspettative, la ricerca ha rivelato promettenti metodi alternativi esplorabili da progetti futuri per ottenere una previsione affidabile.
Applicazione della Comunicazione Semantica a dispositivi di input
GIACOMIN, MARCO
2022/2023
Abstract
The new Semantic Communication (SC) paradigm has been revolutionizing the field of telecommunications with systems capable of understanding and extracting the meaning of messages, overcoming Shannon's theoretical limits. This project explores the application of these principles to input devices, particularly to mouse devices. The work consists of the gathering of data on the mouse movements imparted by an user, and of their processing through machine learning methods (both supervised and non-supervised) with the objective of building a model capable of reliably foreseeing the total displacement of the pointer given the smallest sub-sequence of the complete data. Even if the resulting model didn't satisfy the expectations, the research has unveiled promising alternatives to be explored by future projects to obtain a reliable predictionFile | Dimensione | Formato | |
---|---|---|---|
Giacomin_Marco.pdf
accesso aperto
Dimensione
1.6 MB
Formato
Adobe PDF
|
1.6 MB | Adobe PDF | Visualizza/Apri |
The text of this website © Università degli studi di Padova. Full Text are published under a non-exclusive license. Metadata are under a CC0 License
https://hdl.handle.net/20.500.12608/52380