In human-machine interaction systems, device-free and privacy-aware activity monitoring and gesture recognition is of great interest. In this framework, this work introduces a multi-step wireless imaging approach based on channel state information (CSI) and machine learning for the user's presence detection, localization, identification, and gesture recognition by using commodity Wi-Fi signals. The preliminary experimental validation in a real environment shows an excellent classification accuracy of 98%.
Real-Time CSI-Based Wireless Imaging for Human-Machine Interaction / Polo, Alessandro; Salucci, Marco; Verzura, Stefano; Massa, Andrea. - STAMPA. - (2021), pp. 1649-1650. (Intervento presentato al convegno 2021 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting (APS/URSI) tenutosi a Singapore nel 4th-10th December 2021) [10.1109/APS/URSI47566.2021.9704139].
Real-Time CSI-Based Wireless Imaging for Human-Machine Interaction
Polo, Alessandro;Salucci, Marco;Massa, Andrea
2021-01-01
Abstract
In human-machine interaction systems, device-free and privacy-aware activity monitoring and gesture recognition is of great interest. In this framework, this work introduces a multi-step wireless imaging approach based on channel state information (CSI) and machine learning for the user's presence detection, localization, identification, and gesture recognition by using commodity Wi-Fi signals. The preliminary experimental validation in a real environment shows an excellent classification accuracy of 98%.| File | Dimensione | Formato | |
|---|---|---|---|
|
Real-Time CSI-Based Wireless Imaging for Human-Machine Interaction.pdf
Solo gestori archivio
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
338.56 kB
Formato
Adobe PDF
|
338.56 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione
