This work analyzes human behavior recognition approaches using WiFi channel state information from the perhaps less usual point of view of training and calibration needs. With the help of selected literature examples, as well as with more detailed experimental insights on our own Doppler spectrum-based approach for physical motion/presence/cardinality detection, we first classify the diverse forms of training so far employed into three main categories (trained, trained-once, and training-free). We further discuss under which conditions it is possible to move toward lighter forms of calibration or even succeed in devising fully untrained model-based solutions. Our take home messages are mainly two. First, reduced training might not necessarily kill performance (although, of course, trade-offs will emerge). Second, reduced training must come along with a careful customization of the technical detection approach to the specificities of the behavior recognition application targeted, as it seems very hard to find a one-size-fits-All solution without relying on extensive training.

Di Domenico S., De Sanctis M., Cianca E., Giuliano F., & Bianchi G. (2018). Exploring Training Options for RF Sensing Using CSI. IEEE COMMUNICATIONS MAGAZINE, 56(5), 116-123 [10.1109/MCOM.2018.1700145].

Exploring Training Options for RF Sensing Using CSI

De Sanctis M.;Giuliano F.;Bianchi G.
2018

Abstract

This work analyzes human behavior recognition approaches using WiFi channel state information from the perhaps less usual point of view of training and calibration needs. With the help of selected literature examples, as well as with more detailed experimental insights on our own Doppler spectrum-based approach for physical motion/presence/cardinality detection, we first classify the diverse forms of training so far employed into three main categories (trained, trained-once, and training-free). We further discuss under which conditions it is possible to move toward lighter forms of calibration or even succeed in devising fully untrained model-based solutions. Our take home messages are mainly two. First, reduced training might not necessarily kill performance (although, of course, trade-offs will emerge). Second, reduced training must come along with a careful customization of the technical detection approach to the specificities of the behavior recognition application targeted, as it seems very hard to find a one-size-fits-All solution without relying on extensive training.
Di Domenico S., De Sanctis M., Cianca E., Giuliano F., & Bianchi G. (2018). Exploring Training Options for RF Sensing Using CSI. IEEE COMMUNICATIONS MAGAZINE, 56(5), 116-123 [10.1109/MCOM.2018.1700145].
File in questo prodotto:
File Dimensione Formato  
Exploring Training Options for RF Sensing Using CSI.pdf

Solo gestori archvio

Tipologia: Versione Editoriale
Dimensione 623.3 kB
Formato Adobe PDF
623.3 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/10447/513778
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 32
  • ???jsp.display-item.citation.isi??? 30
social impact