Adaptive filters from control theory are recursive estimators for time varying parameters. We propose an adaptive filter targeting spatial and temporal correlation parameters, that we conjecture to be more stable in the case of regime shifts. This proposal should be suitable for online environmental monitoring tasks. We illustrate an application to sensor data with a spatio-temporal conditional autoregressive model.
Adaptive filters for time-varying correlation parameters
Michele Lambardi di San Miniato
;Ruggero Bellio;Luca Grassetti;Paolo Vidoni
2022-01-01
Abstract
Adaptive filters from control theory are recursive estimators for time varying parameters. We propose an adaptive filter targeting spatial and temporal correlation parameters, that we conjecture to be more stable in the case of regime shifts. This proposal should be suitable for online environmental monitoring tasks. We illustrate an application to sensor data with a spatio-temporal conditional autoregressive model.File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
Sis-2022-4c-low.pdf
non disponibili
Tipologia:
Versione Editoriale (PDF)
Licenza:
Non pubblico
Dimensione
209.99 kB
Formato
Adobe PDF
|
209.99 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.
