Pervasive services often rely on multi-modal classification to implement situation-recognition capabilities. However, current classifiers are still inaccurate and unreliable. In this paper we present preliminary results obtained with a novel approach that combines well established classifiers using a commonsense knowledge base. The approach maps classification labels produced by independent classifiers to concepts organized within the Concept Net network. Then it verifies their semantic proximity by implementing a greedy approximate sub-graph search algorithm. Specifically, different classifiers are fused together on a commonsense basis for both: (i) improve classification accuracy and (ii) deal with missing labels. Experimental results are discussed through a real-world case study in which two classifiers are fused to recognize both user's activities and visited locations.
Improving Situation Recognition via Commonsense Sensor Fusion / Bicocchi, Nicola; Castelli, Gabriella; Mamei, Marco; Zambonelli, Franco. - STAMPA. - (2011), pp. 272-276. (Intervento presentato al convegno 2011 22nd International Workshop on Database and Expert Systems Applications, DEXA 2011 tenutosi a Toulouse, fra nel 29 - 31 August) [10.1109/DEXA.2011.43].
Improving Situation Recognition via Commonsense Sensor Fusion
BICOCCHI, Nicola;CASTELLI, Gabriella;MAMEI, Marco;ZAMBONELLI, Franco
2011
Abstract
Pervasive services often rely on multi-modal classification to implement situation-recognition capabilities. However, current classifiers are still inaccurate and unreliable. In this paper we present preliminary results obtained with a novel approach that combines well established classifiers using a commonsense knowledge base. The approach maps classification labels produced by independent classifiers to concepts organized within the Concept Net network. Then it verifies their semantic proximity by implementing a greedy approximate sub-graph search algorithm. Specifically, different classifiers are fused together on a commonsense basis for both: (i) improve classification accuracy and (ii) deal with missing labels. Experimental results are discussed through a real-world case study in which two classifiers are fused to recognize both user's activities and visited locations.File | Dimensione | Formato | |
---|---|---|---|
issasim.pdf
Accesso riservato
Tipologia:
Versione dell'autore revisionata e accettata per la pubblicazione
Dimensione
262.77 kB
Formato
Adobe PDF
|
262.77 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris