Machine learning has emerged as a promising paradigm for enabling connected, automated vehicles to autonomously cruise the streets and react to unexpected situations. A key challenge, however, is to collect and select real-time and reliable information for the correct classification of unexpected, and often uncommon, events that may happen on the road. Indeed, the data generated by vehicles, or received from neighboring vehicles, may be affected by errors or have different levels of resolution and freshness. To tackle this challenge, we propose an active learning framework that, leveraging the information collected through onboard sensors as well as received from other vehicles, effectively deals with scarce and noisy data. In particular, given the available information, our solution selects the data to add to the training set by trading off between two essential features: quality and diversity. The results, obtained using realworld data sets, show that our method significantly outperforms state-of-the-art solutions, providing high classification accuracy at the cost of a limited bandwidth requirement for the data exchange between vehicles.
Active learning-based classification in automated connected vehicles / Abdellatif, A. A.; Chiasserini, C. F.; Malandrino, F.. - STAMPA. - (2020), pp. 598-603. (Intervento presentato al convegno 2020 IEEE INFOCOM Conference on Computer Communications Workshops, INFOCOM WKSHPS 2020 tenutosi a can nel 2020) [10.1109/INFOCOMWKSHPS50562.2020.9162964].
Active learning-based classification in automated connected vehicles
Chiasserini C. F.;
2020
Abstract
Machine learning has emerged as a promising paradigm for enabling connected, automated vehicles to autonomously cruise the streets and react to unexpected situations. A key challenge, however, is to collect and select real-time and reliable information for the correct classification of unexpected, and often uncommon, events that may happen on the road. Indeed, the data generated by vehicles, or received from neighboring vehicles, may be affected by errors or have different levels of resolution and freshness. To tackle this challenge, we propose an active learning framework that, leveraging the information collected through onboard sensors as well as received from other vehicles, effectively deals with scarce and noisy data. In particular, given the available information, our solution selects the data to add to the training set by trading off between two essential features: quality and diversity. The results, obtained using realworld data sets, show that our method significantly outperforms state-of-the-art solutions, providing high classification accuracy at the cost of a limited bandwidth requirement for the data exchange between vehicles.File | Dimensione | Formato | |
---|---|---|---|
09162964.pdf
accesso riservato
Descrizione: Articolo principale
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
867.71 kB
Formato
Adobe PDF
|
867.71 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Infocom_WKS_v5_embedded.pdf
accesso aperto
Descrizione: Articolo principale
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
Pubblico - Tutti i diritti riservati
Dimensione
631.72 kB
Formato
Adobe PDF
|
631.72 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2859180