Deep learning is a broad class of machine learning techniques based on learning data representation through multiple levels of abstraction. It has been successfully applied in several areas of research, but very few literature addressed the problem of traffic flow forecasting. Thus, driven by the belief that deep learning algorithms may capture the sharp traffic data non-linearities, we aimed to develop a deep architecture, namely a feed-forward neural network, and evaluate its performances in predicting short-term traffic streams. We illustrate our methodology, consisting in a predictors selection step and a subsequent training step, using traffic speed data of the Grande Raccordo Anulare road of Rome for the month of June 2016.
Gli algoritmi di apprendimento approfondito costituiscono una vasta classe di algoritmi machine learning basati sulla rappresentazione dei dati tramite molteplici livelli di astrazione. Essi sono stati applicati con successo in diverse aree di ricerca, tuttavia solo una piccola parte della letteratura deep learning si e interessata al problema della previsione di dati di traffico. Considerando la capacità di questi algoritmi di catturare non linearità presenti all’interno dei dati, ci siamo proposti di sviluppare un’architettura deep learning per prevedere il traffico a breve termine. Illustriamo la nostra metodologia, consistente in una fase di selezione dei predittori e una di apprendimento della rete, considerando una dataset di dati di velocità di veicoli sulla rete autostradale Grande Raccordo Anulare di Roma.
Deep learning to the test. An application to traffic data streams / Deliu, Nina; Brutti, Pierpaolo. - (2018), pp. 1597-1602. (Intervento presentato al convegno 49th Scientific Meeting of the Italian Statistical Society tenutosi a Palermo; Italia).
Deep learning to the test. An application to traffic data streams
Nina Deliu
Methodology
;Pierpaolo BruttiSupervision
2018
Abstract
Deep learning is a broad class of machine learning techniques based on learning data representation through multiple levels of abstraction. It has been successfully applied in several areas of research, but very few literature addressed the problem of traffic flow forecasting. Thus, driven by the belief that deep learning algorithms may capture the sharp traffic data non-linearities, we aimed to develop a deep architecture, namely a feed-forward neural network, and evaluate its performances in predicting short-term traffic streams. We illustrate our methodology, consisting in a predictors selection step and a subsequent training step, using traffic speed data of the Grande Raccordo Anulare road of Rome for the month of June 2016.File | Dimensione | Formato | |
---|---|---|---|
Deliu_Deep-learning_2018.pdf
solo gestori archivio
Tipologia:
Documento in Post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
116.6 kB
Formato
Adobe PDF
|
116.6 kB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.