The analysis of movement data has been recently fostered by the widespread diffusion of new techniques and systems for monitoring, collecting and storing location-aware data, generated by a wealth of technological infrastructures, such as GPS positioning and wireless networks [2]. These have made available massive repositories of spatio-temporal data recording human mobile activities, such as location data from mobile phones, GPS tracks from mobile devices, etc.: is it possible to discover from these data use- ful and timely knowledge about human mobility? The GeoPKDD project [1], since 2005, investigated this direction of research; the lesson learned is that there is a long way to go from raw data of individual trajectories up to high-level collective mobility knowledge, capable of supporting the decisions of mobility and transportation managers. Such analysts reason about semantically rich concepts, such as systematic vs. occasional movement behavior and home- work commuting patterns; accordingly, the mainstream analytical tools of transportation engineering, such as origin/destination ma- trices, are based on semantically rich data collected by means of field surveys and interviews. Clearly, the price to pay for this rich- ness is hard: mass surveys are very expensive, so that their peri- odicity is very broad and obsolescence is rapid; poor data quality is also a plague: people tend to respond elusively and inaccurately. On the other extreme, automatically sensed mobility data record in- dividual trajectories at mass level, in real time. Clearly, the price topay here is exactly the lack of semantics in raw data: How to bridgeFigure 1: The steps of the mobility knowledge discovery pro- cess.
Mobility data mining: discovering movement patterns from trajectory data
Giannotti F;Nanni M;Pedreschi D;Pinelli F;Renso C;Rinzivillo S;Trasarti R
2010
Abstract
The analysis of movement data has been recently fostered by the widespread diffusion of new techniques and systems for monitoring, collecting and storing location-aware data, generated by a wealth of technological infrastructures, such as GPS positioning and wireless networks [2]. These have made available massive repositories of spatio-temporal data recording human mobile activities, such as location data from mobile phones, GPS tracks from mobile devices, etc.: is it possible to discover from these data use- ful and timely knowledge about human mobility? The GeoPKDD project [1], since 2005, investigated this direction of research; the lesson learned is that there is a long way to go from raw data of individual trajectories up to high-level collective mobility knowledge, capable of supporting the decisions of mobility and transportation managers. Such analysts reason about semantically rich concepts, such as systematic vs. occasional movement behavior and home- work commuting patterns; accordingly, the mainstream analytical tools of transportation engineering, such as origin/destination ma- trices, are based on semantically rich data collected by means of field surveys and interviews. Clearly, the price to pay for this rich- ness is hard: mass surveys are very expensive, so that their peri- odicity is very broad and obsolescence is rapid; poor data quality is also a plague: people tend to respond elusively and inaccurately. On the other extreme, automatically sensed mobility data record in- dividual trajectories at mass level, in real time. Clearly, the price topay here is exactly the lack of semantics in raw data: How to bridgeFigure 1: The steps of the mobility knowledge discovery pro- cess.File | Dimensione | Formato | |
---|---|---|---|
prod_92103-doc_131657.pdf
solo utenti autorizzati
Descrizione: Mobility data mining: discovering movement patterns from trajectory data
Tipologia:
Versione Editoriale (PDF)
Dimensione
10.69 MB
Formato
Adobe PDF
|
10.69 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.