The increasing pervasiveness of mobile devices favors the collection of large amounts of movement data that can be analyzed to extract knowledge, i.e. patterns, rules and regularities, from user trajectories. In this paper we present TPM, an integrated algorithm which supports the overall trajectory pattern discovery process for detecting user's mobility behaviors. Specifically, the algorithm includes two main phases: (i) finding dense regions, more densely passed through ones; (ii) extracting trajectory patterns from those regions. Another contribution of the paper is a validation methodology for assessing the effectiveness of the TPM algorithm, e.g., evaluating how the discovered knowledge model fits to the input data it is discovered from. Such methodology represents a general solution that can be used to evaluate the accuracy of any algorithm aiming at extracting dense regions and trajectory patterns from GPS data. Furthermore, we propose novel trajectory similarity measures to evaluate the quality of the extracted patterns. A detailed experimental evaluation, performed by exploiting the proposed validation process, proves the efficiency and effectiveness of TPM.

An approach for the discovery and validation of urban mobility patterns

Cesario E.;Talia D.
2017

Abstract

The increasing pervasiveness of mobile devices favors the collection of large amounts of movement data that can be analyzed to extract knowledge, i.e. patterns, rules and regularities, from user trajectories. In this paper we present TPM, an integrated algorithm which supports the overall trajectory pattern discovery process for detecting user's mobility behaviors. Specifically, the algorithm includes two main phases: (i) finding dense regions, more densely passed through ones; (ii) extracting trajectory patterns from those regions. Another contribution of the paper is a validation methodology for assessing the effectiveness of the TPM algorithm, e.g., evaluating how the discovered knowledge model fits to the input data it is discovered from. Such methodology represents a general solution that can be used to evaluate the accuracy of any algorithm aiming at extracting dense regions and trajectory patterns from GPS data. Furthermore, we propose novel trajectory similarity measures to evaluate the quality of the extracted patterns. A detailed experimental evaluation, performed by exploiting the proposed validation process, proves the efficiency and effectiveness of TPM.
Trajectory pattern mining; Trajectory similarity; Urban computing
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/20.500.11770/303361
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 7
  • ???jsp.display-item.citation.isi??? 8
social impact