In this paper, we investigate the suitability of state-of-the-art representation learning methods to the analysis of behavioral similarity of moving individuals, based on CDR trajectories. The core of the contribution is a novel methodological framework, mob2vec, centered on the combined use of a recent symbolic trajectory segmentation method for the removal of noise, a novel trajectory generalization method incorporating behavioral information, and an unsupervised technique for the learning of vector representations from sequential data. mob2vec is the result of an empirical study conducted on real CDR data through an extensive experimentation. As a result, it is shown that mob2vec generates vector representations of CDR trajectories in low dimensional spaces which preserve the similarity of the mobility behavior of individuals.

Learning Behavioral Representations of Human Mobility / M.L. Damiani, A. Acquaviva, F. Hachem, M. Rossini - In: SIGSPATIAL '20: Proceedings / [a cura di] L. Chang-Tien , F. Wang, G. Trajcevski, Y. Huang, S. Newsam, L. Xiong. - [s.l] : ACM, 2020. - ISBN 978145038019-5. - pp. 1-10 (( Intervento presentato al 28. convegno International Conference on Advances in Geographic Information Systems tenutosi a Seattle nel 2020 [10.1145/3397536.3422255].

Learning Behavioral Representations of Human Mobility

M. L. Damiani;F. Hachem;M. Rossini
2020

Abstract

In this paper, we investigate the suitability of state-of-the-art representation learning methods to the analysis of behavioral similarity of moving individuals, based on CDR trajectories. The core of the contribution is a novel methodological framework, mob2vec, centered on the combined use of a recent symbolic trajectory segmentation method for the removal of noise, a novel trajectory generalization method incorporating behavioral information, and an unsupervised technique for the learning of vector representations from sequential data. mob2vec is the result of an empirical study conducted on real CDR data through an extensive experimentation. As a result, it is shown that mob2vec generates vector representations of CDR trajectories in low dimensional spaces which preserve the similarity of the mobility behavior of individuals.
Mobility; machine learning
Settore INF/01 - Informatica
Next-generation Ultra-Wideband Localization and Communication for the Internet of Things
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
ml-arxiv.pdf

accesso aperto

5.12 MB Adobe PDF Visualizza/Apri
3397536.3422255.pdf

non disponibili

6.49 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

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/2434/763771
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? ND
social impact