Group mobility classification and structure recognition using mobile devices

He Du, Zhiwen Yu, Fei Yi, Zhu Wang, Qi Han, Bin Guo

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

14 Scopus citations

Abstract

Monitoring group mobility and structure is crucial for public safety management and emergency evacuation. In this paper, we propose a fine-grained mobility classification and structure recognition approach for social groups based on hybrid sensing using mobile devices. First, we present a method which classifies group mobility into four levels, including stationary, strolling, walking and running. Second, by combining mobile sensing and Wi-Fi signals, a novel relative position relationship estimation algorithm is developed to understand moving group structures of different shapes. We have conducted real-life experiments in which eight volunteers form two to three small groups moving in a teaching building with different speed and structures. Experimental results show that our approach achieves an accuracy of 99.5% in mobility classification and about 80% in group structure recognition.

Original languageEnglish
Title of host publication2016 IEEE International Conference on Pervasive Computing and Communications, PerCom 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781467387798
DOIs
StatePublished - 19 Apr 2016
Event14th IEEE International Conference on Pervasive Computing and Communications, PerCom 2016 - Sydney, Australia
Duration: 14 Mar 201619 Mar 2016

Publication series

Name2016 IEEE International Conference on Pervasive Computing and Communications, PerCom 2016

Conference

Conference14th IEEE International Conference on Pervasive Computing and Communications, PerCom 2016
Country/TerritoryAustralia
CitySydney
Period14/03/1619/03/16

Keywords

  • group mobility
  • group structure
  • mobile sensing
  • relative position relationship

Fingerprint

Dive into the research topics of 'Group mobility classification and structure recognition using mobile devices'. Together they form a unique fingerprint.

Cite this