User grouping method for ad-hoc conversations based on proximity of users and speaking volumes acquired from portable sensors

Yutaka Karatsu, Jin Nakazawa, Hideyuki Tokuda

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Analyzing groups of people having a conversation enable to provide context-aware services, such as life log, group-wares, and the virtualization of social networks. We propose a novel method for extract chatting groups by leveraging Bluetooth RSSI and voice data acquired from smart phones. Neighboring people are detected from Bluetooth RSSI, and conversation groups are extract by talking states. The purpose of this paper is to define algorithm that works on efficiently on smart phones that are general and widespread mobile devices.

Original languageEnglish
Title of host publicationUbiComp'11 - Proceedings of the 2011 ACM Conference on Ubiquitous Computing
Pages577-578
Number of pages2
DOIs
Publication statusPublished - 2011 Oct 19
Event13th International Conference on Ubiquitous Computing, UbiComp'11 and the Co-located Workshops - Beijing, China
Duration: 2011 Sept 172011 Sept 21

Publication series

NameUbiComp'11 - Proceedings of the 2011 ACM Conference on Ubiquitous Computing

Other

Other13th International Conference on Ubiquitous Computing, UbiComp'11 and the Co-located Workshops
Country/TerritoryChina
CityBeijing
Period11/9/1711/9/21

Keywords

  • ad-hoc conversation
  • context-aware service
  • smartphones
  • user grouping
  • wearable computing

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'User grouping method for ad-hoc conversations based on proximity of users and speaking volumes acquired from portable sensors'. Together they form a unique fingerprint.

Cite this