Full Citation

Title: Prior Knowledge of Human Activities from Social Data

Citation Type: Conference Paper

Publication Year: 2013

ISBN:

ISSN:

DOI:

NSFID:

PMCID:

PMID:

Abstract: We explore the feasibility of utilizing large, crowd-generated online repositories to construct prior knowledge models for high-level activity recognition. Towards this, we mine the popular location-based social network, Foursquare, for geo-tagged activity reports. Although unstructured and noisy, we are able to extract, categorize and geographically map peoples activities, thereby answering the question: what activities are possible where? Through Foursquare text only, we obtain a testing accuracy of 59.2% with 10 activity categories; using additional contextual cues such as venue semantics, we obtain an increased accuracy of 67.4%. By mapping prior odds of activities via geographical coordinates, we directly benefit activity recognition systems built on geo-aware mobile phones.

User Submitted?: No

Authors: Blanke, Ulf; Troester, Gerhard; Zhu, Zack; Calatroni, Alberto

Conference Name: The 2013 International Symposium on Wearable Computers

Publisher Location: Zurich, Switzerland

Data Collections: IPUMS Time Use - ATUS

Topics: Other

Countries: