Efficiently Estimating Statistics of Points of Interests on Maps

Recently, map services (e.g., Google maps) and location-based online social networks (e.g., Foursquare) attract a lot of attention and businesses. With the increasing popularity of these location-based services, exploring and characterizing points of interests (PoIs) such as restaurants and hotels o...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on knowledge and data engineering 2016-02, Vol.28 (2), p.425-438
Main Authors: Wang, Pinghui, He, Wenbo, Liu, Xue
Format: Article
Language:English
Subjects:
Accuracy
Aggregates
Estimates
Estimating
Estimation
Google
Information dissemination
Location-based services
measurement
points of interests
Query processing
sampling
Sampling methods
Searching
Statistics
Urban areas
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recently, map services (e.g., Google maps) and location-based online social networks (e.g., Foursquare) attract a lot of attention and businesses. With the increasing popularity of these location-based services, exploring and characterizing points of interests (PoIs) such as restaurants and hotels on maps provides valuable information for applications such as start-up marketing research. Due to the lack of a direct fully access to PoI databases, it is infeasible to exhaustively search and collect all PoIs within a large area using public APIs, which usually impose a limit on the maximum query rate. In this paper, we propose sampling methods to accurately estimate PoI statistics such as sum and average aggregates from as few queries as possible. Experimental results based on real datasets show that our methods are efficient, and require six times less queries than state-of-the-art methods to achieve the same accuracy.
ISSN:1041-4347
1558-2191
DOI:10.1109/TKDE.2015.2480397