Automated discovery of mobile users locations with improved K-means clustering

Abstract

Location is one of the most commonly used contextual information in mobile context-aware systems. It can be considered on many different levels of granularity, varying from geolocation that is based on GPS systems, up to microlocation that uses Bluetooth Low Energy devices and WiFi access points for locating users inside buildings. Most common use of location is navigation, however recently it is more often considered also as an important component of the user profile. One of the biggest challenges in location-based context-aware systems is the discovery of patterns in user transportation traces and extraction of the most often visited places. In this paper we presented and evaluated a method that allows for automatic extraction of clusters from user location traces. These clusters represents user points of interest like home, work, favourite restaurants, but also transportation routines. The original contribution of this work is a proposal of an approach based on the K-means clustering algorithm equipped with a module for automatic discovery of number of clusters and density-based cluster merging. This method allows for online, adaptable discovery of user points of interests, and transportation routines in mobile systems.